mallahyari/drqa
How to create Question-Answering system combining Langchain and OpenAI
Implements a retrieval-augmented generation (RAG) pipeline with PDF document ingestion, chunking, and semantic search using SentenceTransformers embeddings stored in Qdrant vector database, minimizing API costs by reserving LLM calls only for final response generation. The backend uses FastAPI to orchestrate the data processing pipeline and LangChain integrations, while the React/TypeScript frontend provides the user interface. Supports pluggable vector databases (Pinecone, Weaviate, Elasticsearch) and embedding models beyond OpenAI's offerings.
172 stars. No commits in the last 6 months.
Stars
172
Forks
25
Language
TypeScript
License
—
Category
Last pushed
Jun 08, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/mallahyari/drqa"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
biocypher/biochatter
Backend library for conversational AI in biomedicine
7-docs/7-docs
Use local files or public GitHub repository as a source and ask questions through ChatGPT about it
pgalko/BambooAI
A Python library powered by Language Models (LLMs) for conversational data discovery and analysis.
redis-developer/ArXivChatGuru
Use ArXiv ChatGuru to talk to research papers. This app uses LangChain, OpenAI, Streamlit, and...
redis-developer/LLM-Document-Chat
Using LlamaIndex, Redis, and OpenAI to chat with PDF documents. Supplementary material for blog...