NEWVectors or files. Pick a path.Start →
    Enriched Search

    RAG-Prepared Search

    Optimized pipeline to prepare search results for LLM context windows. Includes reranking and context formatting.

    No credit card to start · Build from $25/mo

    Pipeline Stages

    1
    semantic_search
    filter
    feature_search
    View parameters
    {
      "searches": [
        {
          "feature_uri": "mixpeek://text_extractor@v1/multilingual_e5_large_instruct_v1",
          "query": {
            "input_mode": "text",
            "value": "{{INPUT.query}}"
          },
          "top_k": 100
        }
      ],
      "final_top_k": 30
    }
    2
    rerank
    sort
    rerank
    View parameters
    {
      "inference_name": "baai_bge_reranker_v2_m3",
      "query": "{{INPUT.query}}",
      "document_field": "content",
      "top_k": 10
    }
    3
    rag_prepare
    apply
    rag_prepare
    View parameters
    {
      "max_tokens": 4000,
      "overlap_tokens": 100,
      "include_metadata": true,
      "format": "markdown"
    }

    Input Schema

    query
    text
    required

    Query for RAG context

    Use Cases

    • LLM context preparation
    • Chatbot backends
    • AI assistant integration
    • Context window optimization

    Requirements

    • Collection must have text embeddings indexed
    • Reranker service must be available

    Tags

    rag
    context
    llm
    preparation

    Ready to use this template?

    Clone it into your namespace and start querying in minutes.