A minimal Retrieval-Augmented Generation (RAG) pipeline built with LangChain, Qdrant, and HuggingFace embeddings. Ingest PDF documents into a vector store and query them using an LLM with grounded, context-aware responses.
python knowledge-base data-retrieval data-indexing rag ingestion-pipeline llm ai-workflows langchain query-embedding qdrant-vector-database prompt-template ollama-chat retrieved-augmented-generation rag-pipeline huggingface-embeddings document-loader context-engineering uv-package-manager chatmodel-interface
-
Updated
Sep 2, 2026 - Python