Documentation

Everything you need to call the RAGRef API.

Authentication

All requests use a bearer token in the Authorization header. Keys look like rr_live_... and are scoped per project. Treat them like passwords.

Authorization: Bearer rr_live_your_key_here

Endpoints

POST/v1/corpora

Create a new document corpus. Body: name, chunking strategy, optional metadata.

POST/v1/corpora/{id}/ingest

Ingest and chunk documents. Accepts files, URLs, or inline text.

GET/v1/corpora/{id}/stats

Corpus metadata and index health: token counts, chunk counts, replication status.

GET/v1/retrieve

Hybrid sparse-dense retrieval with RRF fusion. Optional rerank pass.

POST/v1/rerank

Cross-encoder reranking of retrieved candidates.

GET/v1/embed

Embeddings, OpenAI-compatible request shape.

Quickstart

# pip install ragref
from ragref import RAGRefClient

client = RAGRefClient(api_key="rr_live_...")

corpus = client.corpora.create(name="support-docs", chunking="semantic")
corpus.ingest(path="./docs/", recursive=True)

results = client.retrieve(
    corpus_id=corpus.id,
    query="How do I reset my 2FA device?",
    top_k=8, rerank=True,
)

SDKs and integrations

Official clients: Python (pip install ragref) and TypeScript (npm install @ragref/sdk). Community integrations: LangChain retriever, LlamaIndex index, Haystack node.