Artificial intelligence news.
Straight from the original announcements.

Pinecone Adds Google’s Gemini Embedding 2 to Integrated Embedding

November 12, 2026By the AI News Bites Editorial TeamSource: Pinecone
Pinecone Adds Google’s Gemini Embedding 2 to Integrated Embedding
Image: Pinecone

Pinecone has added Google’s Gemini Embedding 2 to its integrated embedding feature for the Documents API. Teams can now send plain text to Pinecone for semantic search without managing a separate embedding provider, Google Cloud account or API key.

Key points
  • Pinecone’s Documents API now supports Google’s Gemini Embedding 2.
  • Teams can send plain text without managing a separate embedding pipeline.
  • The integration supports semantic and full-text search on the same text field.
  • Builder customers get 20M included tokens per month through December 31, 2026.
  • The feature currently supports serverless Documents API indexes and text fields.

Embedding and search in one workflow

Gemini Embedding 2 is Google’s newest Gemini embedding model, according to Pinecone. Developers can select it for a text field when creating a Documents API index, then send documents and queries as plain text.

Pinecone embeds every write and every query for that field with the selected model. It writes each document’s text and embedding together, which Pinecone says keeps full-text and semantic search aligned to the same version of a document. A query can also be embedded and searched in one call.

Pinecone serves Gemini Embedding 2 through Google Vertex AI and retries failed calls. The company says teams do not need to build their own retry logic, manage a Google API key or receive a separate bill for embedding. Tokens appear on the Pinecone invoice at Google’s list price.

Model settings and supported search tasks

The model can be configured on a text field with a selected dimension. Pinecone’s example uses the model name gemini-embedding-2 at 1,536 dimensions, while also enabling full-text search for the same field. If the dimension is omitted, the field uses the model’s full size. Pinecone says any size supported by the model can be used, including dimensions that existing indexes already use.

Gemini Embedding 2 expects a short instruction indicating whether each input is a document or a query. Pinecone adds the appropriate instruction automatically for writes and queries, so users do not need to create model-specific prompts.

By default, fields use the model for general search. Developers can set a task type for classification, clustering or sentence similarity. Individual searches can use question answering, fact verification or code retrieval query. Gemini Embedding 2 supports text in more than 100 languages.

Availability, plan limits and next steps

The integration works on serverless Documents API indexes. It is not supported on BYOC, pod-based or Records API indexes. The Pinecone console and Python SDK 10.3.0 support Gemini Embedding 2, while support for the Node.js and Go SDKs is coming soon.

Gemini Embedding 2 requires a Builder plan or above. The Builder plan includes 10M tokens per month for the model, and Pinecone is doubling that allowance to 20M a month through December 31, 2026.

The integration currently works on text fields, not multimodal fields. Although Gemini Embedding 2 can also embed images, video and audio, Pinecone says multimodal support is planned for a later release. Existing vector indexes can be converted to Documents API indexes without re-embedding, but adding integrated embedding to a converted index is also coming soon. For now, Pinecone directs users to new Documents API indexes when using Gemini Embedding 2.

Related news

Google brings Gemini 4 Hydrogen to Search globallyTop story
BusinessNovember 12, 2026, 19:00

Google brings Gemini 4 Hydrogen to Search globally

Google is bringing Gemini 4 Hydrogen to Search globally, adding improved handling of complex questions, simultaneous queries, structured responses and more visual…

Pinecone adds OpenAI’s text-embedding-3 models to integrated embedding
Products and toolsNovember 10, 2026

Pinecone adds OpenAI’s text-embedding-3 models to integrated embedding

Pinecone now supports OpenAI’s text-embedding-3-small and text-embedding-3-large in its integrated embedding service, allowing teams to use the models for semantic…

Pinecone adds integrated embedding to its Documents API, so users send only text
Products and toolsOctober 22, 2026

Pinecone adds integrated embedding to its Documents API, so users send only text

Pinecone has added integrated embedding to its Documents API, so developers can send raw text and let the service run the embedding pipeline on every write and every…