Mehmet Burak Sayıcı

RAG boilerplate with semantic/propositional chunking, hybrid search (BM25 + dense), LLM reranking, query enhancement agents, CrewAI orchestration, Qdrant vector search, Redis/Mongo sessioning, Celery ingestion pipeline, Gradio UI, and an evaluation suite (Hit-Rate, MRR, hybrid configs).

Boilerplate RAG and LLM in financial analysis. MongoDB, MongoDB VectorDB, Chroma, FastAPI, Langchain, and React submodule for UI.

smallevals — CPU-fast, GPU-blazing fast offline retrieval evaluation for RAG systems with tiny QA models.

VoiceCloningTalkingHead, set of algorithms (or pipelines) that clones voice/talks head without training.

No project description available.

InformationRetrievalTutorial