Documents to RAG - Ragrails

1. Install and set up

pip install "ragrails[voyage,qdrant]"
docker run -p 6333:6333 qdrant/qdrant

2. Ingest a folder

from ragrails import RagRails

rag = RagRails()

result = rag.ingest(
    docs={"folder": "files/docs/"},
    embedding={"provider": "voyage", "model": "voyage-3"},
    storage={"vector_db": "qdrant", "collection": "docs", "url": "http://localhost:6333"},
)

print(f"Stored {result.stored} chunks from {result.sources} documents")

Works for PDFs, DOCX, spreadsheets, HTML, Markdown, and other supported formats.

3. Query

result = rag.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},
)

API to RAGBuild a RAG collection from a REST API, end to end.