From 0fe22df4ce7ffa6a5b1a7eb4749d15aa1d6a8b8b Mon Sep 17 00:00:00 2001
From: nik <nik@heartex.net>
Date: Wed, 5 Mar 2025 14:58:13 +0100
Subject: [PATCH 01/10] Add skill for image+bbox extraction

---
 adala/skills/__init__.py                      |   1 +
 .../collection/label_studio_image_ocr.py      | 384 ++++++++++++++++++
 2 files changed, 385 insertions(+)
 create mode 100644 adala/skills/collection/label_studio_image_ocr.py

diff --git a/adala/skills/__init__.py b/adala/skills/__init__.py
index 6cd7c3fa..65583f39 100644
--- a/adala/skills/__init__.py
+++ b/adala/skills/__init__.py
@@ -4,4 +4,5 @@
 from .collection.rag import RAGSkill
 from .collection.ontology_creation import OntologyCreator, OntologyMerger
 from .collection.label_studio import LabelStudioSkill
+from .collection.label_studio_image_ocr import LabelStudioSkillImageOCR
 from ._base import Skill, TransformSkill, AnalysisSkill, SynthesisSkill
diff --git a/adala/skills/collection/label_studio_image_ocr.py b/adala/skills/collection/label_studio_image_ocr.py
new file mode 100644
index 00000000..1171eb8b
--- /dev/null
+++ b/adala/skills/collection/label_studio_image_ocr.py
@@ -0,0 +1,384 @@
+import re
+import logging
+import pandas as pd
+from typing import List, Optional, Type
+from functools import cached_property
+from copy import deepcopy
+from collections import defaultdict
+import aiohttp
+import base64
+import asyncio
+import io
+from PIL import Image
+from urllib.parse import urlparse
+import uuid
+from adala.skills._base import TransformSkill
+from adala.runtimes import AsyncLiteLLMVisionRuntime
+from adala.runtimes._litellm import MessageChunkType
+from pydantic import BaseModel, Field, model_validator, computed_field
+from difflib import SequenceMatcher
+
+
+from adala.runtimes import Runtime, AsyncRuntime
+from adala.utils.internal_data import InternalDataFrame
+
+from label_studio_sdk.label_interface import LabelInterface
+from label_studio_sdk.label_interface.control_tags import ControlTag, ObjectTag
+from label_studio_sdk._extensions.label_studio_tools.core.utils.json_schema import (
+    json_schema_to_pydantic,
+)
+
+
+logger = logging.getLogger(__name__)
+
+
+def extract_variable_name(input_string):
+    """Extract variable name in which would be specified as $<variable-name>"""
+    pattern = r"\$([a-zA-Z0-9_]+)"
+    matches = re.findall(pattern, input_string)
+    return matches
+
+
+class LabelStudioSkillImageOCR(TransformSkill):
+
+    name: str = "label_studio"
+    input_template: str = "Annotate the input data according to the provided schema."
+    # TODO: remove output_template, fix calling @model_validator(mode='after') in the base class
+    output_template: str = "Output: {field_name}"
+    response_model: Type[BaseModel] = (
+        BaseModel  # why validate_response_model is called in the base class?
+    )
+    # ------------------------------
+    label_config: str = "<View></View>"
+    allowed_control_tags: Optional[list[str]] = None
+    allowed_object_tags: Optional[list[str]] = None
+
+    # TODO: implement postprocessing to verify Taxonomy
+
+    @cached_property
+    def label_interface(self) -> LabelInterface:
+        return LabelInterface(self.label_config)
+
+    @cached_property
+    def image_tags(self) -> List[ObjectTag]:
+        # check if any image tags are used as input variables
+        object_tag_names = self.allowed_object_tags or list(
+            self.label_interface._objects.keys()
+        )
+        tags = []
+        for tag_name in object_tag_names:
+            tag = self.label_interface.get_object(tag_name)
+            if tag.tag.lower() == "image":
+                tags.append(tag)
+        return tags
+
+    def __getstate__(self):
+        """Exclude cached properties when pickling - otherwise the 'Agent' can not be serialized in celery"""
+        state = deepcopy(super().__getstate__())
+        # Remove cached_property values
+        for key in ["label_interface", "ner_tags", "image_tags"]:
+            state["__dict__"].pop(key, None)
+        return state
+
+    @model_validator(mode="after")
+    def validate_response_model(self):
+
+        logger.debug(f"Read labeling config {self.label_config}")
+
+        if self.allowed_control_tags or self.allowed_object_tags:
+            if self.allowed_control_tags:
+                control_tags = {
+                    tag: self.label_interface._controls[tag]
+                    for tag in self.allowed_control_tags
+                }
+            else:
+                control_tags = self.label_interface._controls
+            if self.allowed_object_tags:
+                object_tags = {
+                    tag: self.label_interface._objects[tag]
+                    for tag in self.allowed_object_tags
+                }
+            else:
+                object_tags = self.label_interface._objects
+            interface = LabelInterface.create_instance(
+                tags={**control_tags, **object_tags}
+            )
+            logger.debug(
+                f"Filtered labeling config based on allowed tags {self.allowed_control_tags=} and {self.allowed_object_tags=} to {interface.config}"
+            )
+        else:
+            interface = self.label_interface
+
+        # NOTE: filtered label config is used for the response model, but full label config is used for the prompt, so that the model has as much context as possible.
+        self.field_schema = interface.to_json_schema()
+        logger.debug(f"Converted labeling config to json schema: {self.field_schema}")
+
+        return self
+
+    def _create_response_model_from_field_schema(self):
+        pass
+
+    def apply(
+        self,
+        input: InternalDataFrame,
+        runtime: Runtime,
+    ) -> InternalDataFrame:
+
+        with json_schema_to_pydantic(self.field_schema) as ResponseModel:
+            return runtime.batch_to_batch(
+                input,
+                input_template=self.input_template,
+                output_template="",
+                instructions_template=self.instructions,
+                response_model=ResponseModel,
+            )
+            
+    @classmethod
+    async def process_images_with_ocr(cls, images: list) -> list:
+        """
+        Process a list of images with OCR by calling the OCR service.
+        
+        Args:
+            images: List of image data (URLs or base64 strings)
+            
+        Returns:
+            List of OCR results for each image
+        """
+        
+        async def process_single_image(image_data):
+            # Check if the image is a URL
+            is_url = False
+            try:
+                parsed = urlparse(image_data)
+                is_url = all([parsed.scheme, parsed.netloc])
+            except:
+                is_url = False
+                
+            if not is_url:
+                logger.warning(f"Image data is not a URL. OCR service requires URLs or base64 data.")
+                return None
+            
+            # Download the image and convert to base64
+            async with aiohttp.ClientSession() as session:
+                try:
+                    async with session.get(image_data) as response:
+                        if response.status == 200:
+                            image_bytes = await response.read()
+                            # Get image dimensions
+                            image = Image.open(io.BytesIO(image_bytes))
+                            width, height = image.size
+                            # Convert to base64
+                            base64_data = base64.b64encode(image_bytes).decode('utf-8')
+                        else:
+                            error_text = await response.text()
+                            logger.error(f"Failed to download image: {response.status}, {error_text}")
+                            return None
+                except Exception as e:
+                    logger.error(f"Error downloading image: {str(e)}")
+                    return None
+            
+            # Call the OCR service with base64 data
+            ocr_url = "https://llm-ocr-server.appx.humansignal.com/ocr/base64"
+            
+            # Prepare form data - this is the key change
+            form_data = aiohttp.FormData()
+            form_data.add_field('image_data', base64_data)
+            form_data.add_field('confidence_threshold', str(0.3))
+            form_data.add_field('languages', 'en,ch_sim')
+            
+            async with aiohttp.ClientSession() as session:
+                try:
+                    async with session.post(ocr_url, data=form_data) as response:
+                        if response.status == 200:
+                            json_response = await response.json()
+                            return {
+                                "ocr_data": json_response,
+                                "image_width": width,
+                                "image_height": height
+                            }
+                        else:
+                            error_text = await response.text()
+                            logger.error(f"OCR service returned error: {response.status}, {error_text}")
+                            return None
+                except Exception as e:
+                    logger.error(f"Error calling OCR service: {str(e)}")
+                    return None
+        
+        # Process all images concurrently
+        tasks = [process_single_image(image) for image in images]
+        results = await asyncio.gather(*tasks)
+        
+        # normalize EasyOCR results to RectangleLabels bounding boxes format of Label Studio
+        normalized_results = []
+        for result in results:
+            if not result:
+                continue
+                
+            # Extract OCR response data
+            bboxes = result.get('ocr_data', {}).get('bboxes', [])
+            texts = result.get('ocr_data', {}).get('texts', [])
+            scores = result.get('ocr_data', {}).get('scores', [])
+            original_width = result.get('image_width', 1000)
+            original_height = result.get('image_height', 1000)
+            
+            # Convert to Label Studio format
+            label_studio_results = []
+            
+            for i, (bbox, text, score) in enumerate(zip(bboxes, texts, scores)):
+                # EasyOCR bboxes format is [[x1,y1],[x2,y2],[x3,y3],[x4,y4]]
+                # We need to convert to Label Studio format with x,y as top-left corner
+                # and width, height as percentages
+                
+                # Calculate top-left corner (minimum x and y)
+                x_values = [point[0] for point in bbox]
+                y_values = [point[1] for point in bbox]
+                
+                min_x = min(x_values)
+                min_y = min(y_values)
+                
+                # Calculate width and height
+                max_x = max(x_values)
+                max_y = max(y_values)
+                width = max_x - min_x
+                height = max_y - min_y
+                
+                # Convert to percentages
+                x_percent = (min_x / original_width) * 100
+                y_percent = (min_y / original_height) * 100
+                width_percent = (width / original_width) * 100
+                height_percent = (height / original_height) * 100
+                
+                # generate unique id for the annotation
+                id_gen = str(uuid.uuid4())[:8]
+                # Create Label Studio format annotation
+                annotation = {
+                    "x": x_percent,
+                    "y": y_percent,
+                    "width": width_percent,
+                    "height": height_percent,
+                    "rectanglelabels": ['Transcription'],  # TODO: customize
+                    "score": score, 
+                    "text": text
+                }
+                
+                label_studio_results.append(annotation)
+            
+            # Replace the OCR result with the Label Studio formatted result
+            normalized_results.append(label_studio_results)
+            
+        return normalized_results
+    
+    def _calculate_similarity(self, text: str, reference_texts: List[str]) -> float:
+        """
+        Calculate similarity between a text and a list of reference texts
+
+        Args:
+            text: The text to compare
+            reference_texts: List of reference texts
+
+        Returns:
+            Similarity score between 0 and 1
+        """
+        # Convert to lowercase for case-insensitive comparison
+        text = text.lower()
+        reference_texts = [ref_text.lower() for ref_text in reference_texts]
+        
+        # Use SequenceMatcher to calculate similarity
+        from difflib import SequenceMatcher
+        
+        best_score = 0
+        if reference_texts:
+            for ref_text in reference_texts:
+                # Calculate similarity ratio using SequenceMatcher
+                similarity = SequenceMatcher(None, text, ref_text).ratio()
+                print(f"Similarity between {text} and {ref_text}: {similarity}")
+                
+                # Update best score if this one is higher
+                if similarity > best_score:
+                    best_score = similarity
+        
+        return best_score
+    
+    def _filter_ocr_results(self, ocr_results: list, reference_texts: List[str]) -> list:
+        """
+        Filter OCR results based on similarity to output texts
+        
+        Args:
+            ocr_results: List of OCR results
+            reference_texts: List of reference texts
+                
+        Returns:
+            List of filtered OCR results
+        """
+        filtered_results = []
+        for result in ocr_results:
+            # Simple similarity function - can be replaced with more sophisticated methods
+            similarity = self._calculate_similarity(result['text'], reference_texts)
+            if similarity >= 0.9:
+                filtered_results.append(result)
+            
+        return filtered_results
+        
+
+    async def aapply(
+        self,
+        input: InternalDataFrame,
+        runtime: AsyncRuntime,
+    ) -> InternalDataFrame:
+
+        with json_schema_to_pydantic(self.field_schema) as ResponseModel:
+            # special handling to flag image inputs if they exist
+            input_field_types = defaultdict(lambda: MessageChunkType.TEXT)
+            for tag in self.image_tags:
+                # these are the project variable names, NOT the label config tag names. TODO: pass this info from LSE to avoid recomputing it here.
+                variables = extract_variable_name(tag.value)
+                if len(variables) != 1:
+                    logger.warning(
+                        f"Image tag {tag.name} has multiple variables: {variables}. Cannot mark these variables as image inputs."
+                    )
+                    continue
+                input_field_types[variables[0]] = (
+                    MessageChunkType.IMAGE_URLS
+                    if tag.attr.get("valueList")
+                    else MessageChunkType.IMAGE_URL
+                )
+
+            logger.debug(
+                f"Using VisionRuntime with input field types: {input_field_types}"
+            )
+            output = await runtime.batch_to_batch(
+                input,
+                input_template=self.input_template,
+                output_template="",
+                instructions_template=self.instructions,
+                response_model=ResponseModel,
+                input_field_types=input_field_types,
+            )
+            output['label'] = await self.process_images_with_ocr(input['image'].tolist())
+            
+            # Convert OCR results to a format that can be used for similarity matching
+            # Process each row individually
+            # Process each row to filter OCR results based on similarity to reference texts
+            filtered_labels = []
+            for i, row in output.iterrows():
+                # Filter OCR results based on similarity to reference texts
+                filtered_ocr = self._filter_ocr_results(row['label'], row['output'])
+                filtered_labels.append(filtered_ocr)
+            output['label'] = filtered_labels
+            return output
+
+
+if __name__ == "__main__":
+    images = [
+      "https://htx-pub.s3.amazonaws.com/demo/ocr/pdf/output_0000.png",
+    #   "https://htx-pub.s3.amazonaws.com/demo/ocr/pdf/output_0001.png",
+    #   "https://htx-pub.s3.amazonaws.com/demo/ocr/pdf/output_0002.png",
+    #   "https://htx-pub.s3.amazonaws.com/demo/ocr/pdf/output_0003.png",
+    #   "https://htx-pub.s3.amazonaws.com/demo/ocr/pdf/output_0004.png",
+    #   "https://htx-pub.s3.amazonaws.com/demo/ocr/pdf/output_0005.png",
+    #   "https://htx-pub.s3.amazonaws.com/demo/ocr/pdf/output_0006.png",
+    #   "https://htx-pub.s3.amazonaws.com/demo/ocr/pdf/output_0007.png",
+    #   "https://htx-pub.s3.amazonaws.com/demo/ocr/pdf/output_0008.png"
+    ]
+    results = asyncio.run(LabelStudioSkillImageOCR.process_images_with_ocr(images))
+    print(results)

From aa45c0a270e5000744e785167934dceb6141d583 Mon Sep 17 00:00:00 2001
From: nik <nik@heartex.net>
Date: Thu, 6 Mar 2025 00:00:49 +0100
Subject: [PATCH 02/10] Add per-region textarea support

---
 .../collection/label_studio_image_ocr.py      | 103 ++++++++++++------
 1 file changed, 71 insertions(+), 32 deletions(-)

diff --git a/adala/skills/collection/label_studio_image_ocr.py b/adala/skills/collection/label_studio_image_ocr.py
index 1171eb8b..6d6f7b50 100644
--- a/adala/skills/collection/label_studio_image_ocr.py
+++ b/adala/skills/collection/label_studio_image_ocr.py
@@ -1,7 +1,7 @@
 import re
 import logging
 import pandas as pd
-from typing import List, Optional, Type
+from typing import List, Optional, Type, Dict, Tuple
 from functools import cached_property
 from copy import deepcopy
 from collections import defaultdict
@@ -208,8 +208,13 @@ async def process_single_image(image_data):
         tasks = [process_single_image(image) for image in images]
         results = await asyncio.gather(*tasks)
         
+        return results
+    
+    def _convert_ocr_results_to_label_studio_format(self, results: list) -> Tuple[List, List]:
+        
         # normalize EasyOCR results to RectangleLabels bounding boxes format of Label Studio
-        normalized_results = []
+        all_bbox_annotations = []
+        all_text_annotations = []
         for result in results:
             if not result:
                 continue
@@ -222,7 +227,8 @@ async def process_single_image(image_data):
             original_height = result.get('image_height', 1000)
             
             # Convert to Label Studio format
-            label_studio_results = []
+            bbox_annotations = []
+            text_annotations = []
             
             for i, (bbox, text, score) in enumerate(zip(bboxes, texts, scores)):
                 # EasyOCR bboxes format is [[x1,y1],[x2,y2],[x3,y3],[x4,y4]]
@@ -251,24 +257,41 @@ async def process_single_image(image_data):
                 # generate unique id for the annotation
                 id_gen = str(uuid.uuid4())[:8]
                 # Create Label Studio format annotation
-                annotation = {
+                bbox_annotation = {
                     "x": x_percent,
                     "y": y_percent,
                     "width": width_percent,
                     "height": height_percent,
-                    "rectanglelabels": ['Transcription'],  # TODO: customize
-                    "score": score, 
-                    "text": text
+                    "rotation": 0,
+                    "id": id_gen,
+                    # "rectanglelabels": ['Transcription'],  # TODO: customize
+                    # "score": score, 
+                    # "text": text
+                }
+                text_annotation = {
+                    'text': [text],
+                    'id': id_gen
                 }
+                # annotation = {
+                #     "x": x_percent,
+                #     "y": y_percent,
+                #     "width": width_percent,
+                #     "height": height_percent,
+                #     "rectanglelabels": ['Transcription'],  # TODO: customize
+                #     "score": score, 
+                #     "text": text
+                # }
                 
-                label_studio_results.append(annotation)
+                bbox_annotations.append(bbox_annotation)
+                text_annotations.append(text_annotation)
             
             # Replace the OCR result with the Label Studio formatted result
-            normalized_results.append(label_studio_results)
+            all_bbox_annotations.append(bbox_annotations)
+            all_text_annotations.append(text_annotations)
             
-        return normalized_results
+        return all_bbox_annotations, all_text_annotations
     
-    def _calculate_similarity(self, text: str, reference_texts: List[str]) -> float:
+    def _calculate_similarity(self, text: str, reference_texts: List[str]) -> Tuple[float, str]:
         """
         Calculate similarity between a text and a list of reference texts
 
@@ -277,29 +300,29 @@ def _calculate_similarity(self, text: str, reference_texts: List[str]) -> float:
             reference_texts: List of reference texts
 
         Returns:
-            Similarity score between 0 and 1
+            Similarity score between 0 and 1 and the best matching text
         """
         # Convert to lowercase for case-insensitive comparison
         text = text.lower()
-        reference_texts = [ref_text.lower() for ref_text in reference_texts]
         
         # Use SequenceMatcher to calculate similarity
         from difflib import SequenceMatcher
         
         best_score = 0
+        best_match = None
         if reference_texts:
             for ref_text in reference_texts:
                 # Calculate similarity ratio using SequenceMatcher
-                similarity = SequenceMatcher(None, text, ref_text).ratio()
+                similarity = SequenceMatcher(None, text, ref_text.lower()).ratio()
                 print(f"Similarity between {text} and {ref_text}: {similarity}")
                 
                 # Update best score if this one is higher
                 if similarity > best_score:
                     best_score = similarity
-        
-        return best_score
+                    best_match = ref_text
+        return best_score, best_match
     
-    def _filter_ocr_results(self, ocr_results: list, reference_texts: List[str]) -> list:
+    def _filter_ocr_results(self, ocr_results: Dict, reference_texts: List[str]) -> list:
         """
         Filter OCR results based on similarity to output texts
         
@@ -310,12 +333,18 @@ def _filter_ocr_results(self, ocr_results: list, reference_texts: List[str]) ->
         Returns:
             List of filtered OCR results
         """
-        filtered_results = []
-        for result in ocr_results:
+        filtered_results = {
+            'bboxes': [],
+            'texts': [],
+            'scores': []
+        }
+        for bbox, text, score in zip(ocr_results['bboxes'], ocr_results['texts'], ocr_results['scores']):
             # Simple similarity function - can be replaced with more sophisticated methods
-            similarity = self._calculate_similarity(result['text'], reference_texts)
+            similarity, best_match = self._calculate_similarity(text, reference_texts)
             if similarity >= 0.9:
-                filtered_results.append(result)
+                filtered_results['bboxes'].append(bbox)
+                filtered_results['texts'].append(best_match)
+                filtered_results['scores'].append(score)
             
         return filtered_results
         
@@ -329,6 +358,7 @@ async def aapply(
         with json_schema_to_pydantic(self.field_schema) as ResponseModel:
             # special handling to flag image inputs if they exist
             input_field_types = defaultdict(lambda: MessageChunkType.TEXT)
+            image_value_key = None
             for tag in self.image_tags:
                 # these are the project variable names, NOT the label config tag names. TODO: pass this info from LSE to avoid recomputing it here.
                 variables = extract_variable_name(tag.value)
@@ -337,7 +367,8 @@ async def aapply(
                         f"Image tag {tag.name} has multiple variables: {variables}. Cannot mark these variables as image inputs."
                     )
                     continue
-                input_field_types[variables[0]] = (
+                image_value_key = variables[0]
+                input_field_types[image_value_key] = (
                     MessageChunkType.IMAGE_URLS
                     if tag.attr.get("valueList")
                     else MessageChunkType.IMAGE_URL
@@ -354,17 +385,25 @@ async def aapply(
                 response_model=ResponseModel,
                 input_field_types=input_field_types,
             )
-            output['label'] = await self.process_images_with_ocr(input['image'].tolist())
-            
-            # Convert OCR results to a format that can be used for similarity matching
-            # Process each row individually
-            # Process each row to filter OCR results based on similarity to reference texts
-            filtered_labels = []
+            print(f'Output: {output}')
+            print(f'Process images with OCR: {input[image_value_key].tolist()}')
+            ocr_results = await self.process_images_with_ocr(input[image_value_key].tolist())
+            filtered_ocr_results = []
             for i, row in output.iterrows():
-                # Filter OCR results based on similarity to reference texts
-                filtered_ocr = self._filter_ocr_results(row['label'], row['output'])
-                filtered_labels.append(filtered_ocr)
-            output['label'] = filtered_labels
+                extracted_result = row['output']
+                filtered_ocr_result = {
+                    'image_width': ocr_results[i]['image_width'],
+                    'image_height': ocr_results[i]['image_height'],
+                    'ocr_data': self._filter_ocr_results(ocr_results[i]['ocr_data'], extracted_result)
+                }
+                filtered_ocr_results.append(filtered_ocr_result)
+            print(f'Filtered OCR results: {filtered_ocr_results}')
+            # convert filtered OCR results to Label Studio format
+            bbox_annotations, text_annotations = self._convert_ocr_results_to_label_studio_format(filtered_ocr_results)
+            print(f'Bbox annotations: {bbox_annotations}')
+            print(f'Text annotations: {text_annotations}')
+            output['bbox'] = bbox_annotations
+            output['transcription'] = text_annotations
             return output
 
 

From b00ee19820ccdd5bd27c8d9f031a51c26f253153 Mon Sep 17 00:00:00 2001
From: niklub <niklub@users.noreply.github.com>
Date: Thu, 6 Mar 2025 08:18:20 +0000
Subject: [PATCH 03/10] Sync Follow Merge dependencies

Workflow run: https://github.com/HumanSignal/Adala/actions/runs/13694164225
---
 poetry.lock    | 6 +++---
 pyproject.toml | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/poetry.lock b/poetry.lock
index 9580fe2a..e23593b7 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -3696,7 +3696,7 @@ optional = false
 python-versions = ">=3.9,<4"
 groups = ["main"]
 files = [
-    {file = "4b2f1d9b3befa4a546907321912055a43a408d17.zip", hash = "sha256:4fb8066f51597a7b0b3687527140f3bf8a7259d4e93a9c3de0920f0ef9c4e0ff"},
+    {file = "9bed76c758ac7ffc312c62634d0e9cd873ea5084.zip", hash = "sha256:3437c38a449da104ee01eaa5f22c27206cc93d4d02657574be9c065ad8df4134"},
 ]
 
 [package.dependencies]
@@ -3722,7 +3722,7 @@ xmljson = "0.2.1"
 
 [package.source]
 type = "url"
-url = "https://github.com/HumanSignal/label-studio-sdk/archive/4b2f1d9b3befa4a546907321912055a43a408d17.zip"
+url = "https://github.com/HumanSignal/label-studio-sdk/archive/9bed76c758ac7ffc312c62634d0e9cd873ea5084.zip"
 
 [[package]]
 name = "litellm"
@@ -8487,4 +8487,4 @@ type = ["pytest-mypy"]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.9,<3.9.7 || >3.9.7,<3.13"
-content-hash = "c5fdce848262a8d86c0ef4f385c95754a408d24077294127ed3294f66b77c66c"
+content-hash = "79044b88e569b6564f33b5d1eb1a4b43213d98e7778edbf8dfaafdc78666bf99"
diff --git a/pyproject.toml b/pyproject.toml
index 0d24e767..b09800a3 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -42,7 +42,7 @@ celery = {version = "^5.3.6", extras = ["redis"]}
 kombu = ">=5.4.0rc2" # Pin version to fix https://github.com/celery/celery/issues/8030. TODO: remove when this fix will be included in celery
 uvicorn = "*"
 pydantic-settings = "^2.2.1"
-label-studio-sdk = {url = "https://github.com/HumanSignal/label-studio-sdk/archive/4b2f1d9b3befa4a546907321912055a43a408d17.zip"}
+label-studio-sdk = {url = "https://github.com/HumanSignal/label-studio-sdk/archive/9bed76c758ac7ffc312c62634d0e9cd873ea5084.zip"}
 kafka-python-ng = "^2.2.3"
 requests = "^2.32.0"
 # Using litellm from forked repo until vertex fix is released: https://github.com/BerriAI/litellm/issues/7904

From 0b626a7507cf796007c5fb50c78ee8b1799a6fef Mon Sep 17 00:00:00 2001
From: niklub <niklub@users.noreply.github.com>
Date: Mon, 10 Mar 2025 22:19:54 +0000
Subject: [PATCH 04/10] Sync Follow Merge dependencies

Workflow run: https://github.com/HumanSignal/Adala/actions/runs/13775885307
---
 poetry.lock    | 164 ++++++++++++++++++++++---------------------------
 pyproject.toml |   2 +-
 2 files changed, 73 insertions(+), 93 deletions(-)

diff --git a/poetry.lock b/poetry.lock
index 629690e5..ef7d66bb 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 2.0.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 2.1.1 and should not be changed by hand.
 
