Pinecone Release Notes

Released Go SDK v7.0.0

Released v7.0.0 of the Pinecone Go SDK. This version uses the latest stable API version, 2026-07, and adds support for schema-based document indexes and the Documents API, which brings full-text search to the Go SDK. The v6 release line continues to target 2026-04.

<Warning> Before upgrading to `v7.0.0`, update all relevant code to account for the following [breaking changes](/reference/api/versioning#breaking-changes). See the [v7 migration guide](https://github.com/pinecone-io/go-pinecone/blob/main/guides/migration/v7.md) for full details.

* The module path is now `github.com/pinecone-io/go-pinecone/v7`.
* Pod-based index creation is removed (`CreatePodIndex`, `CreatePodIndexRequest`). Existing pod-based indexes keep working.
* Enum constants are prefixed with their type name. For example, `Aws` is now `CloudAWS`, and `Cosine` is now `IndexMetricCosine`.
* `ListImports` takes a `*ListImportsRequest`, and `QueryByVectorIdRequest.SparseValues` is removed.
* `SourceCollection` and `Schema` on the legacy create requests now return an error. `ConfigureIndexParams.Embed` is replaced by `ConfigureIndexParams.Schema`.
* `Backup` field types changed, and some invalid requests now fail client-side. …

Gemini 2.5 Pro and o4-mini deprecations for Assistant

Google has deprecated the Gemini 2.5 Pro model, and OpenAI has deprecated o4-mini. Pinecone Assistant automatically routes all chat requests that specify gemini-2.5-pro to Gemini 3.5 Flash, and all chat requests that specify o4-mini to GPT-5, at the same price. No code changes are required.

To update your code to explicitly use the newer models, set model: "gemini-3.5-flash" or model: "gpt-5" in your chat requests. For more information, see Choose a model.

Released Node.js SDK v9.0.0

Released v9.0.0 of the Pinecone Node.js SDK. This version uses the latest stable API version, 2026-07, and adds support for schema-based document indexes and the Documents API, which brings full-text search to the Node.js SDK. It also adds pc.backupSchedules for recurring backups. The v8 release line continues to target 2026-04.

<Warning> Before upgrading to `v9.0.0`, update all relevant code to account for the following [breaking changes](/reference/api/versioning#breaking-changes). See the [v9 migration guide](https://github.com/pinecone-io/pinecone-ts-client/blob/main/guides/upgrading/v9-migration.md) for full details.

* Node.js 22 or later is required.
* `pc.preview` and the `Preview*` exports are removed. Document operations move to `index.documents`, where `index` comes from `pc.index({ name, namespace })` or `pc.index(name).namespace(namespace)`. Control operations move to resource clients such as `pc.indexes`.
* Pod-based index creation, legacy metadata-indexing schemas, and the `sourceCollection` and `sourceBackupId` creation options are rejected. Existing pod-based indexes keep working. To restore from a backup, use `pc.backups.createIndex(backupId, options)`. …

Released Python SDK v10.0.0

Released v10.0.0 of the Pinecone Python SDK. This version uses the latest stable API version, 2026-07, and moves schema-based document indexes, SchemaBuilder, and the Documents API out of pinecone.preview onto the main client, bringing full-text search to the Python SDK. It supports Python 3.10 to 3.14.

<Warning> Before upgrading to `v10.0.0`, update all relevant code to account for the following [breaking changes](/reference/api/versioning#breaking-changes). See [Migrating to V10](https://sdk.pinecone.io/python/migration/v10-migration.html) for full details.

* `pinecone.preview` is removed. Use `pc.indexes` and `pc.index(...)` on the main client, and import `SchemaBuilder` from `pinecone`. `AsyncPinecone.index()` is now a coroutine, so it needs an `await`.
* `IndexModel` is built from `schema` and `deployment`, and `created_at` is removed. The `spec`, `embed`, `dimension`, `metric`, and `vector_type` properties are deprecated views that raise when the schema has no single field to resolve them to.
* Bulk upserts default to a `max_concurrency` of 8, up from 4, and can stop early against an unavailable backend. Check `response.errors` for partial failures. …

General availability: Full-text search and the Documents API

Full-text search is now generally available on API version 2026-07, built on the new Documents API.

Create schema-based document indexes that combine full-text (BM25), dense-vector, and sparse-vector ranking fields in a single index. Query them with BM25 token matching, Lucene query syntax, or vector similarity, narrowed by metadata and text-match filters. You can also fetch, update, and delete documents by metadata filter, not just by ID.

This is a change at the REST layer: on 2026-07, POST /indexes is schema-only, so the top-level dimension, metric, vector_type, and spec are replaced by a schema. Existing indexes and SDK create_index calls are unaffected. See Adopt the Documents API to check whether your code is affected and how to move.

Egress metering and monthly egress allowances

Pinecone now meters egress, the data returned to you on reads. Each plan includes a monthly egress allowance: 1 GB on Starter, 10 GB on Builder, and 100 GB on Standard and Enterprise.

Egress is metered on reads that return record data, such as query, fetch, list, and search. Writes, index statistics, and index management requests aren't metered. Egress applies to indexes that use dedicated read nodes as well as on-demand indexes.

On Standard and Enterprise, egress beyond the allowance is billed at the rate on the pricing page, and reads keep serving. On Starter and Builder, reads that return record data are blocked once the allowance is reached, and the allowance resets at the start of the next billing period.

Fuzzy matching and substring search for full-text search

Full-text search now supports two new ways to match text:

• Fuzzy matching (typo tolerance) — In a query_string search, append ~ to a term to match indexed terms within a small edit distance: body:(compxter~1) matches computer. Use term~ for an automatic distance based on term length, or term~N for a fixed distance (N is 0–2). Fuzzy works on existing indexes with no reindex. See Fuzzy matching.
• Substring search with n-grams — Configure a text field for character n-gram tokenization to match on partial words, prefixes, and autocomplete-style queries. Add an ngram object (min_gram, max_gram, prefix_only) to a field's full_text_search config at index creation, then query it with ordinary text or query_string searches. See Substring search with n-grams.

Full-text search remains in public preview under API version 2026-01.alpha.