Retrieval-Augmented Generation(RAG) framework to generate answers from local knowledge base using Open source LLM (zephyr-7b-beta/ Mistral-7B-Instruct-v0.2)

Blog Post here.

Naive RAG

Vector Store: FAISS
Local Knowledge Base: Federal Open Market Committee (FOMC) meeting documents for the years 2020-2023
LLM : HuggingFaceH4/zephyr-7b-beta & Mistral-7B-Instruct-v0.2
Local documents in pdf

NoteBooks:
- 1a: Creating a Vector Store database (FAISS) from pdf documents (local knowledge base)
- 1b: RAG implementation using transformers pipeline
- 1c: RAG implementetion using langchain llm chain with ReRanker
- 1d : Conversational RAG implementation

2a : Graph RAG implemention using Neo4j Graph and Open source LLM(Mistral-7B-Instruct-v0.2)

Colab Notebooks.

Name		Name	Last commit message	Last commit date
Latest commit History 46 Commits
0_LLM_with_Langchain.ipynb		0_LLM_with_Langchain.ipynb
1a_RAG_QA_pdf.ipynb		1a_RAG_QA_pdf.ipynb
1b_RAG_QA_pdf_full.ipynb		1b_RAG_QA_pdf_full.ipynb
1c_RAG_QA_pdf_full_with_langchain.ipynb		1c_RAG_QA_pdf_full_with_langchain.ipynb
1d_Conversational_RAG_with_pdf.ipynb		1d_Conversational_RAG_with_pdf.ipynb
2a_GraphRAG_Neo4j.ipynb		2a_GraphRAG_Neo4j.ipynb
README.md		README.md