Skip to main content
Glama

Multimodal RAG Service

Production-minded retrieval for text, tables, images, and PDFs. Sentence-transformer text vectors and CLIP image vectors are stored in separate FAISS indexes; BM25 sparse results are combined using weighted reciprocal-rank fusion.

Run locally

python -m venv .venv
.venv\\Scripts\\Activate.ps1
pip install -e ".[dev]"
Copy-Item .env.example .env
uvicorn app.main:app --reload

The API documentation is available at http://localhost:8000/docs. Models download automatically at their first embedding request.

Related MCP server: mcp-rag-agent

API

curl -F "files=@report.pdf" http://localhost:8000/v1/documents
curl -X POST http://localhost:8000/v1/search -H "Content-Type: application/json" -d "{\"query\":\"revenue trend\",\"top_k\":5}"
curl -N -X POST http://localhost:8000/v1/chat/stream -H "Content-Type: application/json" -d "{\"query\":\"Summarize the report\"}"

MCP integration

Run the REST API, then start the stdio MCP bridge:

rag-mcp

Set RAG_API_URL to point at a non-default API address. The bridge provides search_knowledge_base, ask_knowledge_base, list_documents, and service_health tools to MCP clients.

Evaluation

Supply JSONL rows containing query, relevant_document_ids, and optionally reference_answer:

python -m app.evaluation --dataset eval/golden.jsonl

Reported metrics include Recall@K, Precision@K, MRR, p50/p95 retrieval latency, ROUGE-L, and BLEU-1.

Container deployment

docker compose up --build

The compose configuration mounts a persistent named volume at /service/data.

Available Tools

4 tools
ask_knowledge_baseB

Answer a question from the knowledge base and return its source citations.

Inputs: question (required), top_k.

list_documentsA

List all documents currently indexed by the RAG service.

Inputs: no named parameters. Returns: result

search_knowledge_baseA

Search text, tables, and images in the indexed knowledge base, returning grounded chunks.

Inputs: query (required), top_k, modality.

service_healthA

Check whether the linked RAG API is available and return index counts.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.8/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: searching returns chunks, asking returns an answer with citations, listing documents provides an index, and health checks API availability. No overlap or ambiguity.

    Naming Consistency4/5

    Most tools follow a verb_noun pattern (search_knowledge_base, ask_knowledge_base, list_documents), but service_health breaks the pattern by using a noun phrase. The naming is still clear and consistent in snake_case.

    Tool Count5/5

    With only 4 tools, the server is tightly scoped for a RAG query service. Each tool is essential and there is no bloat or redundancy.

    Completeness4/5

    The core query workflow (search, ask, list) is covered, and health monitoring is included. However, there is no tool to add or remove documents, which may be a gap if the server is expected to manage the index, but it might be intentionally read-only.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Exposes an existing RAG API as MCP tools, enabling health checks and document-based question answering with source evidence.
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables MCP clients to query a modular RAG knowledge hub with hybrid dense/sparse retrieval, reranking, multimodal image support, and traceable observability, all through natural language tools.
      MIT