NEWVectors or files. Pick a path.Start →

    Retrievers

    Retrievers combine the features your extractors produce into multi-stage search pipelines. Each stage below is one step you can chain: search, filter, rank, enrich, reduce.
    For agentsBuild a multi-stage search with create_retriever on the Mixpeek MCP server (https://mcp.mixpeek.com/mcp) (stages such as feature_search, attribute_filter and rerank), then query it with execute_retriever. Every MCP tool needs an API key; an agent can get one with POST https://api.mixpeek.com/v1/signup/agent.
    Search your own data Retriever docs

    A retriever is the stable multi-stage contract an application binds to by name, so the embedding model, the index and the query plan underneath can all change without breaking a caller. That job is one layer of the semantic layer for unstructured and multimodal data, the architecture that turns raw objects into named features and serves them through contracts an application can bind to.

    34 stages

    • Feature Search

      Filter

      Search and filter documents by vector similarity using feature embeddings

      stage_id feature_searchDocsView stage

    • Attribute Filter

      Filter

      Filter documents by metadata attribute values using boolean logic

      stage_id attribute_filterDocsView stage

    • Llm Filter

      Filter

      Filter documents using LLM-based semantic evaluation

      stage_id llm_filterDocsView stage

    • Agent Search

      Filter

      LLM-driven multi-step retrieval with iterative reasoning and tool orchestration

      stage_id agent_searchDocsView stage

    • Query Expand

      Filter

      Generate query variations with LLM and fuse search results via RRF

      stage_id query_expandDocsView stage

    • Score Threshold

      Filter

      Drop results below an absolute score and return no results when nothing qualifies

      stage_id score_thresholdDocsView stage

    • Sort Attribute

      Sort

      Sort documents by any metadata field value

      stage_id sort_attributeDocsView stage

    • Mmr

      Sort

      Reorder results using Maximal Marginal Relevance for diversity

      stage_id mmrDocsView stage

    • Rerank

      Sort

      Rerank documents using cross-encoder models for accurate relevance

      stage_id rerankDocsView stage

    • Score Normalize

      Sort

      Rescale document scores to a common range for consistent comparison

      stage_id score_normalizeDocsView stage

    • Aggregate

      Reduce

      Compute aggregations (COUNT, SUM, AVG, etc.) on pipeline results

      stage_id aggregateDocsView stage

    How Retriever Pipelines Work

    Combine stages to build sophisticated search and retrieval pipelines. Each stage type serves a specific purpose in the data flow.

    What is a retriever pipeline: a query (text, image, video, or audio) flows through five chained stage groups (Search (feature_search, query_expand, agent_search), Filter (attribute_filter, llm_filter, deduplicate), Rank (rerank, mmr, sort_relevance, score_normalize), Enrich (llm_enrich, taxonomy_enrich, rag_prepare, document_enrich), and Reduce (aggregate, group_by, cluster, sample, limit, summarize)) producing scored, enriched, shaped results from 34 available stages in under 100ms p95. Each stage is JSON: stage_type plus a config with stage_id and parameters. Retrievers are stored, versioned, callable as one endpoint, and exposed to LLM agents as MCP tools.
    The full anatomy: stages chain sequentially (search, filter, rank, enrich, reduce), each processing the output of the one before it. Define the pipeline once in JSON, then call it from any client, or let an agent call it as an MCP tool.

    1. Search

    Retrieve documents from collections using semantic search, keyword search, or hybrid approaches.

    2. Filter

    Remove documents that don't match criteria using attribute filters, score thresholds, or LLM evaluation.

    3. Rank

    Reorder documents by relevance using sorting, cross-encoders, or LLM-based reranking.

    4. Generate

    Create responses from retrieved documents using RAG, summarization, or custom LLM generation.

    Build a retriever from the docs

    The stages described above, with request shapes, and what each one passes to the next.

    RetrieversCreating a named retriever and calling it by name from your app.Multi-stage retrieval deep diveHow stages compose, and what each one passes to the next.Feature search stageThe search stage itself. API reference and worked examples.Rerank stageReordering candidates with a cross-encoder before you return them.

    All retriever stages