Skip to main content

​
POST /v1/pipelines/ingest

Run ingestion → chunking → embedding → storage in one request. 
{
  "markdown": "# Guide\n\nRagrails builds modular RAG pipelines.",
  "embedding": {
    "provider": "voyage",
    "model": "voyage-3"
  },
  "storage": {
    "vector_db": "qdrant",
    "collection": "docs",
    "url": "http://localhost:6333"
  }
}
With a document folder: 
{
  "docs": {"folder": "files/docs/"},
  "chunking": {"chunk_size": 1000, "chunk_overlap": 100},
  "embedding": {"provider": "voyage", "model": "voyage-3"},
  "storage": {"vector_db": "qdrant", "collection": "docs", "url": "http://localhost:6333"}
}

​
POST /v1/pipelines/query

Run query embedding → retrieval. 
{
  "query": "What does the guide cover?",
  "embedding": {
    "provider": "voyage",
    "model": "voyage-3"
  },
  "retrieval": {
    "vector_db": "qdrant",
    "collection": "docs",
    "url": "http://localhost:6333",
    "top_k": 5
  }
}
With reranking: 
{
  "query": "What does the guide cover?",
  "embedding": {"provider": "voyage", "model": "voyage-3"},
  "retrieval": {
    "vector_db": "qdrant",
    "collection": "docs",
    "url": "http://localhost:6333",
    "top_k": 20,
    "rerank": {"enabled": true, "provider": "voyage", "top_k": 5}
  }
}