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

    LLM-Enriched Search Results

    Semantic search with LLM-generated summaries and formatted output. Perfect for RAG applications.

    3 stages
    Read Docs
    Integrate Now

    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": 10
}
    2
    llm_summarization
    apply
    llm_enrich
    View parameters
    {
  "provider": "google",
  "model_name": "gemini-2.5-flash-lite",
  "prompt": "Summarize the following document in 2-3 sentences:\n\n{{DOC.content}}",
  "output_field": "metadata.summary",
  "batch_size": 5,
  "temperature": 0.2
}
    3
    format_output
    apply
    json_transform
    View parameters
    {
  "template": "{\"id\": \"{{DOC.document_id}}\", \"content\": \"{{DOC.content}}\", \"summary\": \"{{DOC.metadata.summary}}\", \"score\": {{DOC.score}}}",
  "fail_on_error": false
}

    Input Schema

    query
    text
    required

    Search query text

    e.g. explain quantum computing

    Use Cases

    • RAG applications
    • Research assistance
    • Content summarization
    • AI-powered search

    Requirements

    • Collection must have text embeddings indexed
    • LLM inference service must be available

    Tags

    llm
    enrichment
    rag
    summarization

    Ready to use this template?

    Clone it into your namespace and start querying in minutes.