Contribution to fix small bug and to reformat #27
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
linhkid
commented
Apr 7, 2024
linhkid
commented
- Fix JSON error when there is incomplete prompt leading to failed json generation
- Add more fields in the summariaztion such as methodology, discussion, data used etc
- Add generated date to digest.html file
rmfan
reviewed
Apr 21, 2024
src/relevancy_prompt.txt
Outdated
| 1. {"Relevancy score": "an integer score out of 10", "Reasons for match": "1-2 sentence short reasonings", "Goal": "What kind of pain points the paper is trying to solve?", "Data": "Summary of the data source used in the paper", "Methodology": "Summary of methodologies used in the paper", "Git": "Link to the code repo (if available)", "Experiments & Results": "Summary of any experiments & its results", "Discussion & Next steps": "Further discussion and next steps of the research"} | ||
|
|
||
| My research interests are: NLP, RAGs, LLM, Optmization in Machine learning, Data science, Generative AI, Optimization in LLM, Finance modelling ... |
There was a problem hiding this comment.
The interests get appended on here:
Line 23 in 0eadab7
No need to add them manually to the relevancy prompt
rmfan
reviewed
Apr 21, 2024
README.md
Outdated
| **ArXiv Digest and Personalized Recommendations using Large Language Models.** | ||
| **ArXiv Digest (extra version) and Personalized Recommendations using Large Language Models.** | ||
|
|
||
| *(Note: This is an adjusted repo to match my needs. For original repo please refer to **AutoLLM** that I forked from)* |
There was a problem hiding this comment.
This is a pull request to the original repo 😄
There was a problem hiding this comment.
Sorry Richard, pls ignore haha.
Revamp workflow, UI and using multiple models for this repo 1.Content Extraction After Filtering: Added a new step in the process between Stage 1 and Stage 2 After papers pass the relevancy filter, the system now extracts HTML content for them Only papers that make it through the threshold get their content fetched Uses the crawl_html_version function from download_new_papers.py that you already have Process Flow: Stage 1: Quick filtering based on title and abstract only Content Extraction: Fetch HTML content for papers that passed the filter Stage 2: Detailed analysis that includes the full content Updated Filter Prompt: Made it clear in the Stage 1 prompt that this is just preliminary screening Specified that papers scoring 7+ will be analyzed in depth with full content Added clearer instructions for the relevancy scoring Fixed Processing Flow: Always processes all available papers Uses fixed batches of 8 papers for Stage 1 (title & abstract only) Guarantees at least 10 papers will be analyzed in depth Revamp UI using Gradio and removed Sending email Workflow Improvements: Added clear comments explaining the fixed parameters Removed the batch update function which is no longer needed Simplified the code overall
Multiagent multipurpose
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.