 [[package]]
 name = "aiohappyeyeballs"
@@ -123,7 +123,7 @@ multidict = ">=4.5,<7.0"
 yarl = ">=1.12.0,<2.0"
 
 [package.extras]
-speedups = ["Brotli", "aiodns (>=3.2.0)", "brotlicffi"]
+speedups = ["Brotli ; platform_python_implementation == \"CPython\"", "aiodns (>=3.2.0) ; sys_platform == \"linux\" or sys_platform == \"darwin\"", "brotlicffi ; platform_python_implementation != \"CPython\""]
 
 [[package]]
 name = "aiokafka"
@@ -206,8 +206,8 @@ files = [
 ]
 
 [package.extras]
-dev = ["aiounittest (==1.4.1)", "attribution (==1.6.2)", "black (==23.3.0)", "coverage[toml] (==7.2.3)", "flake8 (==5.0.4)", "flake8-bugbear (==23.3.12)", "flit (==3.7.1)", "mypy (==1.2.0)", "ufmt (==2.1.0)", "usort (==1.0.6)"]
-docs = ["sphinx (==6.1.3)", "sphinx-mdinclude (==0.5.3)"]
+dev = ["aiounittest (==1.4.1) ; python_version < \"3.8\"", "attribution (==1.6.2)", "black (==23.3.0)", "coverage[toml] (==7.2.3)", "flake8 (==5.0.4)", "flake8-bugbear (==23.3.12)", "flit (==3.7.1)", "mypy (==1.2.0)", "ufmt (==2.1.0)", "usort (==1.0.6)"]
+docs = ["sphinx (==6.1.3) ; python_version >= \"3.8\"", "sphinx-mdinclude (==0.5.3)"]
 
 [[package]]
 name = "amqp"
@@ -256,7 +256,7 @@ typing-extensions = {version = ">=4.1", markers = "python_version < \"3.11\""}
 
 [package.extras]
 doc = ["Sphinx (>=7.4,<8.0)", "packaging", "sphinx-autodoc-typehints (>=1.2.0)", "sphinx-rtd-theme"]
-test = ["anyio[trio]", "coverage[toml] (>=7)", "exceptiongroup (>=1.2.0)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "uvloop (>=0.21.0b1)"]
+test = ["anyio[trio]", "coverage[toml] (>=7)", "exceptiongroup (>=1.2.0)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "uvloop (>=0.21.0b1) ; platform_python_implementation == \"CPython\" and platform_system != \"Windows\""]
 trio = ["trio (>=0.26.1)"]
 
 [[package]]
@@ -412,8 +412,8 @@ files = [
 six = ">=1.12.0"
 
 [package.extras]
-astroid = ["astroid (>=1,<2)", "astroid (>=2,<4)"]
-test = ["astroid (>=1,<2)", "astroid (>=2,<4)", "pytest"]
+astroid = ["astroid (>=1,<2) ; python_version < \"3\"", "astroid (>=2,<4) ; python_version >= \"3\""]
+test = ["astroid (>=1,<2) ; python_version < \"3\"", "astroid (>=2,<4) ; python_version >= \"3\"", "pytest"]
 
 [[package]]
 name = "async-lru"
@@ -455,12 +455,12 @@ files = [
 ]
 
 [package.extras]
-benchmark = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-codspeed", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
-cov = ["cloudpickle", "coverage[toml] (>=5.3)", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
-dev = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pre-commit", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
+benchmark = ["cloudpickle ; platform_python_implementation == \"CPython\"", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\"", "pympler", "pytest (>=4.3.0)", "pytest-codspeed", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\" and python_version < \"3.13\"", "pytest-xdist[psutil]"]
+cov = ["cloudpickle ; platform_python_implementation == \"CPython\"", "coverage[toml] (>=5.3)", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\"", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\" and python_version < \"3.13\"", "pytest-xdist[psutil]"]
+dev = ["cloudpickle ; platform_python_implementation == \"CPython\"", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\"", "pre-commit", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\" and python_version < \"3.13\"", "pytest-xdist[psutil]"]
 docs = ["cogapp", "furo", "myst-parser", "sphinx", "sphinx-notfound-page", "sphinxcontrib-towncrier", "towncrier (<24.7)"]
-tests = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
-tests-mypy = ["mypy (>=1.11.1)", "pytest-mypy-plugins"]
+tests = ["cloudpickle ; platform_python_implementation == \"CPython\"", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\"", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\" and python_version < \"3.13\"", "pytest-xdist[psutil]"]
+tests-mypy = ["mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\"", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\" and python_version < \"3.13\""]
 
 [[package]]
 name = "babel"
@@ -607,7 +607,7 @@ typing-extensions = {version = ">=4.0.1", markers = "python_version < \"3.11\""}
 
 [package.extras]
 colorama = ["colorama (>=0.4.3)"]
-d = ["aiohttp (>=3.7.4)", "aiohttp (>=3.7.4,!=3.9.0)"]
+d = ["aiohttp (>=3.7.4) ; sys_platform != \"win32\" or implementation_name != \"pypy\"", "aiohttp (>=3.7.4,!=3.9.0) ; sys_platform == \"win32\" and implementation_name == \"pypy\""]
 jupyter = ["ipython (>=7.8.0)", "tokenize-rt (>=3.2.0)"]
 uvloop = ["uvloop (>=0.15.2)"]
 
@@ -694,7 +694,7 @@ tomli = {version = ">=1.1.0", markers = "python_version < \"3.11\""}
 
 [package.extras]
 docs = ["furo (>=2023.08.17)", "sphinx (>=7.0,<8.0)", "sphinx-argparse-cli (>=1.5)", "sphinx-autodoc-typehints (>=1.10)", "sphinx-issues (>=3.0.0)"]
-test = ["build[uv,virtualenv]", "filelock (>=3)", "pytest (>=6.2.4)", "pytest-cov (>=2.12)", "pytest-mock (>=2)", "pytest-rerunfailures (>=9.1)", "pytest-xdist (>=1.34)", "setuptools (>=42.0.0)", "setuptools (>=56.0.0)", "setuptools (>=56.0.0)", "setuptools (>=67.8.0)", "wheel (>=0.36.0)"]
+test = ["build[uv,virtualenv]", "filelock (>=3)", "pytest (>=6.2.4)", "pytest-cov (>=2.12)", "pytest-mock (>=2)", "pytest-rerunfailures (>=9.1)", "pytest-xdist (>=1.34)", "setuptools (>=42.0.0) ; python_version < \"3.10\"", "setuptools (>=56.0.0) ; python_version == \"3.10\"", "setuptools (>=56.0.0) ; python_version == \"3.11\"", "setuptools (>=67.8.0) ; python_version >= \"3.12\"", "wheel (>=0.36.0)"]
 typing = ["build[uv]", "importlib-metadata (>=5.1)", "mypy (>=1.9.0,<1.10.0)", "tomli", "typing-extensions (>=3.7.4.3)"]
 uv = ["uv (>=0.1.18)"]
 virtualenv = ["virtualenv (>=20.0.35)"]
@@ -740,32 +740,32 @@ vine = ">=5.1.0,<6.0"
 arangodb = ["pyArango (>=2.0.2)"]
 auth = ["cryptography (==42.0.5)"]
 azureblockblob = ["azure-storage-blob (>=12.15.0)"]
-brotli = ["brotli (>=1.0.0)", "brotlipy (>=0.7.0)"]
+brotli = ["brotli (>=1.0.0) ; platform_python_implementation == \"CPython\"", "brotlipy (>=0.7.0) ; platform_python_implementation == \"PyPy\""]
 cassandra = ["cassandra-driver (>=3.25.0,<4)"]
 consul = ["python-consul2 (==0.1.5)"]
 cosmosdbsql = ["pydocumentdb (==2.3.5)"]
-couchbase = ["couchbase (>=3.0.0)"]
+couchbase = ["couchbase (>=3.0.0) ; platform_python_implementation != \"PyPy\" and (platform_system != \"Windows\" or python_version < \"3.10\")"]
 couchdb = ["pycouchdb (==1.14.2)"]
 django = ["Django (>=2.2.28)"]
 dynamodb = ["boto3 (>=1.26.143)"]
 elasticsearch = ["elastic-transport (<=8.13.0)", "elasticsearch (<=8.13.0)"]
-eventlet = ["eventlet (>=0.32.0)"]
+eventlet = ["eventlet (>=0.32.0) ; python_version < \"3.10\""]
 gcs = ["google-cloud-storage (>=2.10.0)"]
 gevent = ["gevent (>=1.5.0)"]
-librabbitmq = ["librabbitmq (>=2.0.0)"]
-memcache = ["pylibmc (==1.6.3)"]
+librabbitmq = ["librabbitmq (>=2.0.0) ; python_version < \"3.11\""]
+memcache = ["pylibmc (==1.6.3) ; platform_system != \"Windows\""]
 mongodb = ["pymongo[srv] (>=4.0.2)"]
 msgpack = ["msgpack (==1.0.8)"]
 pymemcache = ["python-memcached (>=1.61)"]
-pyro = ["pyro4 (==4.82)"]
+pyro = ["pyro4 (==4.82) ; python_version < \"3.11\""]
 pytest = ["pytest-celery[all] (>=1.0.0)"]
 redis = ["redis (>=4.5.2,!=4.5.5,<6.0.0)"]
 s3 = ["boto3 (>=1.26.143)"]
 slmq = ["softlayer-messaging (>=1.0.3)"]
-solar = ["ephem (==4.1.5)"]
+solar = ["ephem (==4.1.5) ; platform_python_implementation != \"PyPy\""]
 sqlalchemy = ["sqlalchemy (>=1.4.48,<2.1)"]
-sqs = ["boto3 (>=1.26.143)", "kombu[sqs] (>=5.3.4)", "pycurl (>=7.43.0.5)", "urllib3 (>=1.26.16)"]
-tblib = ["tblib (>=1.3.0)", "tblib (>=1.5.0)"]
+sqs = ["boto3 (>=1.26.143)", "kombu[sqs] (>=5.3.4)", "pycurl (>=7.43.0.5) ; sys_platform != \"win32\" and platform_python_implementation == \"CPython\"", "urllib3 (>=1.26.16)"]
+tblib = ["tblib (>=1.3.0) ; python_version < \"3.8.0\"", "tblib (>=1.5.0) ; python_version >= \"3.8.0\""]
 yaml = ["PyYAML (>=3.10)"]
 zookeeper = ["kazoo (>=1.3.1)"]
 zstd = ["zstandard (==0.22.0)"]
@@ -1208,10 +1208,10 @@ files = [
 ]
 
 [package.extras]
-avro = ["avro (>=1.11.1,<2)", "fastavro (>=0.23.0,<1.0)", "fastavro (>=1.0)", "requests"]
-dev = ["avro (>=1.11.1,<2)", "fastavro (>=0.23.0,<1.0)", "fastavro (>=1.0)", "flake8", "pytest", "pytest (==4.6.4)", "pytest-timeout", "requests"]
-doc = ["avro (>=1.11.1,<2)", "fastavro (>=0.23.0,<1.0)", "fastavro (>=1.0)", "requests", "sphinx", "sphinx-rtd-theme"]
-json = ["jsonschema", "pyrsistent", "pyrsistent (==0.16.1)", "requests"]
+avro = ["avro (>=1.11.1,<2)", "fastavro (>=0.23.0,<1.0) ; python_version < \"3.0\"", "fastavro (>=1.0) ; python_version > \"3.0\"", "requests"]
+dev = ["avro (>=1.11.1,<2)", "fastavro (>=0.23.0,<1.0) ; python_version < \"3.0\"", "fastavro (>=1.0) ; python_version > \"3.0\"", "flake8", "pytest (==4.6.4) ; python_version < \"3.0\"", "pytest ; python_version >= \"3.0\"", "pytest-timeout", "requests"]
+doc = ["avro (>=1.11.1,<2)", "fastavro (>=0.23.0,<1.0) ; python_version < \"3.0\"", "fastavro (>=1.0) ; python_version > \"3.0\"", "requests", "sphinx", "sphinx-rtd-theme"]
+json = ["jsonschema", "pyrsistent (==0.16.1) ; python_version < \"3.0\"", "pyrsistent ; python_version > \"3.0\"", "requests"]
 protobuf = ["protobuf", "requests"]
 schema-registry = ["requests"]
 
@@ -1386,7 +1386,7 @@ files = [
 tomli = {version = "*", optional = true, markers = "python_full_version <= \"3.11.0a6\" and extra == \"toml\""}
 
 [package.extras]
-toml = ["tomli"]
+toml = ["tomli ; python_full_version <= \"3.11.0a6\""]
 
 [[package]]
 name = "cryptography"
@@ -1476,8 +1476,8 @@ jinja2 = ">=2.10.1,<4.0"
 packaging = "*"
 pydantic = [
     {version = ">=1.5.1,<2.4.0 || >2.4.0,<3.0", extras = ["email"], markers = "python_version < \"3.10\""},
-    {version = ">=1.9.0,<2.4.0 || >2.4.0,<3.0", extras = ["email"], markers = "python_version >= \"3.10\" and python_version < \"3.11\""},
-    {version = ">=1.10.0,<2.4.0 || >2.4.0,<3.0", extras = ["email"], markers = "python_version >= \"3.11\" and python_version < \"3.12\""},
+    {version = ">=1.9.0,<2.4.0 || >2.4.0,<3.0", extras = ["email"], markers = "python_version == \"3.10\""},
+    {version = ">=1.10.0,<2.4.0 || >2.4.0,<3.0", extras = ["email"], markers = "python_version >= \"3.11\" and python_version < \"4.0\""},
     {version = ">=1.10.0,<2.0.0 || >2.0.0,<2.0.1 || >2.0.1,<2.4.0 || >2.4.0,<3.0", extras = ["email"], markers = "python_version >= \"3.12\" and python_version < \"4.0\""},
 ]
 pyyaml = ">=6.0.1"
@@ -1522,7 +1522,7 @@ xxhash = "*"
 apache-beam = ["apache-beam (>=2.26.0)"]
 audio = ["librosa", "soundfile (>=0.12.1)"]
 benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"]
-dev = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
+dev = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0) ; sys_platform != \"win32\" and python_version < \"3.10\"", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14) ; sys_platform != \"win32\"", "jaxlib (>=0.3.14) ; sys_platform != \"win32\"", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
 docs = ["s3fs", "tensorflow (>=2.6.0)", "torch", "transformers"]
 jax = ["jax (>=0.3.14)", "jaxlib (>=0.3.14)"]
 metrics-tests = ["Werkzeug (>=1.0.1)", "accelerate", "bert-score (>=0.3.6)", "jiwer", "langdetect", "mauve-text", "nltk", "requests-file (>=1.5.1)", "rouge-score", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "spacy (>=3.0.0)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "typer (<0.5.0)"]
@@ -1530,7 +1530,7 @@ quality = ["ruff (>=0.3.0)"]
 s3 = ["s3fs"]
 tensorflow = ["tensorflow (>=2.6.0)"]
 tensorflow-gpu = ["tensorflow (>=2.6.0)"]
-tests = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
+tests = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0) ; sys_platform != \"win32\" and python_version < \"3.10\"", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14) ; sys_platform != \"win32\"", "jaxlib (>=0.3.14) ; sys_platform != \"win32\"", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
 torch = ["torch"]
 vision = ["Pillow (>=6.2.1)"]
 
@@ -1738,7 +1738,7 @@ description = "Backport of PEP 654 (exception groups)"
 optional = false
 python-versions = ">=3.7"
 groups = ["main", "dev"]
-markers = "python_version < \"3.11\""
+markers = "python_version <= \"3.10\""
 files = [
     {file = "exceptiongroup-1.2.2-py3-none-any.whl", hash = "sha256:3111b9d131c238bec2f8f516e123e14ba243563fb135d3fe885990585aa7795b"},
     {file = "exceptiongroup-1.2.2.tar.gz", hash = "sha256:47c2edf7c6738fafb49fd34290706d1a1a2f4d1c6df275526b62cbb4aa5393cc"},
@@ -1760,7 +1760,7 @@ files = [
 ]
 
 [package.extras]
-tests = ["asttokens (>=2.1.0)", "coverage", "coverage-enable-subprocess", "ipython", "littleutils", "pytest", "rich"]
+tests = ["asttokens (>=2.1.0)", "coverage", "coverage-enable-subprocess", "ipython", "littleutils", "pytest", "rich ; python_version >= \"3.11\""]
 
 [[package]]
 name = "faker"
@@ -1853,7 +1853,7 @@ files = [
 [package.extras]
 docs = ["furo (>=2024.8.6)", "sphinx (>=8.0.2)", "sphinx-autodoc-typehints (>=2.4.1)"]
 testing = ["covdefaults (>=2.3)", "coverage (>=7.6.1)", "diff-cover (>=9.2)", "pytest (>=8.3.3)", "pytest-asyncio (>=0.24)", "pytest-cov (>=5)", "pytest-mock (>=3.14)", "pytest-timeout (>=2.3.1)", "virtualenv (>=20.26.4)"]
-typing = ["typing-extensions (>=4.12.2)"]
+typing = ["typing-extensions (>=4.12.2) ; python_version < \"3.11\""]
 
 [[package]]
 name = "flatbuffers"
@@ -1945,18 +1945,18 @@ files = [
 ]
 
 [package.extras]
-all = ["brotli (>=1.0.1)", "brotlicffi (>=0.8.0)", "fs (>=2.2.0,<3)", "lxml (>=4.0)", "lz4 (>=1.7.4.2)", "matplotlib", "munkres", "pycairo", "scipy", "skia-pathops (>=0.5.0)", "sympy", "uharfbuzz (>=0.23.0)", "unicodedata2 (>=15.1.0)", "xattr", "zopfli (>=0.1.4)"]
+all = ["brotli (>=1.0.1) ; platform_python_implementation == \"CPython\"", "brotlicffi (>=0.8.0) ; platform_python_implementation != \"CPython\"", "fs (>=2.2.0,<3)", "lxml (>=4.0)", "lz4 (>=1.7.4.2)", "matplotlib", "munkres ; platform_python_implementation == \"PyPy\"", "pycairo", "scipy ; platform_python_implementation != \"PyPy\"", "skia-pathops (>=0.5.0)", "sympy", "uharfbuzz (>=0.23.0)", "unicodedata2 (>=15.1.0) ; python_version <= \"3.12\"", "xattr ; sys_platform == \"darwin\"", "zopfli (>=0.1.4)"]
 graphite = ["lz4 (>=1.7.4.2)"]
-interpolatable = ["munkres", "pycairo", "scipy"]
+interpolatable = ["munkres ; platform_python_implementation == \"PyPy\"", "pycairo", "scipy ; platform_python_implementation != \"PyPy\""]
 lxml = ["lxml (>=4.0)"]
 pathops = ["skia-pathops (>=0.5.0)"]
 plot = ["matplotlib"]
 repacker = ["uharfbuzz (>=0.23.0)"]
 symfont = ["sympy"]
-type1 = ["xattr"]
+type1 = ["xattr ; sys_platform == \"darwin\""]
 ufo = ["fs (>=2.2.0,<3)"]
-unicode = ["unicodedata2 (>=15.1.0)"]
-woff = ["brotli (>=1.0.1)", "brotlicffi (>=0.8.0)", "zopfli (>=0.1.4)"]
+unicode = ["unicodedata2 (>=15.1.0) ; python_version <= \"3.12\""]
+woff = ["brotli (>=1.0.1) ; platform_python_implementation == \"CPython\"", "brotlicffi (>=0.8.0) ; platform_python_implementation != \"CPython\"", "zopfli (>=0.1.4)"]
 
 [[package]]
 name = "fqdn"
@@ -2531,7 +2531,7 @@ idna = "*"
 sniffio = "*"
 
 [package.extras]
-brotli = ["brotli", "brotlicffi"]
+brotli = ["brotli ; platform_python_implementation == \"CPython\"", "brotlicffi ; platform_python_implementation != \"CPython\""]
 cli = ["click (==8.*)", "pygments (==2.*)", "rich (>=10,<14)"]
 http2 = ["h2 (>=3,<5)"]
 socks = ["socksio (==1.*)"]
@@ -2740,7 +2740,7 @@ zipp = ">=0.5"
 [package.extras]
 doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
 perf = ["ipython"]
-test = ["flufl.flake8", "importlib-resources (>=1.3)", "jaraco.test (>=5.4)", "packaging", "pyfakefs", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-mypy", "pytest-perf (>=0.9.2)", "pytest-ruff (>=0.2.1)"]
+test = ["flufl.flake8", "importlib-resources (>=1.3) ; python_version < \"3.9\"", "jaraco.test (>=5.4)", "packaging", "pyfakefs", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-mypy", "pytest-perf (>=0.9.2)", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\""]
 
 [[package]]
 name = "importlib-resources"
@@ -2759,7 +2759,7 @@ markers = {dev = "python_version < \"3.10\""}
 zipp = {version = ">=3.1.0", markers = "python_version < \"3.10\""}
 
 [package.extras]
-check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1)"]
+check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\""]
 cover = ["pytest-cov"]
 doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
 enabler = ["pytest-enabler (>=2.2)"]
@@ -2780,7 +2780,7 @@ files = [
 
 [package.extras]
 docs = ["jaraco.packaging (>=9)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx"]
-testing = ["pygments", "pytest (>=6)", "pytest-black (>=0.3.7)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-flake8", "pytest-mypy (>=0.9.1)"]
+testing = ["pygments", "pytest (>=6)", "pytest-black (>=0.3.7) ; platform_python_implementation != \"PyPy\"", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-flake8", "pytest-mypy (>=0.9.1) ; platform_python_implementation != \"PyPy\""]
 
 [[package]]
 name = "iniconfig"
@@ -3218,7 +3218,7 @@ traitlets = ">=5.3"
 
 [package.extras]
 docs = ["ipykernel", "myst-parser", "pydata-sphinx-theme", "sphinx (>=4)", "sphinx-autodoc-typehints", "sphinxcontrib-github-alt", "sphinxcontrib-spelling"]
-test = ["coverage", "ipykernel (>=6.14)", "mypy", "paramiko", "pre-commit", "pytest", "pytest-cov", "pytest-jupyter[client] (>=0.4.1)", "pytest-timeout"]
+test = ["coverage", "ipykernel (>=6.14)", "mypy", "paramiko ; sys_platform == \"win32\"", "pre-commit", "pytest", "pytest-cov", "pytest-jupyter[client] (>=0.4.1)", "pytest-timeout"]
 
 [[package]]
 name = "jupyter-console"
@@ -3648,7 +3648,7 @@ azureservicebus = ["azure-servicebus (>=7.10.0)"]
 azurestoragequeues = ["azure-identity (>=1.12.0)", "azure-storage-queue (>=12.6.0)"]
 confluentkafka = ["confluent-kafka (>=2.2.0)"]
 consul = ["python-consul2 (==0.1.5)"]
-librabbitmq = ["librabbitmq (>=2.0.0)"]
+librabbitmq = ["librabbitmq (>=2.0.0) ; python_version < \"3.11\""]
 mongodb = ["pymongo (>=4.1.1)"]
 msgpack = ["msgpack (==1.1.0)"]
 pyro = ["pyro4 (==4.82)"]
@@ -3656,7 +3656,7 @@ qpid = ["qpid-python (>=0.26)", "qpid-tools (>=0.26)"]
 redis = ["redis (>=4.5.2,!=4.5.5,!=5.0.2)"]
 slmq = ["softlayer-messaging (>=1.0.3)"]
 sqlalchemy = ["sqlalchemy (>=1.4.48,<2.1)"]
-sqs = ["boto3 (>=1.26.143)", "pycurl (>=7.43.0.5)", "urllib3 (>=1.26.16)"]
+sqs = ["boto3 (>=1.26.143)", "pycurl (>=7.43.0.5) ; sys_platform != \"win32\" and platform_python_implementation == \"CPython\"", "urllib3 (>=1.26.16)"]
 yaml = ["PyYAML (>=3.10)"]
 zookeeper = ["kazoo (>=2.8.0)"]
 
@@ -3696,7 +3696,7 @@ optional = false
 python-versions = ">=3.9,<4"
 groups = ["main"]
 files = [
-    {file = "9bed76c758ac7ffc312c62634d0e9cd873ea5084.zip", hash = "sha256:3437c38a449da104ee01eaa5f22c27206cc93d4d02657574be9c065ad8df4134"},
+    {file = "5cc1d11e0afbaae6d597c1cbe12805b02af82aac.zip", hash = "sha256:99362c76b98c84e3d24aa6b194768e92c27788216c97663036dcf661c69eaf0b"},
 ]
 
 [package.dependencies]
@@ -3722,7 +3722,7 @@ xmljson = "0.2.1"
 
 [package.source]
 type = "url"
-url = "https://github.com/HumanSignal/label-studio-sdk/archive/9bed76c758ac7ffc312c62634d0e9cd873ea5084.zip"
+url = "https://github.com/HumanSignal/label-studio-sdk/archive/5cc1d11e0afbaae6d597c1cbe12805b02af82aac.zip"
 
 [[package]]
 name = "litellm"
@@ -4191,7 +4191,7 @@ watchdog = ">=2.0"
 
 [package.extras]
 i18n = ["babel (>=2.9.0)"]
-min-versions = ["babel (==2.9.0)", "click (==7.0)", "colorama (==0.4)", "ghp-import (==1.0)", "importlib-metadata (==4.4)", "jinja2 (==2.11.1)", "markdown (==3.3.6)", "markupsafe (==2.0.1)", "mergedeep (==1.3.4)", "mkdocs-get-deps (==0.2.0)", "packaging (==20.5)", "pathspec (==0.11.1)", "pyyaml (==5.1)", "pyyaml-env-tag (==0.1)", "watchdog (==2.0)"]
+min-versions = ["babel (==2.9.0)", "click (==7.0)", "colorama (==0.4) ; platform_system == \"Windows\"", "ghp-import (==1.0)", "importlib-metadata (==4.4) ; python_version < \"3.10\"", "jinja2 (==2.11.1)", "markdown (==3.3.6)", "markupsafe (==2.0.1)", "mergedeep (==1.3.4)", "mkdocs-get-deps (==0.2.0)", "packaging (==20.5)", "pathspec (==0.11.1)", "pyyaml (==5.1)", "pyyaml-env-tag (==0.1)", "watchdog (==2.0)"]
 
 [[package]]
 name = "mkdocs-autorefs"
@@ -4508,7 +4508,7 @@ files = [
 [package.extras]
 develop = ["codecov", "pycodestyle", "pytest (>=4.6)", "pytest-cov", "wheel"]
 docs = ["sphinx"]
-gmpy = ["gmpy2 (>=2.1.0a4)"]
+gmpy = ["gmpy2 (>=2.1.0a4) ; platform_python_implementation != \"PyPy\""]
 tests = ["pytest (>=4.6)"]
 
 [[package]]
@@ -4529,7 +4529,7 @@ PyJWT = {version = ">=1.0.0,<3", extras = ["crypto"]}
 requests = ">=2.0.0,<3"
 
 [package.extras]
-broker = ["pymsalruntime (>=0.14,<0.18)", "pymsalruntime (>=0.17,<0.18)"]
+broker = ["pymsalruntime (>=0.14,<0.18) ; python_version >= \"3.6\" and platform_system == \"Windows\"", "pymsalruntime (>=0.17,<0.18) ; python_version >= \"3.8\" and platform_system == \"Darwin\""]
 
 [[package]]
 name = "multidict"
@@ -4817,7 +4817,7 @@ tornado = ">=6.2.0"
 [package.extras]
 dev = ["hatch", "pre-commit"]
 docs = ["myst-parser", "nbsphinx", "pydata-sphinx-theme", "sphinx (>=1.3.6)", "sphinxcontrib-github-alt", "sphinxcontrib-spelling"]
-test = ["importlib-resources (>=5.0)", "ipykernel", "jupyter-server[test] (>=2.4.0,<3)", "jupyterlab-server[test] (>=2.27.1,<3)", "nbval", "pytest (>=7.0)", "pytest-console-scripts", "pytest-timeout", "pytest-tornasync", "requests"]
+test = ["importlib-resources (>=5.0) ; python_version < \"3.10\"", "ipykernel", "jupyter-server[test] (>=2.4.0,<3)", "jupyterlab-server[test] (>=2.27.1,<3)", "nbval", "pytest (>=7.0)", "pytest-console-scripts", "pytest-timeout", "pytest-tornasync", "requests"]
 
 [[package]]
 name = "notebook-shim"
@@ -5524,7 +5524,7 @@ docs = ["furo", "olefile", "sphinx (>=7.3)", "sphinx-copybutton", "sphinx-inline
 fpx = ["olefile"]
 mic = ["olefile"]
 tests = ["check-manifest", "coverage", "defusedxml", "markdown2", "olefile", "packaging", "pyroma", "pytest", "pytest-cov", "pytest-timeout"]
-typing = ["typing-extensions"]
+typing = ["typing-extensions ; python_version < \"3.10\""]
 xmp = ["defusedxml"]
 
 [[package]]
@@ -5663,7 +5663,7 @@ files = [
 ]
 
 [package.extras]
-test = ["enum34", "ipaddress", "mock", "pywin32", "wmi"]
+test = ["enum34 ; python_version <= \"3.4\"", "ipaddress ; python_version < \"3.0\"", "mock ; python_version < \"3.0\"", "pywin32 ; sys_platform == \"win32\"", "wmi ; sys_platform == \"win32\""]
 
 [[package]]
 name = "ptyprocess"
@@ -5817,7 +5817,7 @@ typing-extensions = {version = ">=4.6.1", markers = "python_version < \"3.13\""}
 
 [package.extras]
 email = ["email-validator (>=2.0.0)"]
-timezone = ["tzdata"]
+timezone = ["tzdata ; python_version >= \"3.9\" and sys_platform == \"win32\""]
 
 [[package]]
 name = "pydantic-core"
@@ -6992,9 +6992,9 @@ files = [
 ]
 
 [package.extras]
-nativelib = ["pyobjc-framework-Cocoa", "pywin32"]
-objc = ["pyobjc-framework-Cocoa"]
-win32 = ["pywin32"]
+nativelib = ["pyobjc-framework-Cocoa ; sys_platform == \"darwin\"", "pywin32 ; sys_platform == \"win32\""]
+objc = ["pyobjc-framework-Cocoa ; sys_platform == \"darwin\""]
+win32 = ["pywin32 ; sys_platform == \"win32\""]
 
 [[package]]
 name = "setuptools"
@@ -7009,9 +7009,9 @@ files = [
 ]
 
 [package.extras]
-core = ["importlib-metadata (>=6)", "importlib-resources (>=5.10.2)", "jaraco.text (>=3.7)", "more-itertools (>=8.8)", "ordered-set (>=3.1.1)", "packaging (>=24)", "platformdirs (>=2.6.2)", "tomli (>=2.0.1)", "wheel (>=0.43.0)"]
+core = ["importlib-metadata (>=6) ; python_version < \"3.10\"", "importlib-resources (>=5.10.2) ; python_version < \"3.9\"", "jaraco.text (>=3.7)", "more-itertools (>=8.8)", "ordered-set (>=3.1.1)", "packaging (>=24)", "platformdirs (>=2.6.2)", "tomli (>=2.0.1) ; python_version < \"3.11\"", "wheel (>=0.43.0)"]
 doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "pygments-github-lexers (==0.0.5)", "pyproject-hooks (!=1.1)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-favicon", "sphinx-inline-tabs", "sphinx-lint", "sphinx-notfound-page (>=1,<2)", "sphinx-reredirects", "sphinxcontrib-towncrier", "towncrier (<24.7)"]
-test = ["build[virtualenv] (>=1.0.3)", "filelock (>=3.4.0)", "importlib-metadata", "ini2toml[lite] (>=0.14)", "jaraco.develop (>=7.21)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "jaraco.test", "mypy (==1.11.*)", "packaging (>=23.2)", "pip (>=19.1)", "pyproject-hooks (!=1.1)", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-home (>=0.5)", "pytest-mypy", "pytest-perf", "pytest-ruff (<0.4)", "pytest-ruff (>=0.2.1)", "pytest-ruff (>=0.3.2)", "pytest-subprocess", "pytest-timeout", "pytest-xdist (>=3)", "tomli", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel"]
+test = ["build[virtualenv] (>=1.0.3)", "filelock (>=3.4.0)", "importlib-metadata", "ini2toml[lite] (>=0.14)", "jaraco.develop (>=7.21) ; python_version >= \"3.9\" and sys_platform != \"cygwin\"", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "jaraco.test", "mypy (==1.11.*)", "packaging (>=23.2)", "pip (>=19.1)", "pyproject-hooks (!=1.1)", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-home (>=0.5)", "pytest-mypy", "pytest-perf ; sys_platform != \"cygwin\"", "pytest-ruff (<0.4) ; platform_system == \"Windows\"", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\"", "pytest-ruff (>=0.3.2) ; sys_platform != \"cygwin\"", "pytest-subprocess", "pytest-timeout", "pytest-xdist (>=3)", "tomli", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel"]
 
 [[package]]
 name = "shellingham"
@@ -7396,7 +7396,7 @@ files = [
     {file = "toml-0.10.2-py2.py3-none-any.whl", hash = "sha256:806143ae5bfb6a3c6e736a764057db0e6a0e05e338b5630894a5f779cabb4f9b"},
     {file = "toml-0.10.2.tar.gz", hash = "sha256:b3bda1d108d5dd99f4a20d24d9c348e91c4db7ab1b749200bded2f839ccbe68f"},
 ]
-markers = {main = "python_version < \"3.11\""}
+markers = {main = "python_version <= \"3.10\""}
 
 [[package]]
 name = "tomli"
@@ -7405,7 +7405,7 @@ description = "A lil' TOML parser"
 optional = false
 python-versions = ">=3.7"
 groups = ["main", "dev"]
-markers = "python_version < \"3.11\""
+markers = "python_version <= \"3.10\""
 files = [
     {file = "tomli-2.0.1-py3-none-any.whl", hash = "sha256:939de3e7a6161af0c887ef91b7d41a53e7c5a1ca976325f429cb46ea9bc30ecc"},
     {file = "tomli-2.0.1.tar.gz", hash = "sha256:de526c12914f0c550d15924c62d72abc48d6fe7364aa87328337a31007fe8a4f"},
@@ -7692,36 +7692,16 @@ description = "HTTP library with thread-safe connection pooling, file post, and
 optional = false
 python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,>=2.7"
 groups = ["main", "dev"]
-markers = "platform_python_implementation == \"PyPy\" or python_version < \"3.10\""
 files = [
     {file = "urllib3-1.26.20-py2.py3-none-any.whl", hash = "sha256:0ed14ccfbf1c30a9072c7ca157e4319b70d65f623e91e7b32fadb2853431016e"},
     {file = "urllib3-1.26.20.tar.gz", hash = "sha256:40c2dc0c681e47eb8f90e7e27bf6ff7df2e677421fd46756da1161c39ca70d32"},
 ]
 
