LLM-Powered Retrieval & Search Systems
6 repos
Systems and frameworks for building retrieval-augmented generation (RAG) applications that combine large language models with vector databases and semantic search. This cluster covers the full stack from vector indexing and storage through search backends to complete chat applications, with implementations spanning Python for ML workflows, Rust for performance-critical components, and Jupyter notebooks for prototyping and analysis.
Python · 4
Jupyter Notebook · 1
TypeScript · 1
rag ·85,139
llm ·84,278
chatgpt ·70,726
retrieval-augmented-generation ·53,196
ollama ·51,519
langchain ·51,519
faiss ·51,519
ai ·44,987
python ·44,833
vector-search ·44,833
