# Pinecone Docs ## Docs - [null](https://docs.pinecone.io/.github/pull_request_template) - [Notebooks](https://docs.pinecone.io/examples/notebooks) - [Reference architectures](https://docs.pinecone.io/examples/reference-architectures) - [Sample apps](https://docs.pinecone.io/examples/sample-apps) - [Legal semantic search](https://docs.pinecone.io/examples/sample-apps/legal-semantic-search) - [Namespace Notes](https://docs.pinecone.io/examples/sample-apps/namespace-notes) - [Pinecone Assistant](https://docs.pinecone.io/examples/sample-apps/pinecone-assistant) - [Shop The Look](https://docs.pinecone.io/examples/sample-apps/shop-the-look) - [Chat with an assistant](https://docs.pinecone.io/guides/assistant/chat-with-assistant) - [Check assistant status](https://docs.pinecone.io/guides/assistant/check-assistant-status) - [Check assistant file status](https://docs.pinecone.io/guides/assistant/check-file-status) - [Create an assistant](https://docs.pinecone.io/guides/assistant/create-assistant) - [Delete an assistant](https://docs.pinecone.io/guides/assistant/delete-assistant) - [Delete an uploaded file](https://docs.pinecone.io/guides/assistant/delete-file) - [Evaluate answers](https://docs.pinecone.io/guides/assistant/evaluate-answers) - [List assistants](https://docs.pinecone.io/guides/assistant/list-assistants) - [List the files in an assistant](https://docs.pinecone.io/guides/assistant/list-files) - [Understanding Pinecone Assistant](https://docs.pinecone.io/guides/assistant/understanding-assistant) - [Understanding Evaluation API](https://docs.pinecone.io/guides/assistant/understanding-evaluation) - [Update an assistant](https://docs.pinecone.io/guides/assistant/update-an-assistant) - [Upload a file to an assistant](https://docs.pinecone.io/guides/assistant/upload-file) - [Create and load private datasets](https://docs.pinecone.io/guides/data/create-and-load-private-datasets) - [Check data freshness](https://docs.pinecone.io/guides/data/data-freshness/check-data-freshness) - [Understanding data freshness](https://docs.pinecone.io/guides/data/data-freshness/understanding-data-freshness) - [Delete data](https://docs.pinecone.io/guides/data/delete-data) - [Encode sparse vectors](https://docs.pinecone.io/guides/data/encode-sparse-vectors) - [Fetch data](https://docs.pinecone.io/guides/data/fetch-data) - [Import data](https://docs.pinecone.io/guides/data/import-data) - [List record IDs](https://docs.pinecone.io/guides/data/list-record-ids) - [Manage RAG documents](https://docs.pinecone.io/guides/data/manage-rag-documents) - [Query data](https://docs.pinecone.io/guides/data/query-data) - [Query sparse-dense vectors](https://docs.pinecone.io/guides/data/query-sparse-dense-vectors) - [Target an index](https://docs.pinecone.io/guides/data/target-an-index) - [Understanding hybrid search](https://docs.pinecone.io/guides/data/understanding-hybrid-search) - [Understanding imports](https://docs.pinecone.io/guides/data/understanding-imports) - [Understanding metadata](https://docs.pinecone.io/guides/data/understanding-metadata) - [Update data](https://docs.pinecone.io/guides/data/update-data) - [Upsert data](https://docs.pinecone.io/guides/data/upsert-data) - [Upsert sparse-dense vectors](https://docs.pinecone.io/guides/data/upsert-sparse-dense-vectors) - [Use public Pinecone datasets](https://docs.pinecone.io/guides/data/use-public-pinecone-datasets) - [Use sample datasets](https://docs.pinecone.io/guides/data/use-sample-datasets) - [Pinecone Assistant quickstart](https://docs.pinecone.io/guides/get-started/assistant-quickstart) - [Build a RAG chatbot](https://docs.pinecone.io/guides/get-started/build-a-rag-chatbot) - [More examples](https://docs.pinecone.io/guides/get-started/examples) - [Glossary](https://docs.pinecone.io/guides/get-started/glossary) - [Image search](https://docs.pinecone.io/guides/get-started/image-search) - [Implement multitenancy using namespaces](https://docs.pinecone.io/guides/get-started/implement-multitenancy) - [Upsert and search documents](https://docs.pinecone.io/guides/get-started/integrated-inference) - [Key features](https://docs.pinecone.io/guides/get-started/key-features) - [Multimodal search](https://docs.pinecone.io/guides/get-started/multimodal-search) - [Pinecone Documentation](https://docs.pinecone.io/guides/get-started/overview) - [Pinecone Database quickstart](https://docs.pinecone.io/guides/get-started/quickstart) - [Recommender](https://docs.pinecone.io/guides/get-started/recommender) - [Semantic search](https://docs.pinecone.io/guides/get-started/semantic-search) - [Threat detection](https://docs.pinecone.io/guides/get-started/threat-detection) - [Back up an index](https://docs.pinecone.io/guides/indexes/back-up-an-index) - [Choose a pod type and size](https://docs.pinecone.io/guides/indexes/choose-a-pod-type-and-size) - [Configure an index](https://docs.pinecone.io/guides/indexes/configure-an-index) - [Convert a gcp-starter index to serverless](https://docs.pinecone.io/guides/indexes/convert-a-gcp-starter-index-to-serverless) - [Create an index](https://docs.pinecone.io/guides/indexes/create-an-index) - [Delete an index](https://docs.pinecone.io/guides/indexes/delete-an-index) - [Migrate a pod-based index to serverless](https://docs.pinecone.io/guides/indexes/migrate-a-pod-based-index-to-serverless) - [Prevent index deletion](https://docs.pinecone.io/guides/indexes/prevent-index-deletion) - [Restore an index](https://docs.pinecone.io/guides/indexes/restore-an-index) - [Scale pod-based indexes](https://docs.pinecone.io/guides/indexes/scale-pod-based-indexes) - [Tag an index](https://docs.pinecone.io/guides/indexes/tag-an-index) - [Understanding