 [package.extras]
-brotli = ["brotli (==1.0.9)", "brotli (>=1.0.9)", "brotlicffi (>=0.8.0)", "brotlipy (>=0.6.0)"]
-secure = ["certifi", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "ipaddress", "pyOpenSSL (>=0.14)", "urllib3-secure-extra"]
+brotli = ["brotli (==1.0.9) ; os_name != \"nt\" and python_version < \"3\" and platform_python_implementation == \"CPython\"", "brotli (>=1.0.9) ; python_version >= \"3\" and platform_python_implementation == \"CPython\"", "brotlicffi (>=0.8.0) ; (os_name != \"nt\" or python_version >= \"3\") and platform_python_implementation != \"CPython\"", "brotlipy (>=0.6.0) ; os_name == \"nt\" and python_version < \"3\""]
+secure = ["certifi", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "ipaddress ; python_version == \"2.7\"", "pyOpenSSL (>=0.14)", "urllib3-secure-extra"]
 socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
 
-[[package]]
-name = "urllib3"
-version = "2.2.3"
-description = "HTTP library with thread-safe connection pooling, file post, and more."
-optional = false
-python-versions = ">=3.8"
-groups = ["main", "dev"]
-markers = "python_version >= \"3.10\" and platform_python_implementation != \"PyPy\""
-files = [
-    {file = "urllib3-2.2.3-py3-none-any.whl", hash = "sha256:ca899ca043dcb1bafa3e262d73aa25c465bfb49e0bd9dd5d59f1d0acba2f8fac"},
-    {file = "urllib3-2.2.3.tar.gz", hash = "sha256:e7d814a81dad81e6caf2ec9fdedb284ecc9c73076b62654547cc64ccdcae26e9"},
-]
-
-[package.extras]
-brotli = ["brotli (>=1.0.9)", "brotlicffi (>=0.8.0)"]
-h2 = ["h2 (>=4,<5)"]
-socks = ["pysocks (>=1.5.6,!=1.5.7,<2.0)"]
-zstd = ["zstandard (>=0.18.0)"]
-
 [[package]]
 name = "uvicorn"
 version = "0.30.6"
@@ -7742,12 +7722,12 @@ httptools = {version = ">=0.5.0", optional = true, markers = "extra == \"standar
 python-dotenv = {version = ">=0.13", optional = true, markers = "extra == \"standard\""}
 pyyaml = {version = ">=5.1", optional = true, markers = "extra == \"standard\""}
 typing-extensions = {version = ">=4.0", markers = "python_version < \"3.11\""}
-uvloop = {version = ">=0.14.0,<0.15.0 || >0.15.0,<0.15.1 || >0.15.1", optional = true, markers = "(sys_platform != \"win32\" and sys_platform != \"cygwin\") and platform_python_implementation != \"PyPy\" and extra == \"standard\""}
+uvloop = {version = ">=0.14.0,<0.15.0 || >0.15.0,<0.15.1 || >0.15.1", optional = true, markers = "sys_platform != \"win32\" and sys_platform != \"cygwin\" and platform_python_implementation != \"PyPy\" and extra == \"standard\""}
 watchfiles = {version = ">=0.13", optional = true, markers = "extra == \"standard\""}
 websockets = {version = ">=10.4", optional = true, markers = "extra == \"standard\""}
 
 [package.extras]
-standard = ["colorama (>=0.4)", "httptools (>=0.5.0)", "python-dotenv (>=0.13)", "pyyaml (>=5.1)", "uvloop (>=0.14.0,!=0.15.0,!=0.15.1)", "watchfiles (>=0.13)", "websockets (>=10.4)"]
+standard = ["colorama (>=0.4) ; sys_platform == \"win32\"", "httptools (>=0.5.0)", "python-dotenv (>=0.13)", "pyyaml (>=5.1)", "uvloop (>=0.14.0,!=0.15.0,!=0.15.1) ; sys_platform != \"win32\" and sys_platform != \"cygwin\" and platform_python_implementation != \"PyPy\"", "watchfiles (>=0.13)", "websockets (>=10.4)"]
 
 [[package]]
 name = "uvloop"
@@ -7756,7 +7736,7 @@ description = "Fast implementation of asyncio event loop on top of libuv"
 optional = false
 python-versions = ">=3.8.0"
 groups = ["main"]
-markers = "(sys_platform != \"win32\" and sys_platform != \"cygwin\") and platform_python_implementation != \"PyPy\""
+markers = "sys_platform != \"win32\" and sys_platform != \"cygwin\" and platform_python_implementation != \"PyPy\""
 files = [
     {file = "uvloop-0.20.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:9ebafa0b96c62881d5cafa02d9da2e44c23f9f0cd829f3a32a6aff771449c996"},
     {file = "uvloop-0.20.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:35968fc697b0527a06e134999eef859b4034b37aebca537daeb598b9d45a137b"},
@@ -7793,7 +7773,7 @@ files = [
 
 [package.extras]
 docs = ["Sphinx (>=4.1.2,<4.2.0)", "sphinx-rtd-theme (>=0.5.2,<0.6.0)", "sphinxcontrib-asyncio (>=0.3.0,<0.4.0)"]
-test = ["Cython (>=0.29.36,<0.30.0)", "aiohttp (==3.9.0b0)", "aiohttp (>=3.8.1)", "flake8 (>=5.0,<6.0)", "mypy (>=0.800)", "psutil", "pyOpenSSL (>=23.0.0,<23.1.0)", "pycodestyle (>=2.9.0,<2.10.0)"]
+test = ["Cython (>=0.29.36,<0.30.0)", "aiohttp (==3.9.0b0) ; python_version >= \"3.12\"", "aiohttp (>=3.8.1) ; python_version < \"3.12\"", "flake8 (>=5.0,<6.0)", "mypy (>=0.800)", "psutil", "pyOpenSSL (>=23.0.0,<23.1.0)", "pycodestyle (>=2.9.0,<2.10.0)"]
 
 [[package]]
 name = "vcrpy"
@@ -8477,14 +8457,14 @@ files = [
 markers = {dev = "python_version < \"3.10\""}
 
 [package.extras]
-check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1)"]
+check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\""]
 cover = ["pytest-cov"]
 doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
 enabler = ["pytest-enabler (>=2.2)"]
-test = ["big-O", "importlib-resources", "jaraco.functools", "jaraco.itertools", "jaraco.test", "more-itertools", "pytest (>=6,!=8.1.*)", "pytest-ignore-flaky"]
+test = ["big-O", "importlib-resources ; python_version < \"3.9\"", "jaraco.functools", "jaraco.itertools", "jaraco.test", "more-itertools", "pytest (>=6,!=8.1.*)", "pytest-ignore-flaky"]
 type = ["pytest-mypy"]
 
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.9,<3.9.7 || >3.9.7,<3.13"
-content-hash = "79044b88e569b6564f33b5d1eb1a4b43213d98e7778edbf8dfaafdc78666bf99"
+content-hash = "5bb9e01fd3caa4e768a907809651e0477d9416971ef63988323bfdc8f0302325"
diff --git a/pyproject.toml b/pyproject.toml
index f758c590..0e6b7653 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -42,7 +42,7 @@ celery = {version = "^5.3.6", extras = ["redis"]}
 kombu = ">=5.4.0rc2" # Pin version to fix https://github.com/celery/celery/issues/8030. TODO: remove when this fix will be included in celery
 uvicorn = "*"
 pydantic-settings = "^2.2.1"
-label-studio-sdk = {url = "https://github.com/HumanSignal/label-studio-sdk/archive/9bed76c758ac7ffc312c62634d0e9cd873ea5084.zip"}
+label-studio-sdk = {url = "https://github.com/HumanSignal/label-studio-sdk/archive/5cc1d11e0afbaae6d597c1cbe12805b02af82aac.zip"}
 kafka-python-ng = "^2.2.3"
 requests = "^2.32.0"
 # Using litellm from forked repo until vertex fix is released: https://github.com/BerriAI/litellm/issues/7904

From d39a5dc825ef01ac366f8a6238f8100204cd8552 Mon Sep 17 00:00:00 2001
From: nik <nik@heartex.net>
Date: Mon, 10 Mar 2025 22:22:33 +0000
Subject: [PATCH 05/10] Lock poetry

---
 .../collection/label_studio_image_ocr.py      | 264 +++++++++++++-----
 poetry.lock                                   | 263 ++++++++++++-----
 pyproject.toml                                |   1 +
 3 files changed, 389 insertions(+), 139 deletions(-)

diff --git a/adala/skills/collection/label_studio_image_ocr.py b/adala/skills/collection/label_studio_image_ocr.py
index 6d6f7b50..fd41c7cf 100644
--- a/adala/skills/collection/label_studio_image_ocr.py
+++ b/adala/skills/collection/label_studio_image_ocr.py
@@ -9,6 +9,7 @@
 import base64
 import asyncio
 import io
+from thefuzz import fuzz
 from PIL import Image
 from urllib.parse import urlparse
 import uuid
@@ -210,6 +211,34 @@ async def process_single_image(image_data):
         
         return results
     
+    def _get_normalized_bbox(self, bbox: List[List[int]], original_width: int, original_height: int) -> List[float]:
+        # Calculate top-left corner (minimum x and y)
+        # bbox format is [[x1,y1],[x2,y2],[x3,y3],[x4,y4]]
+        x_values = [point[0] for point in bbox]
+        y_values = [point[1] for point in bbox]
+        
+        min_x = min(x_values)
+        min_y = min(y_values)
+        
+        # Calculate width and height
+        max_x = max(x_values)
+        max_y = max(y_values)
+        width = max_x - min_x
+        height = max_y - min_y
+        
+        # Convert to percentages
+        x_percent = (min_x / original_width) * 100
+        y_percent = (min_y / original_height) * 100
+        width_percent = (width / original_width) * 100
+        height_percent = (height / original_height) * 100
+        
+        return {
+            'x': x_percent,
+            'y': y_percent,
+            'width': width_percent,
+            'height': height_percent
+        }
+    
     def _convert_ocr_results_to_label_studio_format(self, results: list) -> Tuple[List, List]:
         
         # normalize EasyOCR results to RectangleLabels bounding boxes format of Label Studio
@@ -235,52 +264,18 @@ def _convert_ocr_results_to_label_studio_format(self, results: list) -> Tuple[Li
                 # We need to convert to Label Studio format with x,y as top-left corner
                 # and width, height as percentages
                 
-                # Calculate top-left corner (minimum x and y)
-                x_values = [point[0] for point in bbox]
-                y_values = [point[1] for point in bbox]
-                
-                min_x = min(x_values)
-                min_y = min(y_values)
-                
-                # Calculate width and height
-                max_x = max(x_values)
-                max_y = max(y_values)
-                width = max_x - min_x
-                height = max_y - min_y
-                
-                # Convert to percentages
-                x_percent = (min_x / original_width) * 100
-                y_percent = (min_y / original_height) * 100
-                width_percent = (width / original_width) * 100
-                height_percent = (height / original_height) * 100
+                bbox_annotation = self._get_normalized_bbox(bbox, original_width, original_height)
                 
                 # generate unique id for the annotation
                 id_gen = str(uuid.uuid4())[:8]
                 # Create Label Studio format annotation
-                bbox_annotation = {
-                    "x": x_percent,
-                    "y": y_percent,
-                    "width": width_percent,
-                    "height": height_percent,
-                    "rotation": 0,
-                    "id": id_gen,
-                    # "rectanglelabels": ['Transcription'],  # TODO: customize
-                    # "score": score, 
-                    # "text": text
-                }
+                bbox_annotation['id'] = id_gen
+                bbox_annotation['rotation'] = 0
+                
                 text_annotation = {
                     'text': [text],
                     'id': id_gen
                 }
-                # annotation = {
-                #     "x": x_percent,
-                #     "y": y_percent,
-                #     "width": width_percent,
-                #     "height": height_percent,
-                #     "rectanglelabels": ['Transcription'],  # TODO: customize
-                #     "score": score, 
-                #     "text": text
-                # }
                 
                 bbox_annotations.append(bbox_annotation)
                 text_annotations.append(text_annotation)
@@ -291,9 +286,65 @@ def _convert_ocr_results_to_label_studio_format(self, results: list) -> Tuple[Li
             
         return all_bbox_annotations, all_text_annotations
     
-    def _calculate_similarity(self, text: str, reference_texts: List[str]) -> Tuple[float, str]:
+    def _convert_ocr_results_to_label_studio_format_v2(self, results: list) -> Tuple[List, List]:
+        """
+        Same as _convert_ocr_results_to_label_studio_format, but uses a different approach to filter the OCR results:
+        results['ocr_data'] contains a dictionary of reference texts as keys and lists of OCR results as values.
+        For each reference text, we create a group of `bbox_annotations` and `text_annotations`. 
+        In text_annotations, we place "parentID" as the id of the bbox_annotation that it belongs to (pick the first text_annotation id as parentID)
         """
-        Calculate similarity between a text and a list of reference texts
+        all_bbox_annotations = []
+        all_text_annotations = []
+        
+        for result in results:
+            bbox_annotations = []
+            text_annotations = []
+            
+            original_width = result['image_width']
+            original_height = result['image_height']
+            
+            # Process each reference text and its associated OCR results
+            for reference_text, ocr_matches in result['ocr_data'].items():
+                # Create a group for this reference text
+                group_id = None
+                
+                # Process each OCR match for this reference text
+                for bbox, text, score in zip(ocr_matches['bboxes'], ocr_matches['texts'], ocr_matches['scores']):
+                    
+                    bbox_annotation = self._get_normalized_bbox(bbox, original_width, original_height)
+                    
+                    # Generate unique id for the annotation
+                    id_gen = str(uuid.uuid4())[:8]
+                    if group_id is None:
+                        group_id = id_gen
+                    
+                    # Create bbox annotation
+                    bbox_annotation['rotation'] = 0
+                    bbox_annotation['id'] = id_gen
+                    bbox_annotation['score'] = score
+                    # Create text annotation
+                    text_annotation = {
+                        'text': [text],
+                        'id': id_gen,
+                    }
+                    if group_id != id_gen:
+                        text_annotation['parent_id'] = group_id
+                        bbox_annotation['parent_id'] = group_id
+                    
+                    bbox_annotations.append(bbox_annotation)
+                    text_annotations.append(text_annotation)
+                
+            # Add annotations for this result to the overall lists
+            all_bbox_annotations.append(bbox_annotations)
+            all_text_annotations.append(text_annotations)
+            
+        return all_bbox_annotations, all_text_annotations
+                
+        
+    @classmethod
+    def _calculate_similarity(cls, text: str, reference_texts: List[str]) -> Tuple[float, str]:
+        """
+        Calculate similarity between a text and substrings within reference texts.
 
         Args:
             text: The text to compare
@@ -304,22 +355,21 @@ def _calculate_similarity(self, text: str, reference_texts: List[str]) -> Tuple[
         """
         # Convert to lowercase for case-insensitive comparison
         text = text.lower()
-        
-        # Use SequenceMatcher to calculate similarity
-        from difflib import SequenceMatcher
+        text_len = len(text)
         
         best_score = 0
         best_match = None
+        
         if reference_texts:
             for ref_text in reference_texts:
-                # Calculate similarity ratio using SequenceMatcher
-                similarity = SequenceMatcher(None, text, ref_text.lower()).ratio()
-                print(f"Similarity between {text} and {ref_text}: {similarity}")
-                
-                # Update best score if this one is higher
-                if similarity > best_score:
-                    best_score = similarity
+                ref_text_lower = ref_text.lower()
+                best_window_score = fuzz.partial_ratio(text, ref_text_lower)
+                if best_window_score > best_score:
+                    best_score = best_window_score
                     best_match = ref_text
+        best_score = float(best_score) / 100
+        print(f"Best substring similarity between '{text}' and '{best_match}': {best_score}")
+                    
         return best_score, best_match
     
     def _filter_ocr_results(self, ocr_results: Dict, reference_texts: List[str]) -> list:
@@ -347,6 +397,99 @@ def _filter_ocr_results(self, ocr_results: Dict, reference_texts: List[str]) ->
                 filtered_results['scores'].append(score)
             
         return filtered_results
+    
+    def _filter_ocr_results_v2(self, ocr_results: Dict, reference_texts: List[str]) -> Dict[str, List]:
+        
+        output = {}
+        for ref_text in reference_texts:
+            ref_text_lower = ref_text.lower()
+            output[ref_text] = {
+                'bboxes': [],
+                'texts': [],
+                'scores': []
+            }
+            for text, score, bbox in zip(ocr_results['texts'], ocr_results['scores'], ocr_results['bboxes']):
+                text_lower = text.lower()
+                # check if text is a fuzzy substring of ref_text
+                similarity = fuzz.partial_ratio(text_lower, ref_text_lower)
+                if similarity >= 95:
+                    output[ref_text]['bboxes'].append(bbox)
+                    output[ref_text]['texts'].append(text)
+                    output[ref_text]['scores'].append(score)
+            
+        # Filter to keep only horizontally aligned bounding boxes
+        for ref_text in output:
+            if not output[ref_text]['bboxes']:
+                continue
+                
+            # Group bounding boxes by their vertical position (y-coordinate)
+            # Using the middle y-coordinate of each box for grouping
+            y_groups = {}
+            for i, bbox in enumerate(output[ref_text]['bboxes']):
+                # Calculate middle y-coordinate of the bounding box
+                # bbox format is [[x1,y1],[x2,y2],[x3,y3],[x4,y4]]
+                # Calculate middle y-coordinate of the bounding box
+                # bbox format is [[x1,y1],[x2,y2],[x3,y3],[x4,y4]]
+                y_values = [point[1] for point in bbox]
+                mid_y = sum(y_values) / len(y_values)
+                
+                # Group with tolerance of 10 pixels
+                group_key = int(mid_y / 10) * 10
+                if group_key not in y_groups:
+                    y_groups[group_key] = []
+                y_groups[group_key].append(i)
+            
+            # Find the group with the maximum number of bounding boxes
+            max_group_key = max(y_groups.keys(), key=lambda k: len(y_groups[k]), default=None)
+            
+            if max_group_key is not None:
+                # Keep only the bounding boxes in the largest horizontal group
+                indices_to_keep = y_groups[max_group_key]
+                
+                # Create new filtered lists
+                filtered_bboxes = [output[ref_text]['bboxes'][i] for i in indices_to_keep]
+                filtered_texts = [output[ref_text]['texts'][i] for i in indices_to_keep]
+                filtered_scores = [output[ref_text]['scores'][i] for i in indices_to_keep]
+                
+                # Sort bounding boxes by x-coordinate to maintain reading order
+                sorted_indices = sorted(range(len(filtered_bboxes)), 
+                                       key=lambda i: min(point[0] for point in filtered_bboxes[i]))
+                
+                filtered_bboxes = [filtered_bboxes[i] for i in sorted_indices]
+                filtered_texts = [filtered_texts[i] for i in sorted_indices]
+                filtered_scores = [filtered_scores[i] for i in sorted_indices]
+                
+                # Create a combined bounding box that encompasses all individual boxes
+                if filtered_bboxes:
+                    # Find min and max coordinates across all bounding boxes
+                    all_x = [point[0] for bbox in filtered_bboxes for point in bbox]
+                    all_y = [point[1] for bbox in filtered_bboxes for point in bbox]
+                    
+                    min_x, max_x = min(all_x), max(all_x)
+                    min_y, max_y = min(all_y), max(all_y)
+                    
+                    # Create a new bounding box with the min/max coordinates
+                    combined_bbox = [
+                        [min_x, min_y],  # top-left
+                        [max_x, min_y],  # top-right
+                        [max_x, max_y],  # bottom-right
+                        [min_x, max_y]   # bottom-left
+                    ]
+                    
+                    # Calculate average score
+                    avg_score = sum(filtered_scores) / len(filtered_scores) if filtered_scores else 0
+                    
+                    # Add the combined bounding box to the results
+                    filtered_bboxes.insert(0, combined_bbox)
+                    filtered_texts.insert(0, ref_text)  # Use the reference text for the combined box
+                    filtered_scores.insert(0, avg_score)
+                
+                # Update the output with filtered results
+                output[ref_text]['bboxes'] = filtered_bboxes
+                output[ref_text]['texts'] = filtered_texts
+                output[ref_text]['scores'] = filtered_scores
+        
+        return output
         
 
     async def aapply(
@@ -394,30 +537,15 @@ async def aapply(
                 filtered_ocr_result = {
                     'image_width': ocr_results[i]['image_width'],
                     'image_height': ocr_results[i]['image_height'],
-                    'ocr_data': self._filter_ocr_results(ocr_results[i]['ocr_data'], extracted_result)
+                    'ocr_data': self._filter_ocr_results_v2(ocr_results[i]['ocr_data'], extracted_result)
                 }
                 filtered_ocr_results.append(filtered_ocr_result)
             print(f'Filtered OCR results: {filtered_ocr_results}')
             # convert filtered OCR results to Label Studio format
-            bbox_annotations, text_annotations = self._convert_ocr_results_to_label_studio_format(filtered_ocr_results)
+            # bbox_annotations, text_annotations = self._convert_ocr_results_to_label_studio_format(filtered_ocr_results)
+            bbox_annotations, text_annotations = self._convert_ocr_results_to_label_studio_format_v2(filtered_ocr_results)
             print(f'Bbox annotations: {bbox_annotations}')
             print(f'Text annotations: {text_annotations}')
             output['bbox'] = bbox_annotations
             output['transcription'] = text_annotations
             return output
-
-
-if __name__ == "__main__":
-    images = [
-      "https://htx-pub.s3.amazonaws.com/demo/ocr/pdf/output_0000.png",
-    #   "https://htx-pub.s3.amazonaws.com/demo/ocr/pdf/output_0001.png",
-    #   "https://htx-pub.s3.amazonaws.com/demo/ocr/pdf/output_0002.png",
-    #   "https://htx-pub.s3.amazonaws.com/demo/ocr/pdf/output_0003.png",
-    #   "https://htx-pub.s3.amazonaws.com/demo/ocr/pdf/output_0004.png",
-    #   "https://htx-pub.s3.amazonaws.com/demo/ocr/pdf/output_0005.png",
-    #   "https://htx-pub.s3.amazonaws.com/demo/ocr/pdf/output_0006.png",
-    #   "https://htx-pub.s3.amazonaws.com/demo/ocr/pdf/output_0007.png",
-    #   "https://htx-pub.s3.amazonaws.com/demo/ocr/pdf/output_0008.png"
-    ]
-    results = asyncio.run(LabelStudioSkillImageOCR.process_images_with_ocr(images))
-    print(results)
diff --git a/poetry.lock b/poetry.lock
index ef7d66bb..e9434af6 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 2.1.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 2.0.1 and should not be changed by hand.
 
 [[package]]
 name = "aiohappyeyeballs"
@@ -123,7 +123,7 @@ multidict = ">=4.5,<7.0"
 yarl = ">=1.12.0,<2.0"
 
 [package.extras]
-speedups = ["Brotli ; platform_python_implementation == \"CPython\"", "aiodns (>=3.2.0) ; sys_platform == \"linux\" or sys_platform == \"darwin\"", "brotlicffi ; platform_python_implementation != \"CPython\""]
+speedups = ["Brotli", "aiodns (>=3.2.0)", "brotlicffi"]
 
 [[package]]
 name = "aiokafka"
@@ -206,8 +206,8 @@ files = [
 ]
 
 [package.extras]
-dev = ["aiounittest (==1.4.1) ; python_version < \"3.8\"", "attribution (==1.6.2)", "black (==23.3.0)", "coverage[toml] (==7.2.3)", "flake8 (==5.0.4)", "flake8-bugbear (==23.3.12)", "flit (==3.7.1)", "mypy (==1.2.0)", "ufmt (==2.1.0)", "usort (==1.0.6)"]
-docs = ["sphinx (==6.1.3) ; python_version >= \"3.8\"", "sphinx-mdinclude (==0.5.3)"]
+dev = ["aiounittest (==1.4.1)", "attribution (==1.6.2)", "black (==23.3.0)", "coverage[toml] (==7.2.3)", "flake8 (==5.0.4)", "flake8-bugbear (==23.3.12)", "flit (==3.7.1)", "mypy (==1.2.0)", "ufmt (==2.1.0)", "usort (==1.0.6)"]
+docs = ["sphinx (==6.1.3)", "sphinx-mdinclude (==0.5.3)"]
 
 [[package]]
 name = "amqp"
@@ -256,7 +256,7 @@ typing-extensions = {version = ">=4.1", markers = "python_version < \"3.11\""}
 
 [package.extras]
 doc = ["Sphinx (>=7.4,<8.0)", "packaging", "sphinx-autodoc-typehints (>=1.2.0)", "sphinx-rtd-theme"]
-test = ["anyio[trio]", "coverage[toml] (>=7)", "exceptiongroup (>=1.2.0)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "uvloop (>=0.21.0b1) ; platform_python_implementation == \"CPython\" and platform_system != \"Windows\""]
+test = ["anyio[trio]", "coverage[toml] (>=7)", "exceptiongroup (>=1.2.0)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "uvloop (>=0.21.0b1)"]
 trio = ["trio (>=0.26.1)"]
 
 [[package]]
@@ -412,8 +412,8 @@ files = [
 six = ">=1.12.0"
 
 [package.extras]
-astroid = ["astroid (>=1,<2) ; python_version < \"3\"", "astroid (>=2,<4) ; python_version >= \"3\""]
-test = ["astroid (>=1,<2) ; python_version < \"3\"", "astroid (>=2,<4) ; python_version >= \"3\"", "pytest"]
+astroid = ["astroid (>=1,<2)", "astroid (>=2,<4)"]
+test = ["astroid (>=1,<2)", "astroid (>=2,<4)", "pytest"]
 
 [[package]]
 name = "async-lru"
@@ -455,12 +455,12 @@ files = [
 ]
 
 [package.extras]
-benchmark = ["cloudpickle ; platform_python_implementation == \"CPython\"", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\"", "pympler", "pytest (>=4.3.0)", "pytest-codspeed", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\" and python_version < \"3.13\"", "pytest-xdist[psutil]"]
-cov = ["cloudpickle ; platform_python_implementation == \"CPython\"", "coverage[toml] (>=5.3)", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\"", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\" and python_version < \"3.13\"", "pytest-xdist[psutil]"]
-dev = ["cloudpickle ; platform_python_implementation == \"CPython\"", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\"", "pre-commit", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\" and python_version < \"3.13\"", "pytest-xdist[psutil]"]
+benchmark = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-codspeed", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
+cov = ["cloudpickle", "coverage[toml] (>=5.3)", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
+dev = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pre-commit", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
 docs = ["cogapp", "furo", "myst-parser", "sphinx", "sphinx-notfound-page", "sphinxcontrib-towncrier", "towncrier (<24.7)"]
-tests = ["cloudpickle ; platform_python_implementation == \"CPython\"", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\"", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\" and python_version < \"3.13\"", "pytest-xdist[psutil]"]
-tests-mypy = ["mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\"", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\" and python_version < \"3.13\""]
+tests = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
+tests-mypy = ["mypy (>=1.11.1)", "pytest-mypy-plugins"]
 
 [[package]]
 name = "babel"
@@ -607,7 +607,7 @@ typing-extensions = {version = ">=4.0.1", markers = "python_version < \"3.11\""}
 
 [package.extras]
 colorama = ["colorama (>=0.4.3)"]
-d = ["aiohttp (>=3.7.4) ; sys_platform != \"win32\" or implementation_name != \"pypy\"", "aiohttp (>=3.7.4,!=3.9.0) ; sys_platform == \"win32\" and implementation_name == \"pypy\""]
+d = ["aiohttp (>=3.7.4)", "aiohttp (>=3.7.4,!=3.9.0)"]
 jupyter = ["ipython (>=7.8.0)", "tokenize-rt (>=3.2.0)"]
 uvloop = ["uvloop (>=0.15.2)"]
 
@@ -694,7 +694,7 @@ tomli = {version = ">=1.1.0", markers = "python_version < \"3.11\""}
 
