# Pinecone Docs ## Docs - [2022 releases](https://docs.pinecone.io/assistant-release-notes/2022.md) - [2023 releases](https://docs.pinecone.io/assistant-release-notes/2023.md) - [2024 releases](https://docs.pinecone.io/assistant-release-notes/2024.md) - [2025 releases](https://docs.pinecone.io/assistant-release-notes/2025.md) - [2026 releases](https://docs.pinecone.io/assistant-release-notes/2026.md) - [Feature availability](https://docs.pinecone.io/assistant-release-notes/feature-availability.md) - [Assistant examples](https://docs.pinecone.io/examples/assistant.md) - [Notebooks](https://docs.pinecone.io/examples/notebooks.md) - [Reference architectures](https://docs.pinecone.io/examples/reference-architectures.md) - [Sample apps](https://docs.pinecone.io/examples/sample-apps.md) - [Access your invoices](https://docs.pinecone.io/guides/assistant/admin/access-your-invoices.md): View and download billing invoices from Pinecone. - [Change your payment method](https://docs.pinecone.io/guides/assistant/admin/change-payment-method.md): Update billing payment method for your organization. - [Configure audit logs](https://docs.pinecone.io/guides/assistant/admin/configure-audit-logs.md): Track user and API actions with audit log configuration. - [Configure SSO with Okta](https://docs.pinecone.io/guides/assistant/admin/configure-sso-with-okta.md): Enable SSO authentication using Okta integration. - [Create a project](https://docs.pinecone.io/guides/assistant/admin/create-a-project.md): Create a new Pinecone project in your organization. - [Downgrade your plan](https://docs.pinecone.io/guides/assistant/admin/downgrade-billing-plan.md): Downgrade from a paid plan to the free Starter plan. - [Download a usage report](https://docs.pinecone.io/guides/assistant/admin/download-usage-report.md): Export organization usage and cost reports. - [Manage API keys](https://docs.pinecone.io/guides/assistant/admin/manage-api-keys.md): Create and manage API keys with custom permissions. - [Manage organization members](https://docs.pinecone.io/guides/assistant/admin/manage-organization-members.md): Invite and control organization member access levels. - [Manage service accounts at the organization-level](https://docs.pinecone.io/guides/assistant/admin/manage-organization-service-accounts.md): Create service accounts for organization-level API access. - [Manage project members](https://docs.pinecone.io/guides/assistant/admin/manage-project-members.md): Add and manage team members in your project. - [Manage service accounts at the project-level](https://docs.pinecone.io/guides/assistant/admin/manage-project-service-accounts.md): Enable programmatic access with project-level service accounts. - [Manage projects](https://docs.pinecone.io/guides/assistant/admin/manage-projects.md): View, rename, and delete projects in your organization. - [Monitor usage and cost](https://docs.pinecone.io/guides/assistant/admin/monitor-spend-and-usage.md): Set monthly spend alerts and monitor usage across your organization. - [Organizations overview](https://docs.pinecone.io/guides/assistant/admin/organizations-overview.md): Understand organization structure, projects, and billing. - [Projects overview](https://docs.pinecone.io/guides/assistant/admin/projects-overview.md): Learn about projects, roles, and collaboration. - [Security overview](https://docs.pinecone.io/guides/assistant/admin/security-overview.md): Understand Pinecone's security features, including authentication, encryption, and audit logs. - [Upgrade your plan](https://docs.pinecone.io/guides/assistant/admin/upgrade-billing-plan.md): Upgrade to a paid plan to access advanced features and limits. - [Chat through the OpenAI-compatible interface](https://docs.pinecone.io/guides/assistant/chat-through-the-openai-compatible-interface.md): Integrate OpenAI-compatible chat interface with Pinecone Assistant. - [Chat through the standard interface](https://docs.pinecone.io/guides/assistant/chat-with-assistant.md): Chat with your assistant using the standard interface and API. - [Context snippets overview](https://docs.pinecone.io/guides/assistant/context-snippets-overview.md): Retrieve context snippets from your assistant's knowledge base. - [Create an assistant](https://docs.pinecone.io/guides/assistant/create-assistant.md): Create and deploy a Pinecone Assistant for your knowledge base. - [Evaluate answers](https://docs.pinecone.io/guides/assistant/evaluate-answers.md): Measure assistant response quality with LLM-based evaluation. - [Evaluation overview](https://docs.pinecone.io/guides/assistant/evaluation-overview.md): Learn about evaluating the correctness and completeness of assistant responses. - [Files in Pinecone Assistant](https://docs.pinecone.io/guides/assistant/files-overview.md): Understand supported file types and metadata in Pinecone Assistant. - [Manage assistants](https://docs.pinecone.io/guides/assistant/manage-assistants.md): View, update, and delete, and check the status of assistants. - [Manage files](https://docs.pinecone.io/guides/assistant/manage-files.md): List, check status, and delete files from your assistant. - [Use an Assistant MCP server](https://docs.pinecone.io/guides/assistant/mcp-server.md): Connect AI agents to Pinecone Assistant via Model Context Protocol. - [Multimodal context for