Experiment project with LLM RAG using llama3 and langchain
rag/tmp/docs
and load from UI
- Retrieval-Augmented Generation (RAG)
- Enhance the accuracy and reliability of GenAI models with data from external sources
- LLM (ChatGPT, Gemini...) does not know your data
- LLM might not know or give out-of-date answer about knowledege beyond the cut-off point
- LLM does not know about specific knowledge (eg: your company data for customer support, your bespoke software user manual...)
- RAG solves above problems
- //TODO
- Load PDFs from directory
- Q&A with context from loaded PDFs
- Stream text to UI
- Add message history (memory)
- Format chat response
- Upload PDF from UI
- Measure performance & reliability
- Support images, tables in PDF
- https://ollama.com/library/llama3
- https://python.langchain.com/docs/use_cases/question_answering
- https://www.databricks.com/glossary/retrieval-augmented-generation-rag
Logo generated with Dream Studio (https://beta.dreamstudio.ai/)