 [package.extras]
 docs = ["furo (>=2023.08.17)", "sphinx (>=7.0,<8.0)", "sphinx-argparse-cli (>=1.5)", "sphinx-autodoc-typehints (>=1.10)", "sphinx-issues (>=3.0.0)"]
-test = ["build[uv,virtualenv]", "filelock (>=3)", "pytest (>=6.2.4)", "pytest-cov (>=2.12)", "pytest-mock (>=2)", "pytest-rerunfailures (>=9.1)", "pytest-xdist (>=1.34)", "setuptools (>=42.0.0) ; python_version < \"3.10\"", "setuptools (>=56.0.0) ; python_version == \"3.10\"", "setuptools (>=56.0.0) ; python_version == \"3.11\"", "setuptools (>=67.8.0) ; python_version >= \"3.12\"", "wheel (>=0.36.0)"]
+test = ["build[uv,virtualenv]", "filelock (>=3)", "pytest (>=6.2.4)", "pytest-cov (>=2.12)", "pytest-mock (>=2)", "pytest-rerunfailures (>=9.1)", "pytest-xdist (>=1.34)", "setuptools (>=42.0.0)", "setuptools (>=56.0.0)", "setuptools (>=56.0.0)", "setuptools (>=67.8.0)", "wheel (>=0.36.0)"]
 typing = ["build[uv]", "importlib-metadata (>=5.1)", "mypy (>=1.9.0,<1.10.0)", "tomli", "typing-extensions (>=3.7.4.3)"]
 uv = ["uv (>=0.1.18)"]
 virtualenv = ["virtualenv (>=20.0.35)"]
@@ -740,32 +740,32 @@ vine = ">=5.1.0,<6.0"
 arangodb = ["pyArango (>=2.0.2)"]
 auth = ["cryptography (==42.0.5)"]
 azureblockblob = ["azure-storage-blob (>=12.15.0)"]
-brotli = ["brotli (>=1.0.0) ; platform_python_implementation == \"CPython\"", "brotlipy (>=0.7.0) ; platform_python_implementation == \"PyPy\""]
+brotli = ["brotli (>=1.0.0)", "brotlipy (>=0.7.0)"]
 cassandra = ["cassandra-driver (>=3.25.0,<4)"]
 consul = ["python-consul2 (==0.1.5)"]
 cosmosdbsql = ["pydocumentdb (==2.3.5)"]
-couchbase = ["couchbase (>=3.0.0) ; platform_python_implementation != \"PyPy\" and (platform_system != \"Windows\" or python_version < \"3.10\")"]
+couchbase = ["couchbase (>=3.0.0)"]
 couchdb = ["pycouchdb (==1.14.2)"]
 django = ["Django (>=2.2.28)"]
 dynamodb = ["boto3 (>=1.26.143)"]
 elasticsearch = ["elastic-transport (<=8.13.0)", "elasticsearch (<=8.13.0)"]
-eventlet = ["eventlet (>=0.32.0) ; python_version < \"3.10\""]
+eventlet = ["eventlet (>=0.32.0)"]
 gcs = ["google-cloud-storage (>=2.10.0)"]
 gevent = ["gevent (>=1.5.0)"]
-librabbitmq = ["librabbitmq (>=2.0.0) ; python_version < \"3.11\""]
-memcache = ["pylibmc (==1.6.3) ; platform_system != \"Windows\""]
+librabbitmq = ["librabbitmq (>=2.0.0)"]
+memcache = ["pylibmc (==1.6.3)"]
 mongodb = ["pymongo[srv] (>=4.0.2)"]
 msgpack = ["msgpack (==1.0.8)"]
 pymemcache = ["python-memcached (>=1.61)"]
-pyro = ["pyro4 (==4.82) ; python_version < \"3.11\""]
+pyro = ["pyro4 (==4.82)"]
 pytest = ["pytest-celery[all] (>=1.0.0)"]
 redis = ["redis (>=4.5.2,!=4.5.5,<6.0.0)"]
 s3 = ["boto3 (>=1.26.143)"]
 slmq = ["softlayer-messaging (>=1.0.3)"]
-solar = ["ephem (==4.1.5) ; platform_python_implementation != \"PyPy\""]
+solar = ["ephem (==4.1.5)"]
 sqlalchemy = ["sqlalchemy (>=1.4.48,<2.1)"]
-sqs = ["boto3 (>=1.26.143)", "kombu[sqs] (>=5.3.4)", "pycurl (>=7.43.0.5) ; sys_platform != \"win32\" and platform_python_implementation == \"CPython\"", "urllib3 (>=1.26.16)"]
-tblib = ["tblib (>=1.3.0) ; python_version < \"3.8.0\"", "tblib (>=1.5.0) ; python_version >= \"3.8.0\""]
+sqs = ["boto3 (>=1.26.143)", "kombu[sqs] (>=5.3.4)", "pycurl (>=7.43.0.5)", "urllib3 (>=1.26.16)"]
+tblib = ["tblib (>=1.3.0)", "tblib (>=1.5.0)"]
 yaml = ["PyYAML (>=3.10)"]
 zookeeper = ["kazoo (>=1.3.1)"]
 zstd = ["zstandard (==0.22.0)"]
@@ -1208,10 +1208,10 @@ files = [
 ]
 
 [package.extras]
-avro = ["avro (>=1.11.1,<2)", "fastavro (>=0.23.0,<1.0) ; python_version < \"3.0\"", "fastavro (>=1.0) ; python_version > \"3.0\"", "requests"]
-dev = ["avro (>=1.11.1,<2)", "fastavro (>=0.23.0,<1.0) ; python_version < \"3.0\"", "fastavro (>=1.0) ; python_version > \"3.0\"", "flake8", "pytest (==4.6.4) ; python_version < \"3.0\"", "pytest ; python_version >= \"3.0\"", "pytest-timeout", "requests"]
-doc = ["avro (>=1.11.1,<2)", "fastavro (>=0.23.0,<1.0) ; python_version < \"3.0\"", "fastavro (>=1.0) ; python_version > \"3.0\"", "requests", "sphinx", "sphinx-rtd-theme"]
-json = ["jsonschema", "pyrsistent (==0.16.1) ; python_version < \"3.0\"", "pyrsistent ; python_version > \"3.0\"", "requests"]
+avro = ["avro (>=1.11.1,<2)", "fastavro (>=0.23.0,<1.0)", "fastavro (>=1.0)", "requests"]
+dev = ["avro (>=1.11.1,<2)", "fastavro (>=0.23.0,<1.0)", "fastavro (>=1.0)", "flake8", "pytest", "pytest (==4.6.4)", "pytest-timeout", "requests"]
+doc = ["avro (>=1.11.1,<2)", "fastavro (>=0.23.0,<1.0)", "fastavro (>=1.0)", "requests", "sphinx", "sphinx-rtd-theme"]
+json = ["jsonschema", "pyrsistent", "pyrsistent (==0.16.1)", "requests"]
 protobuf = ["protobuf", "requests"]
 schema-registry = ["requests"]
 
@@ -1386,7 +1386,7 @@ files = [
 tomli = {version = "*", optional = true, markers = "python_full_version <= \"3.11.0a6\" and extra == \"toml\""}
 
 [package.extras]
-toml = ["tomli ; python_full_version <= \"3.11.0a6\""]
+toml = ["tomli"]
 
 [[package]]
 name = "cryptography"
@@ -1476,8 +1476,8 @@ jinja2 = ">=2.10.1,<4.0"
 packaging = "*"
 pydantic = [
     {version = ">=1.5.1,<2.4.0 || >2.4.0,<3.0", extras = ["email"], markers = "python_version < \"3.10\""},
-    {version = ">=1.9.0,<2.4.0 || >2.4.0,<3.0", extras = ["email"], markers = "python_version == \"3.10\""},
-    {version = ">=1.10.0,<2.4.0 || >2.4.0,<3.0", extras = ["email"], markers = "python_version >= \"3.11\" and python_version < \"4.0\""},
+    {version = ">=1.9.0,<2.4.0 || >2.4.0,<3.0", extras = ["email"], markers = "python_version >= \"3.10\" and python_version < \"3.11\""},
+    {version = ">=1.10.0,<2.4.0 || >2.4.0,<3.0", extras = ["email"], markers = "python_version >= \"3.11\" and python_version < \"3.12\""},
     {version = ">=1.10.0,<2.0.0 || >2.0.0,<2.0.1 || >2.0.1,<2.4.0 || >2.4.0,<3.0", extras = ["email"], markers = "python_version >= \"3.12\" and python_version < \"4.0\""},
 ]
 pyyaml = ">=6.0.1"
@@ -1522,7 +1522,7 @@ xxhash = "*"
 apache-beam = ["apache-beam (>=2.26.0)"]
 audio = ["librosa", "soundfile (>=0.12.1)"]
 benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"]
-dev = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0) ; sys_platform != \"win32\" and python_version < \"3.10\"", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14) ; sys_platform != \"win32\"", "jaxlib (>=0.3.14) ; sys_platform != \"win32\"", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
+dev = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
 docs = ["s3fs", "tensorflow (>=2.6.0)", "torch", "transformers"]
 jax = ["jax (>=0.3.14)", "jaxlib (>=0.3.14)"]
 metrics-tests = ["Werkzeug (>=1.0.1)", "accelerate", "bert-score (>=0.3.6)", "jiwer", "langdetect", "mauve-text", "nltk", "requests-file (>=1.5.1)", "rouge-score", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "spacy (>=3.0.0)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "typer (<0.5.0)"]
@@ -1530,7 +1530,7 @@ quality = ["ruff (>=0.3.0)"]
 s3 = ["s3fs"]
 tensorflow = ["tensorflow (>=2.6.0)"]
 tensorflow-gpu = ["tensorflow (>=2.6.0)"]
-tests = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0) ; sys_platform != \"win32\" and python_version < \"3.10\"", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14) ; sys_platform != \"win32\"", "jaxlib (>=0.3.14) ; sys_platform != \"win32\"", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
+tests = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
 torch = ["torch"]
 vision = ["Pillow (>=6.2.1)"]
 
@@ -1738,7 +1738,7 @@ description = "Backport of PEP 654 (exception groups)"
 optional = false
 python-versions = ">=3.7"
 groups = ["main", "dev"]
-markers = "python_version <= \"3.10\""
+markers = "python_version < \"3.11\""
 files = [
     {file = "exceptiongroup-1.2.2-py3-none-any.whl", hash = "sha256:3111b9d131c238bec2f8f516e123e14ba243563fb135d3fe885990585aa7795b"},
     {file = "exceptiongroup-1.2.2.tar.gz", hash = "sha256:47c2edf7c6738fafb49fd34290706d1a1a2f4d1c6df275526b62cbb4aa5393cc"},
@@ -1760,7 +1760,7 @@ files = [
 ]
 
 [package.extras]
-tests = ["asttokens (>=2.1.0)", "coverage", "coverage-enable-subprocess", "ipython", "littleutils", "pytest", "rich ; python_version >= \"3.11\""]
+tests = ["asttokens (>=2.1.0)", "coverage", "coverage-enable-subprocess", "ipython", "littleutils", "pytest", "rich"]
 
 [[package]]
 name = "faker"
@@ -1853,7 +1853,7 @@ files = [
 [package.extras]
 docs = ["furo (>=2024.8.6)", "sphinx (>=8.0.2)", "sphinx-autodoc-typehints (>=2.4.1)"]
 testing = ["covdefaults (>=2.3)", "coverage (>=7.6.1)", "diff-cover (>=9.2)", "pytest (>=8.3.3)", "pytest-asyncio (>=0.24)", "pytest-cov (>=5)", "pytest-mock (>=3.14)", "pytest-timeout (>=2.3.1)", "virtualenv (>=20.26.4)"]
-typing = ["typing-extensions (>=4.12.2) ; python_version < \"3.11\""]
+typing = ["typing-extensions (>=4.12.2)"]
 
 [[package]]
 name = "flatbuffers"
@@ -1945,18 +1945,18 @@ files = [
 ]
 
 [package.extras]
-all = ["brotli (>=1.0.1) ; platform_python_implementation == \"CPython\"", "brotlicffi (>=0.8.0) ; platform_python_implementation != \"CPython\"", "fs (>=2.2.0,<3)", "lxml (>=4.0)", "lz4 (>=1.7.4.2)", "matplotlib", "munkres ; platform_python_implementation == \"PyPy\"", "pycairo", "scipy ; platform_python_implementation != \"PyPy\"", "skia-pathops (>=0.5.0)", "sympy", "uharfbuzz (>=0.23.0)", "unicodedata2 (>=15.1.0) ; python_version <= \"3.12\"", "xattr ; sys_platform == \"darwin\"", "zopfli (>=0.1.4)"]
+all = ["brotli (>=1.0.1)", "brotlicffi (>=0.8.0)", "fs (>=2.2.0,<3)", "lxml (>=4.0)", "lz4 (>=1.7.4.2)", "matplotlib", "munkres", "pycairo", "scipy", "skia-pathops (>=0.5.0)", "sympy", "uharfbuzz (>=0.23.0)", "unicodedata2 (>=15.1.0)", "xattr", "zopfli (>=0.1.4)"]
 graphite = ["lz4 (>=1.7.4.2)"]
-interpolatable = ["munkres ; platform_python_implementation == \"PyPy\"", "pycairo", "scipy ; platform_python_implementation != \"PyPy\""]
+interpolatable = ["munkres", "pycairo", "scipy"]
 lxml = ["lxml (>=4.0)"]
 pathops = ["skia-pathops (>=0.5.0)"]
 plot = ["matplotlib"]
 repacker = ["uharfbuzz (>=0.23.0)"]
 symfont = ["sympy"]
-type1 = ["xattr ; sys_platform == \"darwin\""]
+type1 = ["xattr"]
 ufo = ["fs (>=2.2.0,<3)"]
-unicode = ["unicodedata2 (>=15.1.0) ; python_version <= \"3.12\""]
-woff = ["brotli (>=1.0.1) ; platform_python_implementation == \"CPython\"", "brotlicffi (>=0.8.0) ; platform_python_implementation != \"CPython\"", "zopfli (>=0.1.4)"]
+unicode = ["unicodedata2 (>=15.1.0)"]
+woff = ["brotli (>=1.0.1)", "brotlicffi (>=0.8.0)", "zopfli (>=0.1.4)"]
 
 [[package]]
 name = "fqdn"
@@ -2531,7 +2531,7 @@ idna = "*"
 sniffio = "*"
 
 [package.extras]
-brotli = ["brotli ; platform_python_implementation == \"CPython\"", "brotlicffi ; platform_python_implementation != \"CPython\""]
+brotli = ["brotli", "brotlicffi"]
 cli = ["click (==8.*)", "pygments (==2.*)", "rich (>=10,<14)"]
 http2 = ["h2 (>=3,<5)"]
 socks = ["socksio (==1.*)"]
@@ -2740,7 +2740,7 @@ zipp = ">=0.5"
 [package.extras]
 doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
 perf = ["ipython"]
-test = ["flufl.flake8", "importlib-resources (>=1.3) ; python_version < \"3.9\"", "jaraco.test (>=5.4)", "packaging", "pyfakefs", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-mypy", "pytest-perf (>=0.9.2)", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\""]
+test = ["flufl.flake8", "importlib-resources (>=1.3)", "jaraco.test (>=5.4)", "packaging", "pyfakefs", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-mypy", "pytest-perf (>=0.9.2)", "pytest-ruff (>=0.2.1)"]
 
 [[package]]
 name = "importlib-resources"
@@ -2759,7 +2759,7 @@ markers = {dev = "python_version < \"3.10\""}
 zipp = {version = ">=3.1.0", markers = "python_version < \"3.10\""}
 
 [package.extras]
-check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\""]
+check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1)"]
 cover = ["pytest-cov"]
 doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
 enabler = ["pytest-enabler (>=2.2)"]
@@ -2780,7 +2780,7 @@ files = [
 
 [package.extras]
 docs = ["jaraco.packaging (>=9)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx"]
-testing = ["pygments", "pytest (>=6)", "pytest-black (>=0.3.7) ; platform_python_implementation != \"PyPy\"", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-flake8", "pytest-mypy (>=0.9.1) ; platform_python_implementation != \"PyPy\""]
+testing = ["pygments", "pytest (>=6)", "pytest-black (>=0.3.7)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-flake8", "pytest-mypy (>=0.9.1)"]
 
 [[package]]
 name = "iniconfig"
@@ -3218,7 +3218,7 @@ traitlets = ">=5.3"
 
 [package.extras]
 docs = ["ipykernel", "myst-parser", "pydata-sphinx-theme", "sphinx (>=4)", "sphinx-autodoc-typehints", "sphinxcontrib-github-alt", "sphinxcontrib-spelling"]
-test = ["coverage", "ipykernel (>=6.14)", "mypy", "paramiko ; sys_platform == \"win32\"", "pre-commit", "pytest", "pytest-cov", "pytest-jupyter[client] (>=0.4.1)", "pytest-timeout"]
+test = ["coverage", "ipykernel (>=6.14)", "mypy", "paramiko", "pre-commit", "pytest", "pytest-cov", "pytest-jupyter[client] (>=0.4.1)", "pytest-timeout"]
 
 [[package]]
 name = "jupyter-console"
@@ -3648,7 +3648,7 @@ azureservicebus = ["azure-servicebus (>=7.10.0)"]
 azurestoragequeues = ["azure-identity (>=1.12.0)", "azure-storage-queue (>=12.6.0)"]
 confluentkafka = ["confluent-kafka (>=2.2.0)"]
 consul = ["python-consul2 (==0.1.5)"]
-librabbitmq = ["librabbitmq (>=2.0.0) ; python_version < \"3.11\""]
+librabbitmq = ["librabbitmq (>=2.0.0)"]
 mongodb = ["pymongo (>=4.1.1)"]
 msgpack = ["msgpack (==1.1.0)"]
 pyro = ["pyro4 (==4.82)"]
@@ -3656,7 +3656,7 @@ qpid = ["qpid-python (>=0.26)", "qpid-tools (>=0.26)"]
 redis = ["redis (>=4.5.2,!=4.5.5,!=5.0.2)"]
 slmq = ["softlayer-messaging (>=1.0.3)"]
 sqlalchemy = ["sqlalchemy (>=1.4.48,<2.1)"]
-sqs = ["boto3 (>=1.26.143)", "pycurl (>=7.43.0.5) ; sys_platform != \"win32\" and platform_python_implementation == \"CPython\"", "urllib3 (>=1.26.16)"]
+sqs = ["boto3 (>=1.26.143)", "pycurl (>=7.43.0.5)", "urllib3 (>=1.26.16)"]
 yaml = ["PyYAML (>=3.10)"]
 zookeeper = ["kazoo (>=2.8.0)"]
 
@@ -4191,7 +4191,7 @@ watchdog = ">=2.0"
 
 [package.extras]
 i18n = ["babel (>=2.9.0)"]
-min-versions = ["babel (==2.9.0)", "click (==7.0)", "colorama (==0.4) ; platform_system == \"Windows\"", "ghp-import (==1.0)", "importlib-metadata (==4.4) ; python_version < \"3.10\"", "jinja2 (==2.11.1)", "markdown (==3.3.6)", "markupsafe (==2.0.1)", "mergedeep (==1.3.4)", "mkdocs-get-deps (==0.2.0)", "packaging (==20.5)", "pathspec (==0.11.1)", "pyyaml (==5.1)", "pyyaml-env-tag (==0.1)", "watchdog (==2.0)"]
+min-versions = ["babel (==2.9.0)", "click (==7.0)", "colorama (==0.4)", "ghp-import (==1.0)", "importlib-metadata (==4.4)", "jinja2 (==2.11.1)", "markdown (==3.3.6)", "markupsafe (==2.0.1)", "mergedeep (==1.3.4)", "mkdocs-get-deps (==0.2.0)", "packaging (==20.5)", "pathspec (==0.11.1)", "pyyaml (==5.1)", "pyyaml-env-tag (==0.1)", "watchdog (==2.0)"]
 
 [[package]]
 name = "mkdocs-autorefs"
@@ -4508,7 +4508,7 @@ files = [
 [package.extras]
 develop = ["codecov", "pycodestyle", "pytest (>=4.6)", "pytest-cov", "wheel"]
 docs = ["sphinx"]
-gmpy = ["gmpy2 (>=2.1.0a4) ; platform_python_implementation != \"PyPy\""]
+gmpy = ["gmpy2 (>=2.1.0a4)"]
 tests = ["pytest (>=4.6)"]
 
 [[package]]
@@ -4529,7 +4529,7 @@ PyJWT = {version = ">=1.0.0,<3", extras = ["crypto"]}
 requests = ">=2.0.0,<3"
 
 [package.extras]
-broker = ["pymsalruntime (>=0.14,<0.18) ; python_version >= \"3.6\" and platform_system == \"Windows\"", "pymsalruntime (>=0.17,<0.18) ; python_version >= \"3.8\" and platform_system == \"Darwin\""]
+broker = ["pymsalruntime (>=0.14,<0.18)", "pymsalruntime (>=0.17,<0.18)"]
 
 [[package]]
 name = "multidict"
@@ -4817,7 +4817,7 @@ tornado = ">=6.2.0"
 [package.extras]
 dev = ["hatch", "pre-commit"]
 docs = ["myst-parser", "nbsphinx", "pydata-sphinx-theme", "sphinx (>=1.3.6)", "sphinxcontrib-github-alt", "sphinxcontrib-spelling"]
-test = ["importlib-resources (>=5.0) ; python_version < \"3.10\"", "ipykernel", "jupyter-server[test] (>=2.4.0,<3)", "jupyterlab-server[test] (>=2.27.1,<3)", "nbval", "pytest (>=7.0)", "pytest-console-scripts", "pytest-timeout", "pytest-tornasync", "requests"]
+test = ["importlib-resources (>=5.0)", "ipykernel", "jupyter-server[test] (>=2.4.0,<3)", "jupyterlab-server[test] (>=2.27.1,<3)", "nbval", "pytest (>=7.0)", "pytest-console-scripts", "pytest-timeout", "pytest-tornasync", "requests"]
 
 [[package]]
 name = "notebook-shim"
@@ -5524,7 +5524,7 @@ docs = ["furo", "olefile", "sphinx (>=7.3)", "sphinx-copybutton", "sphinx-inline
 fpx = ["olefile"]
 mic = ["olefile"]
 tests = ["check-manifest", "coverage", "defusedxml", "markdown2", "olefile", "packaging", "pyroma", "pytest", "pytest-cov", "pytest-timeout"]
-typing = ["typing-extensions ; python_version < \"3.10\""]
+typing = ["typing-extensions"]
 xmp = ["defusedxml"]
 
 [[package]]
@@ -5663,7 +5663,7 @@ files = [
 ]
 
 [package.extras]
-test = ["enum34 ; python_version <= \"3.4\"", "ipaddress ; python_version < \"3.0\"", "mock ; python_version < \"3.0\"", "pywin32 ; sys_platform == \"win32\"", "wmi ; sys_platform == \"win32\""]
+test = ["enum34", "ipaddress", "mock", "pywin32", "wmi"]
 
 [[package]]
 name = "ptyprocess"
@@ -5817,7 +5817,7 @@ typing-extensions = {version = ">=4.6.1", markers = "python_version < \"3.13\""}
 
 [package.extras]
 email = ["email-validator (>=2.0.0)"]
-timezone = ["tzdata ; python_version >= \"3.9\" and sys_platform == \"win32\""]
+timezone = ["tzdata"]
 
 [[package]]
 name = "pydantic-core"
@@ -6524,6 +6524,113 @@ files = [
 [package.dependencies]
 cffi = {version = "*", markers = "implementation_name == \"pypy\""}
 
+[[package]]
+name = "rapidfuzz"
+version = "3.12.2"
+description = "rapid fuzzy string matching"
+optional = false
+python-versions = ">=3.9"
+groups = ["main"]
+files = [
+    {file = "rapidfuzz-3.12.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:0b9a75e0385a861178adf59e86d6616cbd0d5adca7228dc9eeabf6f62cf5b0b1"},
+    {file = "rapidfuzz-3.12.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:6906a7eb458731e3dd2495af1d0410e23a21a2a2b7ced535e6d5cd15cb69afc5"},
+    {file = "rapidfuzz-3.12.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f4b3334a8958b689f292d5ce8a928140ac98919b51e084f04bf0c14276e4c6ba"},
+    {file = "rapidfuzz-3.12.2-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:85a54ce30345cff2c79cbcffa063f270ad1daedd0d0c3ff6e541d3c3ba4288cf"},
+    {file = "rapidfuzz-3.12.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:acb63c5072c08058f8995404201a52fc4e1ecac105548a4d03c6c6934bda45a3"},
+    {file = "rapidfuzz-3.12.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5385398d390c6571f0f2a7837e6ddde0c8b912dac096dc8c87208ce9aaaa7570"},
+    {file = "rapidfuzz-3.12.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5032cbffa245b4beba0067f8ed17392ef2501b346ae3c1f1d14b950edf4b6115"},
+    {file = "rapidfuzz-3.12.2-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:195adbb384d89d6c55e2fd71e7fb262010f3196e459aa2f3f45f31dd7185fe72"},
+    {file = "rapidfuzz-3.12.2-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:f43b773a4d4950606fb25568ecde5f25280daf8f97b87eb323e16ecd8177b328"},
+    {file = "rapidfuzz-3.12.2-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:55a43be0e0fa956a919043c19d19bd988991d15c59f179d413fe5145ed9deb43"},
+    {file = "rapidfuzz-3.12.2-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:71cf1ea16acdebe9e2fb62ee7a77f8f70e877bebcbb33b34e660af2eb6d341d9"},
+    {file = "rapidfuzz-3.12.2-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:a3692d4ab36d44685f61326dca539975a4eda49b2a76f0a3df177d8a2c0de9d2"},
+    {file = "rapidfuzz-3.12.2-cp310-cp310-win32.whl", hash = "sha256:09227bd402caa4397ba1d6e239deea635703b042dd266a4092548661fb22b9c6"},
+    {file = "rapidfuzz-3.12.2-cp310-cp310-win_amd64.whl", hash = "sha256:0f05b7b95f9f87254b53fa92048367a8232c26cee7fc8665e4337268c3919def"},
+    {file = "rapidfuzz-3.12.2-cp310-cp310-win_arm64.whl", hash = "sha256:6938738e00d9eb6e04097b3f565097e20b0c398f9c58959a2bc64f7f6be3d9da"},
+    {file = "rapidfuzz-3.12.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:e9c4d984621ae17404c58f8d06ed8b025e167e52c0e6a511dfec83c37e9220cd"},
+    {file = "rapidfuzz-3.12.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:9f9132c55d330f0a1d34ce6730a76805323a6250d97468a1ca766a883d6a9a25"},
+    {file = "rapidfuzz-3.12.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:39b343b6cb4b2c3dbc8d2d4c5ee915b6088e3b144ddf8305a57eaab16cf9fc74"},
+    {file = "rapidfuzz-3.12.2-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:24081077b571ec4ee6d5d7ea0e49bc6830bf05b50c1005028523b9cd356209f3"},
+    {file = "rapidfuzz-3.12.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c988a4fc91856260355773bf9d32bebab2083d4c6df33fafeddf4330e5ae9139"},
+    {file = "rapidfuzz-3.12.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:780b4469ee21cf62b1b2e8ada042941fd2525e45d5fb6a6901a9798a0e41153c"},
+    {file = "rapidfuzz-3.12.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:edd84b0a323885493c893bad16098c5e3b3005d7caa995ae653da07373665d97"},
+    {file = "rapidfuzz-3.12.2-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:efa22059c765b3d8778083805b199deaaf643db070f65426f87d274565ddf36a"},
+    {file = "rapidfuzz-3.12.2-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:095776b11bb45daf7c2973dd61cc472d7ea7f2eecfa454aef940b4675659b92f"},
+    {file = "rapidfuzz-3.12.2-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:7e2574cf4aa86065600b664a1ac7b8b8499107d102ecde836aaaa403fc4f1784"},
+    {file = "rapidfuzz-3.12.2-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:d5a3425a6c50fd8fbd991d8f085ddb504791dae6ef9cc3ab299fea2cb5374bef"},
+    {file = "rapidfuzz-3.12.2-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:97fb05e1ddb7b71a054040af588b0634214ee87cea87900d309fafc16fd272a4"},
+    {file = "rapidfuzz-3.12.2-cp311-cp311-win32.whl", hash = "sha256:b4c5a0413589aef936892fbfa94b7ff6f7dd09edf19b5a7b83896cc9d4e8c184"},
+    {file = "rapidfuzz-3.12.2-cp311-cp311-win_amd64.whl", hash = "sha256:58d9ae5cf9246d102db2a2558b67fe7e73c533e5d769099747921232d88b9be2"},
+    {file = "rapidfuzz-3.12.2-cp311-cp311-win_arm64.whl", hash = "sha256:7635fe34246cd241c8e35eb83084e978b01b83d5ef7e5bf72a704c637f270017"},
+    {file = "rapidfuzz-3.12.2-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:1d982a651253ffe8434d9934ff0c1089111d60502228464721a2a4587435e159"},
+    {file = "rapidfuzz-3.12.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:02e6466caa0222d5233b1f05640873671cd99549a5c5ba4c29151634a1e56080"},
+    {file = "rapidfuzz-3.12.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e956b3f053e474abae69ac693a52742109d860ac2375fe88e9387d3277f4c96c"},
+    {file = "rapidfuzz-3.12.2-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2dee7d740a2d5418d4f964f39ab8d89923e6b945850db833e798a1969b19542a"},
+    {file = "rapidfuzz-3.12.2-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a057cdb0401e42c84b6516c9b1635f7aedd5e430c6e388bd5f6bcd1d6a0686bb"},
+    {file = "rapidfuzz-3.12.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:dccf8d4fb5b86d39c581a59463c596b1d09df976da26ff04ae219604223d502f"},
+    {file = "rapidfuzz-3.12.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:21d5b3793c6f5aecca595cd24164bf9d3c559e315ec684f912146fc4e769e367"},
+    {file = "rapidfuzz-3.12.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:46a616c0e13cff2de1761b011e0b14bb73b110182f009223f1453d505c9a975c"},
+    {file = "rapidfuzz-3.12.2-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:19fa5bc4301a1ee55400d4a38a8ecf9522b0391fc31e6da5f4d68513fe5c0026"},
+    {file = "rapidfuzz-3.12.2-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:544a47190a0d25971658a9365dba7095397b4ce3e897f7dd0a77ca2cf6fa984e"},
+    {file = "rapidfuzz-3.12.2-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:f21af27c5e001f0ba1b88c36a0936437dfe034c452548d998891c21125eb640f"},
+    {file = "rapidfuzz-3.12.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:b63170d9db00629b5b3f2862114d8d6ee19127eaba0eee43762d62a25817dbe0"},
+    {file = "rapidfuzz-3.12.2-cp312-cp312-win32.whl", hash = "sha256:6c7152d77b2eb6bfac7baa11f2a9c45fd5a2d848dbb310acd0953b3b789d95c9"},
+    {file = "rapidfuzz-3.12.2-cp312-cp312-win_amd64.whl", hash = "sha256:1a314d170ee272ac87579f25a6cf8d16a031e1f7a7b07663434b41a1473bc501"},
+    {file = "rapidfuzz-3.12.2-cp312-cp312-win_arm64.whl", hash = "sha256:d41e8231326e94fd07c4d8f424f6bed08fead6f5e6688d1e6e787f1443ae7631"},
+    {file = "rapidfuzz-3.12.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:941f31038dba5d3dedcfcceba81d61570ad457c873a24ceb13f4f44fcb574260"},
+    {file = "rapidfuzz-3.12.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:fe2dfc454ee51ba168a67b1e92b72aad251e45a074972cef13340bbad2fd9438"},
+    {file = "rapidfuzz-3.12.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:78fafaf7f5a48ee35ccd7928339080a0136e27cf97396de45259eca1d331b714"},
+    {file = "rapidfuzz-3.12.2-cp313-cp313-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e0c7989ff32c077bb8fd53253fd6ca569d1bfebc80b17557e60750e6909ba4fe"},
+    {file = "rapidfuzz-3.12.2-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:96fa00bc105caa34b6cd93dca14a29243a3a7f0c336e4dcd36348d38511e15ac"},
+    {file = "rapidfuzz-3.12.2-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:bccfb30c668620c5bc3490f2dc7d7da1cca0ead5a9da8b755e2e02e2ef0dff14"},
+    {file = "rapidfuzz-3.12.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2f9b0adc3d894beb51f5022f64717b6114a6fabaca83d77e93ac7675911c8cc5"},
+    {file = "rapidfuzz-3.12.2-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:32691aa59577f42864d5535cb6225d0f47e2c7bff59cf4556e5171e96af68cc1"},
+    {file = "rapidfuzz-3.12.2-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:758b10380ad34c1f51753a070d7bb278001b5e6fcf544121c6df93170952d705"},
+    {file = "rapidfuzz-3.12.2-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:50a9c54c0147b468363119132d514c5024fbad1ed8af12bd8bd411b0119f9208"},
+    {file = "rapidfuzz-3.12.2-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:e3ceb87c11d2d0fbe8559bb795b0c0604b84cfc8bb7b8720b5c16e9e31e00f41"},
+    {file = "rapidfuzz-3.12.2-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:f7c9a003002434889255ff5676ca0f8934a478065ab5e702f75dc42639505bba"},
+    {file = "rapidfuzz-3.12.2-cp313-cp313-win32.whl", hash = "sha256:cf165a76870cd875567941cf861dfd361a0a6e6a56b936c5d30042ddc9def090"},
+    {file = "rapidfuzz-3.12.2-cp313-cp313-win_amd64.whl", hash = "sha256:55bcc003541f5f16ec0a73bf6de758161973f9e8d75161954380738dd147f9f2"},
+    {file = "rapidfuzz-3.12.2-cp313-cp313-win_arm64.whl", hash = "sha256:69f6ecdf1452139f2b947d0c169a605de578efdb72cbb2373cb0a94edca1fd34"},
+    {file = "rapidfuzz-3.12.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:c4c852cd8bed1516a64fd6e2d4c6f270d4356196ee03fda2af1e5a9e13c34643"},
+    {file = "rapidfuzz-3.12.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:42e7f747b55529a6d0d1588695d71025e884ab48664dca54b840413dea4588d8"},
+    {file = "rapidfuzz-3.12.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a749fd2690f24ef256b264a781487746bbb95344364fe8fe356f0eef7ef206ba"},
+    {file = "rapidfuzz-3.12.2-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9a11e1d036170bbafa43a9e63d8c309273564ec5bdfc5439062f439d1a16965a"},
+    {file = "rapidfuzz-3.12.2-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:dfb337f1832c1231e3d5621bd0ebebb854e46036aedae3e6a49c1fc08f16f249"},
+    {file = "rapidfuzz-3.12.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e88c6e68fca301722fa3ab7fd3ca46998012c14ada577bc1e2c2fc04f2067ca6"},
+    {file = "rapidfuzz-3.12.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:17e1a3a8b4b5125cfb63a6990459b25b87ea769bdaf90d05bb143f8febef076a"},
+    {file = "rapidfuzz-3.12.2-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:b9f8177b24ccc0a843e85932b1088c5e467a7dd7a181c13f84c684b796bea815"},
+    {file = "rapidfuzz-3.12.2-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:6c506bdc2f304051592c0d3b0e82eed309248ec10cdf802f13220251358375ea"},
+    {file = "rapidfuzz-3.12.2-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:30bf15c1ecec2798b713d551df17f23401a3e3653ad9ed4e83ad1c2b06e86100"},
+    {file = "rapidfuzz-3.12.2-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:bd9a67cfc83e8453ef17ddd1c2c4ce4a74d448a197764efb54c29f29fb41f611"},
+    {file = "rapidfuzz-3.12.2-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:7a6eaec2ef658dd650c6eb9b36dff7a361ebd7d8bea990ce9d639b911673b2cb"},
+    {file = "rapidfuzz-3.12.2-cp39-cp39-win32.whl", hash = "sha256:d7701769f110332cde45c41759cb2a497de8d2dca55e4c519a46aed5fbb19d1a"},
+    {file = "rapidfuzz-3.12.2-cp39-cp39-win_amd64.whl", hash = "sha256:296bf0fd4f678488670e262c87a3e4f91900b942d73ae38caa42a417e53643b1"},
+    {file = "rapidfuzz-3.12.2-cp39-cp39-win_arm64.whl", hash = "sha256:7957f5d768de14f6b2715303ccdf224b78416738ee95a028a2965c95f73afbfb"},
+    {file = "rapidfuzz-3.12.2-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:e5fd3ce849b27d063755829cda27a9dab6dbd63be3801f2a40c60ec563a4c90f"},
+    {file = "rapidfuzz-3.12.2-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:54e53662d71ed660c83c5109127c8e30b9e607884b7c45d2aff7929bbbd00589"},
+    {file = "rapidfuzz-3.12.2-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2b9e43cf2213e524f3309d329f1ad8dbf658db004ed44f6ae1cd2919aa997da5"},
+    {file = "rapidfuzz-3.12.2-pp310-pypy310_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:29ca445e320e5a8df3bd1d75b4fa4ecfa7c681942b9ac65b55168070a1a1960e"},
+    {file = "rapidfuzz-3.12.2-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:83eb7ef732c2f8533c6b5fbe69858a722c218acc3e1fc190ab6924a8af7e7e0e"},
+    {file = "rapidfuzz-3.12.2-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:648adc2dd2cf873efc23befcc6e75754e204a409dfa77efd0fea30d08f22ef9d"},
+    {file = "rapidfuzz-3.12.2-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:9b1e6f48e1ffa0749261ee23a1c6462bdd0be5eac83093f4711de17a42ae78ad"},
+    {file = "rapidfuzz-3.12.2-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:1ae9ded463f2ca4ba1eb762913c5f14c23d2e120739a62b7f4cc102eab32dc90"},
+    {file = "rapidfuzz-3.12.2-pp311-pypy311_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dda45f47b559be72ecbce45c7f71dc7c97b9772630ab0f3286d97d2c3025ab71"},
+    {file = "rapidfuzz-3.12.2-pp311-pypy311_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b3745c6443890265513a3c8777f2de4cb897aeb906a406f97741019be8ad5bcc"},
+    {file = "rapidfuzz-3.12.2-pp311-pypy311_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:36d3ef4f047ed1bc96fa29289f9e67a637ddca5e4f4d3dc7cb7f50eb33ec1664"},
+    {file = "rapidfuzz-3.12.2-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:54bb69ebe5ca0bd7527357e348f16a4c0c52fe0c2fcc8a041010467dcb8385f7"},
+    {file = "rapidfuzz-3.12.2-pp39-pypy39_pp73-macosx_10_15_x86_64.whl", hash = "sha256:3f2ddd5b99b254039a8c82be5749d4d75943f62eb2c2918acf6ffd586852834f"},
+    {file = "rapidfuzz-3.12.2-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:8117dab9b26a1aaffab59b4e30f80ac4d55e61ad4139a637c149365960933bee"},
+    {file = "rapidfuzz-3.12.2-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:40c0f16d62d6553527de3dab2fb69709c4383430ea44bce8fb4711ed4cbc6ae3"},
+    {file = "rapidfuzz-3.12.2-pp39-pypy39_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f177e1eb6e4f5261a89c475e21bce7a99064a8f217d2336fb897408f46f0ceaf"},
+    {file = "rapidfuzz-3.12.2-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5df0cecc2852fcb078ed1b4482fac4fc2c2e7787f3edda8920d9a4c0f51b1c95"},
+    {file = "rapidfuzz-3.12.2-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:3b3c4df0321df6f8f0b61afbaa2ced9622750ee1e619128db57a18533d139820"},
+    {file = "rapidfuzz-3.12.2.tar.gz", hash = "sha256:b0ba1ccc22fff782e7152a3d3d0caca44ec4e32dc48ba01c560b8593965b5aa3"},
+]
+
+[package.extras]
+all = ["numpy"]
+
 [[package]]
 name = "redis"
 version = "5.0.8"
@@ -6992,9 +7099,9 @@ files = [
 ]
 
