# /rag-pipeline - RAG Pipeline & Document Ingestion System

> Document chunking, hybrid vector search, re-ranking, and context synthesis.

Canonical: https://www.agentickit.co/commands/rag-pipeline
Last updated: 2026-11-18

Builds full Retrieval-Augmented Generation flows: PDF/text chunking, embedding generation, vector storage, hybrid search, and citation injection.

**Usage:** `Use when building 'chat-with-your-docs' features or enterprise knowledge retrieval.`

## Pipeline
1. Implement document parser and overlapping text chunking algorithm
2. Generate vector embeddings and store in partitioned database tables
3. Build hybrid retrieval engine combining vector similarity and keyword search
4. Synthesize answers with context injection and verifiable source citations

## Output files
- `src/lib/rag/...`
- `src/app/api/rag/route.ts`

**Claude Code frontmatter:** `argument-hint: [knowledge source and retrieval need]` · `model: inherit`

## Related
- [ai-engineer](https://www.agentickit.co/agents/ai-engineer)
- [data-engineer](https://www.agentickit.co/agents/data-engineer)
- [rag-patterns](https://www.agentickit.co/skills/rag-patterns)
- [vector-database](https://www.agentickit.co/skills/vector-database)
- [llm-integration](https://www.agentickit.co/skills/llm-integration)
