Vector-to-document index conversion is now available
Summary
- Pinecone has introduced vector-to-document index conversion, enabling teams to add full-text search to legacy vector indexes without re-importing records.
- The conversion job builds a new document index while the legacy index continues serving traffic, preserving vectors, record IDs, namespaces, and metadata.
- In internal tests, converting 100 million records took under 20 minutes.
- The feature is available on Standard and Enterprise serverless plans and is billed at a bulk import rate of $0.25 per GB.
Why it matters
This feature eliminates the operational friction and downtime previously required to migrate massive vector datasets to support full-text search, streamlining hybrid search architectures for large-scale applications.