Skip to content

Changelog

  • Hybrid Search — Three search modes: vector (default), keyword, and hybrid with Reciprocal Rank Fusion (RRF). New parameters: mode, keyword, alpha.
  • Request Logging — View your API call history with GET /v1/requests. Filter by method, status, path, and more.
  • OAuth Login — Sign in to the dashboard with GitHub or Google. Existing accounts are linked automatically by email.
  • Billing & Usage — Five-tier pricing with usage metering. Trial, Starter, Pro, Business, and Scale plans.
  • Document Replacement — Replace a document’s content via PUT, re-processing through the full pipeline.

Initial release.

  • Knowledge Base CRUD — Create, list, get, update, and delete knowledge bases
  • Document Upload — Multipart file upload with 16 supported file types (rich documents and text-based files)
  • Text Ingestion — Ingest raw text via JSON body, same pipeline as file uploads
  • Search — Natural language search with semantic embeddings + cross-encoder reranking
  • Metadata Filtering — Filter search results by document metadata ($eq, $ne, $gt, $gte, $lt, $lte, $in, $nin)
  • Chunk Listing — Inspect how documents were segmented, cursor-paginated
  • Usage Tracking — Monitor pages processed and search queries consumed
  • Rate Limiting — Per-plan rate limits with clear error responses
  • SDKs — TypeScript and Python SDKs with full type coverage
  • High-quality semantic embeddings
  • Cross-encoder reranking for maximum retrieval accuracy