RAG Pipeline Builder

advanced

Retrieval-augmented generation pipeline combining vector search with document ingestion.

Architecture

Qdrant MCP

Vector database for storing and querying document embeddings

84/100

uvx mcp-server-qdrant

LlamaCloud MCP

Document ingestion, parsing, and chunking pipeline

78/100

uvx llamacloud-mcp@latest

Pinecone MCP

Managed vector index for production-scale retrieval

78/100

npx -y @pinecone-database/mcp

Expected Output

RAG Pipeline Status Documents ingested: 156 Chunks created: 1,240 Vectors stored: 1,240 Query: "How do I configure auth?" Retrieved: 5 relevant chunks (similarity > 0.82) -> Answer generated with source citations

Related Recipes

Data Warehouse Query Assistant

INTERMEDIATE

Explore multiple databases, draft safe SQL, and export reviewed analysis artifacts.

dataanalysis

4 components

Data Exploration Toolkit

BEGINNER

Multi-database data exploration with PostgreSQL, MongoDB, and Redis for caching.

data

3 components

Knowledge Management System

BEGINNER

Searchable knowledge base combining Notion content with Elasticsearch-powered search.

dataproductivity

2 components