 [package.extras]
-nativelib = ["pyobjc-framework-Cocoa ; sys_platform == \"darwin\"", "pywin32 ; sys_platform == \"win32\""]
-objc = ["pyobjc-framework-Cocoa ; sys_platform == \"darwin\""]
-win32 = ["pywin32 ; sys_platform == \"win32\""]
+nativelib = ["pyobjc-framework-Cocoa", "pywin32"]
+objc = ["pyobjc-framework-Cocoa"]
+win32 = ["pywin32"]
 
 [[package]]
 name = "setuptools"
@@ -7009,9 +7116,9 @@ files = [
 ]
 
 [package.extras]
-core = ["importlib-metadata (>=6) ; python_version < \"3.10\"", "importlib-resources (>=5.10.2) ; python_version < \"3.9\"", "jaraco.text (>=3.7)", "more-itertools (>=8.8)", "ordered-set (>=3.1.1)", "packaging (>=24)", "platformdirs (>=2.6.2)", "tomli (>=2.0.1) ; python_version < \"3.11\"", "wheel (>=0.43.0)"]
+core = ["importlib-metadata (>=6)", "importlib-resources (>=5.10.2)", "jaraco.text (>=3.7)", "more-itertools (>=8.8)", "ordered-set (>=3.1.1)", "packaging (>=24)", "platformdirs (>=2.6.2)", "tomli (>=2.0.1)", "wheel (>=0.43.0)"]
 doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "pygments-github-lexers (==0.0.5)", "pyproject-hooks (!=1.1)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-favicon", "sphinx-inline-tabs", "sphinx-lint", "sphinx-notfound-page (>=1,<2)", "sphinx-reredirects", "sphinxcontrib-towncrier", "towncrier (<24.7)"]
-test = ["build[virtualenv] (>=1.0.3)", "filelock (>=3.4.0)", "importlib-metadata", "ini2toml[lite] (>=0.14)", "jaraco.develop (>=7.21) ; python_version >= \"3.9\" and sys_platform != \"cygwin\"", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "jaraco.test", "mypy (==1.11.*)", "packaging (>=23.2)", "pip (>=19.1)", "pyproject-hooks (!=1.1)", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-home (>=0.5)", "pytest-mypy", "pytest-perf ; sys_platform != \"cygwin\"", "pytest-ruff (<0.4) ; platform_system == \"Windows\"", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\"", "pytest-ruff (>=0.3.2) ; sys_platform != \"cygwin\"", "pytest-subprocess", "pytest-timeout", "pytest-xdist (>=3)", "tomli", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel"]
+test = ["build[virtualenv] (>=1.0.3)", "filelock (>=3.4.0)", "importlib-metadata", "ini2toml[lite] (>=0.14)", "jaraco.develop (>=7.21)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "jaraco.test", "mypy (==1.11.*)", "packaging (>=23.2)", "pip (>=19.1)", "pyproject-hooks (!=1.1)", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-home (>=0.5)", "pytest-mypy", "pytest-perf", "pytest-ruff (<0.4)", "pytest-ruff (>=0.2.1)", "pytest-ruff (>=0.3.2)", "pytest-subprocess", "pytest-timeout", "pytest-xdist (>=3)", "tomli", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel"]
 
 [[package]]
 name = "shellingham"
@@ -7195,6 +7302,21 @@ docs = ["myst-parser", "pydata-sphinx-theme", "sphinx"]
 test = ["pre-commit", "pytest (>=7.0)", "pytest-timeout"]
 typing = ["mypy (>=1.6,<2.0)", "traitlets (>=5.11.1)"]
 
+[[package]]
+name = "thefuzz"
+version = "0.22.1"
+description = "Fuzzy string matching in python"
+optional = false
+python-versions = ">=3.8"
+groups = ["main"]
+files = [
+    {file = "thefuzz-0.22.1-py3-none-any.whl", hash = "sha256:59729b33556850b90e1093c4cf9e618af6f2e4c985df193fdf3c5b5cf02ca481"},
+    {file = "thefuzz-0.22.1.tar.gz", hash = "sha256:7138039a7ecf540da323792d8592ef9902b1d79eb78c147d4f20664de79f3680"},
+]
+
+[package.dependencies]
+rapidfuzz = ">=3.0.0,<4.0.0"
+
 [[package]]
 name = "tiktoken"
 version = "0.7.0"
@@ -7396,7 +7518,7 @@ files = [
     {file = "toml-0.10.2-py2.py3-none-any.whl", hash = "sha256:806143ae5bfb6a3c6e736a764057db0e6a0e05e338b5630894a5f779cabb4f9b"},
     {file = "toml-0.10.2.tar.gz", hash = "sha256:b3bda1d108d5dd99f4a20d24d9c348e91c4db7ab1b749200bded2f839ccbe68f"},
 ]
-markers = {main = "python_version <= \"3.10\""}
+markers = {main = "python_version < \"3.11\""}
 
 [[package]]
 name = "tomli"
@@ -7405,7 +7527,7 @@ description = "A lil' TOML parser"
 optional = false
 python-versions = ">=3.7"
 groups = ["main", "dev"]
-markers = "python_version <= \"3.10\""
+markers = "python_version < \"3.11\""
 files = [
     {file = "tomli-2.0.1-py3-none-any.whl", hash = "sha256:939de3e7a6161af0c887ef91b7d41a53e7c5a1ca976325f429cb46ea9bc30ecc"},
     {file = "tomli-2.0.1.tar.gz", hash = "sha256:de526c12914f0c550d15924c62d72abc48d6fe7364aa87328337a31007fe8a4f"},
@@ -7698,8 +7820,8 @@ files = [
 ]
 
 [package.extras]
-brotli = ["brotli (==1.0.9) ; os_name != \"nt\" and python_version < \"3\" and platform_python_implementation == \"CPython\"", "brotli (>=1.0.9) ; python_version >= \"3\" and platform_python_implementation == \"CPython\"", "brotlicffi (>=0.8.0) ; (os_name != \"nt\" or python_version >= \"3\") and platform_python_implementation != \"CPython\"", "brotlipy (>=0.6.0) ; os_name == \"nt\" and python_version < \"3\""]
-secure = ["certifi", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "ipaddress ; python_version == \"2.7\"", "pyOpenSSL (>=0.14)", "urllib3-secure-extra"]
+brotli = ["brotli (==1.0.9)", "brotli (>=1.0.9)", "brotlicffi (>=0.8.0)", "brotlipy (>=0.6.0)"]
+secure = ["certifi", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "ipaddress", "pyOpenSSL (>=0.14)", "urllib3-secure-extra"]
 socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
 
 [[package]]
@@ -7722,12 +7844,12 @@ httptools = {version = ">=0.5.0", optional = true, markers = "extra == \"standar
 python-dotenv = {version = ">=0.13", optional = true, markers = "extra == \"standard\""}
 pyyaml = {version = ">=5.1", optional = true, markers = "extra == \"standard\""}
 typing-extensions = {version = ">=4.0", markers = "python_version < \"3.11\""}
-uvloop = {version = ">=0.14.0,<0.15.0 || >0.15.0,<0.15.1 || >0.15.1", optional = true, markers = "sys_platform != \"win32\" and sys_platform != \"cygwin\" and platform_python_implementation != \"PyPy\" and extra == \"standard\""}
+uvloop = {version = ">=0.14.0,<0.15.0 || >0.15.0,<0.15.1 || >0.15.1", optional = true, markers = "(sys_platform != \"win32\" and sys_platform != \"cygwin\") and platform_python_implementation != \"PyPy\" and extra == \"standard\""}
 watchfiles = {version = ">=0.13", optional = true, markers = "extra == \"standard\""}
 websockets = {version = ">=10.4", optional = true, markers = "extra == \"standard\""}
 
 [package.extras]
-standard = ["colorama (>=0.4) ; sys_platform == \"win32\"", "httptools (>=0.5.0)", "python-dotenv (>=0.13)", "pyyaml (>=5.1)", "uvloop (>=0.14.0,!=0.15.0,!=0.15.1) ; sys_platform != \"win32\" and sys_platform != \"cygwin\" and platform_python_implementation != \"PyPy\"", "watchfiles (>=0.13)", "websockets (>=10.4)"]
+standard = ["colorama (>=0.4)", "httptools (>=0.5.0)", "python-dotenv (>=0.13)", "pyyaml (>=5.1)", "uvloop (>=0.14.0,!=0.15.0,!=0.15.1)", "watchfiles (>=0.13)", "websockets (>=10.4)"]
 
 [[package]]
 name = "uvloop"
@@ -7736,7 +7858,7 @@ description = "Fast implementation of asyncio event loop on top of libuv"
 optional = false
 python-versions = ">=3.8.0"
 groups = ["main"]
-markers = "sys_platform != \"win32\" and sys_platform != \"cygwin\" and platform_python_implementation != \"PyPy\""
+markers = "(sys_platform != \"win32\" and sys_platform != \"cygwin\") and platform_python_implementation != \"PyPy\""
 files = [
     {file = "uvloop-0.20.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:9ebafa0b96c62881d5cafa02d9da2e44c23f9f0cd829f3a32a6aff771449c996"},
     {file = "uvloop-0.20.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:35968fc697b0527a06e134999eef859b4034b37aebca537daeb598b9d45a137b"},
@@ -7773,7 +7895,7 @@ files = [
 
 [package.extras]
 docs = ["Sphinx (>=4.1.2,<4.2.0)", "sphinx-rtd-theme (>=0.5.2,<0.6.0)", "sphinxcontrib-asyncio (>=0.3.0,<0.4.0)"]
-test = ["Cython (>=0.29.36,<0.30.0)", "aiohttp (==3.9.0b0) ; python_version >= \"3.12\"", "aiohttp (>=3.8.1) ; python_version < \"3.12\"", "flake8 (>=5.0,<6.0)", "mypy (>=0.800)", "psutil", "pyOpenSSL (>=23.0.0,<23.1.0)", "pycodestyle (>=2.9.0,<2.10.0)"]
+test = ["Cython (>=0.29.36,<0.30.0)", "aiohttp (==3.9.0b0)", "aiohttp (>=3.8.1)", "flake8 (>=5.0,<6.0)", "mypy (>=0.800)", "psutil", "pyOpenSSL (>=23.0.0,<23.1.0)", "pycodestyle (>=2.9.0,<2.10.0)"]
 
 [[package]]
 name = "vcrpy"
@@ -7783,7 +7905,6 @@ optional = false
 python-versions = ">=3.8"
 groups = ["dev"]
 files = [
-    {file = "vcrpy-6.0.1-py2.py3-none-any.whl", hash = "sha256:621c3fb2d6bd8aa9f87532c688e4575bcbbde0c0afeb5ebdb7e14cac409edfdd"},
     {file = "vcrpy-6.0.1.tar.gz", hash = "sha256:9e023fee7f892baa0bbda2f7da7c8ac51165c1c6e38ff8688683a12a4bde9278"},
 ]
 
@@ -8457,14 +8578,14 @@ files = [
 markers = {dev = "python_version < \"3.10\""}
 
 [package.extras]
-check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\""]
+check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1)"]
 cover = ["pytest-cov"]
 doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
 enabler = ["pytest-enabler (>=2.2)"]
-test = ["big-O", "importlib-resources ; python_version < \"3.9\"", "jaraco.functools", "jaraco.itertools", "jaraco.test", "more-itertools", "pytest (>=6,!=8.1.*)", "pytest-ignore-flaky"]
+test = ["big-O", "importlib-resources", "jaraco.functools", "jaraco.itertools", "jaraco.test", "more-itertools", "pytest (>=6,!=8.1.*)", "pytest-ignore-flaky"]
 type = ["pytest-mypy"]
 
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.9,<3.9.7 || >3.9.7,<3.13"
-content-hash = "5bb9e01fd3caa4e768a907809651e0477d9416971ef63988323bfdc8f0302325"
+content-hash = "1fb88649c8e32945d93894586aaca712ec2dfe8276d5e23393f1940297816185"
diff --git a/pyproject.toml b/pyproject.toml
index 0e6b7653..0164ca8a 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -50,6 +50,7 @@ requests = "^2.32.0"
 litellm = {url = "https://github.com/HumanSignal/litellm/archive/c0506d5844ef20d0db14144fbcbf99c05637bde3.zip"}
 pandarallel = "^1.6.5"
 instructor = "^1.4.3"
+thefuzz = "0.22.1"
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^7.4.3"

From e235c64dd61b63d5c0e658cc5e3018aab161daf9 Mon Sep 17 00:00:00 2001
From: nik <nik@heartex.net>
Date: Fri, 14 Mar 2025 14:52:57 +0000
Subject: [PATCH 06/10] WIP: working stuff with Labels

---
 .../collection/label_studio_image_ocr.py      | 228 ++++++++++++++----
 1 file changed, 178 insertions(+), 50 deletions(-)

diff --git a/adala/skills/collection/label_studio_image_ocr.py b/adala/skills/collection/label_studio_image_ocr.py
index fd41c7cf..1bde9aa3 100644
--- a/adala/skills/collection/label_studio_image_ocr.py
+++ b/adala/skills/collection/label_studio_image_ocr.py
@@ -18,7 +18,7 @@
 from adala.runtimes._litellm import MessageChunkType
 from pydantic import BaseModel, Field, model_validator, computed_field
 from difflib import SequenceMatcher
-
+import numpy as np
 
 from adala.runtimes import Runtime, AsyncRuntime
 from adala.utils.internal_data import InternalDataFrame
@@ -28,6 +28,7 @@
 from label_studio_sdk._extensions.label_studio_tools.core.utils.json_schema import (
     json_schema_to_pydantic,
 )
+from .match_bbox_by_text import find_text_in_image
 
 
 logger = logging.getLogger(__name__)
@@ -490,6 +491,12 @@ def _filter_ocr_results_v2(self, ocr_results: Dict, reference_texts: List[str])
                 output[ref_text]['scores'] = filtered_scores
         
         return output
+    
+    
+    def _get_labels(self) -> List[str]:
+        # TODO: validate labels are coming from <Labels> tag, use control tag name
+        # format: {'StartDate': LabelTag(attr={'value': 'StartDate', 'background': 'red'}, tag='Label', value='StartDate', parent_name='columns'), 'EndDate': LabelTag(attr={'value': 'EndDate', 'background': 'green'}, tag='Label', value='EndDate', parent_name='columns'), 'Amount': LabelTag(attr={'value': 'Amount'}, tag='Label', value='Amount', parent_name='columns')}
+        return list(self.label_interface.labels)[0]
         
 
     async def aapply(
@@ -497,55 +504,176 @@ async def aapply(
         input: InternalDataFrame,
         runtime: AsyncRuntime,
     ) -> InternalDataFrame:
-
-        with json_schema_to_pydantic(self.field_schema) as ResponseModel:
-            # special handling to flag image inputs if they exist
-            input_field_types = defaultdict(lambda: MessageChunkType.TEXT)
-            image_value_key = None
-            for tag in self.image_tags:
-                # these are the project variable names, NOT the label config tag names. TODO: pass this info from LSE to avoid recomputing it here.
-                variables = extract_variable_name(tag.value)
-                if len(variables) != 1:
-                    logger.warning(
-                        f"Image tag {tag.name} has multiple variables: {variables}. Cannot mark these variables as image inputs."
-                    )
-                    continue
-                image_value_key = variables[0]
-                input_field_types[image_value_key] = (
-                    MessageChunkType.IMAGE_URLS
-                    if tag.attr.get("valueList")
-                    else MessageChunkType.IMAGE_URL
+        
+        labels = self._get_labels()
+        # validate labels
+        from adala.utils.pydantic_generator import field_schema_to_pydantic_class
+        LineItem = field_schema_to_pydantic_class(
+            class_name="LineItem",
+            description="A single line extracted from the document",
+            field_schema={label: {"type": "string"} for label in labels}
+        )
+        
+        class ResponseModel(BaseModel):
+            lines: List[LineItem]
+        
+        input_field_types = defaultdict(lambda: MessageChunkType.TEXT)
+        image_value_key = None
+        for tag in self.image_tags:
+            # these are the project variable names, NOT the label config tag names. TODO: pass this info from LSE to avoid recomputing it here.
+            variables = extract_variable_name(tag.value)
+            if len(variables) != 1:
+                logger.warning(
+                    f"Image tag {tag.name} has multiple variables: {variables}. Cannot mark these variables as image inputs."
                 )
-
-            logger.debug(
-                f"Using VisionRuntime with input field types: {input_field_types}"
-            )
-            output = await runtime.batch_to_batch(
-                input,
-                input_template=self.input_template,
-                output_template="",
-                instructions_template=self.instructions,
-                response_model=ResponseModel,
-                input_field_types=input_field_types,
+                continue
+            image_value_key = variables[0]
+            input_field_types[image_value_key] = (
+                MessageChunkType.IMAGE_URLS
+                if tag.attr.get("valueList")
+                else MessageChunkType.IMAGE_URL
             )
-            print(f'Output: {output}')
-            print(f'Process images with OCR: {input[image_value_key].tolist()}')
-            ocr_results = await self.process_images_with_ocr(input[image_value_key].tolist())
-            filtered_ocr_results = []
-            for i, row in output.iterrows():
-                extracted_result = row['output']
-                filtered_ocr_result = {
-                    'image_width': ocr_results[i]['image_width'],
-                    'image_height': ocr_results[i]['image_height'],
-                    'ocr_data': self._filter_ocr_results_v2(ocr_results[i]['ocr_data'], extracted_result)
+
+        logger.debug(
+            f"Using VisionRuntime with input field types: {input_field_types}"
+        )
+        output = await runtime.batch_to_batch(
+            input,
+            input_template=self.input_template,
+            output_template="",
+            instructions_template=self.instructions,
+            response_model=ResponseModel,
+            input_field_types=input_field_types,
+        )
+        print(f'Output: {output}')
+        
+        images = input[image_value_key].tolist()
+        all_bbox_annotations = []
+        all_text_annotations = []
+        all_label_annotations = []
+        for i, row in output.iterrows():
+            extracted_results = row['lines']
+            
+            ocr_results = find_text_in_image(images[i], extracted_results)
+            bbox_annotations = []
+            text_annotations = []
+            label_annotations = []
+            for ocr_result in ocr_results:
+                # Add bbox annotation
+                
+                bbox_id = ocr_result['element']['id']
+                parent_id = ocr_result['element'].get('parent_id')
+                
+                bbox_annotation = ocr_result['element']
+                bbox_annotation['score'] = ocr_result['matching_score'] * ocr_result['element']['score']
+                
+                bbox_annotations.append(ocr_result['element'])
+                
+                # Add text annotation
+                text_annotation = {
+                    'text': [ocr_result['reference_text']],
+                    'id': bbox_id
                 }
-                filtered_ocr_results.append(filtered_ocr_result)
-            print(f'Filtered OCR results: {filtered_ocr_results}')
-            # convert filtered OCR results to Label Studio format
-            # bbox_annotations, text_annotations = self._convert_ocr_results_to_label_studio_format(filtered_ocr_results)
-            bbox_annotations, text_annotations = self._convert_ocr_results_to_label_studio_format_v2(filtered_ocr_results)
-            print(f'Bbox annotations: {bbox_annotations}')
-            print(f'Text annotations: {text_annotations}')
-            output['bbox'] = bbox_annotations
-            output['transcription'] = text_annotations
-            return output
+                if parent_id:
+                    text_annotation['parent_id'] = parent_id
+                text_annotations.append(text_annotation)
+                
+                label = ocr_result.pop('reference_label', None)
+
+                if label:
+                    label_annotation = {
+                        'labels': [label],
+                        'id': bbox_id
+                    }
+                    if parent_id:
+                        label_annotation['parent_id'] = parent_id
+                    label_annotations.append(label_annotation)
+                    
+            all_bbox_annotations.append(bbox_annotations)
+            all_text_annotations.append(text_annotations)   
+            all_label_annotations.append(label_annotations)
+        output['bbox'] = all_bbox_annotations
+        output['transcription'] = all_text_annotations
+        output['columns'] = all_label_annotations
+        return output
+            
+
+        # with json_schema_to_pydantic(self.field_schema) as ResponseModel:
+        #     # special handling to flag image inputs if they exist
+        #     input_field_types = defaultdict(lambda: MessageChunkType.TEXT)
+        #     image_value_key = None
+        #     for tag in self.image_tags:
+        #         # these are the project variable names, NOT the label config tag names. TODO: pass this info from LSE to avoid recomputing it here.
+        #         variables = extract_variable_name(tag.value)
+        #         if len(variables) != 1:
+        #             logger.warning(
+        #                 f"Image tag {tag.name} has multiple variables: {variables}. Cannot mark these variables as image inputs."
+        #             )
+        #             continue
+        #         image_value_key = variables[0]
+        #         input_field_types[image_value_key] = (
+        #             MessageChunkType.IMAGE_URLS
+        #             if tag.attr.get("valueList")
+        #             else MessageChunkType.IMAGE_URL
+        #         )
+
+        #     logger.debug(
+        #         f"Using VisionRuntime with input field types: {input_field_types}"
+        #     )
+        #     output = await runtime.batch_to_batch(
+        #         input,
+        #         input_template=self.input_template,
+        #         output_template="",
+        #         instructions_template=self.instructions,
+        #         response_model=ResponseModel,
+        #         input_field_types=input_field_types,
+        #     )
+        #     print(f'Output: {output}')
+            # print(f'Process images with OCR: {input[image_value_key].tolist()}')
+            # # ocr_results = await self.process_images_with_ocr(input[image_value_key].tolist())
+            # # filtered_ocr_results = []
+            # images = input[image_value_key].tolist()
+            # all_bbox_annotations = []
+            # all_text_annotations = []
+            # for i, row in output.iterrows():
+            #     extracted_result = row['output']
+                
+            #     ocr_results = find_text_in_image(images[i], extracted_result)
+            #     bbox_annotations = []
+            #     text_annotations = []
+            #     for ocr_result in ocr_results:
+            #         # Convert OCR results to Label Studio format
+            #         parent_id = ocr_result['bbox']['id']
+
+            #         for word in ocr_result['words']:
+            #             bbox_annotation = word['bbox']
+            #             bbox_annotation['rotation'] = 0
+            #             bbox_annotation['parent_id'] = parent_id
+            #             bbox_annotation['score'] = word['score']
+                                                
+            #             text_annotation = {
+            #                 'text': [word['text']],
+            #                 'id': bbox_annotation['id'],
+            #                 'parent_id': parent_id
+            #             }
+                        
+            #             bbox_annotations.append(bbox_annotation)
+            #             text_annotations.append(text_annotation)
+                        
+            #         bbox_annotation = ocr_result['bbox']
+            #         bbox_annotation['rotation'] = 0
+            #         bbox_annotation['score'] = float(np.sqrt(ocr_result['detection_score'] * ocr_result['matching_score']))
+                    
+            #         text_annotation = {
+            #             'text': [ocr_result['reference_text']],
+            #             'id': parent_id
+            #         }
+                    
+            #         bbox_annotations.append(bbox_annotation)
+            #         text_annotations.append(text_annotation)
+                        
+            #     all_bbox_annotations.append(bbox_annotations)
+            #     all_text_annotations.append(text_annotations)   
+            # output['bbox'] = all_bbox_annotations
+            # output['transcription'] = all_text_annotations
+            # return output

