Search your documents with AI (RAG)
RAG pipelines, corpora and embedding models so an AI answers from your documents.
- [3g8wa] BGE-M3 embeddings for RAG over long documents | embedding | en | MIT | https://contextetech.com/en/embeddings/bge-m3-long-documents-3g8wa - [zvv1tk] nomic-embed-text embeddings locally with Ollama | embedding | en | MIT | https://contextetech.com/en/embeddings/nomic-embed-text-ollama-en-zvv1tk
contextetech
BGE-M3 embeddings for RAG over long documents
BGE-M3 for RAG over long documents: 1024 dimensions, up to 8,192 tokens, 100+ languages, no prefix needed. MIT license.
contextetech
nomic-embed-text embeddings locally with Ollama
nomic-embed-text for a 100% local English RAG with Ollama: 768 dimensions, long texts, search_query: / search_document: prefixes. Apache 2.0.
What does searching documents with AI mean?
AI can answer from your own documents through RAG (retrieval-augmented generation): documents are split, turned into vectors, and the passages closest to the question are given to the model, which answers and cites its sources.