~/ / Embeddings and search (RAG)
Tools to build retrieval-augmented generation (RAG) step by step. Split documents into chunks, compare embeddings, store and search them in PostgreSQL with pgvector, build a prompt that answers only from the sources, and check that the citations in the answer match them.
Keep Ollama embeddings in PostgreSQL with pgvector, search them with HNSW or IVFFlat, and pass the results to /api/chat so that the answer cites its sources.
Published: Tools you can use: pgvector SQL Builder, Embeddings to pgvector INSERT, RAG Prompt Builder, RAG Citation Checker
Make embeddings with Ollama's /api/embed: the models and their sizes, truncate and dimensions, unit-length vectors and cosine similarity, from the official docs.
Published: Tools you can use: RAG Text Chunker, Embedding Similarity Calculator