4 articles with this tag
Use LangChain with ChromaDB for persistent local embeddings — setup, metadata filtering, similarity search, and collection management with full Python code.
Learn 10 LangChain document compressors that slash context length, cut LLM costs, and keep RAG pipelines fast and accurate in production.
Master LangChain document transformers to preprocess documents for RAG — splitters, filters, embeddings, and redundancy removal in Python.
Set up LanceDB as a serverless, open-source vector database with LangChain. Covers local and cloud modes, IVF_PQ indexing, ANN search, and a full RAG example.
Join AiTechWorlds on Telegram and get daily AI tips, prompt engineering templates, coding resources, and exclusive content — 100% free!
No spam. Leave anytime.