rag

Process Rag

Process crawled content for RAG: chunk text and generate embeddings.

This endpoint:

  1. Retrieves crawled content from the contents table
  2. Chunks the text based on configuration
  3. Generates embeddings for each chunk
  4. Saves chunks to content_chunks table
  5. Returns quality metrics
post/api/crawl/{crawl_id}/process-rag

Request

  • Base URL: https://voyant.io (the document declares no server; this is the origin it was published from)
  • URL: https://voyant.io/api/crawl/{crawl_id}/process-rag
  • Auth: HTTP bearer

Path parameters

crawl_idstring required

Request body

chunk_sizeinteger

Characters per chunk

chunk_overlapinteger

Overlap between chunks

min_chunk_sizeinteger

Minimum chunk size

embedding_modelstring

OpenAI embedding model

Response

Successful Response

task_idstring required
statusstring required
messagestring required

Changes

No recorded changes to this operation across all 1 revision of this API.