BriefsToolAvailable now
Pinecone adds integrated embedding to the Documents API
Pinecone updates its Documents API to run embedding models natively, combining semantic search and full-text search in a single request.
Summary
Pinecone now runs embedding models directly inside its platform on serverless indexes, eliminating the need for external embedding providers and separate pipelines. Developers can pass raw text for both writes and queries while combining semantic search, sparse keyword matching, and full-text search in one call. Three models are available at launch, with support for additional providers planned.
What changed
- Pinecone launched integrated embedding on the Documents API for serverless indexes.
- Three models are available at launch: llama-text-embed-v2, multilingual-e5-large, and pinecone-sparse-english-v0.
- Applications can send plain text queries using embed, sparse_embed, and text scoring methods on the same field.
- Developers can set store_text to false to discard raw text after vectorization while keeping vectors.
Availability
Available now“Integrated embedding on the Documents API is available today on serverless indexes.”
Founder takeaway
If you use Pinecone for search, consider moving your embedding step server-side to remove separate provider pipelines and simplify your application code.
Source
Researched and drafted with AI from the official sources above, then checked automatically before publishing. Spotted a mistake? Tell us.
Related
More briefs
Vercel adds sandbox plugin support for running Paseo AI agents
Paseo now supports running AI agents in the cloud using the Vercel Sandbox plugin.
Vercel1 min read
Vercel introduces Virtual Models on AI Gateway for AI apps
Vercel released Virtual Models on AI Gateway to let developers manage model strings and fallbacks centrally.
Vercel1 min read
Vercel CLI allows AI agents to enable web analytics and observability
AI agents can now enable Web Analytics and Observability Plus for projects without requiring an interactive terminal.
Vercel1 min read
One email, every Monday
Briefs are published here through the day. Monday Heist is the email: one useful AI workflow, the files to use it, and the catch. The first issue is being prepared; subscribers get it first. Free, and you can leave in one click.
One email. Every Monday.