Skip to content

Commit 467904b

Browse files
anastasdsdmartinol
authored andcommitted
Rename command group to rag and feature gate behind ILAB_DEV_PREVIEW
Signed-off-by: Daniele Martinoli <[email protected]>
1 parent 7c36742 commit 467904b

File tree

1 file changed

+21
-16
lines changed

1 file changed

+21
-16
lines changed

docs/rag/ilab-rag-retrieval.md

Lines changed: 21 additions & 16 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
# Design Proposal - Embedding Ingestion Pipeline And RAG-Based Chat
22

3-
**TODOs**
3+
Not addressed in this document:
44

55
* Vector store authentication options.
66
* Document versioning and data update policies.
@@ -22,9 +22,10 @@ This document proposes enhancements to the `ilab` CLI to support workflows utili
2222
(RAG) artifacts within `InstructLab`. The proposed changes introduce new commands and options for the embedding ingestion
2323
and RAG-based chat pipelines:
2424

25-
* A new `ilab data` sub-command to process customer documentation.
25+
* A new `ilab rag` command group, feature gated behind a `ILAB_DEV_PREVIEW` environment variable.
26+
* A new `ilab rag` sub-command group to process customer documentation.
2627
* Either from knowledge taxonomy or from actual user documents.
27-
* A new `ilab data` sub-command to generate and ingest embeddings from pre-processed documents into a configured vector store.
28+
* A new `ilab rag` sub-command to generate and ingest embeddings from pre-processed documents into a configured vector store.
2829
* An option to enhance the chat pipeline by using the stored embeddings to augment the context of conversations, improving relevance and accuracy.
2930

3031
### 1.1 User Experience Overview
@@ -94,18 +95,18 @@ consistently to all new and updated commands.
9495

9596
### 2.2 Document Processing Pipeline
9697

97-
The proposal is to add a `process` sub-command to the `data` command group.
98+
The proposal is to add a `process` sub-command to the `rag` command group.
9899

99100
For the Taxonomy path (no Model Training):
100101

101102
```bash
102-
ilab data process --output /path/to/processed/folder
103+
ilab rag convert --output /path/to/processed/folder
103104
```
104105

105106
For the Plug-and-Play RAG path:
106107

107108
```bash
108-
ilab data process --input /path/to/docs/folder --output /path/to/processed/folder
109+
ilab rag convert --input /path/to/docs/folder --output /path/to/processed/folder
109110
```
110111

111112
#### Processing-Command Purpose
@@ -134,11 +135,13 @@ The generated artifacts can later be used to generate and ingest the embeddings
134135

135136
### 2.3 Document Processing Pipeline Options
136137

138+
**Note**: The `--help` option will be aware of the `rag` command group only if `ILAB_DEV_PREVIEW` environment variable is set to `true`.
139+
137140
```bash
138-
% ilab data process --help
139-
Usage: ilab data process [OPTIONS]
141+
% ilab rag convert --help
142+
Usage: ilab rag convert [OPTIONS]
140143

141-
The document processing pipeline
144+
The document processing pipeline for retrieval augmented generation
142145

143146
Options:
144147
--input DIRECTORY The folder with user documents to process. In case
@@ -159,23 +162,23 @@ Options:
159162

160163
### 2.4 Embedding Ingestion Pipeline
161164

162-
The proposal is to add an `ingest` sub-command to the `data` command group.
165+
The proposal is to add an `ingest` sub-command to the `rag` command group.
163166

164167
For the Model Training path:
165168

166169
```bash
167-
ilab data ingest
170+
ilab rag ingest
168171
```
169172

170173
For the Taxonomy or Plug-and-Play RAG paths:
171174

172175
```bash
173-
ilab data ingest --input path/to/processed/folder
176+
ilab rag ingest --input path/to/processed/folder
174177
```
175178

176179
#### Ingestion-Working Assumption
177180

178-
The documents at the specified path have already been processed using the `data process` command or an equivalent method
181+
The documents at the specified path have already been processed using the `rag convert` command or an equivalent method
179182
(see [Getting Started with Knowledge Contributions][ilab-knowledge]).
180183

181184
#### Ingestion-Command Purpose
@@ -209,9 +212,11 @@ context for RAG-based chat pipelines.
209212

210213
### 2.5 Embedding Ingestion Pipeline Options
211214

215+
**Note**: The `--help` option will be aware of the `rag` command group only if `ILAB_DEV_PREVIEW` environment variable is set to `true`.
216+
212217
```bash
213-
% ilab data ingest --help
214-
Usage: ilab data ingest [OPTIONS]
218+
% ilab rag ingest --help
219+
Usage: ilab rag ingest [OPTIONS]
215220
216221
The embedding ingestion pipeline
217222
@@ -411,7 +416,7 @@ ilab model chat --rag --retrieval-strategy query-expansion --retrieval-strategy-
411416
Generate a containerized RAG artifact to expose a `/query` endpoint that can serve as an alternative source :
412417
413418
```bash
414-
ilab data ingest --build-image --image-name=docker.io/user/my_rag_artifacts:1.0
419+
ilab rag ingest --build-image --image-name=docker.io/user/my_rag_artifacts:1.0
415420
```
416421
417422
Then serve it and use it in a chat session:

0 commit comments

Comments
 (0)