- News Research Tool using LLM (RAG implementation on unstructured web links)
- This Python program is a news research tool that utilizes the power of the Mistral Large Language Model (LLM) to analyze and answer your questions across various websites.
- Whether you’re a researcher, journalist, or just curious about current events, this tool provides an efficient way to gather relevant information.
- Provide a list of website URLs.
- Ask a question related to the content on any of the provided websites, or about the combined information from all sites.
- The program retrieves relevant information from the websites and uses Mistral to answer your question in a comprehensive way.
- Saves time and effort by eliminating the need to manually search and analyze multiple websites.
- Gains insights from the combined knowledge of multiple news sources.
- Leverages the power of Mistral's advanced language processing capabilities for accurate and insightful answers.
Final Version: News_Research_Tool_Advanced_V3.ipynb
Model Used: https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF
- python
- pandas
- numpy
- unstructured
- ctransformers
- langchain
- langchain_community
- chromadb
- sentence-transformers
- bitsandbytes
- torch
- transformers
In this project, the content has to be provided by the user. A better but a different version of this project can be found here:
https://github.com/rajdas2001/News-Analysis-Tool-using-LLM-and-News-API/tree/main
Given a topic, the program can fetch content on its own using News API (https://newsapi.org/).