From 08f7cd277a01ff432a715f87a0a9b58ddbd8e536 Mon Sep 17 00:00:00 2001
From: niklub <niklub@users.noreply.github.com>
Date: Sat, 15 Mar 2025 13:08:21 +0000
Subject: [PATCH 07/10] Sync Follow Merge dependencies

Workflow run: https://github.com/HumanSignal/Adala/actions/runs/13873160528
---
 poetry.lock    | 7 ++++---
 pyproject.toml | 2 +-
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/poetry.lock b/poetry.lock
index 384fda43..8427a586 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -3696,7 +3696,7 @@ optional = false
 python-versions = ">=3.9,<4"
 groups = ["main"]
 files = [
-    {file = "5cc1d11e0afbaae6d597c1cbe12805b02af82aac.zip", hash = "sha256:99362c76b98c84e3d24aa6b194768e92c27788216c97663036dcf661c69eaf0b"},
+    {file = "45a8a21065f0e2653857ebb52b8e10ef47856406.zip", hash = "sha256:372fd478fd0ddbd7fe004c04121fc8a8b45da1d03022dd3ef58096e7a13825ba"},
 ]
 
 [package.dependencies]
@@ -3722,7 +3722,7 @@ xmljson = "0.2.1"
 
 [package.source]
 type = "url"
-url = "https://github.com/HumanSignal/label-studio-sdk/archive/5cc1d11e0afbaae6d597c1cbe12805b02af82aac.zip"
+url = "https://github.com/HumanSignal/label-studio-sdk/archive/45a8a21065f0e2653857ebb52b8e10ef47856406.zip"
 
 [[package]]
 name = "litellm"
@@ -7905,6 +7905,7 @@ optional = false
 python-versions = ">=3.8"
 groups = ["dev"]
 files = [
+    {file = "vcrpy-6.0.1-py2.py3-none-any.whl", hash = "sha256:621c3fb2d6bd8aa9f87532c688e4575bcbbde0c0afeb5ebdb7e14cac409edfdd"},
     {file = "vcrpy-6.0.1.tar.gz", hash = "sha256:9e023fee7f892baa0bbda2f7da7c8ac51165c1c6e38ff8688683a12a4bde9278"},
 ]
 
@@ -8588,4 +8589,4 @@ type = ["pytest-mypy"]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.9,<3.9.7 || >3.9.7,<3.13"
-content-hash = "1fb88649c8e32945d93894586aaca712ec2dfe8276d5e23393f1940297816185"
+content-hash = "a7e509bc9fa5f39e65602b640489efb8e748502530428f1035ea5597632523c3"
diff --git a/pyproject.toml b/pyproject.toml
index 0164ca8a..c5430455 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -42,7 +42,7 @@ celery = {version = "^5.3.6", extras = ["redis"]}
 kombu = ">=5.4.0rc2" # Pin version to fix https://github.com/celery/celery/issues/8030. TODO: remove when this fix will be included in celery
 uvicorn = "*"
 pydantic-settings = "^2.2.1"
-label-studio-sdk = {url = "https://github.com/HumanSignal/label-studio-sdk/archive/5cc1d11e0afbaae6d597c1cbe12805b02af82aac.zip"}
+label-studio-sdk = {url = "https://github.com/HumanSignal/label-studio-sdk/archive/45a8a21065f0e2653857ebb52b8e10ef47856406.zip"}
 kafka-python-ng = "^2.2.3"
 requests = "^2.32.0"
 # Using litellm from forked repo until vertex fix is released: https://github.com/BerriAI/litellm/issues/7904

From ae1228fb63f57f309e8df5695bfac08b56fa9d70 Mon Sep 17 00:00:00 2001
From: niklub <niklub@users.noreply.github.com>
Date: Sat, 15 Mar 2025 13:10:48 +0000
Subject: [PATCH 08/10] Sync Follow Merge dependencies

Workflow run: https://github.com/HumanSignal/Adala/actions/runs/13873181688
---
 poetry.lock    | 6 +++---
 pyproject.toml | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/poetry.lock b/poetry.lock
index 8427a586..fcc39697 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -3696,7 +3696,7 @@ optional = false
 python-versions = ">=3.9,<4"
 groups = ["main"]
 files = [
-    {file = "45a8a21065f0e2653857ebb52b8e10ef47856406.zip", hash = "sha256:372fd478fd0ddbd7fe004c04121fc8a8b45da1d03022dd3ef58096e7a13825ba"},
+    {file = "e3f6c7061c8798c91fce779ec7f4571e985e3810.zip", hash = "sha256:d89db23bfc023a38c8605fe3d661a2e21dee0522541d8ebca73be783ab9219a6"},
 ]
 
 [package.dependencies]
@@ -3722,7 +3722,7 @@ xmljson = "0.2.1"
 
 [package.source]
 type = "url"
-url = "https://github.com/HumanSignal/label-studio-sdk/archive/45a8a21065f0e2653857ebb52b8e10ef47856406.zip"
+url = "https://github.com/HumanSignal/label-studio-sdk/archive/e3f6c7061c8798c91fce779ec7f4571e985e3810.zip"
 
 [[package]]
 name = "litellm"
@@ -8589,4 +8589,4 @@ type = ["pytest-mypy"]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.9,<3.9.7 || >3.9.7,<3.13"
-content-hash = "a7e509bc9fa5f39e65602b640489efb8e748502530428f1035ea5597632523c3"
+content-hash = "a10c0d67b278861c3b9c8f6172f9aadff4c0c02f9d0d8fc1d3720b3a6f0c2104"
diff --git a/pyproject.toml b/pyproject.toml
index c5430455..68418573 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -42,7 +42,7 @@ celery = {version = "^5.3.6", extras = ["redis"]}
 kombu = ">=5.4.0rc2" # Pin version to fix https://github.com/celery/celery/issues/8030. TODO: remove when this fix will be included in celery
 uvicorn = "*"
 pydantic-settings = "^2.2.1"
-label-studio-sdk = {url = "https://github.com/HumanSignal/label-studio-sdk/archive/45a8a21065f0e2653857ebb52b8e10ef47856406.zip"}
+label-studio-sdk = {url = "https://github.com/HumanSignal/label-studio-sdk/archive/e3f6c7061c8798c91fce779ec7f4571e985e3810.zip"}
 kafka-python-ng = "^2.2.3"
 requests = "^2.32.0"
 # Using litellm from forked repo until vertex fix is released: https://github.com/BerriAI/litellm/issues/7904

From cdf6b14f47e8680a18565a88f9080c94e2eda08a Mon Sep 17 00:00:00 2001
From: nik <nik@heartex.net>
Date: Mon, 17 Mar 2025 16:39:35 +0000
Subject: [PATCH 09/10] Update deps

---
 Dockerfile.app |   3 +-
 poetry.lock    | 157 +++++++++++++++++++++++++++----------------------
 pyproject.toml |   1 +
 3 files changed, 89 insertions(+), 72 deletions(-)

diff --git a/Dockerfile.app b/Dockerfile.app
index 6d4c6433..231eb7e4 100644
--- a/Dockerfile.app
+++ b/Dockerfile.app
@@ -32,7 +32,8 @@ RUN --mount=type=cache,target="/var/cache/apt",sharing=locked \
     set -eux; \
     apt-get update; \
     apt-get upgrade -y; \
-    apt-get install --no-install-recommends -y procps; \
+    apt-get install --no-install-recommends -y \ 
+        procps tesseract-ocr tesseract-ocr-chi-sim tesseract-ocr-chi-tra tesseract-ocr-deu; \
     apt-get autoremove -y
 
 RUN --mount=type=cache,target=${PIP_CACHE_DIR},sharing=locked \
diff --git a/poetry.lock b/poetry.lock
index fcc39697..581e267f 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 2.1.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 2.0.1 and should not be changed by hand.
 
 [[package]]
 name = "aiohappyeyeballs"
@@ -123,7 +123,7 @@ multidict = ">=4.5,<7.0"
 yarl = ">=1.12.0,<2.0"
 
 [package.extras]
-speedups = ["Brotli ; platform_python_implementation == \"CPython\"", "aiodns (>=3.2.0) ; sys_platform == \"linux\" or sys_platform == \"darwin\"", "brotlicffi ; platform_python_implementation != \"CPython\""]
+speedups = ["Brotli", "aiodns (>=3.2.0)", "brotlicffi"]
 
 [[package]]
 name = "aiokafka"
@@ -206,8 +206,8 @@ files = [
 ]
 
 [package.extras]
-dev = ["aiounittest (==1.4.1) ; python_version < \"3.8\"", "attribution (==1.6.2)", "black (==23.3.0)", "coverage[toml] (==7.2.3)", "flake8 (==5.0.4)", "flake8-bugbear (==23.3.12)", "flit (==3.7.1)", "mypy (==1.2.0)", "ufmt (==2.1.0)", "usort (==1.0.6)"]
-docs = ["sphinx (==6.1.3) ; python_version >= \"3.8\"", "sphinx-mdinclude (==0.5.3)"]
+dev = ["aiounittest (==1.4.1)", "attribution (==1.6.2)", "black (==23.3.0)", "coverage[toml] (==7.2.3)", "flake8 (==5.0.4)", "flake8-bugbear (==23.3.12)", "flit (==3.7.1)", "mypy (==1.2.0)", "ufmt (==2.1.0)", "usort (==1.0.6)"]
+docs = ["sphinx (==6.1.3)", "sphinx-mdinclude (==0.5.3)"]
 
 [[package]]
 name = "amqp"
@@ -256,7 +256,7 @@ typing-extensions = {version = ">=4.1", markers = "python_version < \"3.11\""}
 
 [package.extras]
 doc = ["Sphinx (>=7.4,<8.0)", "packaging", "sphinx-autodoc-typehints (>=1.2.0)", "sphinx-rtd-theme"]
-test = ["anyio[trio]", "coverage[toml] (>=7)", "exceptiongroup (>=1.2.0)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "uvloop (>=0.21.0b1) ; platform_python_implementation == \"CPython\" and platform_system != \"Windows\""]
+test = ["anyio[trio]", "coverage[toml] (>=7)", "exceptiongroup (>=1.2.0)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "uvloop (>=0.21.0b1)"]
 trio = ["trio (>=0.26.1)"]
 
 [[package]]
@@ -412,8 +412,8 @@ files = [
 six = ">=1.12.0"
 
 [package.extras]
-astroid = ["astroid (>=1,<2) ; python_version < \"3\"", "astroid (>=2,<4) ; python_version >= \"3\""]
-test = ["astroid (>=1,<2) ; python_version < \"3\"", "astroid (>=2,<4) ; python_version >= \"3\"", "pytest"]
+astroid = ["astroid (>=1,<2)", "astroid (>=2,<4)"]
+test = ["astroid (>=1,<2)", "astroid (>=2,<4)", "pytest"]
 
 [[package]]
 name = "async-lru"
@@ -455,12 +455,12 @@ files = [
 ]
 
 [package.extras]
-benchmark = ["cloudpickle ; platform_python_implementation == \"CPython\"", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\"", "pympler", "pytest (>=4.3.0)", "pytest-codspeed", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\" and python_version < \"3.13\"", "pytest-xdist[psutil]"]
-cov = ["cloudpickle ; platform_python_implementation == \"CPython\"", "coverage[toml] (>=5.3)", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\"", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\" and python_version < \"3.13\"", "pytest-xdist[psutil]"]
-dev = ["cloudpickle ; platform_python_implementation == \"CPython\"", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\"", "pre-commit", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\" and python_version < \"3.13\"", "pytest-xdist[psutil]"]
+benchmark = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-codspeed", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
+cov = ["cloudpickle", "coverage[toml] (>=5.3)", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
+dev = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pre-commit", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
 docs = ["cogapp", "furo", "myst-parser", "sphinx", "sphinx-notfound-page", "sphinxcontrib-towncrier", "towncrier (<24.7)"]
-tests = ["cloudpickle ; platform_python_implementation == \"CPython\"", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\"", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\" and python_version < \"3.13\"", "pytest-xdist[psutil]"]
-tests-mypy = ["mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\"", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\" and python_version < \"3.13\""]
+tests = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
+tests-mypy = ["mypy (>=1.11.1)", "pytest-mypy-plugins"]
 
 [[package]]
 name = "babel"
@@ -607,7 +607,7 @@ typing-extensions = {version = ">=4.0.1", markers = "python_version < \"3.11\""}
 
 [package.extras]
 colorama = ["colorama (>=0.4.3)"]
-d = ["aiohttp (>=3.7.4) ; sys_platform != \"win32\" or implementation_name != \"pypy\"", "aiohttp (>=3.7.4,!=3.9.0) ; sys_platform == \"win32\" and implementation_name == \"pypy\""]
+d = ["aiohttp (>=3.7.4)", "aiohttp (>=3.7.4,!=3.9.0)"]
 jupyter = ["ipython (>=7.8.0)", "tokenize-rt (>=3.2.0)"]
 uvloop = ["uvloop (>=0.15.2)"]
 
@@ -694,7 +694,7 @@ tomli = {version = ">=1.1.0", markers = "python_version < \"3.11\""}
 
 [package.extras]
 docs = ["furo (>=2023.08.17)", "sphinx (>=7.0,<8.0)", "sphinx-argparse-cli (>=1.5)", "sphinx-autodoc-typehints (>=1.10)", "sphinx-issues (>=3.0.0)"]
-test = ["build[uv,virtualenv]", "filelock (>=3)", "pytest (>=6.2.4)", "pytest-cov (>=2.12)", "pytest-mock (>=2)", "pytest-rerunfailures (>=9.1)", "pytest-xdist (>=1.34)", "setuptools (>=42.0.0) ; python_version < \"3.10\"", "setuptools (>=56.0.0) ; python_version == \"3.10\"", "setuptools (>=56.0.0) ; python_version == \"3.11\"", "setuptools (>=67.8.0) ; python_version >= \"3.12\"", "wheel (>=0.36.0)"]
+test = ["build[uv,virtualenv]", "filelock (>=3)", "pytest (>=6.2.4)", "pytest-cov (>=2.12)", "pytest-mock (>=2)", "pytest-rerunfailures (>=9.1)", "pytest-xdist (>=1.34)", "setuptools (>=42.0.0)", "setuptools (>=56.0.0)", "setuptools (>=56.0.0)", "setuptools (>=67.8.0)", "wheel (>=0.36.0)"]
 typing = ["build[uv]", "importlib-metadata (>=5.1)", "mypy (>=1.9.0,<1.10.0)", "tomli", "typing-extensions (>=3.7.4.3)"]
 uv = ["uv (>=0.1.18)"]
 virtualenv = ["virtualenv (>=20.0.35)"]
@@ -740,32 +740,32 @@ vine = ">=5.1.0,<6.0"
 arangodb = ["pyArango (>=2.0.2)"]
 auth = ["cryptography (==42.0.5)"]
 azureblockblob = ["azure-storage-blob (>=12.15.0)"]
-brotli = ["brotli (>=1.0.0) ; platform_python_implementation == \"CPython\"", "brotlipy (>=0.7.0) ; platform_python_implementation == \"PyPy\""]
+brotli = ["brotli (>=1.0.0)", "brotlipy (>=0.7.0)"]
 cassandra = ["cassandra-driver (>=3.25.0,<4)"]
 consul = ["python-consul2 (==0.1.5)"]
 cosmosdbsql = ["pydocumentdb (==2.3.5)"]
-couchbase = ["couchbase (>=3.0.0) ; platform_python_implementation != \"PyPy\" and (platform_system != \"Windows\" or python_version < \"3.10\")"]
+couchbase = ["couchbase (>=3.0.0)"]
 couchdb = ["pycouchdb (==1.14.2)"]
 django = ["Django (>=2.2.28)"]
 dynamodb = ["boto3 (>=1.26.143)"]
 elasticsearch = ["elastic-transport (<=8.13.0)", "elasticsearch (<=8.13.0)"]
-eventlet = ["eventlet (>=0.32.0) ; python_version < \"3.10\""]
+eventlet = ["eventlet (>=0.32.0)"]
 gcs = ["google-cloud-storage (>=2.10.0)"]
 gevent = ["gevent (>=1.5.0)"]
-librabbitmq = ["librabbitmq (>=2.0.0) ; python_version < \"3.11\""]
-memcache = ["pylibmc (==1.6.3) ; platform_system != \"Windows\""]
+librabbitmq = ["librabbitmq (>=2.0.0)"]
+memcache = ["pylibmc (==1.6.3)"]
 mongodb = ["pymongo[srv] (>=4.0.2)"]
 msgpack = ["msgpack (==1.0.8)"]
 pymemcache = ["python-memcached (>=1.61)"]
-pyro = ["pyro4 (==4.82) ; python_version < \"3.11\""]
+pyro = ["pyro4 (==4.82)"]
 pytest = ["pytest-celery[all] (>=1.0.0)"]
 redis = ["redis (>=4.5.2,!=4.5.5,<6.0.0)"]
 s3 = ["boto3 (>=1.26.143)"]
 slmq = ["softlayer-messaging (>=1.0.3)"]
-solar = ["ephem (==4.1.5) ; platform_python_implementation != \"PyPy\""]
+solar = ["ephem (==4.1.5)"]
 sqlalchemy = ["sqlalchemy (>=1.4.48,<2.1)"]
-sqs = ["boto3 (>=1.26.143)", "kombu[sqs] (>=5.3.4)", "pycurl (>=7.43.0.5) ; sys_platform != \"win32\" and platform_python_implementation == \"CPython\"", "urllib3 (>=1.26.16)"]
-tblib = ["tblib (>=1.3.0) ; python_version < \"3.8.0\"", "tblib (>=1.5.0) ; python_version >= \"3.8.0\""]
+sqs = ["boto3 (>=1.26.143)", "kombu[sqs] (>=5.3.4)", "pycurl (>=7.43.0.5)", "urllib3 (>=1.26.16)"]
+tblib = ["tblib (>=1.3.0)", "tblib (>=1.5.0)"]
 yaml = ["PyYAML (>=3.10)"]
 zookeeper = ["kazoo (>=1.3.1)"]
 zstd = ["zstandard (==0.22.0)"]
@@ -1208,10 +1208,10 @@ files = [
 ]
 
 [package.extras]
-avro = ["avro (>=1.11.1,<2)", "fastavro (>=0.23.0,<1.0) ; python_version < \"3.0\"", "fastavro (>=1.0) ; python_version > \"3.0\"", "requests"]
-dev = ["avro (>=1.11.1,<2)", "fastavro (>=0.23.0,<1.0) ; python_version < \"3.0\"", "fastavro (>=1.0) ; python_version > \"3.0\"", "flake8", "pytest (==4.6.4) ; python_version < \"3.0\"", "pytest ; python_version >= \"3.0\"", "pytest-timeout", "requests"]
-doc = ["avro (>=1.11.1,<2)", "fastavro (>=0.23.0,<1.0) ; python_version < \"3.0\"", "fastavro (>=1.0) ; python_version > \"3.0\"", "requests", "sphinx", "sphinx-rtd-theme"]
-json = ["jsonschema", "pyrsistent (==0.16.1) ; python_version < \"3.0\"", "pyrsistent ; python_version > \"3.0\"", "requests"]
+avro = ["avro (>=1.11.1,<2)", "fastavro (>=0.23.0,<1.0)", "fastavro (>=1.0)", "requests"]
+dev = ["avro (>=1.11.1,<2)", "fastavro (>=0.23.0,<1.0)", "fastavro (>=1.0)", "flake8", "pytest", "pytest (==4.6.4)", "pytest-timeout", "requests"]
+doc = ["avro (>=1.11.1,<2)", "fastavro (>=0.23.0,<1.0)", "fastavro (>=1.0)", "requests", "sphinx", "sphinx-rtd-theme"]
+json = ["jsonschema", "pyrsistent", "pyrsistent (==0.16.1)", "requests"]
 protobuf = ["protobuf", "requests"]
 schema-registry = ["requests"]
 
@@ -1386,7 +1386,7 @@ files = [
 tomli = {version = "*", optional = true, markers = "python_full_version <= \"3.11.0a6\" and extra == \"toml\""}
 
 [package.extras]
-toml = ["tomli ; python_full_version <= \"3.11.0a6\""]
+toml = ["tomli"]
 
 [[package]]
 name = "cryptography"
@@ -1476,8 +1476,8 @@ jinja2 = ">=2.10.1,<4.0"
 packaging = "*"
 pydantic = [
     {version = ">=1.5.1,<2.4.0 || >2.4.0,<3.0", extras = ["email"], markers = "python_version < \"3.10\""},
-    {version = ">=1.9.0,<2.4.0 || >2.4.0,<3.0", extras = ["email"], markers = "python_version == \"3.10\""},
-    {version = ">=1.10.0,<2.4.0 || >2.4.0,<3.0", extras = ["email"], markers = "python_version >= \"3.11\" and python_version < \"4.0\""},
+    {version = ">=1.9.0,<2.4.0 || >2.4.0,<3.0", extras = ["email"], markers = "python_version >= \"3.10\" and python_version < \"3.11\""},
+    {version = ">=1.10.0,<2.4.0 || >2.4.0,<3.0", extras = ["email"], markers = "python_version >= \"3.11\" and python_version < \"3.12\""},
     {version = ">=1.10.0,<2.0.0 || >2.0.0,<2.0.1 || >2.0.1,<2.4.0 || >2.4.0,<3.0", extras = ["email"], markers = "python_version >= \"3.12\" and python_version < \"4.0\""},
 ]
 pyyaml = ">=6.0.1"
@@ -1522,7 +1522,7 @@ xxhash = "*"
 apache-beam = ["apache-beam (>=2.26.0)"]
 audio = ["librosa", "soundfile (>=0.12.1)"]
 benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"]
-dev = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0) ; sys_platform != \"win32\" and python_version < \"3.10\"", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14) ; sys_platform != \"win32\"", "jaxlib (>=0.3.14) ; sys_platform != \"win32\"", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
+dev = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
 docs = ["s3fs", "tensorflow (>=2.6.0)", "torch", "transformers"]
 jax = ["jax (>=0.3.14)", "jaxlib (>=0.3.14)"]
 metrics-tests = ["Werkzeug (>=1.0.1)", "accelerate", "bert-score (>=0.3.6)", "jiwer", "langdetect", "mauve-text", "nltk", "requests-file (>=1.5.1)", "rouge-score", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "spacy (>=3.0.0)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "typer (<0.5.0)"]
@@ -1530,7 +1530,7 @@ quality = ["ruff (>=0.3.0)"]
 s3 = ["s3fs"]
 tensorflow = ["tensorflow (>=2.6.0)"]
 tensorflow-gpu = ["tensorflow (>=2.6.0)"]
-tests = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0) ; sys_platform != \"win32\" and python_version < \"3.10\"", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14) ; sys_platform != \"win32\"", "jaxlib (>=0.3.14) ; sys_platform != \"win32\"", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
+tests = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
 torch = ["torch"]
 vision = ["Pillow (>=6.2.1)"]
 
@@ -1738,7 +1738,7 @@ description = "Backport of PEP 654 (exception groups)"
 optional = false
 python-versions = ">=3.7"
 groups = ["main", "dev"]
-markers = "python_version <= \"3.10\""
+markers = "python_version < \"3.11\""
 files = [
     {file = "exceptiongroup-1.2.2-py3-none-any.whl", hash = "sha256:3111b9d131c238bec2f8f516e123e14ba243563fb135d3fe885990585aa7795b"},
     {file = "exceptiongroup-1.2.2.tar.gz", hash = "sha256:47c2edf7c6738fafb49fd34290706d1a1a2f4d1c6df275526b62cbb4aa5393cc"},
@@ -1760,7 +1760,7 @@ files = [
 ]
 
 [package.extras]
-tests = ["asttokens (>=2.1.0)", "coverage", "coverage-enable-subprocess", "ipython", "littleutils", "pytest", "rich ; python_version >= \"3.11\""]
+tests = ["asttokens (>=2.1.0)", "coverage", "coverage-enable-subprocess", "ipython", "littleutils", "pytest", "rich"]
 
 [[package]]
 name = "faker"
@@ -1853,7 +1853,7 @@ files = [
 [package.extras]
 docs = ["furo (>=2024.8.6)", "sphinx (>=8.0.2)", "sphinx-autodoc-typehints (>=2.4.1)"]
 testing = ["covdefaults (>=2.3)", "coverage (>=7.6.1)", "diff-cover (>=9.2)", "pytest (>=8.3.3)", "pytest-asyncio (>=0.24)", "pytest-cov (>=5)", "pytest-mock (>=3.14)", "pytest-timeout (>=2.3.1)", "virtualenv (>=20.26.4)"]
-typing = ["typing-extensions (>=4.12.2) ; python_version < \"3.11\""]
+typing = ["typing-extensions (>=4.12.2)"]
 
 [[package]]
 name = "flatbuffers"
@@ -1945,18 +1945,18 @@ files = [
 ]
 
 [package.extras]
-all = ["brotli (>=1.0.1) ; platform_python_implementation == \"CPython\"", "brotlicffi (>=0.8.0) ; platform_python_implementation != \"CPython\"", "fs (>=2.2.0,<3)", "lxml (>=4.0)", "lz4 (>=1.7.4.2)", "matplotlib", "munkres ; platform_python_implementation == \"PyPy\"", "pycairo", "scipy ; platform_python_implementation != \"PyPy\"", "skia-pathops (>=0.5.0)", "sympy", "uharfbuzz (>=0.23.0)", "unicodedata2 (>=15.1.0) ; python_version <= \"3.12\"", "xattr ; sys_platform == \"darwin\"", "zopfli (>=0.1.4)"]
+all = ["brotli (>=1.0.1)", "brotlicffi (>=0.8.0)", "fs (>=2.2.0,<3)", "lxml (>=4.0)", "lz4 (>=1.7.4.2)", "matplotlib", "munkres", "pycairo", "scipy", "skia-pathops (>=0.5.0)", "sympy", "uharfbuzz (>=0.23.0)", "unicodedata2 (>=15.1.0)", "xattr", "zopfli (>=0.1.4)"]
 graphite = ["lz4 (>=1.7.4.2)"]
-interpolatable = ["munkres ; platform_python_implementation == \"PyPy\"", "pycairo", "scipy ; platform_python_implementation != \"PyPy\""]
+interpolatable = ["munkres", "pycairo", "scipy"]
 lxml = ["lxml (>=4.0)"]
 pathops = ["skia-pathops (>=0.5.0)"]
 plot = ["matplotlib"]
 repacker = ["uharfbuzz (>=0.23.0)"]
 symfont = ["sympy"]
-type1 = ["xattr ; sys_platform == \"darwin\""]
+type1 = ["xattr"]
 ufo = ["fs (>=2.2.0,<3)"]
-unicode = ["unicodedata2 (>=15.1.0) ; python_version <= \"3.12\""]
-woff = ["brotli (>=1.0.1) ; platform_python_implementation == \"CPython\"", "brotlicffi (>=0.8.0) ; platform_python_implementation != \"CPython\"", "zopfli (>=0.1.4)"]
+unicode = ["unicodedata2 (>=15.1.0)"]
+woff = ["brotli (>=1.0.1)", "brotlicffi (>=0.8.0)", "zopfli (>=0.1.4)"]
 
 [[package]]
 name = "fqdn"
@@ -2531,7 +2531,7 @@ idna = "*"
 sniffio = "*"
 
 [package.extras]
-brotli = ["brotli ; platform_python_implementation == \"CPython\"", "brotlicffi ; platform_python_implementation != \"CPython\""]
+brotli = ["brotli", "brotlicffi"]
 cli = ["click (==8.*)", "pygments (==2.*)", "rich (>=10,<14)"]
 http2 = ["h2 (>=3,<5)"]
 socks = ["socksio (==1.*)"]
@@ -2740,7 +2740,7 @@ zipp = ">=0.5"
 [package.extras]
 doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
 perf = ["ipython"]
-test = ["flufl.flake8", "importlib-resources (>=1.3) ; python_version < \"3.9\"", "jaraco.test (>=5.4)", "packaging", "pyfakefs", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-mypy", "pytest-perf (>=0.9.2)", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\""]
+test = ["flufl.flake8", "importlib-resources (>=1.3)", "jaraco.test (>=5.4)", "packaging", "pyfakefs", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-mypy", "pytest-perf (>=0.9.2)", "pytest-ruff (>=0.2.1)"]
 
 [[package]]
 name = "importlib-resources"
@@ -2759,7 +2759,7 @@ markers = {dev = "python_version < \"3.10\""}
 zipp = {version = ">=3.1.0", markers = "python_version < \"3.10\""}
 
 [package.extras]
-check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\""]
+check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1)"]
 cover = ["pytest-cov"]
 doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
 enabler = ["pytest-enabler (>=2.2)"]
@@ -2780,7 +2780,7 @@ files = [
 
 [package.extras]
 docs = ["jaraco.packaging (>=9)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx"]
-testing = ["pygments", "pytest (>=6)", "pytest-black (>=0.3.7) ; platform_python_implementation != \"PyPy\"", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-flake8", "pytest-mypy (>=0.9.1) ; platform_python_implementation != \"PyPy\""]
+testing = ["pygments", "pytest (>=6)", "pytest-black (>=0.3.7)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-flake8", "pytest-mypy (>=0.9.1)"]
 
 [[package]]
 name = "iniconfig"
@@ -3218,7 +3218,7 @@ traitlets = ">=5.3"
 
 [package.extras]
 docs = ["ipykernel", "myst-parser", "pydata-sphinx-theme", "sphinx (>=4)", "sphinx-autodoc-typehints", "sphinxcontrib-github-alt", "sphinxcontrib-spelling"]
-test = ["coverage", "ipykernel (>=6.14)", "mypy", "paramiko ; sys_platform == \"win32\"", "pre-commit", "pytest", "pytest-cov", "pytest-jupyter[client] (>=0.4.1)", "pytest-timeout"]
+test = ["coverage", "ipykernel (>=6.14)", "mypy", "paramiko", "pre-commit", "pytest", "pytest-cov", "pytest-jupyter[client] (>=0.4.1)", "pytest-timeout"]
 