backups and collections](https://docs.pinecone.io/guides/indexes/understanding-backups-and-collections) - [Understanding indexes](https://docs.pinecone.io/guides/indexes/understanding-indexes) - [Use namespaces](https://docs.pinecone.io/guides/indexes/use-namespaces) - [View index information](https://docs.pinecone.io/guides/indexes/view-index-information) - [Generate embeddings](https://docs.pinecone.io/guides/inference/generate-embeddings) - [Rerank documents](https://docs.pinecone.io/guides/inference/rerank) - [Understanding Pinecone Inference](https://docs.pinecone.io/guides/inference/understanding-inference) - [Configure customer-managed encryption keys](https://docs.pinecone.io/guides/operations/configure-cmek) - [Connect to AWS PrivateLink](https://docs.pinecone.io/guides/operations/connect-to-aws-privatelink) - [Integrate with Amazon S3](https://docs.pinecone.io/guides/operations/integrations/integrate-with-amazon-s3) - [Manage storage integrations](https://docs.pinecone.io/guides/operations/integrations/manage-storage-integrations) - [Local development and testing](https://docs.pinecone.io/guides/operations/local-testing) - [Monitoring](https://docs.pinecone.io/guides/operations/monitoring) - [Move to production](https://docs.pinecone.io/guides/operations/move-to-production) - [Performance tuning](https://docs.pinecone.io/guides/operations/performance-tuning) - [Understanding security](https://docs.pinecone.io/guides/operations/understanding-security) - [Configure SSO with Okta](https://docs.pinecone.io/guides/organizations/configure-single-sign-on/okta) - [Change your billing plan](https://docs.pinecone.io/guides/organizations/manage-billing/changing-your-billing-plan) - [Set up billing through AWS Marketplace](https://docs.pinecone.io/guides/organizations/manage-billing/setting-up-billing-through-aws-marketplace) - [Set up billing through Azure Marketplace](https://docs.pinecone.io/guides/organizations/manage-billing/setting-up-billing-through-azure-marketplace) - [Set up billing through GCP Marketplace](https://docs.pinecone.io/guides/organizations/manage-billing/setting-up-billing-through-gcp-marketplace) - [Subscription status](https://docs.pinecone.io/guides/organizations/manage-billing/subscription-status) - [Understanding subscription status](https://docs.pinecone.io/guides/organizations/manage-billing/understanding-subscription-status) - [Costs](https://docs.pinecone.io/guides/organizations/manage-cost/costs) - [Manage cost](https://docs.pinecone.io/guides/organizations/manage-cost/manage-cost) - [Monitor your usage](https://docs.pinecone.io/guides/organizations/manage-cost/monitor-your-usage) - [Understanding cost](https://docs.pinecone.io/guides/organizations/manage-cost/understanding-cost) - [Manage organization members](https://docs.pinecone.io/guides/organizations/manage-organization-members) - [Understanding organizations](https://docs.pinecone.io/guides/organizations/understanding-organizations) - [Create a project](https://docs.pinecone.io/guides/projects/create-a-project) - [Manage API keys](https://docs.pinecone.io/guides/projects/manage-api-keys) - [Manage project members](https://docs.pinecone.io/guides/projects/manage-project-members) - [Rename a project](https://docs.pinecone.io/guides/projects/rename-a-project) - [Set a project pod limit](https://docs.pinecone.io/guides/projects/set-a-project-pod-limit) - [Understanding projects](https://docs.pinecone.io/guides/projects/understanding-projects) - [Airbyte](https://docs.pinecone.io/integrations/airbyte) - [Amazon Bedrock](https://docs.pinecone.io/integrations/amazon-bedrock): Pinecone as a Knowledge Base for Amazon Bedrock - [Amazon SageMaker](https://docs.pinecone.io/integrations/amazon-sagemaker) - [Anyscale](https://docs.pinecone.io/integrations/anyscale) - [Apify](https://docs.pinecone.io/integrations/apify) - [Aryn](https://docs.pinecone.io/integrations/aryn) - [Amazon Web Services (AWS)](https://docs.pinecone.io/integrations/aws) - [Azure](https://docs.pinecone.io/integrations/azure) - [Attribute usage to your integration](https://docs.pinecone.io/integrations/build-integration/attribute-usage-to-your-integration) - [Become a Pinecone partner](https://docs.pinecone.io/integrations/build-integration/become-a-partner) - [Connect your users to Pinecone](https://docs.pinecone.io/integrations/build-integration/connect-your-users-to-pinecone) - [Cohere](https://docs.pinecone.io/integrations/cohere): Using Cohere and Pinecone to generate and index high-quality vector embeddings - [Confluent](https://docs.pinecone.io/integrations/confluent) - [Context Data](https://docs.pinecone.io/integrations/context-data) - [Databricks](https://docs.pinecone.io/integrations/databricks): Using Databricks and Pinecone to create and index vector embeddings at scale - [Datadog](https://docs.pinecone.io/integrations/datadog): Monitoring Pinecone with Datadog - [Datavolo](https://docs.pinecone.io/integrations/datavolo) - [Elasticsearch](https://docs.pinecone.io/integrations/elasticsearch) - [Estuary](https://docs.pinecone.io/integrations/estuary) - [Fleak](https://docs.pinecone.io/integrations/fleak) - [FlowiseAI](https://docs.pinecone.io/integrations/flowise) - [Gathr](https://docs.pinecone.io/integrations/gathr) - [Google Cloud Platform (GCP)](https://docs.pinecone.io/integrations/gcp) - [GitHub Copilot](https://docs.pinecone.io/integrations/github-copilot) - [Haystack](https://docs.pinecone.io/integrations/haystack): Using Haystack and Pinecone to keep your NLP-driven apps up-to-date - [Hugging Face Inference Endpoints](https://docs.pinecone.io/integrations/hugging-face-inference-endpoints): Using