> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pinecone.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Pinecone 2023 changelog

> Every change to Pinecone in 2023, including new features, API updates, deprecations, and pricing and plan changes.

All Pinecone products share this changelog. Use the filters to narrow the list.

<Update label="2023-12" tags={["Database"]}>
  ### Starter plan supports up to 100 namespaces

  The free Starter plan now supports up to 100 namespaces. [Namespaces](/guides/index-data/indexing-overview#namespaces) let you partition vectors within an index to speed up queries or comply with [multitenancy](/guides/index-data/implement-multitenancy) requirements.
</Update>

<Update label="2023-11" tags={["Database"]}>
  ### Pinecone AWS Reference Architecture

  The new [Pinecone AWS Reference Architecture](https://github.com/pinecone-io/aws-reference-architecture-pulumi/tree/main) is an open-source, distributed system that performs vector-database-enabled semantic search over Postgres records. You can use it as a learning resource or as a starting point for high-scale use cases.
</Update>

<Update label="2023-11" tags={["SDK"]}>
  ### Canopy RAG framework

  [Canopy](https://github.com/pinecone-io/canopy/blob/main/README.md) is a new open-source Retrieval Augmented Generation (RAG) framework and context engine built on top of Pinecone. It enables you to start chatting with your documents or text data with a few simple commands.

  The latest version of the Canopy SDK (v0.2.0) adds support for OpenAI SDK v1.2.3. See the [release notes](https://github.com/pinecone-io/canopy/releases/tag/V0.2.0) in GitHub for more details.
</Update>

<Update label="2023-11" tags={["Billing"]}>
  ### VAT and GST collection

  Pinecone is now registered to collect Value Added Tax (VAT) or Goods and Services Tax (GST) for accounts based in various global regions. If applicable, add your VAT or GST number to your account under **Settings > Billing**.
</Update>

<Update label="2023-10" tags={["Database"]}>
  ### Collections are generally available

  [Collections](/guides/manage-data/back-up-an-index) are now generally available.
</Update>

<Update label="2023-10" tags={["SDK"]}>
  ### Released Node.js SDK v1.1.2

  The latest version of our Node.js SDK is v1.1.2. See the [release notes](https://github.com/pinecone-io/pinecone-ts-client/releases/tag/v1.1.2) in GitHub for more details.
</Update>

<Update label="2023-10" tags={["General"]}>
  ### Console improvements

  * The Index Browser is now available in the console. This allows you to preview, query, and filter by metadata directly from the console. The Index Browser can be found within the index detail page.
  * We've improved the design of our metrics page to include new charts for record and error count plus additional latencies (p90, p99) to help triage and understand issues.
</Update>

<Update label="2023-10" tags={["Database"]}>
  ### New integrations

  * Knowledge Base for Amazon Bedrock is now available in private preview. Integrate your enterprise data via retrieval augmented generation (RAG) when building search and GenAI applications. [Learn more](https://www.pinecone.io/blog/amazon-bedrock-integration/).
  * Pinecone Sink Connector for Confluent is now available in public preview. Gain access to data streams from across your business to build a real-time knowledge base for your AI applications. [Learn more](https://www.pinecone.io/confluent-integration).
</Update>

<Update label="2023-10" tags={["Billing"]}>
  ### Pinecone is now available in Microsoft Marketplace

  You can now [sign up for Pinecone billing through Microsoft Marketplace](/guides/organizations/manage-billing/upgrade-billing-plan).
</Update>

<Update label="2023-10" tags={["Compliance"]}>
  ### HIPAA compliance

  Pinecone is now HIPAA compliant across all of our cloud providers (AWS, Azure, and GCP).
</Update>

<Update label="2023-09-11" tags={["Database"]}>
  ### Azure support is generally available

  Pinecone Azure support via the [`eastus-azure` region](/guides/projects/understanding-projects#project-environments) is now generally available.
</Update>

<Update label="2023-08-14" tags={["Database"]}>
  ### Azure support is in public preview

  Pinecone now supports deploying projects to Azure using the new [`eastus-azure` region](/guides/projects/understanding-projects#project-environments). This is a public preview environment, so test thoroughly before deploying to production.
</Update>

<Update label="2023-06-21" tags={["Database"]}>
  ### `gcp-starter` region is in public preview

  The new `gcp-starter` region is now in public preview. This region has distinct limitations from other Starter plan regions. `gcp-starter` is the default region for some new users.
</Update>

<Update label="2023-04-26" tags={["Database"]}>
  ### Increased Starter plan capacity

  [Indexes in the Starter plan](/guides/index-data/indexing-overview#starter-plan) now support approximately 100,000 1536-dimensional embeddings with metadata. Capacity is proportional for other dimensionalities.
</Update>

<Update label="2023-04-03" tags={["Database"]}>
  ### New US and EU cloud regions

  Pinecone now supports [new US and EU cloud regions](/guides/projects/understanding-projects#project-environments).
</Update>

<Update label="2023-03-21" tags={["General"]}>
  ### SSO support on Enterprise plans

  Pinecone now supports SSO on some Enterprise plans. [Contact Support](https://app.pinecone.io/organizations/-/settings/support) to set up your integration.
</Update>

<Update label="2023-03-01" tags={["Database"]}>
  ### Increased metadata size limit

  Pinecone now supports [40 KB of metadata per vector](/guides/index-data/indexing-overview#metadata-size).
</Update>

<Update label="2023-02-22" tags={["Database", "Search"]}>
  ### Sparse-dense embeddings are in public preview

  Pinecone now supports [vectors with sparse and dense values](/guides/search/hybrid-search/single-index). To use sparse-dense embeddings in Python, upgrade to Python SDK version 2.2.0.
</Update>

<Update label="2023-02-22" tags={["SDK"]}>
  ### Released Python SDK v2.2.0

  Python SDK version 2.2.0 with support for sparse-dense embeddings is now available on [GitHub](https://github.com/pinecone-io/pinecone-python-client) and [PyPI](https://pypi.org/project/pinecone-client/2.2.0/).
</Update>

<Update label="2023-02-15" tags={["SDK"]}>
  ### New Node.js SDK is in public preview

  You can now try out our new [Node.js SDK for Pinecone](https://sdk.pinecone.io/typescript/).
</Update>

<Update label="2023-02-14" tags={["General"]}>
  ### New usage reports in the Pinecone console

  You can now monitor your current and projected Pinecone usage with the [**Usage** dashboard](/guides/manage-cost/monitor-usage-and-costs).
</Update>

<Update label="2023-01-31" tags={["Billing"]}>
  ### Pinecone is now available in AWS Marketplace

  You can now [sign up for Pinecone billing through Amazon Web Services Marketplace](/guides/organizations/manage-billing/upgrade-billing-plan).
</Update>

<Update label="2023-01-03" tags={["SDK"]}>
  ### Released Python SDK v2.1.0

  The [latest release of the Python SDK](https://github.com/pinecone-io/pinecone-python-client/releases/tag/2.1.0) makes the following changes:

  * Fixes "Connection Reset by peer" error after long idle periods
  * Adds typing and explicit names for arguments in all client operations
  * Adds docstrings to all client operations
  * Adds support for batch upserts by passing `batch_size` to the upsert method
  * Improves gRPC query results parsing performance
</Update>