Retrieve

Pull the right outside knowledge into context, just in time: search, RAG, embeddings, rerankers, docs and code fetchers.

30 listed entries

Screenshot of the BGE-M3 website

BGE-M3

Multilingual embedding model that does dense, sparse and multi-vector retrieval in one model (BAAI).

tool
All 4 numbersShow less

Website captured Oct 19

Contextual retrieval

Prepend chunk-specific context before embedding and BM25 indexing. Anthropic measured 49% fewer failed retrievals, and 67% fewer with reranking.

process
    Screenshot of the Exa website

    Exa

    Neural web search API for agents: finds pages by meaning and returns their contents.

    tool
    All 4 numbersShow less

    Website captured Oct 19

    Just-in-time retrieval

    Keep lightweight references (file paths, stored queries, links) in context and load the data with tools only when it's needed.

    process
      Screenshot of the Tavily website

      Tavily

      Search API built for agents: returns ranked, extracted web results ready for the context window.

      tool
      All 4 numbersShow less

      Website captured Oct 19

      How they connect