 [[package]]
 name = "jupyter-console"
@@ -3648,7 +3648,7 @@ azureservicebus = ["azure-servicebus (>=7.10.0)"]
 azurestoragequeues = ["azure-identity (>=1.12.0)", "azure-storage-queue (>=12.6.0)"]
 confluentkafka = ["confluent-kafka (>=2.2.0)"]
 consul = ["python-consul2 (==0.1.5)"]
-librabbitmq = ["librabbitmq (>=2.0.0) ; python_version < \"3.11\""]
+librabbitmq = ["librabbitmq (>=2.0.0)"]
 mongodb = ["pymongo (>=4.1.1)"]
 msgpack = ["msgpack (==1.1.0)"]
 pyro = ["pyro4 (==4.82)"]
@@ -3656,7 +3656,7 @@ qpid = ["qpid-python (>=0.26)", "qpid-tools (>=0.26)"]
 redis = ["redis (>=4.5.2,!=4.5.5,!=5.0.2)"]
 slmq = ["softlayer-messaging (>=1.0.3)"]
 sqlalchemy = ["sqlalchemy (>=1.4.48,<2.1)"]
-sqs = ["boto3 (>=1.26.143)", "pycurl (>=7.43.0.5) ; sys_platform != \"win32\" and platform_python_implementation == \"CPython\"", "urllib3 (>=1.26.16)"]
+sqs = ["boto3 (>=1.26.143)", "pycurl (>=7.43.0.5)", "urllib3 (>=1.26.16)"]
 yaml = ["PyYAML (>=3.10)"]
 zookeeper = ["kazoo (>=2.8.0)"]
 
@@ -4191,7 +4191,7 @@ watchdog = ">=2.0"
 
 [package.extras]
 i18n = ["babel (>=2.9.0)"]
-min-versions = ["babel (==2.9.0)", "click (==7.0)", "colorama (==0.4) ; platform_system == \"Windows\"", "ghp-import (==1.0)", "importlib-metadata (==4.4) ; python_version < \"3.10\"", "jinja2 (==2.11.1)", "markdown (==3.3.6)", "markupsafe (==2.0.1)", "mergedeep (==1.3.4)", "mkdocs-get-deps (==0.2.0)", "packaging (==20.5)", "pathspec (==0.11.1)", "pyyaml (==5.1)", "pyyaml-env-tag (==0.1)", "watchdog (==2.0)"]
+min-versions = ["babel (==2.9.0)", "click (==7.0)", "colorama (==0.4)", "ghp-import (==1.0)", "importlib-metadata (==4.4)", "jinja2 (==2.11.1)", "markdown (==3.3.6)", "markupsafe (==2.0.1)", "mergedeep (==1.3.4)", "mkdocs-get-deps (==0.2.0)", "packaging (==20.5)", "pathspec (==0.11.1)", "pyyaml (==5.1)", "pyyaml-env-tag (==0.1)", "watchdog (==2.0)"]
 
 [[package]]
 name = "mkdocs-autorefs"
@@ -4508,7 +4508,7 @@ files = [
 [package.extras]
 develop = ["codecov", "pycodestyle", "pytest (>=4.6)", "pytest-cov", "wheel"]
 docs = ["sphinx"]
-gmpy = ["gmpy2 (>=2.1.0a4) ; platform_python_implementation != \"PyPy\""]
+gmpy = ["gmpy2 (>=2.1.0a4)"]
 tests = ["pytest (>=4.6)"]
 
 [[package]]
@@ -4529,7 +4529,7 @@ PyJWT = {version = ">=1.0.0,<3", extras = ["crypto"]}
 requests = ">=2.0.0,<3"
 
 [package.extras]
-broker = ["pymsalruntime (>=0.14,<0.18) ; python_version >= \"3.6\" and platform_system == \"Windows\"", "pymsalruntime (>=0.17,<0.18) ; python_version >= \"3.8\" and platform_system == \"Darwin\""]
+broker = ["pymsalruntime (>=0.14,<0.18)", "pymsalruntime (>=0.17,<0.18)"]
 
 [[package]]
 name = "multidict"
@@ -4817,7 +4817,7 @@ tornado = ">=6.2.0"
 [package.extras]
 dev = ["hatch", "pre-commit"]
 docs = ["myst-parser", "nbsphinx", "pydata-sphinx-theme", "sphinx (>=1.3.6)", "sphinxcontrib-github-alt", "sphinxcontrib-spelling"]
-test = ["importlib-resources (>=5.0) ; python_version < \"3.10\"", "ipykernel", "jupyter-server[test] (>=2.4.0,<3)", "jupyterlab-server[test] (>=2.27.1,<3)", "nbval", "pytest (>=7.0)", "pytest-console-scripts", "pytest-timeout", "pytest-tornasync", "requests"]
+test = ["importlib-resources (>=5.0)", "ipykernel", "jupyter-server[test] (>=2.4.0,<3)", "jupyterlab-server[test] (>=2.27.1,<3)", "nbval", "pytest (>=7.0)", "pytest-console-scripts", "pytest-timeout", "pytest-tornasync", "requests"]
 
 [[package]]
 name = "notebook-shim"
@@ -5524,7 +5524,7 @@ docs = ["furo", "olefile", "sphinx (>=7.3)", "sphinx-copybutton", "sphinx-inline
 fpx = ["olefile"]
 mic = ["olefile"]
 tests = ["check-manifest", "coverage", "defusedxml", "markdown2", "olefile", "packaging", "pyroma", "pytest", "pytest-cov", "pytest-timeout"]
-typing = ["typing-extensions ; python_version < \"3.10\""]
+typing = ["typing-extensions"]
 xmp = ["defusedxml"]
 
 [[package]]
@@ -5663,7 +5663,7 @@ files = [
 ]
 
 [package.extras]
-test = ["enum34 ; python_version <= \"3.4\"", "ipaddress ; python_version < \"3.0\"", "mock ; python_version < \"3.0\"", "pywin32 ; sys_platform == \"win32\"", "wmi ; sys_platform == \"win32\""]
+test = ["enum34", "ipaddress", "mock", "pywin32", "wmi"]
 
 [[package]]
 name = "ptyprocess"
@@ -5817,7 +5817,7 @@ typing-extensions = {version = ">=4.6.1", markers = "python_version < \"3.13\""}
 
 [package.extras]
 email = ["email-validator (>=2.0.0)"]
-timezone = ["tzdata ; python_version >= \"3.9\" and sys_platform == \"win32\""]
+timezone = ["tzdata"]
 
 [[package]]
 name = "pydantic-core"
@@ -6063,6 +6063,22 @@ files = [
 [package.extras]
 dev = ["build", "flake8", "mypy", "pytest", "twine"]
 
+[[package]]
+name = "pytesseract"
+version = "0.3.13"
+description = "Python-tesseract is a python wrapper for Google's Tesseract-OCR"
+optional = false
+python-versions = ">=3.8"
+groups = ["main"]
+files = [
+    {file = "pytesseract-0.3.13-py3-none-any.whl", hash = "sha256:7a99c6c2ac598360693d83a416e36e0b33a67638bb9d77fdcac094a3589d4b34"},
+    {file = "pytesseract-0.3.13.tar.gz", hash = "sha256:4bf5f880c99406f52a3cfc2633e42d9dc67615e69d8a509d74867d3baddb5db9"},
+]
+
+[package.dependencies]
+packaging = ">=21.3"
+Pillow = ">=8.0.0"
+
 [[package]]
 name = "pytest"
 version = "7.4.4"
@@ -7099,9 +7115,9 @@ files = [
 ]
 
 [package.extras]
-nativelib = ["pyobjc-framework-Cocoa ; sys_platform == \"darwin\"", "pywin32 ; sys_platform == \"win32\""]
-objc = ["pyobjc-framework-Cocoa ; sys_platform == \"darwin\""]
-win32 = ["pywin32 ; sys_platform == \"win32\""]
+nativelib = ["pyobjc-framework-Cocoa", "pywin32"]
+objc = ["pyobjc-framework-Cocoa"]
+win32 = ["pywin32"]
 
 [[package]]
 name = "setuptools"
@@ -7116,9 +7132,9 @@ files = [
 ]
 
 [package.extras]
-core = ["importlib-metadata (>=6) ; python_version < \"3.10\"", "importlib-resources (>=5.10.2) ; python_version < \"3.9\"", "jaraco.text (>=3.7)", "more-itertools (>=8.8)", "ordered-set (>=3.1.1)", "packaging (>=24)", "platformdirs (>=2.6.2)", "tomli (>=2.0.1) ; python_version < \"3.11\"", "wheel (>=0.43.0)"]
+core = ["importlib-metadata (>=6)", "importlib-resources (>=5.10.2)", "jaraco.text (>=3.7)", "more-itertools (>=8.8)", "ordered-set (>=3.1.1)", "packaging (>=24)", "platformdirs (>=2.6.2)", "tomli (>=2.0.1)", "wheel (>=0.43.0)"]
 doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "pygments-github-lexers (==0.0.5)", "pyproject-hooks (!=1.1)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-favicon", "sphinx-inline-tabs", "sphinx-lint", "sphinx-notfound-page (>=1,<2)", "sphinx-reredirects", "sphinxcontrib-towncrier", "towncrier (<24.7)"]
-test = ["build[virtualenv] (>=1.0.3)", "filelock (>=3.4.0)", "importlib-metadata", "ini2toml[lite] (>=0.14)", "jaraco.develop (>=7.21) ; python_version >= \"3.9\" and sys_platform != \"cygwin\"", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "jaraco.test", "mypy (==1.11.*)", "packaging (>=23.2)", "pip (>=19.1)", "pyproject-hooks (!=1.1)", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-home (>=0.5)", "pytest-mypy", "pytest-perf ; sys_platform != \"cygwin\"", "pytest-ruff (<0.4) ; platform_system == \"Windows\"", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\"", "pytest-ruff (>=0.3.2) ; sys_platform != \"cygwin\"", "pytest-subprocess", "pytest-timeout", "pytest-xdist (>=3)", "tomli", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel"]
+test = ["build[virtualenv] (>=1.0.3)", "filelock (>=3.4.0)", "importlib-metadata", "ini2toml[lite] (>=0.14)", "jaraco.develop (>=7.21)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "jaraco.test", "mypy (==1.11.*)", "packaging (>=23.2)", "pip (>=19.1)", "pyproject-hooks (!=1.1)", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-home (>=0.5)", "pytest-mypy", "pytest-perf", "pytest-ruff (<0.4)", "pytest-ruff (>=0.2.1)", "pytest-ruff (>=0.3.2)", "pytest-subprocess", "pytest-timeout", "pytest-xdist (>=3)", "tomli", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel"]
 
 [[package]]
 name = "shellingham"
@@ -7518,7 +7534,7 @@ files = [
     {file = "toml-0.10.2-py2.py3-none-any.whl", hash = "sha256:806143ae5bfb6a3c6e736a764057db0e6a0e05e338b5630894a5f779cabb4f9b"},
     {file = "toml-0.10.2.tar.gz", hash = "sha256:b3bda1d108d5dd99f4a20d24d9c348e91c4db7ab1b749200bded2f839ccbe68f"},
 ]
-markers = {main = "python_version <= \"3.10\""}
+markers = {main = "python_version < \"3.11\""}
 
 [[package]]
 name = "tomli"
@@ -7527,7 +7543,7 @@ description = "A lil' TOML parser"
 optional = false
 python-versions = ">=3.7"
 groups = ["main", "dev"]
-markers = "python_version <= \"3.10\""
+markers = "python_version < \"3.11\""
 files = [
     {file = "tomli-2.0.1-py3-none-any.whl", hash = "sha256:939de3e7a6161af0c887ef91b7d41a53e7c5a1ca976325f429cb46ea9bc30ecc"},
     {file = "tomli-2.0.1.tar.gz", hash = "sha256:de526c12914f0c550d15924c62d72abc48d6fe7364aa87328337a31007fe8a4f"},
@@ -7820,8 +7836,8 @@ files = [
 ]
 
 [package.extras]
-brotli = ["brotli (==1.0.9) ; os_name != \"nt\" and python_version < \"3\" and platform_python_implementation == \"CPython\"", "brotli (>=1.0.9) ; python_version >= \"3\" and platform_python_implementation == \"CPython\"", "brotlicffi (>=0.8.0) ; (os_name != \"nt\" or python_version >= \"3\") and platform_python_implementation != \"CPython\"", "brotlipy (>=0.6.0) ; os_name == \"nt\" and python_version < \"3\""]
-secure = ["certifi", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "ipaddress ; python_version == \"2.7\"", "pyOpenSSL (>=0.14)", "urllib3-secure-extra"]
+brotli = ["brotli (==1.0.9)", "brotli (>=1.0.9)", "brotlicffi (>=0.8.0)", "brotlipy (>=0.6.0)"]
+secure = ["certifi", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "ipaddress", "pyOpenSSL (>=0.14)", "urllib3-secure-extra"]
 socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
 
 [[package]]
@@ -7844,12 +7860,12 @@ httptools = {version = ">=0.5.0", optional = true, markers = "extra == \"standar
 python-dotenv = {version = ">=0.13", optional = true, markers = "extra == \"standard\""}
 pyyaml = {version = ">=5.1", optional = true, markers = "extra == \"standard\""}
 typing-extensions = {version = ">=4.0", markers = "python_version < \"3.11\""}
-uvloop = {version = ">=0.14.0,<0.15.0 || >0.15.0,<0.15.1 || >0.15.1", optional = true, markers = "sys_platform != \"win32\" and sys_platform != \"cygwin\" and platform_python_implementation != \"PyPy\" and extra == \"standard\""}
+uvloop = {version = ">=0.14.0,<0.15.0 || >0.15.0,<0.15.1 || >0.15.1", optional = true, markers = "(sys_platform != \"win32\" and sys_platform != \"cygwin\") and platform_python_implementation != \"PyPy\" and extra == \"standard\""}
 watchfiles = {version = ">=0.13", optional = true, markers = "extra == \"standard\""}
 websockets = {version = ">=10.4", optional = true, markers = "extra == \"standard\""}
 
 [package.extras]
-standard = ["colorama (>=0.4) ; sys_platform == \"win32\"", "httptools (>=0.5.0)", "python-dotenv (>=0.13)", "pyyaml (>=5.1)", "uvloop (>=0.14.0,!=0.15.0,!=0.15.1) ; sys_platform != \"win32\" and sys_platform != \"cygwin\" and platform_python_implementation != \"PyPy\"", "watchfiles (>=0.13)", "websockets (>=10.4)"]
+standard = ["colorama (>=0.4)", "httptools (>=0.5.0)", "python-dotenv (>=0.13)", "pyyaml (>=5.1)", "uvloop (>=0.14.0,!=0.15.0,!=0.15.1)", "watchfiles (>=0.13)", "websockets (>=10.4)"]
 
 [[package]]
 name = "uvloop"
@@ -7858,7 +7874,7 @@ description = "Fast implementation of asyncio event loop on top of libuv"
 optional = false
 python-versions = ">=3.8.0"
 groups = ["main"]
-markers = "sys_platform != \"win32\" and sys_platform != \"cygwin\" and platform_python_implementation != \"PyPy\""
+markers = "(sys_platform != \"win32\" and sys_platform != \"cygwin\") and platform_python_implementation != \"PyPy\""
 files = [
     {file = "uvloop-0.20.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:9ebafa0b96c62881d5cafa02d9da2e44c23f9f0cd829f3a32a6aff771449c996"},
     {file = "uvloop-0.20.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:35968fc697b0527a06e134999eef859b4034b37aebca537daeb598b9d45a137b"},
@@ -7895,7 +7911,7 @@ files = [
 
 [package.extras]
 docs = ["Sphinx (>=4.1.2,<4.2.0)", "sphinx-rtd-theme (>=0.5.2,<0.6.0)", "sphinxcontrib-asyncio (>=0.3.0,<0.4.0)"]
-test = ["Cython (>=0.29.36,<0.30.0)", "aiohttp (==3.9.0b0) ; python_version >= \"3.12\"", "aiohttp (>=3.8.1) ; python_version < \"3.12\"", "flake8 (>=5.0,<6.0)", "mypy (>=0.800)", "psutil", "pyOpenSSL (>=23.0.0,<23.1.0)", "pycodestyle (>=2.9.0,<2.10.0)"]
+test = ["Cython (>=0.29.36,<0.30.0)", "aiohttp (==3.9.0b0)", "aiohttp (>=3.8.1)", "flake8 (>=5.0,<6.0)", "mypy (>=0.800)", "psutil", "pyOpenSSL (>=23.0.0,<23.1.0)", "pycodestyle (>=2.9.0,<2.10.0)"]
 
 [[package]]
 name = "vcrpy"
@@ -7905,7 +7921,6 @@ optional = false
 python-versions = ">=3.8"
 groups = ["dev"]
 files = [
-    {file = "vcrpy-6.0.1-py2.py3-none-any.whl", hash = "sha256:621c3fb2d6bd8aa9f87532c688e4575bcbbde0c0afeb5ebdb7e14cac409edfdd"},
     {file = "vcrpy-6.0.1.tar.gz", hash = "sha256:9e023fee7f892baa0bbda2f7da7c8ac51165c1c6e38ff8688683a12a4bde9278"},
 ]
 
@@ -8579,14 +8594,14 @@ files = [
 markers = {dev = "python_version < \"3.10\""}
 
 [package.extras]
-check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\""]
+check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1)"]
 cover = ["pytest-cov"]
 doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
 enabler = ["pytest-enabler (>=2.2)"]
-test = ["big-O", "importlib-resources ; python_version < \"3.9\"", "jaraco.functools", "jaraco.itertools", "jaraco.test", "more-itertools", "pytest (>=6,!=8.1.*)", "pytest-ignore-flaky"]
+test = ["big-O", "importlib-resources", "jaraco.functools", "jaraco.itertools", "jaraco.test", "more-itertools", "pytest (>=6,!=8.1.*)", "pytest-ignore-flaky"]
 type = ["pytest-mypy"]
 
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.9,<3.9.7 || >3.9.7,<3.13"
-content-hash = "a10c0d67b278861c3b9c8f6172f9aadff4c0c02f9d0d8fc1d3720b3a6f0c2104"
+content-hash = "72960a903c05976830225f572261c64d423402a2ef58317b2f339119c3c8f375"
diff --git a/pyproject.toml b/pyproject.toml
index 68418573..183d5ad8 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -51,6 +51,7 @@ litellm = {url = "https://github.com/HumanSignal/litellm/archive/c0506d5844ef20d
 pandarallel = "^1.6.5"
 instructor = "^1.4.3"
 thefuzz = "0.22.1"
+pytesseract = "^0.3.13"
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^7.4.3"

From 8a0f936f80a3eea471b9939ade71d99f34da8646 Mon Sep 17 00:00:00 2001
From: niklub <niklub@users.noreply.github.com>
Date: Mon, 17 Mar 2025 16:41:56 +0000
Subject: [PATCH 10/10] Sync Follow Merge dependencies

Workflow run: https://github.com/HumanSignal/Adala/actions/runs/13904950905
---
 poetry.lock    | 145 +++++++++++++++++++++++++------------------------
 pyproject.toml |   2 +-
 2 files changed, 74 insertions(+), 73 deletions(-)

diff --git a/poetry.lock b/poetry.lock
index 581e267f..85b81803 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 2.0.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 2.1.1 and should not be changed by hand.
 
 [[package]]
 name = "aiohappyeyeballs"
@@ -123,7 +123,7 @@ multidict = ">=4.5,<7.0"
 yarl = ">=1.12.0,<2.0"
 
 [package.extras]
-speedups = ["Brotli", "aiodns (>=3.2.0)", "brotlicffi"]
+speedups = ["Brotli ; platform_python_implementation == \"CPython\"", "aiodns (>=3.2.0) ; sys_platform == \"linux\" or sys_platform == \"darwin\"", "brotlicffi ; platform_python_implementation != \"CPython\""]
 
 [[package]]
 name = "aiokafka"
@@ -206,8 +206,8 @@ files = [
 ]
 
 [package.extras]
-dev = ["aiounittest (==1.4.1)", "attribution (==1.6.2)", "black (==23.3.0)", "coverage[toml] (==7.2.3)", "flake8 (==5.0.4)", "flake8-bugbear (==23.3.12)", "flit (==3.7.1)", "mypy (==1.2.0)", "ufmt (==2.1.0)", "usort (==1.0.6)"]
-docs = ["sphinx (==6.1.3)", "sphinx-mdinclude (==0.5.3)"]
+dev = ["aiounittest (==1.4.1) ; python_version < \"3.8\"", "attribution (==1.6.2)", "black (==23.3.0)", "coverage[toml] (==7.2.3)", "flake8 (==5.0.4)", "flake8-bugbear (==23.3.12)", "flit (==3.7.1)", "mypy (==1.2.0)", "ufmt (==2.1.0)", "usort (==1.0.6)"]
+docs = ["sphinx (==6.1.3) ; python_version >= \"3.8\"", "sphinx-mdinclude (==0.5.3)"]
 
 [[package]]
 name = "amqp"
@@ -256,7 +256,7 @@ typing-extensions = {version = ">=4.1", markers = "python_version < \"3.11\""}
 
 [package.extras]
 doc = ["Sphinx (>=7.4,<8.0)", "packaging", "sphinx-autodoc-typehints (>=1.2.0)", "sphinx-rtd-theme"]
-test = ["anyio[trio]", "coverage[toml] (>=7)", "exceptiongroup (>=1.2.0)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "uvloop (>=0.21.0b1)"]
+test = ["anyio[trio]", "coverage[toml] (>=7)", "exceptiongroup (>=1.2.0)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "uvloop (>=0.21.0b1) ; platform_python_implementation == \"CPython\" and platform_system != \"Windows\""]
 trio = ["trio (>=0.26.1)"]
 
 [[package]]
@@ -412,8 +412,8 @@ files = [
 six = ">=1.12.0"
 
 [package.extras]
-astroid = ["astroid (>=1,<2)", "astroid (>=2,<4)"]
-test = ["astroid (>=1,<2)", "astroid (>=2,<4)", "pytest"]
+astroid = ["astroid (>=1,<2) ; python_version < \"3\"", "astroid (>=2,<4) ; python_version >= \"3\""]
+test = ["astroid (>=1,<2) ; python_version < \"3\"", "astroid (>=2,<4) ; python_version >= \"3\"", "pytest"]
 
 [[package]]
 name = "async-lru"
@@ -455,12 +455,12 @@ files = [
 ]
 
 [package.extras]
-benchmark = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-codspeed", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
-cov = ["cloudpickle", "coverage[toml] (>=5.3)", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
-dev = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pre-commit", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
+benchmark = ["cloudpickle ; platform_python_implementation == \"CPython\"", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\"", "pympler", "pytest (>=4.3.0)", "pytest-codspeed", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\" and python_version < \"3.13\"", "pytest-xdist[psutil]"]
+cov = ["cloudpickle ; platform_python_implementation == \"CPython\"", "coverage[toml] (>=5.3)", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\"", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\" and python_version < \"3.13\"", "pytest-xdist[psutil]"]
+dev = ["cloudpickle ; platform_python_implementation == \"CPython\"", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\"", "pre-commit", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\" and python_version < \"3.13\"", "pytest-xdist[psutil]"]
 docs = ["cogapp", "furo", "myst-parser", "sphinx", "sphinx-notfound-page", "sphinxcontrib-towncrier", "towncrier (<24.7)"]
-tests = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
-tests-mypy = ["mypy (>=1.11.1)", "pytest-mypy-plugins"]
+tests = ["cloudpickle ; platform_python_implementation == \"CPython\"", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\"", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\" and python_version < \"3.13\"", "pytest-xdist[psutil]"]
+tests-mypy = ["mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\"", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.9\" and python_version < \"3.13\""]
 
 [[package]]
 name = "babel"
@@ -607,7 +607,7 @@ typing-extensions = {version = ">=4.0.1", markers = "python_version < \"3.11\""}
 
 [package.extras]
 colorama = ["colorama (>=0.4.3)"]
-d = ["aiohttp (>=3.7.4)", "aiohttp (>=3.7.4,!=3.9.0)"]
+d = ["aiohttp (>=3.7.4) ; sys_platform != \"win32\" or implementation_name != \"pypy\"", "aiohttp (>=3.7.4,!=3.9.0) ; sys_platform == \"win32\" and implementation_name == \"pypy\""]
 jupyter = ["ipython (>=7.8.0)", "tokenize-rt (>=3.2.0)"]
 uvloop = ["uvloop (>=0.15.2)"]
 
@@ -694,7 +694,7 @@ tomli = {version = ">=1.1.0", markers = "python_version < \"3.11\""}
 
 [package.extras]
 docs = ["furo (>=2023.08.17)", "sphinx (>=7.0,<8.0)", "sphinx-argparse-cli (>=1.5)", "sphinx-autodoc-typehints (>=1.10)", "sphinx-issues (>=3.0.0)"]
-test = ["build[uv,virtualenv]", "filelock (>=3)", "pytest (>=6.2.4)", "pytest-cov (>=2.12)", "pytest-mock (>=2)", "pytest-rerunfailures (>=9.1)", "pytest-xdist (>=1.34)", "setuptools (>=42.0.0)", "setuptools (>=56.0.0)", "setuptools (>=56.0.0)", "setuptools (>=67.8.0)", "wheel (>=0.36.0)"]
+test = ["build[uv,virtualenv]", "filelock (>=3)", "pytest (>=6.2.4)", "pytest-cov (>=2.12)", "pytest-mock (>=2)", "pytest-rerunfailures (>=9.1)", "pytest-xdist (>=1.34)", "setuptools (>=42.0.0) ; python_version < \"3.10\"", "setuptools (>=56.0.0) ; python_version == \"3.10\"", "setuptools (>=56.0.0) ; python_version == \"3.11\"", "setuptools (>=67.8.0) ; python_version >= \"3.12\"", "wheel (>=0.36.0)"]
 typing = ["build[uv]", "importlib-metadata (>=5.1)", "mypy (>=1.9.0,<1.10.0)", "tomli", "typing-extensions (>=3.7.4.3)"]
 uv = ["uv (>=0.1.18)"]
 virtualenv = ["virtualenv (>=20.0.35)"]
@@ -740,32 +740,32 @@ vine = ">=5.1.0,<6.0"
 arangodb = ["pyArango (>=2.0.2)"]
 auth = ["cryptography (==42.0.5)"]
 azureblockblob = ["azure-storage-blob (>=12.15.0)"]
-brotli = ["brotli (>=1.0.0)", "brotlipy (>=0.7.0)"]
+brotli = ["brotli (>=1.0.0) ; platform_python_implementation == \"CPython\"", "brotlipy (>=0.7.0) ; platform_python_implementation == \"PyPy\""]
 cassandra = ["cassandra-driver (>=3.25.0,<4)"]
 consul = ["python-consul2 (==0.1.5)"]
 cosmosdbsql = ["pydocumentdb (==2.3.5)"]
-couchbase = ["couchbase (>=3.0.0)"]
+couchbase = ["couchbase (>=3.0.0) ; platform_python_implementation != \"PyPy\" and (platform_system != \"Windows\" or python_version < \"3.10\")"]
 couchdb = ["pycouchdb (==1.14.2)"]
 django = ["Django (>=2.2.28)"]
 dynamodb = ["boto3 (>=1.26.143)"]
 elasticsearch = ["elastic-transport (<=8.13.0)", "elasticsearch (<=8.13.0)"]
-eventlet = ["eventlet (>=0.32.0)"]
+eventlet = ["eventlet (>=0.32.0) ; python_version < \"3.10\""]
 gcs = ["google-cloud-storage (>=2.10.0)"]
 gevent = ["gevent (>=1.5.0)"]
-librabbitmq = ["librabbitmq (>=2.0.0)"]
-memcache = ["pylibmc (==1.6.3)"]
+librabbitmq = ["librabbitmq (>=2.0.0) ; python_version < \"3.11\""]
+memcache = ["pylibmc (==1.6.3) ; platform_system != \"Windows\""]
 mongodb = ["pymongo[srv] (>=4.0.2)"]
 msgpack = ["msgpack (==1.0.8)"]
 pymemcache = ["python-memcached (>=1.61)"]
-pyro = ["pyro4 (==4.82)"]
+pyro = ["pyro4 (==4.82) ; python_version < \"3.11\""]
 pytest = ["pytest-celery[all] (>=1.0.0)"]
 redis = ["redis (>=4.5.2,!=4.5.5,<6.0.0)"]
 s3 = ["boto3 (>=1.26.143)"]
 slmq = ["softlayer-messaging (>=1.0.3)"]
-solar = ["ephem (==4.1.5)"]
+solar = ["ephem (==4.1.5) ; platform_python_implementation != \"PyPy\""]
 sqlalchemy = ["sqlalchemy (>=1.4.48,<2.1)"]
-sqs = ["boto3 (>=1.26.143)", "kombu[sqs] (>=5.3.4)", "pycurl (>=7.43.0.5)", "urllib3 (>=1.26.16)"]
-tblib = ["tblib (>=1.3.0)", "tblib (>=1.5.0)"]
+sqs = ["boto3 (>=1.26.143)", "kombu[sqs] (>=5.3.4)", "pycurl (>=7.43.0.5) ; sys_platform != \"win32\" and platform_python_implementation == \"CPython\"", "urllib3 (>=1.26.16)"]
+tblib = ["tblib (>=1.3.0) ; python_version < \"3.8.0\"", "tblib (>=1.5.0) ; python_version >= \"3.8.0\""]
 yaml = ["PyYAML (>=3.10)"]
 zookeeper = ["kazoo (>=1.3.1)"]
 zstd = ["zstandard (==0.22.0)"]
@@ -1208,10 +1208,10 @@ files = [
 ]
 