Hugging Face Inference Endpoints and Pinecone to generate and index high-quality vector embeddings - [Instill AI](https://docs.pinecone.io/integrations/instill) - [Jina AI](https://docs.pinecone.io/integrations/jina) - [LangChain](https://docs.pinecone.io/integrations/langchain): Using LangChain and Pinecone to add knowledge to LLMs - [Langtrace](https://docs.pinecone.io/integrations/langtrace) - [LlamaIndex](https://docs.pinecone.io/integrations/llamaindex): Using LlamaIndex and Pinecone to build semantic search and RAG applications - [Matillion](https://docs.pinecone.io/integrations/matillion) - [New Relic](https://docs.pinecone.io/integrations/new-relic) - [Nexla](https://docs.pinecone.io/integrations/nexla) - [Nuclia](https://docs.pinecone.io/integrations/nuclia) - [OctoAI](https://docs.pinecone.io/integrations/octoai) - [OpenAI](https://docs.pinecone.io/integrations/openai): Using OpenAI and Pinecone to combine deep learning capabilities for embedding generation with efficient vector storage and retrieval - [Integrations](https://docs.pinecone.io/integrations/overview): Pinecone integrations enable you to build and deploy AI applications faster and more efficiently. Integrate Pinecone with your favorite frameworks, data sources, and infrastructure providers. - [Pulumi](https://docs.pinecone.io/integrations/pulumi) - [Redpanda](https://docs.pinecone.io/integrations/redpanda) - [Snowflake](https://docs.pinecone.io/integrations/snowflake) - [StreamNative](https://docs.pinecone.io/integrations/streamnative) - [Terraform](https://docs.pinecone.io/integrations/terraform): Using Terraform to manage Pinecone resources - [Traceloop](https://docs.pinecone.io/integrations/traceloop) - [TruLens](https://docs.pinecone.io/integrations/trulens): Using TruLens and Pinecone to evaluate grounded LLM applications - [Twelve Labs](https://docs.pinecone.io/integrations/twelve-labs) - [Unstructured](https://docs.pinecone.io/integrations/unstructured) - [Vercel](https://docs.pinecone.io/integrations/vercel) - [Voyage AI](https://docs.pinecone.io/integrations/voyage): Using Voyage AI and Pinecone to generate and index high-quality vector embeddings - [CLIP-ViT-B-32-laion2B-s34B-b79K](https://docs.pinecone.io/models/CLIP-ViT-B-32-laion2B-s34B-b79K) - [all-MiniLM-L12-v2](https://docs.pinecone.io/models/all-MiniLM-L12-v2) - [all-mpnet-base-v2](https://docs.pinecone.io/models/all-mpnet-base-v2) - [bge-reranker-v2-m3](https://docs.pinecone.io/models/bge-reranker-v2-m3) - [CLIP](https://docs.pinecone.io/models/clip) - [embed-english-light-v3.0](https://docs.pinecone.io/models/cohere-embed-english-light-v3.0) - [embed-english-v3.0](https://docs.pinecone.io/models/cohere-embed-english-v3.0) - [embed-multilingual-v3.0](https://docs.pinecone.io/models/cohere-embed-multilingual-v3.0) - [e5-base-v2](https://docs.pinecone.io/models/e5-base-v2) - [e5-large-v2](https://docs.pinecone.io/models/e5-large-v2) - [gte-base](https://docs.pinecone.io/models/gte-base) - [gte-large](https://docs.pinecone.io/models/gte-large) - [instructor-large](https://docs.pinecone.io/models/instructor-large) - [instructor-xl](https://docs.pinecone.io/models/instructor-xl) - [jina-embeddings-v2-base-en](https://docs.pinecone.io/models/jina-embeddings-v2-base-en) - [jina-embeddings-v3](https://docs.pinecone.io/models/jina-embeddings-v3) - [Marengo-retrieval-2.6](https://docs.pinecone.io/models/marengo-retrieval-2-6) - [mistral-embed](https://docs.pinecone.io/models/mistral-embed) - [multilingual-e5-large](https://docs.pinecone.io/models/multilingual-e5-large) - [Model Gallery](https://docs.pinecone.io/models/overview): Pinecone integrations enable you to build and deploy AI applications faster and more efficiently. Integrate Pinecone with your favorite frameworks, data sources, and infrastructure providers. - [rerank-english-v2](https://docs.pinecone.io/models/rerank-english-v2) - [text-embedding-3-large](https://docs.pinecone.io/models/text-embedding-3-large) - [text-embedding-3-small](https://docs.pinecone.io/models/text-embedding-3-small) - [text-embedding-ada-002](https://docs.pinecone.io/models/text-embedding-ada-002) - [voyage-2](https://docs.pinecone.io/models/voyage-02) - [voyage-code-2](https://docs.pinecone.io/models/voyage-code-2) - [voyage-large-2](https://docs.pinecone.io/models/voyage-large-2) - [Configure an index](https://docs.pinecone.io/reference/api/2024-04/control-plane/configure_index): This operation configures the pod size and number of replicas for a pod-based index. It is not possible to change the pod type of an index. However, you can create a collection from an index and then [create a new index with a different pod type](http://docs.pinecone.io/guides/indexes/create-an-index#create-an-index-from-a-collection) from the collection. - [Create a collection](https://docs.pinecone.io/reference/api/2024-04/control-plane/create_collection): This operation creates a Pinecone collection. Serverless indexes do not support collections. - [Create an index](https://docs.pinecone.io/reference/api/2024-04/control-plane/create_index): This operation deploys a Pinecone index. This is where you specify the measure of similarity, the dimension of vectors to be stored in the index, which cloud provider you would like to deploy with, and more. For guidance and examples, see [Create an index](https://docs.pinecone.io/guides/indexes/create-an-index#create-a-serverless-index). - [Delete a collection](https://docs.pinecone.io/reference/api/2024-04/control-plane/delete_collection): This operation deletes an existing collection. Serverless indexes do not support collections. - [Delete an index](https://docs.pinecone.io/reference/api/2024-04/control-plane/delete_index): This operation deletes an existing index. - [Describe a collection](https://docs.pinecone.io/reference/api/2024-04/control-plane/describe_collection): This operation gets a description of a collection. Serverless indexes do not support collections. - [Describe an index](https://docs.pinecone.io/reference/api/2024-04/control-plane/describe_index): Get a description of an index. - [List collections](https://docs.pinecone.io/reference/api/2024-04/control-plane/list_collections): This operation returns a list of all collections in a project. Serverless indexes do not support collections. - [List indexes](https://docs.pinecone.io/reference/api/2024-04/control-plane/list_indexes): This operation returns a list of all indexes in a project. - [Delete vectors](https://docs.pinecone.io/reference/api/2024-04/data-plane/delete): The `delete` operation deletes vectors, by id, from a single namespace. For guidance and examples, see [Delete data](https://docs.pinecone.io/guides/data/delete-data). - [Get index stats](https://docs.pinecone.io/reference/api/2024-04/data-plane/describeindexstats): The `describe_index_stats` operation returns statistics about the contents of an index, including the vector count per namespace, the number of dimensions, and the index fullness. Serverless indexes scale automatically as needed, so index fullness is relevant only for pod-based indexes. For pod-based indexes, the index fullness result may be inaccurate during pod resizing; to get the status of a pod resizing process, use [`describe_index`](https://docs.pinecone.io/reference/api/control-plane/describe_index). - [Fetch vectors](https://docs.pinecone.io/reference/api/2024-04/data-plane/fetch): The `fetch` operation looks up and returns vectors, by ID, from a single namespace. The returned vectors include the vector data and/or metadata. For guidance and examples, see [Fetch data](https://docs.pinecone.io/guides/data/fetch-data). - [List vector IDs](https://docs.pinecone.io/reference/api/2024-04/data-plane/list): The `list` operation lists the IDs of vectors in a single namespace of a serverless index. An optional prefix can be passed to limit the results to IDs with a common prefix. `list` returns up to 100 IDs at a time by default in sorted order (bitwise "C" collation). If the `limit` parameter is set, `list` returns up to that number of IDs instead. Whenever there are additional IDs to return, the response also includes a `pagination_token` that you can use to get the next batch of IDs. When the response does not include a `pagination_token`, there are no more IDs to return. For guidance and examples, see [List record IDs](https://docs.pinecone.io/guides/data/list-record-ids). **Note:** `list` is supported only for serverless indexes. - [Query vectors](https://docs.pinecone.io/reference/api/2024-04/data-plane/query): The `query` operation searches a namespace, using a query vector. It retrieves the ids of the most similar items in a namespace, along with their similarity scores. For guidance and examples, see [Query data](https://docs.pinecone.io/guides/data/query-data). - [Update a vector](https://docs.pinecone.io/reference/api/2024-04/data-plane/update): The `update` operation updates a vector in a namespace. If a value is included, it will overwrite the previous value. If a `set_metadata` is included, the values of the fields specified in it will be added or overwrite the previous value. For guidance and examples, see [Update data](https://docs.pinecone.io/guides/data/update-data). - [Upsert vectors](https://docs.pinecone.io/reference/api/2024-04/data-plane/upsert): The `upsert` operation writes vectors into a namespace. If a new value is upserted for an existing vector ID, it will overwrite the previous value. For guidance and examples, see [Upsert data](https://docs.pinecone.io/guides/data/upsert-data). - [Configure an index](https://docs.pinecone.io/reference/api/2024-07/control-plane/configure_index): This operation configures an existing index. For serverless indexes, you can configure only index deletion protection. For pod-based indexes, you can configure the pod size, number of replicas, and index deletion protection. It is not possible to change the pod type of a pod-based index. However, you can create a collection from a pod-based index and then [create a new pod-based index with a different pod type](http://docs.pinecone.io/guides/indexes/create-an-index#create-an-index-from-a-collection) from the collection. For guidance and examples, see [Configure an index](http://docs.pinecone.io/guides/indexes/configure-an-index). - [Create a collection](https://docs.pinecone.io/reference/api/2024-07/control-plane/create_collection): This operation creates a Pinecone collection. Serverless indexes do not support collections. - [Create an index](https://docs.pinecone.io/reference/api/2024-07/control-plane/create_index): This operation deploys a Pinecone index. This is where you specify the measure of similarity, the dimension of vectors to be stored in the index, which cloud provider you would like to deploy with, and more. For guidance and examples, see [Create an index](https://docs.pinecone.io/guides/indexes/create-an-index#create-a-serverless-index). - [Delete a collection](https://docs.pinecone.io/reference/api/2024-07/control-plane/delete_collection): This operation deletes an existing collection. Serverless indexes do not support collections. - [Delete an index](https://docs.pinecone.io/reference/api/2024-07/control-plane/delete_index): This operation deletes an existing index. - [Describe a collection](https://docs.pinecone.io/reference/api/2024-07/control-plane/describe_collection): This operation gets a description of a collection. Serverless indexes do not support collections. - [Describe an index](https://docs.pinecone.io/reference/api/2024-07/control-plane/describe_index): Get a description of an index. - [List collections](https://docs.pinecone.io/reference/api/2024-07/control-plane/list_collections): This operation returns a list of all collections in a project. Serverless indexes do not support collections. - [List indexes](https://docs.pinecone.io/reference/api/2024-07/control-plane/list_indexes): This operation returns a list of all indexes in a project. - [Delete vectors](https://docs.pinecone.io/reference/api/2024-07/data-plane/delete): The `delete` operation deletes vectors, by id, from a single namespace. For guidance and examples, see [Delete data](https://docs.pinecone.io/guides/data/delete-data). - [Get index stats](https://docs.pinecone.io/reference/api/2024-07/data-plane/describeindexstats): The `describe_index_stats` operation returns statistics about the contents of an index, including the vector count per namespace, the number of dimensions, and the index fullness. Serverless indexes scale automatically as needed, so index fullness is relevant only for pod-based indexes. For pod-based indexes, the index fullness result may be inaccurate during pod resizing; to get the status of a pod resizing process, use [`describe_index`](https://docs.pinecone.io/reference/api/control-plane/describe_index). - [Fetch vectors](https://docs.pinecone.io/reference/api/2024-07/data-plane/fetch): The `fetch` operation looks up and returns vectors, by ID, from a single namespace. The returned vectors include the vector data and/or metadata. For guidance and examples, see [Fetch data](https://docs.pinecone.io/guides/data/fetch-data). - [List vector IDs](https://docs.pinecone.io/reference/api/2024-07/data-plane/list): The `list` operation lists the IDs of vectors in a single namespace of a serverless index. An optional prefix can be passed to limit the results to IDs with a common prefix. `list` returns up to 100 IDs at a time by default in sorted order (bitwise "C" collation). If the `limit` parameter is set, `list` returns up to that number of IDs instead. Whenever there are additional IDs to return, the response also includes a `pagination_token` that you can use to get the next batch of IDs. When the response does not include a `pagination_token`, there are no more IDs to return. For guidance and examples, see [List record IDs](https://docs.pinecone.io/guides/data/list-record-ids). **Note:** `list` is supported only for serverless indexes. - [Query vectors](https://docs.pinecone.io/reference/api/2024-07/data-plane/query): The `query` operation searches a namespace, using a query vector. It retrieves the ids of the most similar items in a namespace, along with their similarity scores. For guidance and examples, see [Query data](https://docs.pinecone.io/guides/data/query-data). - [Update a vector](https://docs.pinecone.io/reference/api/2024-07/data-plane/update): The `update` operation updates a vector in a namespace. If a value is included, it will overwrite the previous value. If a `set_metadata` is included, the values of the fields specified in it will be added or overwrite the previous value. For guidance and examples, see [Update data](https://docs.pinecone.io/guides/data/update-data). - [Upsert vectors](https://docs.pinecone.io/reference/api/2024-07/data-plane/upsert): The `upsert` operation writes vectors into a namespace. If a new value is upserted for an existing vector ID, it will overwrite the previous value. For guidance and examples, see [Upsert data](https://docs.pinecone.io/guides/data/upsert-data). - [Embed data](https://docs.pinecone.io/reference/api/2024-07/inference/generate-embeddings): Generate embeddings for input data. For guidance and examples, see [Generate embeddings](https://docs.pinecone.io/guides/inference/generate-embeddings). - [Configure an index](https://docs.pinecone.io/reference/api/2024-10/control-plane/configure_index): This operation configures an existing index. For serverless indexes, you can configure only index deletion protection and tags. For pod-based indexes, you can configure the pod size, number of replicas, tags, and index deletion protection. It is not possible to change the pod type of a pod-based index. However, you can create a collection from a pod-based index and then [create a new pod-based index with a different pod type](http://docs.pinecone.io/guides/indexes/create-an-index#create-an-index-from-a-collection) from the collection. For guidance and examples, see [Configure an index](http://docs.pinecone.io/guides/indexes/configure-an-index). - [Create a collection](https://docs.pinecone.io/reference/api/2024-10/control-plane/create_collection): This operation creates a Pinecone collection. Serverless indexes do not support collections. - [Create an index](https://docs.pinecone.io/reference/api/2024-10/control-plane/create_index): This operation deploys a Pinecone index. This is where you specify the measure of similarity, the dimension of vectors to be stored in the index, which cloud provider you would like to deploy with, and more. For guidance and examples, see [Create an index](https://docs.pinecone.io/guides/indexes/create-an-index#create-a-serverless-index). - [Delete a collection](https://docs.pinecone.io/reference/api/2024-10/control-plane/delete_collection): This operation deletes an existing collection. Serverless indexes do not support collections. - [Delete an index](https://docs.pinecone.io/reference/api/2024-10/control-plane/delete_index): This operation deletes an existing index. - [Describe a collection](https://docs.pinecone.io/reference/api/2024-10/control-plane/describe_collection): This operation gets a description of a collection. Serverless indexes do not support collections. - [Describe an index](https://docs.pinecone.io/reference/api/2024-10/control-plane/describe_index): Get a description of an index. - [List collections](https://docs.pinecone.io/reference/api/2024-10/control-plane/list_collections): This operation returns a list of all collections in a project. Serverless indexes do not support collections. - [List indexes](https://docs.pinecone.io/reference/api/2024-10/control-plane/list_indexes): This operation returns a list of all indexes in a project. - [Cancel an import](https://docs.pinecone.io/reference/api/2024-10/data-plane/cancel_import): The `cancel_import` operation cancels an import operation if it is not yet finished. It has no effect if the operation is already finished. For guidance and examples, see [Import data](https://docs.pinecone.io/guides/data/import-data). - [Delete vectors](https://docs.pinecone.io/reference/api/2024-10/data-plane/delete): The `delete` operation deletes vectors, by id, from a single namespace. For guidance and examples, see [Delete data](https://docs.pinecone.io/guides/data/delete-data). - [Describe an import](https://docs.pinecone.io/reference/api/2024-10/data-plane/describe_import): The `describe_import` operation returns details of a specific import operation. For guidance and examples, see [Import data](https://docs.pinecone.io/guides/data/import-data). - [Get index stats](https://docs.pinecone.io/reference/api/2024-10/data-plane/describeindexstats): The `describe_index_stats` operation returns statistics about the contents of an index, including the vector count per namespace, the number of dimensions, and the index fullness. Serverless indexes scale automatically as needed, so index fullness is relevant only for pod-based indexes. For pod-based indexes, the index fullness result may be inaccurate during pod resizing; to get the status of a pod resizing process, use [`describe_index`](https://docs.pinecone.io/reference/api/control-plane/describe_index). - [Fetch vectors](https://docs.pinecone.io/reference/api/2024-10/data-plane/fetch): The `fetch` operation looks up and returns vectors, by ID, from a single namespace. The returned vectors include the vector data and/or metadata. For guidance and examples, see [Fetch data](https://docs.pinecone.io/guides/data/fetch-data). - [List vector IDs](https://docs.pinecone.io/reference/api/2024-10/data-plane/list): The `list` operation lists the IDs of vectors in a single namespace of a serverless index. An optional prefix can be passed to limit the results to IDs with a common prefix. By default, `list` returns up to 100 IDs per page in sorted order (bitwise "C" collation). If the `limit` parameter is set, `list` returns up to that number of IDs instead. Whenever there are additional IDs to return, the response also includes a `pagination_token` that you can use to get the next batch of IDs. When the response does not include a `pagination_token`, there are no more IDs to return. For guidance and examples, see [List record IDs](https://docs.pinecone.io/guides/data/list-record-ids). **Note:** `list_vectors` is supported only for serverless indexes. - [List imports](https://docs.pinecone.io/reference/api/2024-10/data-plane/list_imports): The `list_imports` operation lists all recent and ongoing import operations. By default, `list_imports` returns up to 100 imports per page. If the `limit` parameter is set, `list` returns up to that number of imports instead. Whenever there are additional IDs to return, the response also includes a `pagination_token` that you can use to get the next batch of imports. When the response does not include a `pagination_token`, there are no more imports to return. For guidance and examples, see [Import data](https://docs.pinecone.io/guides/data/import-data). - [Query vectors](https://docs.pinecone.io/reference/api/2024-10/data-plane/query): The `query` operation searches a namespace, using a query vector. It retrieves the ids of the most similar items in a namespace, along with their similarity scores. For guidance and examples, see [Query data](https://docs.pinecone.io/guides/data/query-data). - [Start import](https://docs.pinecone.io/reference/api/2024-10/data-plane/start_import): The `start_import` operation starts an asynchronous import of vectors from object storage into an index. For guidance and examples, see [Import data](https://docs.pinecone.io/guides/data/import-data). - [Update a vector](https://docs.pinecone.io/reference/api/2024-10/data-plane/update): The `update` operation updates a vector in a namespace. If a value is included, it will overwrite the previous value. If a `set_metadata` is included, the values of the fields specified in it will be added or overwrite the previous value. For guidance and examples, see [Update data](https://docs.pinecone.io/guides/data/update-data). - [Upsert vectors](https://docs.pinecone.io/reference/api/2024-10/data-plane/upsert): The `upsert` operation writes vectors into a namespace. If a new value is upserted for an existing vector ID, it will overwrite the previous value. For guidance and examples, see [Upsert data](https://docs.pinecone.io/guides/data/upsert-data). - [Embed data](https://docs.pinecone.io/reference/api/2024-10/inference/generate-embeddings): Generate embeddings for input data. For guidance