Master RAG Pipelines: Advanced AI Agents for Document Retrieval

Master RAG Pipelines: Advanced AI Agents for Document Retrieval

This skill assists developers in building and optimizing retrieval-augmented generation (RAG) pipelines specifically tailored for document retrieval scenarios. It focuses on structuring the data retrieval process efficiently and measuring retrieval performance before engaging in prompt tuning.

What this skill does:

• Ingests, normalizes, chunks, embeds, stores, and retrieves documents, providing answers with citations.
• Utilizes a hybrid approach combining vector and full-text search with rank fusion (RRF).
• Facilitates pinned embeddings within a pgvector environment for efficient data handling.
• Ensures tenant isolation within query processes to maintain data integrity and security.
• Includes an "I don't know" path to handle uncertain results appropriately.
• Evaluates retrieval methods using metrics such as recall@k and mean reciprocal rank (MRR) before prompt tuning.
• Maintains a default storage setting (`ai.rag_store: pgvector`) for streamlined configuration.

Who it is for:

This skill is designed for developers and AI teams utilizing AI coding agents such as Claude Code, Cursor, and Codex. It is particularly beneficial for those involved in creating sophisticated document retrieval systems and enhancing the reliability of AI-generated answers.

Use cases:

• Streamlining the development of RAG pipelines for internal document retrieval systems.
• Enhancing the accuracy of AI-driven customer support by providing precise document citations.
• Optimizing query isolation for multi-tenant systems to ensure secure and reliable service.

Technical details:

• Integration with pgvector for managing pinned and vector embeddings.
• Combines vector-based and full-text search methodologies using rank fusion (RRF).
• Evaluates document retrieval using standard metrics like recall@k and MRR.
• Builds upon the existing infrastructure with seamless integration for AI agent capabilities across platforms.
• Reporting capabilities to audit and refine the current state of document retrieval processes.

Source & Licence

This package is built on open-source work published by VelimirMueller (VelimirMueller/lab-claude-skills) and distributed under MIT. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted, provided the original copyright and licence notice are retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.