Skip to content

x-46/rag-pipeline

Repository files navigation

rag-pipeline

A RAG pipeline that ingests PDFs, Markdown files, and source code into a hybrid vector store and answers questions via multi-query retrieval, cross-encoder reranking, and parent-child context expansion.

Built with Qdrant, MongoDB, LangChain, Unstructured / Docling, FastEmbed BM25, and a HuggingFace cross-encoder. Models (LLM + embeddings) connect via any OpenAI-compatible API endpoint.

Docs

About

No description, website, or topics provided.

Resources

License

Stars

2 stars

Watchers

0 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors