Interactive Document Understanding and Querying using LLMs

• What its purpose is:
  • Implemented a system that performs Retrieval Augmented Generation (RAG) with LLM to create answers based on the user’s data.
  • Enabled users to effectively query their own data repositories, retrieving accurate and context-based information.
  • Modeled the user data and query in the same vector space, performed semantic search to retrieve potential answers for that query.
  • Generated contextually relevant responses using the LLM model, delivered information and precise insights tailored to user queries.
• Technologies Used:
• Python, Open AI API, Langchain
• GitHub: Project Link