v7.1.0
and v7.2.0
of the Pinecone Python SDK. These versions fix minor bugs and add support for managing namespaces.v4.0.0
and v4.0.1
of the Pinecone Go SDK.Go SDK v4.0.0
uses the latest stable API version, 2025-04
, and includes support for the following:v4.0.1
expands the DescribeIndex
response to include the private_host
value for connecting to indexes with a private endpoint.v6.1.1
of the Pinecone Node.js SDK. This version adds support for setting the sampling temperature for an assistant, and expands the describeIndex
response to include the private_host
value for connecting to indexes with a private endpoint.v5.1.0
of the Pinecone Java SDK. This version adds support for listing and describing embedding and reranking models hosted by Pinecone.v6.1.0
of the Pinecone Node.js SDK. This version adds support for controlling the context snippets sent to the LLM by an assistant.v7.0.1
and v7.0.2
of the Pinecone Python SDK. These versions fix minor bugs discovered since the release of the v7.0.0
major version.v6.0.1
of the Pinecone Node.js SDK. This version adds pagination to the listBackups
operation.2025-04
is now the latest stable version2025-04
is now the latest stable version of the Pinecone APIs. For highlights, see the SDK releases below.v7.0.0
of the Pinecone Python SDK. This version uses the latest stable API version, 2025-04
, and includes support for the following:pinecone-plugin-assistant
package required to work with Pinecone Assistant is now included by default; it is no longer necessary to install the plugin separately.v6.0.0
of the Pinecone Node.js SDK. This version uses the latest stable API version, 2025-04
, and includes support for the following:v5.0.0
of the Pinecone Java SDK. This version uses the latest stable API version, 2025-04
, and includes support for the following:v4.0.0
of the Pinecone .NET SDK. This version uses the latest stable API version, 2025-04
, and includes support for the following:v4.0.0
, update all relevant code to account for the following breaking changes. See the v4.0.0
release notes for full details.create_index
and create_for_model
operations:
CreateIndexRequestMetric
has been renamed to MetricType
.list_indexes
operation:
ModelIndexEmbedMetric
has been renamed to MetricType
.embed
operation:
SparseEmbedding.SparseIndices
has changed from IEnumerable<int>
to IEnumerable<long>
.v3.1.0
of the Pinecone .NET SDK. This version adds support for indexes with integrated embedding and reranking.context_options
in the request.v3.1.0
of the Pinecone Go SDK. This version adds support for indexes with integrated embedding and reranking.top_k
parameter (default is 15) when retrieving context snippets.v5.0.0
of the Pinecone Node.js SDK. This version uses the latest stable API version, 2025-01
, and includes support for Pinecone Assistant and sparse-only indexes.2025-04
and later.2025-01
is now the latest stable version2025-01
is now the latest stable version of the Pinecone APIs.v6.0.0
of the Pinecone Python SDK. This version uses the latest stable API version, 2025-01
, and includes support for the following:pinecone-plugin-records
package to use the v6.0.0
release.Metric
, AwsRegion
, GcpRegion
, PodType
, EmbedModel
, RerankModel
. This is a backwards compatible change; you can still pass string values for affected fields.PineconeAsyncio
and IndexAsyncio
, which provide async
methods for use with asyncio. This makes it possible to use Pinecone with modern async web frameworks such as FastAPI, Quart, and Sanic. Async support should significantly increase the efficiency of running many upserts in parallel.v6.0.0
, update all relevant code to account for the following breaking changes. See the v6.0.0
release notes for full details.pinecone-plugin-records
and pinecone-plugin-inference
plugins into the pinecone
package. If you are using these plugins, you must unstall them to use v6.0.0
.tqdm
, which is used to provide a progress bar when upserting data into Pinecone. If tqdm
is available in the environment, the Pinecone SDK will detect and use it, but tdqm
is no longer required to run the SDK. Popular notebook platforms such as Jupyter and Google Colab already include tqdm
in the environment by default, but if you are running small scripts in other environments and want to continue seeing progress bars, you will need to separately install the tqdm
package.config
, openapi_config
, and index_api
) to instead prefer dedicated keyword arguments for individual settings such as api_key
, proxy_url
, etc.v4.0.0
of the Pinecone Java SDK. This version uses the latest stable API version, 2025-01
, and adds support for sparse-only indexes.v4.0.0
, update all relevant code to account for the following breaking changes. See the v4.0.0
release notes for full details.embed
method:
parameters
now accepts Map<String, Object>
instead of EmbedRequestParameters
.Embeddings
response class now has dense and sparse embeddings. You now must use getDenseEmbedding()
or getSparseEmbedding()
. For example, instead of embeddings.getData().get(0).getValues()
, you would use embeddings.getData().get(0).getDenseEmbedding().getValues()
.rerank
method:
documents
now accepts List<Map<String, Object>>
instead of List<Map<String, String>>
.parameters
now accepts Map<String, Object>
instead of Map<String, String>
.v3.0.0
of the Pinecone Go SDK. This version uses the latest stable API version, 2025-01
, and adds support for sparse-only indexes.v3.0.0
, update all relevant code to account for the following breaking changes. See the v3.0.0
release notes for full details.embed
operation:
EmbedParameters
is no longer typed as a pointer.create_index
operation:
CreateServerlessIndexRequest
and CreatePodIndexRequest
structs have been updated, and fields are now classified as pointers to better denote optionality around creating specific types of indexes: Metric
, Dimension
, VectorType
, and DeletionProtection
.Values
in the Vector
type are now a pointer to allow flexibility when working with sparse-only indexes.v3.0.0
of the Pinecone .NET SDK. This version uses the latest stable API version, 2025-01
, and adds support for sparse-only indexes.v3.0.0
, update all relevant code to account for the following breaking changes. See the v3.0.0
release notes for full details.embed
operation:
Embedding
type has changed from a simple object to a discriminated union, supporting both DenseEmbedding
and SparseEmbedding
. New helper methods available on the Embedding type: IsDense
and IsSparse
for type checking, AsDense()
and AsSparse()
for type conversion, and Match()
and Visit()
for pattern matching.Parameters
property now uses Dictionary<string, object?>?
instead of EmbedRequestParameters
.rerank
operation:
Document
property now uses Dictionary<string, object?>?
instead of Dictionary<string, string>?
.Parameters
property now uses Dictionary<string, object?>?
instead of Dictionary<string, string>?
.v4.1.0
of the Pinecone Node.js SDK. This version adds support for index tags when creating or configuring indexes. It also adds a new RetryOnServerFailure
class that automatically retries asynchronous operations with exponential backoff when the server responds with a 500
or 503
error.v2.2.0
of the Pinecone Go SDK. This version adds support for index tags when creating or configuring indexes.