and examples, see [Generate embeddings](https://docs.pinecone.io/guides/inference/generate-embeddings). - [Rerank documents](https://docs.pinecone.io/reference/api/2024-10/inference/rerank): Rerank documents according to their relevance to a query. For guidance and examples, see [Rerank documents](https://docs.pinecone.io/guides/inference/rerank). - [Chat with an assistant](https://docs.pinecone.io/reference/api/assistant/chat_assistant): The `chat_assistant` operation allows you to [chat with an assistant](https://docs.pinecone.io/guides/assistant/chat-with-assistant) and get back citations in structured form. This is the recommended way to chat with an assistant, as it offers more functionality and control over the assistant's responses and references than the `chat_completion_assistant` operation. - [Chat through an OpenAI-compatible interface](https://docs.pinecone.io/reference/api/assistant/chat_completion_assistant): The `chat_completion_assistant` endpoint is used to [chat with an assistant](https://docs.pinecone.io/guides/assistant/chat-with-assistant). This endpoint is based on the OpenAI Chat Completion API, a commonly used and adopted API. It is useful if you need inline citations or OpenAI-compatible responses, but has limited functionality compared to the [`chat_assistant`](https://docs.pinecone.io/reference/api/assistant/chat_assistant) endpoint. - [Create an assistant](https://docs.pinecone.io/reference/api/assistant/create_assistant): The `create_assistant` endpoint [creates a Pinecone Assistant](https://docs.pinecone.io/guides/assistant/create-assistant). This is where you specify the underlying training model, which cloud provider you would like to deploy with, and more. - [Upload file to assistant](https://docs.pinecone.io/reference/api/assistant/create_file): The `upload_file` endpoint [uploads a file](https://docs.pinecone.io/guides/assistant/upload-file) to the specified assistant. - [Delete an assistant](https://docs.pinecone.io/reference/api/assistant/delete_assistant): The `delete_assistant` endpoint [deletes an existing assistant](https://docs.pinecone.io/guides/assistant/delete-assistant). - [Delete an uploaded file](https://docs.pinecone.io/reference/api/assistant/delete_file): The `delete_file` endpoint [deletes an uploaded file](https://docs.pinecone.io/guides/assistant/delete-file) from an assistant. - [Describe a file upload](https://docs.pinecone.io/reference/api/assistant/describe_file): The `describe_file` endpoint provides the [current status and metadata of a file](https://docs.pinecone.io/guides/assistant/check-file-status) uploaded to an assistant. - [Check assistant status](https://docs.pinecone.io/reference/api/assistant/get_assistant): The `get_assistant` endpoint [gets the status](https://docs.pinecone.io/guides/assistant/check-assistant-status) of an assistant. - [List assistants](https://docs.pinecone.io/reference/api/assistant/list_assistants): The `list_assistants` endpoint returns a [list of all assistants](https://docs.pinecone.io/guides/assistant/list-assistants) in a project. - [List Files](https://docs.pinecone.io/reference/api/assistant/list_files): The `list_files` endpoint returns a [list of all files in an assistant](https://docs.pinecone.io//guides/assistant/list-files), with an option to filter files with metadata. - [Evaluate an answer](https://docs.pinecone.io/reference/api/assistant/metrics_alignment): The `metrics_alignment` endpoint [evaluates](https://docs.pinecone.io/guides/assistant/understanding-evaluation) the correctness, completeness, and alignment of a generated answer with respect to a question and a ground truth answer. The correctness and completeness are evaluated based on the precision and recall of the generated answer with respect to the ground truth answer facts. Alignment is the harmonic mean of correctness and completeness. - [Update an assistant](https://docs.pinecone.io/reference/api/assistant/update_assistant): The `update_assistant` endpoint [updates an existing assistant](https://docs.pinecone.io/guides/assistant/update-assistant). You can modify the assistant's instructions and metadata. - [Authentication](https://docs.pinecone.io/reference/api/authentication) - [Errors](https://docs.pinecone.io/reference/api/errors) - [API reference](https://docs.pinecone.io/reference/api/introduction) - [Create an index for an embedding model](https://docs.pinecone.io/reference/api/unstable/control-plane/create_for_model): This operation creates a serverless index configured for a specific embedding model. - [Search a namespace](https://docs.pinecone.io/reference/api/unstable/data-plane/search_records): This operation converts a query to a vector embedding and then searches a namespace using the embedding. It returns the most similar records in the namespace, along with their similarity scores. - [Upsert records into a namespace](https://docs.pinecone.io/reference/api/unstable/data-plane/upsert_records): This operation converts input data to vector embeddings and then upserts the embeddings into a namespace. - [API versioning](https://docs.pinecone.io/reference/api/versioning) - [Pod-based architecture](https://docs.pinecone.io/reference/architecture/pod-based-architecture) - [Serverless architecture](https://docs.pinecone.io/reference/architecture/serverless-architecture) - [.NET SDK](https://docs.pinecone.io/reference/dotnet-sdk) - [Go SDK](https://docs.pinecone.io/reference/go-sdk) - [Java SDK](https://docs.pinecone.io/reference/java-sdk) - [Known limitations](https://docs.pinecone.io/reference/known-limitations) - [Node.js SDK](https://docs.pinecone.io/reference/node-sdk) - [Object