 [package.extras]
-avro = ["avro (>=1.11.1,<2)", "fastavro (>=0.23.0,<1.0)", "fastavro (>=1.0)", "requests"]
-dev = ["avro (>=1.11.1,<2)", "fastavro (>=0.23.0,<1.0)", "fastavro (>=1.0)", "flake8", "pytest", "pytest (==4.6.4)", "pytest-timeout", "requests"]
-doc = ["avro (>=1.11.1,<2)", "fastavro (>=0.23.0,<1.0)", "fastavro (>=1.0)", "requests", "sphinx", "sphinx-rtd-theme"]
-json = ["jsonschema", "pyrsistent", "pyrsistent (==0.16.1)", "requests"]
+avro = ["avro (>=1.11.1,<2)", "fastavro (>=0.23.0,<1.0) ; python_version < \"3.0\"", "fastavro (>=1.0) ; python_version > \"3.0\"", "requests"]
+dev = ["avro (>=1.11.1,<2)", "fastavro (>=0.23.0,<1.0) ; python_version < \"3.0\"", "fastavro (>=1.0) ; python_version > \"3.0\"", "flake8", "pytest (==4.6.4) ; python_version < \"3.0\"", "pytest ; python_version >= \"3.0\"", "pytest-timeout", "requests"]
+doc = ["avro (>=1.11.1,<2)", "fastavro (>=0.23.0,<1.0) ; python_version < \"3.0\"", "fastavro (>=1.0) ; python_version > \"3.0\"", "requests", "sphinx", "sphinx-rtd-theme"]
+json = ["jsonschema", "pyrsistent (==0.16.1) ; python_version < \"3.0\"", "pyrsistent ; python_version > \"3.0\"", "requests"]
 protobuf = ["protobuf", "requests"]
 schema-registry = ["requests"]
 
@@ -1386,7 +1386,7 @@ files = [
 tomli = {version = "*", optional = true, markers = "python_full_version <= \"3.11.0a6\" and extra == \"toml\""}
 
 [package.extras]
-toml = ["tomli"]
+toml = ["tomli ; python_full_version <= \"3.11.0a6\""]
 
 [[package]]
 name = "cryptography"
@@ -1476,8 +1476,8 @@ jinja2 = ">=2.10.1,<4.0"
 packaging = "*"
 pydantic = [
     {version = ">=1.5.1,<2.4.0 || >2.4.0,<3.0", extras = ["email"], markers = "python_version < \"3.10\""},
-    {version = ">=1.9.0,<2.4.0 || >2.4.0,<3.0", extras = ["email"], markers = "python_version >= \"3.10\" and python_version < \"3.11\""},
-    {version = ">=1.10.0,<2.4.0 || >2.4.0,<3.0", extras = ["email"], markers = "python_version >= \"3.11\" and python_version < \"3.12\""},
+    {version = ">=1.9.0,<2.4.0 || >2.4.0,<3.0", extras = ["email"], markers = "python_version == \"3.10\""},
+    {version = ">=1.10.0,<2.4.0 || >2.4.0,<3.0", extras = ["email"], markers = "python_version >= \"3.11\" and python_version < \"4.0\""},
     {version = ">=1.10.0,<2.0.0 || >2.0.0,<2.0.1 || >2.0.1,<2.4.0 || >2.4.0,<3.0", extras = ["email"], markers = "python_version >= \"3.12\" and python_version < \"4.0\""},
 ]
 pyyaml = ">=6.0.1"
@@ -1522,7 +1522,7 @@ xxhash = "*"
 apache-beam = ["apache-beam (>=2.26.0)"]
 audio = ["librosa", "soundfile (>=0.12.1)"]
 benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"]
-dev = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
+dev = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0) ; sys_platform != \"win32\" and python_version < \"3.10\"", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14) ; sys_platform != \"win32\"", "jaxlib (>=0.3.14) ; sys_platform != \"win32\"", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
 docs = ["s3fs", "tensorflow (>=2.6.0)", "torch", "transformers"]
 jax = ["jax (>=0.3.14)", "jaxlib (>=0.3.14)"]
 metrics-tests = ["Werkzeug (>=1.0.1)", "accelerate", "bert-score (>=0.3.6)", "jiwer", "langdetect", "mauve-text", "nltk", "requests-file (>=1.5.1)", "rouge-score", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "spacy (>=3.0.0)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "typer (<0.5.0)"]
@@ -1530,7 +1530,7 @@ quality = ["ruff (>=0.3.0)"]
 s3 = ["s3fs"]
 tensorflow = ["tensorflow (>=2.6.0)"]
 tensorflow-gpu = ["tensorflow (>=2.6.0)"]
-tests = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
+tests = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0) ; sys_platform != \"win32\" and python_version < \"3.10\"", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14) ; sys_platform != \"win32\"", "jaxlib (>=0.3.14) ; sys_platform != \"win32\"", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
 torch = ["torch"]
 vision = ["Pillow (>=6.2.1)"]
 
@@ -1738,7 +1738,7 @@ description = "Backport of PEP 654 (exception groups)"
 optional = false
 python-versions = ">=3.7"
 groups = ["main", "dev"]
-markers = "python_version < \"3.11\""
+markers = "python_version <= \"3.10\""
 files = [
     {file = "exceptiongroup-1.2.2-py3-none-any.whl", hash = "sha256:3111b9d131c238bec2f8f516e123e14ba243563fb135d3fe885990585aa7795b"},
     {file = "exceptiongroup-1.2.2.tar.gz", hash = "sha256:47c2edf7c6738fafb49fd34290706d1a1a2f4d1c6df275526b62cbb4aa5393cc"},
@@ -1760,7 +1760,7 @@ files = [
 ]
 
 [package.extras]
-tests = ["asttokens (>=2.1.0)", "coverage", "coverage-enable-subprocess", "ipython", "littleutils", "pytest", "rich"]
+tests = ["asttokens (>=2.1.0)", "coverage", "coverage-enable-subprocess", "ipython", "littleutils", "pytest", "rich ; python_version >= \"3.11\""]
 
 [[package]]
 name = "faker"
@@ -1853,7 +1853,7 @@ files = [
 [package.extras]
 docs = ["furo (>=2024.8.6)", "sphinx (>=8.0.2)", "sphinx-autodoc-typehints (>=2.4.1)"]
 testing = ["covdefaults (>=2.3)", "coverage (>=7.6.1)", "diff-cover (>=9.2)", "pytest (>=8.3.3)", "pytest-asyncio (>=0.24)", "pytest-cov (>=5)", "pytest-mock (>=3.14)", "pytest-timeout (>=2.3.1)", "virtualenv (>=20.26.4)"]
-typing = ["typing-extensions (>=4.12.2)"]
+typing = ["typing-extensions (>=4.12.2) ; python_version < \"3.11\""]
 
 [[package]]
 name = "flatbuffers"
@@ -1945,18 +1945,18 @@ files = [
 ]
 
 [package.extras]
-all = ["brotli (>=1.0.1)", "brotlicffi (>=0.8.0)", "fs (>=2.2.0,<3)", "lxml (>=4.0)", "lz4 (>=1.7.4.2)", "matplotlib", "munkres", "pycairo", "scipy", "skia-pathops (>=0.5.0)", "sympy", "uharfbuzz (>=0.23.0)", "unicodedata2 (>=15.1.0)", "xattr", "zopfli (>=0.1.4)"]
+all = ["brotli (>=1.0.1) ; platform_python_implementation == \"CPython\"", "brotlicffi (>=0.8.0) ; platform_python_implementation != \"CPython\"", "fs (>=2.2.0,<3)", "lxml (>=4.0)", "lz4 (>=1.7.4.2)", "matplotlib", "munkres ; platform_python_implementation == \"PyPy\"", "pycairo", "scipy ; platform_python_implementation != \"PyPy\"", "skia-pathops (>=0.5.0)", "sympy", "uharfbuzz (>=0.23.0)", "unicodedata2 (>=15.1.0) ; python_version <= \"3.12\"", "xattr ; sys_platform == \"darwin\"", "zopfli (>=0.1.4)"]
 graphite = ["lz4 (>=1.7.4.2)"]
-interpolatable = ["munkres", "pycairo", "scipy"]
+interpolatable = ["munkres ; platform_python_implementation == \"PyPy\"", "pycairo", "scipy ; platform_python_implementation != \"PyPy\""]
 lxml = ["lxml (>=4.0)"]
 pathops = ["skia-pathops (>=0.5.0)"]
 plot = ["matplotlib"]
 repacker = ["uharfbuzz (>=0.23.0)"]
 symfont = ["sympy"]
-type1 = ["xattr"]
+type1 = ["xattr ; sys_platform == \"darwin\""]
 ufo = ["fs (>=2.2.0,<3)"]
-unicode = ["unicodedata2 (>=15.1.0)"]
-woff = ["brotli (>=1.0.1)", "brotlicffi (>=0.8.0)", "zopfli (>=0.1.4)"]
+unicode = ["unicodedata2 (>=15.1.0) ; python_version <= \"3.12\""]
+woff = ["brotli (>=1.0.1) ; platform_python_implementation == \"CPython\"", "brotlicffi (>=0.8.0) ; platform_python_implementation != \"CPython\"", "zopfli (>=0.1.4)"]
 
 [[package]]
 name = "fqdn"
@@ -2531,7 +2531,7 @@ idna = "*"
 sniffio = "*"
 
 [package.extras]
-brotli = ["brotli", "brotlicffi"]
+brotli = ["brotli ; platform_python_implementation == \"CPython\"", "brotlicffi ; platform_python_implementation != \"CPython\""]
 cli = ["click (==8.*)", "pygments (==2.*)", "rich (>=10,<14)"]
 http2 = ["h2 (>=3,<5)"]
 socks = ["socksio (==1.*)"]
@@ -2740,7 +2740,7 @@ zipp = ">=0.5"
 [package.extras]
 doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
 perf = ["ipython"]
-test = ["flufl.flake8", "importlib-resources (>=1.3)", "jaraco.test (>=5.4)", "packaging", "pyfakefs", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-mypy", "pytest-perf (>=0.9.2)", "pytest-ruff (>=0.2.1)"]
+test = ["flufl.flake8", "importlib-resources (>=1.3) ; python_version < \"3.9\"", "jaraco.test (>=5.4)", "packaging", "pyfakefs", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-mypy", "pytest-perf (>=0.9.2)", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\""]
 
 [[package]]
 name = "importlib-resources"
@@ -2759,7 +2759,7 @@ markers = {dev = "python_version < \"3.10\""}
 zipp = {version = ">=3.1.0", markers = "python_version < \"3.10\""}
 
 [package.extras]
-check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1)"]
+check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\""]
 cover = ["pytest-cov"]
 doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
 enabler = ["pytest-enabler (>=2.2)"]
@@ -2780,7 +2780,7 @@ files = [
 
 [package.extras]
 docs = ["jaraco.packaging (>=9)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx"]
-testing = ["pygments", "pytest (>=6)", "pytest-black (>=0.3.7)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-flake8", "pytest-mypy (>=0.9.1)"]
+testing = ["pygments", "pytest (>=6)", "pytest-black (>=0.3.7) ; platform_python_implementation != \"PyPy\"", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-flake8", "pytest-mypy (>=0.9.1) ; platform_python_implementation != \"PyPy\""]
 
 [[package]]
 name = "iniconfig"
@@ -3218,7 +3218,7 @@ traitlets = ">=5.3"
 
 [package.extras]
 docs = ["ipykernel", "myst-parser", "pydata-sphinx-theme", "sphinx (>=4)", "sphinx-autodoc-typehints", "sphinxcontrib-github-alt", "sphinxcontrib-spelling"]
-test = ["coverage", "ipykernel (>=6.14)", "mypy", "paramiko", "pre-commit", "pytest", "pytest-cov", "pytest-jupyter[client] (>=0.4.1)", "pytest-timeout"]
+test = ["coverage", "ipykernel (>=6.14)", "mypy", "paramiko ; sys_platform == \"win32\"", "pre-commit", "pytest", "pytest-cov", "pytest-jupyter[client] (>=0.4.1)", "pytest-timeout"]
 
 [[package]]
 name = "jupyter-console"
@@ -3648,7 +3648,7 @@ azureservicebus = ["azure-servicebus (>=7.10.0)"]
 azurestoragequeues = ["azure-identity (>=1.12.0)", "azure-storage-queue (>=12.6.0)"]
 confluentkafka = ["confluent-kafka (>=2.2.0)"]
 consul = ["python-consul2 (==0.1.5)"]
-librabbitmq = ["librabbitmq (>=2.0.0)"]
+librabbitmq = ["librabbitmq (>=2.0.0) ; python_version < \"3.11\""]
 mongodb = ["pymongo (>=4.1.1)"]
 msgpack = ["msgpack (==1.1.0)"]
 pyro = ["pyro4 (==4.82)"]
@@ -3656,7 +3656,7 @@ qpid = ["qpid-python (>=0.26)", "qpid-tools (>=0.26)"]
 redis = ["redis (>=4.5.2,!=4.5.5,!=5.0.2)"]
 slmq = ["softlayer-messaging (>=1.0.3)"]
 sqlalchemy = ["sqlalchemy (>=1.4.48,<2.1)"]
-sqs = ["boto3 (>=1.26.143)", "pycurl (>=7.43.0.5)", "urllib3 (>=1.26.16)"]
+sqs = ["boto3 (>=1.26.143)", "pycurl (>=7.43.0.5) ; sys_platform != \"win32\" and platform_python_implementation == \"CPython\"", "urllib3 (>=1.26.16)"]
 yaml = ["PyYAML (>=3.10)"]
 zookeeper = ["kazoo (>=2.8.0)"]
 
@@ -3696,7 +3696,7 @@ optional = false
 python-versions = ">=3.9,<4"
 groups = ["main"]
 files = [
-    {file = "e3f6c7061c8798c91fce779ec7f4571e985e3810.zip", hash = "sha256:d89db23bfc023a38c8605fe3d661a2e21dee0522541d8ebca73be783ab9219a6"},
+    {file = "2b0d2cc9403c83cd99dc3e6cc06a580d9e9db4f1.zip", hash = "sha256:118574bddf431edf96d564f55173f6e0f104d233c1ebc3dac8ca68decd4fc6f4"},
 ]
 
 [package.dependencies]
@@ -3722,7 +3722,7 @@ xmljson = "0.2.1"
 
 [package.source]
 type = "url"
-url = "https://github.com/HumanSignal/label-studio-sdk/archive/e3f6c7061c8798c91fce779ec7f4571e985e3810.zip"
+url = "https://github.com/HumanSignal/label-studio-sdk/archive/2b0d2cc9403c83cd99dc3e6cc06a580d9e9db4f1.zip"
 
 [[package]]
 name = "litellm"
@@ -4191,7 +4191,7 @@ watchdog = ">=2.0"
 
 [package.extras]
 i18n = ["babel (>=2.9.0)"]
-min-versions = ["babel (==2.9.0)", "click (==7.0)", "colorama (==0.4)", "ghp-import (==1.0)", "importlib-metadata (==4.4)", "jinja2 (==2.11.1)", "markdown (==3.3.6)", "markupsafe (==2.0.1)", "mergedeep (==1.3.4)", "mkdocs-get-deps (==0.2.0)", "packaging (==20.5)", "pathspec (==0.11.1)", "pyyaml (==5.1)", "pyyaml-env-tag (==0.1)", "watchdog (==2.0)"]
+min-versions = ["babel (==2.9.0)", "click (==7.0)", "colorama (==0.4) ; platform_system == \"Windows\"", "ghp-import (==1.0)", "importlib-metadata (==4.4) ; python_version < \"3.10\"", "jinja2 (==2.11.1)", "markdown (==3.3.6)", "markupsafe (==2.0.1)", "mergedeep (==1.3.4)", "mkdocs-get-deps (==0.2.0)", "packaging (==20.5)", "pathspec (==0.11.1)", "pyyaml (==5.1)", "pyyaml-env-tag (==0.1)", "watchdog (==2.0)"]
 
 [[package]]
 name = "mkdocs-autorefs"
@@ -4508,7 +4508,7 @@ files = [
 [package.extras]
 develop = ["codecov", "pycodestyle", "pytest (>=4.6)", "pytest-cov", "wheel"]
 docs = ["sphinx"]
-gmpy = ["gmpy2 (>=2.1.0a4)"]
+gmpy = ["gmpy2 (>=2.1.0a4) ; platform_python_implementation != \"PyPy\""]
 tests = ["pytest (>=4.6)"]
 
 [[package]]
@@ -4529,7 +4529,7 @@ PyJWT = {version = ">=1.0.0,<3", extras = ["crypto"]}
 requests = ">=2.0.0,<3"
 
 [package.extras]
-broker = ["pymsalruntime (>=0.14,<0.18)", "pymsalruntime (>=0.17,<0.18)"]
+broker = ["pymsalruntime (>=0.14,<0.18) ; python_version >= \"3.6\" and platform_system == \"Windows\"", "pymsalruntime (>=0.17,<0.18) ; python_version >= \"3.8\" and platform_system == \"Darwin\""]
 
 [[package]]
 name = "multidict"
@@ -4817,7 +4817,7 @@ tornado = ">=6.2.0"
 [package.extras]
 dev = ["hatch", "pre-commit"]
 docs = ["myst-parser", "nbsphinx", "pydata-sphinx-theme", "sphinx (>=1.3.6)", "sphinxcontrib-github-alt", "sphinxcontrib-spelling"]
-test = ["importlib-resources (>=5.0)", "ipykernel", "jupyter-server[test] (>=2.4.0,<3)", "jupyterlab-server[test] (>=2.27.1,<3)", "nbval", "pytest (>=7.0)", "pytest-console-scripts", "pytest-timeout", "pytest-tornasync", "requests"]
+test = ["importlib-resources (>=5.0) ; python_version < \"3.10\"", "ipykernel", "jupyter-server[test] (>=2.4.0,<3)", "jupyterlab-server[test] (>=2.27.1,<3)", "nbval", "pytest (>=7.0)", "pytest-console-scripts", "pytest-timeout", "pytest-tornasync", "requests"]
 
 [[package]]
 name = "notebook-shim"
@@ -5524,7 +5524,7 @@ docs = ["furo", "olefile", "sphinx (>=7.3)", "sphinx-copybutton", "sphinx-inline
 fpx = ["olefile"]
 mic = ["olefile"]
 tests = ["check-manifest", "coverage", "defusedxml", "markdown2", "olefile", "packaging", "pyroma", "pytest", "pytest-cov", "pytest-timeout"]
-typing = ["typing-extensions"]
+typing = ["typing-extensions ; python_version < \"3.10\""]
 xmp = ["defusedxml"]
 
 [[package]]
@@ -5663,7 +5663,7 @@ files = [
 ]
 
 [package.extras]
-test = ["enum34", "ipaddress", "mock", "pywin32", "wmi"]
+test = ["enum34 ; python_version <= \"3.4\"", "ipaddress ; python_version < \"3.0\"", "mock ; python_version < \"3.0\"", "pywin32 ; sys_platform == \"win32\"", "wmi ; sys_platform == \"win32\""]
 
 [[package]]
 name = "ptyprocess"
@@ -5817,7 +5817,7 @@ typing-extensions = {version = ">=4.6.1", markers = "python_version < \"3.13\""}
 
 [package.extras]
 email = ["email-validator (>=2.0.0)"]
-timezone = ["tzdata"]
+timezone = ["tzdata ; python_version >= \"3.9\" and sys_platform == \"win32\""]
 
 [[package]]
 name = "pydantic-core"
@@ -7115,9 +7115,9 @@ files = [
 ]
 
 [package.extras]
-nativelib = ["pyobjc-framework-Cocoa", "pywin32"]
-objc = ["pyobjc-framework-Cocoa"]
-win32 = ["pywin32"]
+nativelib = ["pyobjc-framework-Cocoa ; sys_platform == \"darwin\"", "pywin32 ; sys_platform == \"win32\""]
+objc = ["pyobjc-framework-Cocoa ; sys_platform == \"darwin\""]
+win32 = ["pywin32 ; sys_platform == \"win32\""]
 
 [[package]]
 name = "setuptools"
@@ -7132,9 +7132,9 @@ files = [
 ]
 
 [package.extras]
-core = ["importlib-metadata (>=6)", "importlib-resources (>=5.10.2)", "jaraco.text (>=3.7)", "more-itertools (>=8.8)", "ordered-set (>=3.1.1)", "packaging (>=24)", "platformdirs (>=2.6.2)", "tomli (>=2.0.1)", "wheel (>=0.43.0)"]
+core = ["importlib-metadata (>=6) ; python_version < \"3.10\"", "importlib-resources (>=5.10.2) ; python_version < \"3.9\"", "jaraco.text (>=3.7)", "more-itertools (>=8.8)", "ordered-set (>=3.1.1)", "packaging (>=24)", "platformdirs (>=2.6.2)", "tomli (>=2.0.1) ; python_version < \"3.11\"", "wheel (>=0.43.0)"]
 doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "pygments-github-lexers (==0.0.5)", "pyproject-hooks (!=1.1)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-favicon", "sphinx-inline-tabs", "sphinx-lint", "sphinx-notfound-page (>=1,<2)", "sphinx-reredirects", "sphinxcontrib-towncrier", "towncrier (<24.7)"]
-test = ["build[virtualenv] (>=1.0.3)", "filelock (>=3.4.0)", "importlib-metadata", "ini2toml[lite] (>=0.14)", "jaraco.develop (>=7.21)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "jaraco.test", "mypy (==1.11.*)", "packaging (>=23.2)", "pip (>=19.1)", "pyproject-hooks (!=1.1)", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-home (>=0.5)", "pytest-mypy", "pytest-perf", "pytest-ruff (<0.4)", "pytest-ruff (>=0.2.1)", "pytest-ruff (>=0.3.2)", "pytest-subprocess", "pytest-timeout", "pytest-xdist (>=3)", "tomli", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel"]
+test = ["build[virtualenv] (>=1.0.3)", "filelock (>=3.4.0)", "importlib-metadata", "ini2toml[lite] (>=0.14)", "jaraco.develop (>=7.21) ; python_version >= \"3.9\" and sys_platform != \"cygwin\"", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "jaraco.test", "mypy (==1.11.*)", "packaging (>=23.2)", "pip (>=19.1)", "pyproject-hooks (!=1.1)", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-home (>=0.5)", "pytest-mypy", "pytest-perf ; sys_platform != \"cygwin\"", "pytest-ruff (<0.4) ; platform_system == \"Windows\"", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\"", "pytest-ruff (>=0.3.2) ; sys_platform != \"cygwin\"", "pytest-subprocess", "pytest-timeout", "pytest-xdist (>=3)", "tomli", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel"]
 
 [[package]]
 name = "shellingham"
@@ -7534,7 +7534,7 @@ files = [
     {file = "toml-0.10.2-py2.py3-none-any.whl", hash = "sha256:806143ae5bfb6a3c6e736a764057db0e6a0e05e338b5630894a5f779cabb4f9b"},
     {file = "toml-0.10.2.tar.gz", hash = "sha256:b3bda1d108d5dd99f4a20d24d9c348e91c4db7ab1b749200bded2f839ccbe68f"},
 ]
-markers = {main = "python_version < \"3.11\""}
+markers = {main = "python_version <= \"3.10\""}
 
 [[package]]
 name = "tomli"
@@ -7543,7 +7543,7 @@ description = "A lil' TOML parser"
 optional = false
 python-versions = ">=3.7"
 groups = ["main", "dev"]
-markers = "python_version < \"3.11\""
+markers = "python_version <= \"3.10\""
 files = [
     {file = "tomli-2.0.1-py3-none-any.whl", hash = "sha256:939de3e7a6161af0c887ef91b7d41a53e7c5a1ca976325f429cb46ea9bc30ecc"},
     {file = "tomli-2.0.1.tar.gz", hash = "sha256:de526c12914f0c550d15924c62d72abc48d6fe7364aa87328337a31007fe8a4f"},
@@ -7836,8 +7836,8 @@ files = [
 ]
 
 [package.extras]
-brotli = ["brotli (==1.0.9)", "brotli (>=1.0.9)", "brotlicffi (>=0.8.0)", "brotlipy (>=0.6.0)"]
-secure = ["certifi", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "ipaddress", "pyOpenSSL (>=0.14)", "urllib3-secure-extra"]
+brotli = ["brotli (==1.0.9) ; os_name != \"nt\" and python_version < \"3\" and platform_python_implementation == \"CPython\"", "brotli (>=1.0.9) ; python_version >= \"3\" and platform_python_implementation == \"CPython\"", "brotlicffi (>=0.8.0) ; (os_name != \"nt\" or python_version >= \"3\") and platform_python_implementation != \"CPython\"", "brotlipy (>=0.6.0) ; os_name == \"nt\" and python_version < \"3\""]
+secure = ["certifi", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "ipaddress ; python_version == \"2.7\"", "pyOpenSSL (>=0.14)", "urllib3-secure-extra"]
 socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
 
 [[package]]
@@ -7860,12 +7860,12 @@ httptools = {version = ">=0.5.0", optional = true, markers = "extra == \"standar
 python-dotenv = {version = ">=0.13", optional = true, markers = "extra == \"standard\""}
 pyyaml = {version = ">=5.1", optional = true, markers = "extra == \"standard\""}
 typing-extensions = {version = ">=4.0", markers = "python_version < \"3.11\""}
-uvloop = {version = ">=0.14.0,<0.15.0 || >0.15.0,<0.15.1 || >0.15.1", optional = true, markers = "(sys_platform != \"win32\" and sys_platform != \"cygwin\") and platform_python_implementation != \"PyPy\" and extra == \"standard\""}
+uvloop = {version = ">=0.14.0,<0.15.0 || >0.15.0,<0.15.1 || >0.15.1", optional = true, markers = "sys_platform != \"win32\" and sys_platform != \"cygwin\" and platform_python_implementation != \"PyPy\" and extra == \"standard\""}
 watchfiles = {version = ">=0.13", optional = true, markers = "extra == \"standard\""}
 websockets = {version = ">=10.4", optional = true, markers = "extra == \"standard\""}
 
 [package.extras]
-standard = ["colorama (>=0.4)", "httptools (>=0.5.0)", "python-dotenv (>=0.13)", "pyyaml (>=5.1)", "uvloop (>=0.14.0,!=0.15.0,!=0.15.1)", "watchfiles (>=0.13)", "websockets (>=10.4)"]
+standard = ["colorama (>=0.4) ; sys_platform == \"win32\"", "httptools (>=0.5.0)", "python-dotenv (>=0.13)", "pyyaml (>=5.1)", "uvloop (>=0.14.0,!=0.15.0,!=0.15.1) ; sys_platform != \"win32\" and sys_platform != \"cygwin\" and platform_python_implementation != \"PyPy\"", "watchfiles (>=0.13)", "websockets (>=10.4)"]
 
 [[package]]
 name = "uvloop"
@@ -7874,7 +7874,7 @@ description = "Fast implementation of asyncio event loop on top of libuv"
 optional = false
 python-versions = ">=3.8.0"
 groups = ["main"]
-markers = "(sys_platform != \"win32\" and sys_platform != \"cygwin\") and platform_python_implementation != \"PyPy\""
+markers = "sys_platform != \"win32\" and sys_platform != \"cygwin\" and platform_python_implementation != \"PyPy\""
 files = [
     {file = "uvloop-0.20.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:9ebafa0b96c62881d5cafa02d9da2e44c23f9f0cd829f3a32a6aff771449c996"},
     {file = "uvloop-0.20.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:35968fc697b0527a06e134999eef859b4034b37aebca537daeb598b9d45a137b"},
@@ -7911,7 +7911,7 @@ files = [
 
 [package.extras]
 docs = ["Sphinx (>=4.1.2,<4.2.0)", "sphinx-rtd-theme (>=0.5.2,<0.6.0)", "sphinxcontrib-asyncio (>=0.3.0,<0.4.0)"]
-test = ["Cython (>=0.29.36,<0.30.0)", "aiohttp (==3.9.0b0)", "aiohttp (>=3.8.1)", "flake8 (>=5.0,<6.0)", "mypy (>=0.800)", "psutil", "pyOpenSSL (>=23.0.0,<23.1.0)", "pycodestyle (>=2.9.0,<2.10.0)"]
+test = ["Cython (>=0.29.36,<0.30.0)", "aiohttp (==3.9.0b0) ; python_version >= \"3.12\"", "aiohttp (>=3.8.1) ; python_version < \"3.12\"", "flake8 (>=5.0,<6.0)", "mypy (>=0.800)", "psutil", "pyOpenSSL (>=23.0.0,<23.1.0)", "pycodestyle (>=2.9.0,<2.10.0)"]
 
 [[package]]
 name = "vcrpy"
@@ -7921,6 +7921,7 @@ optional = false
 python-versions = ">=3.8"
 groups = ["dev"]
 files = [
+    {file = "vcrpy-6.0.1-py2.py3-none-any.whl", hash = "sha256:621c3fb2d6bd8aa9f87532c688e4575bcbbde0c0afeb5ebdb7e14cac409edfdd"},
     {file = "vcrpy-6.0.1.tar.gz", hash = "sha256:9e023fee7f892baa0bbda2f7da7c8ac51165c1c6e38ff8688683a12a4bde9278"},
 ]
 
@@ -8594,14 +8595,14 @@ files = [
 markers = {dev = "python_version < \"3.10\""}
 
 [package.extras]
-check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1)"]
+check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\""]
 cover = ["pytest-cov"]
 doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
 enabler = ["pytest-enabler (>=2.2)"]
-test = ["big-O", "importlib-resources", "jaraco.functools", "jaraco.itertools", "jaraco.test", "more-itertools", "pytest (>=6,!=8.1.*)", "pytest-ignore-flaky"]
+test = ["big-O", "importlib-resources ; python_version < \"3.9\"", "jaraco.functools", "jaraco.itertools", "jaraco.test", "more-itertools", "pytest (>=6,!=8.1.*)", "pytest-ignore-flaky"]
 type = ["pytest-mypy"]
 
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.9,<3.9.7 || >3.9.7,<3.13"
-content-hash = "72960a903c05976830225f572261c64d423402a2ef58317b2f339119c3c8f375"
+content-hash = "167ce58f336fb164546c14a06fe12ae870266918f4290ab8b41d31e4b72d8307"
diff --git a/pyproject.toml b/pyproject.toml
index 183d5ad8..d230b4a0 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -42,7 +42,7 @@ celery = {version = "^5.3.6", extras = ["redis"]}
 kombu = ">=5.4.0rc2" # Pin version to fix https://github.com/celery/celery/issues/8030. TODO: remove when this fix will be included in celery
 uvicorn = "*"
 pydantic-settings = "^2.2.1"
-label-studio-sdk = {url = "https://github.com/HumanSignal/label-studio-sdk/archive/e3f6c7061c8798c91fce779ec7f4571e985e3810.zip"}
+label-studio-sdk = {url = "https://github.com/HumanSignal/label-studio-sdk/archive/2b0d2cc9403c83cd99dc3e6cc06a580d9e9db4f1.zip"}
 kafka-python-ng = "^2.2.3"
 requests = "^2.32.0"
 # Using litellm from forked repo until vertex fix is released: https://github.com/BerriAI/litellm/issues/7904