fleet-doc-rag

Integrate a domain-aware document-RAG service with FastAPI, Qdrant, and Ollama.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/marvelousempire/ai-skills-library --skill fleet-doc-rag
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: fleet-doc-rag
Source: https://github.com/marvelousempire/ai-skills-library/tree/main/skills/infra/fleet-doc-rag
Command: npx skills add https://github.com/marvelousempire/ai-skills-library --skill fleet-doc-rag

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires fastapi, qdrant, ollama, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill provides a domain-aware document-RAG service that integrates with chat apps, allowing for efficient retrieval and ranking of documents without the need to integrate document ingestion into the chat app itself.

Core Features & Use Cases

  • Hybrid Retrieval: Combines document brain with chat brain for comprehensive information retrieval.
  • Domain-Aware Embeddings: Uses local Ollama embeddings and Qdrant for per-domain collections with metadata.
  • Idempotent Commands: Ensures ingestion commands are idempotent, avoiding duplicates.
  • Graceful Degradation: Handles failures gracefully, ensuring the app degrades to local-only if needed.
  • Use Case: For a chat app looking to add a document brain to its existing RAG capabilities, this skill allows for seamless integration and improved information retrieval.

Quick Start

Use the fleet-doc-rag skill to search for documents related to "financial" domain using the query "financing strategy".

Frequently Asked Questions about fleet-doc-rag

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add a document brain to my chat app for domain-specific retrieval?

To add a document brain to your chat app for domain-specific retrieval, use a hybrid RAG service that ingests documents and creates domain-aware embeddings, keeping retrieval logic separate from the chat application itself.

How does hybrid retrieval combine a document brain with a chat brain?

Hybrid retrieval combines a document brain with a chat brain by ingesting domain-specific documents into local collections and ranking the results alongside the chat app's existing information retrieval capabilities.

Do I need FastAPI, Qdrant, and Ollama to deploy a domain-aware document RAG service?

Yes, you need FastAPI, Qdrant, and Ollama to deploy and operate this domain-aware document RAG service, as they handle the API service, vector collections, and local embeddings respectively.

How to ingest domain-specific documents without creating duplicate entries?

To ingest domain-specific documents without creating duplicate entries, use idempotent ingestion commands that ensure repeated operations do not duplicate data within the Qdrant vector collections.

What happens when the document RAG service fails during chat app retrieval?

When the document RAG service fails during chat app retrieval, the application handles failures gracefully with graceful degradation, ensuring the app degrades to local-only retrieval if needed.