identifiers](https://docs.pinecone.io/reference/object-identifiers) - [Introduction](https://docs.pinecone.io/reference/pinecone-sdks) - [Python SDK](https://docs.pinecone.io/reference/python-sdk) - [Quotas and limits](https://docs.pinecone.io/reference/quotas-and-limits) - [Rust SDK](https://docs.pinecone.io/reference/rust-sdk) - [Pinecone datasets](https://docs.pinecone.io/reference/tools/pinecone-datasets) - [Spark-Pinecone connector](https://docs.pinecone.io/reference/tools/pinecone-spark-connector) - [Pinecone text client](https://docs.pinecone.io/reference/tools/pinecone-text-client) - [2022 releases](https://docs.pinecone.io/release-notes/2022) - [2023 releases](https://docs.pinecone.io/release-notes/2023) - [2024 releases](https://docs.pinecone.io/release-notes/2024) - [Feature availability](https://docs.pinecone.io/release-notes/feature-availability) - [Available cloud regions](https://docs.pinecone.io/troubleshooting/available-cloud-regions) - [Best Practices](https://docs.pinecone.io/troubleshooting/best-practices) - [Billing disputes and refunds](https://docs.pinecone.io/troubleshooting/billing-disputes-and-refunds) - [Contact Support](https://docs.pinecone.io/troubleshooting/contact-support) - [CORS Issues](https://docs.pinecone.io/troubleshooting/cors-issues) - [Create and manage vectors with metadata](https://docs.pinecone.io/troubleshooting/create-and-manage-vectors-with-metadata) - [Custom data processing agreements](https://docs.pinecone.io/troubleshooting/custom-data-processing-agreements) - [Debug model vs. Pinecone recall issues](https://docs.pinecone.io/troubleshooting/debug-model-vs-pinecone-recall-issues) - [Delete a namespace](https://docs.pinecone.io/troubleshooting/delete-a-namespace) - [Delete your account](https://docs.pinecone.io/troubleshooting/delete-your-account) - [Delete your organization](https://docs.pinecone.io/troubleshooting/delete-your-organization) - [Differences between Lexical and Semantic Search regarding relevancy](https://docs.pinecone.io/troubleshooting/differences-between-lexical-semantic-search) - [Embedding values changed when upserted](https://docs.pinecone.io/troubleshooting/embedding-values-changed-when-upserted) - [Error: Cannot import name 'Pinecone' from 'pinecone'](https://docs.pinecone.io/troubleshooting/error-cannot-import-name-pinecone) - [Error: Handshake read failed when connecting](https://docs.pinecone.io/troubleshooting/error-handshake-read-failed) - [Export indexes](https://docs.pinecone.io/troubleshooting/export-indexes) - [Handle large numbers of deletes by metadata](https://docs.pinecone.io/troubleshooting/handle-deletes-by-metadata) - [How and when to add replicas](https://docs.pinecone.io/troubleshooting/how-and-when-to-add-replicas) - [How and when to increase index size](https://docs.pinecone.io/troubleshooting/how-and-when-to-increase-index-size) - [How to work with Support](https://docs.pinecone.io/troubleshooting/how-to-work-with-support) - [Serverless index creation error - max serverless indexes](https://docs.pinecone.io/troubleshooting/index-creation-error-max-serverless) - [Index creation error - missing spec parameter](https://docs.pinecone.io/troubleshooting/index-creation-error-missing-spec) - [Keep customer data separate in Pinecone](https://docs.pinecone.io/troubleshooting/keep-customer-data-separate) - [Limitations of querying by ID](https://docs.pinecone.io/troubleshooting/limitations-of-querying-by-id) - [Login code issues](https://docs.pinecone.io/troubleshooting/login-code-issues) - [Metadata re-configuration](https://docs.pinecone.io/troubleshooting/metadata-reconfiguration) - [Metadata string value returned as a datetime object](https://docs.pinecone.io/troubleshooting/metadata-string-value-returned-as-datetime) - [Minimize latencies](https://docs.pinecone.io/troubleshooting/minimize-latencies) - [Python AttributeError: module pinecone has no attribute init](https://docs.pinecone.io/troubleshooting/module-pinecone-has-no-attribute-init) - [Namespaces vs. metadata filtering](https://docs.pinecone.io/troubleshooting/namespaces-vs-metadata-filtering) - [Node.JS Troubleshooting](https://docs.pinecone.io/troubleshooting/nodejs-troubleshooting) - [Non-indexed field filter issues](https://docs.pinecone.io/troubleshooting/non-indexed-field-filter-issues) - [Parallel queries](https://docs.pinecone.io/troubleshooting/parallel-queries) - [PineconeAttribute errors with LangChain](https://docs.pinecone.io/troubleshooting/pinecone-attribute-errors-with-langchain) - [Pinecone Support SLAs](https://docs.pinecone.io/troubleshooting/pinecone-support-slas) - [Pods are full](https://docs.pinecone.io/troubleshooting/pods-are-full) - [Remove a metadata field from a record](https://docs.pinecone.io/troubleshooting/remove-metadata-field) - [Restrictions on index names](https://docs.pinecone.io/troubleshooting/restrictions-on-index-names) - [Return all vectors in an index](https://docs.pinecone.io/troubleshooting/return-all-vectors-in-an-index) - [Select index type and size](https://docs.pinecone.io/troubleshooting/select-index-type-and-size) - [Serverless index connection errors](https://docs.pinecone.io/troubleshooting/serverless-index-connection-errors) - [Unable to pip install](https://docs.pinecone.io/troubleshooting/unable-to-pip-install) - [Use namespaces instead of several indexes](https://docs.pinecone.io/troubleshooting/use-namespaces-instead-of-several-indexes) - [Vertically downscaling](https://docs.pinecone.io/troubleshooting/vertically-downscaling) - [Wait for index creation to be complete](https://docs.pinecone.io/troubleshooting/wait-for-index-creation)