assistants](https://docs.pinecone.io/guides/assistant/multimodal.md): Process images and charts in PDFs with multimodal assistants. - [Pinecone Assistant](https://docs.pinecone.io/guides/assistant/overview.md): Pinecone Assistant is a service that allow you to build production-grade chat and agent-based applications quickly. - [Pricing and limits](https://docs.pinecone.io/guides/assistant/pricing-and-limits.md): Understand Pinecone Assistant pricing and service limits. - [Pinecone Assistant: n8n quickstart](https://docs.pinecone.io/guides/assistant/quickstart/n8n-quickstart.md): Create an n8n workflow to chat with documents using Pinecone Assistant and OpenAI. - [Pinecone Assistant: SDK quickstart](https://docs.pinecone.io/guides/assistant/quickstart/sdk-quickstart.md): Use a Pinecone SDK to create an assistant, upload documents, and chat with the assistant. - [Retrieve context snippets](https://docs.pinecone.io/guides/assistant/retrieve-context-snippets.md): Access relevant context and citations from Pinecone Assistant. - [Upload files](https://docs.pinecone.io/guides/assistant/upload-files.md): Upload local files to an assistant. - [Concepts](https://docs.pinecone.io/guides/get-started/concepts.md): Understand concepts in Pinecone and how they relate to each other. - [Architecture](https://docs.pinecone.io/guides/get-started/database-architecture.md): Learn how Pinecone's architecture enables fast, relevant vector search at any scale. - [Pinecone documentation](https://docs.pinecone.io/guides/get-started/overview.md): Pinecone is the leading vector database for building accurate and performant AI applications at scale in production. - [Quickstart](https://docs.pinecone.io/guides/get-started/quickstart.md): Get started with Pinecone manually, with AI assistance, or with no-code tools. - [Test Pinecone at scale](https://docs.pinecone.io/guides/get-started/test-at-scale.md): Test Pinecone with a real-world dataset and semantic search workload. - [Check data freshness](https://docs.pinecone.io/guides/index-data/check-data-freshness.md): Monitor data freshness in Pinecone using log sequence numbers and vector counts. - [Create an index](https://docs.pinecone.io/guides/index-data/create-an-index.md): Create dense or sparse indexes for semantic and lexical search. - [Data ingestion overview](https://docs.pinecone.io/guides/index-data/data-ingestion-overview.md): Learn about the different ways to ingest data into Pinecone. - [Data modeling](https://docs.pinecone.io/guides/index-data/data-modeling.md): Learn how to structure records for efficient data retrieval and management in Pinecone. - [Dedicated Read Nodes](https://docs.pinecone.io/guides/index-data/dedicated-read-nodes.md): Dedicated read nodes use provisioned hardware for read operations, providing predictable, low-latency performance at high query volumes. - [Implement multitenancy](https://docs.pinecone.io/guides/index-data/implement-multitenancy.md): Use namespaces to isolate tenant data securely. - [Import records](https://docs.pinecone.io/guides/index-data/import-data.md): Import large datasets efficiently from S3, GCS, or Azure into Pinecone indexes. - [Indexing overview](https://docs.pinecone.io/guides/index-data/indexing-overview.md): Understand key concepts related to indexing data in Pinecone. - [Upsert records](https://docs.pinecone.io/guides/index-data/upsert-data.md): Add or update records in Pinecone indexes and manage data with namespaces. - [Back up a pod-based index](https://docs.pinecone.io/guides/indexes/pods/back-up-a-pod-based-index.md): Backup pod-based indexes using Pinecone collections - [Choose a pod type and size](https://docs.pinecone.io/guides/indexes/pods/choose-a-pod-type-and-size.md): Select the right pod configuration for your workload - [Create a pod-based index](https://docs.pinecone.io/guides/indexes/pods/create-a-pod-based-index.md): Create and configure a pod-based Pinecone index - [Manage pod-based indexes](https://docs.pinecone.io/guides/indexes/pods/manage-pod-based-indexes.md): List, describe, and configure pod-based indexes - [Migrate a pod-based index to serverless](https://docs.pinecone.io/guides/indexes/pods/migrate-a-pod-based-index-to-serverless.md): Migrate existing pod indexes to cost-effective serverless - [Restore a pod-based index](https://docs.pinecone.io/guides/indexes/pods/restore-a-pod-based-index.md): Restore pod-based indexes from collections - [Scale pod-based indexes](https://docs.pinecone.io/guides/indexes/pods/scale-pod-based-indexes.md): Scale indexes vertically or horizontally as needed - [Understanding collections](https://docs.pinecone.io/guides/indexes/pods/understanding-collections.md): Create static backups of pod-based indexes with collections - [Understanding pod-based indexes](https://docs.pinecone.io/guides/indexes/pods/understanding-pod-based-indexes.md): Learn about pod-based index architecture and types - [Manage cost](https://docs.pinecone.io/guides/manage-cost/manage-cost.md): Learn strategies for managing cost in Pinecone. - [Monitor usage and costs](https://docs.pinecone.io/guides/manage-cost/monitor-usage-and-costs.md): Monitor usage and costs for your Pinecone organization and indexes. - [Understanding cost](https://docs.pinecone.io/guides/manage-cost/understanding-cost.md): Understand how costs are incurred in Pinecone. - [Back up an index](https://docs.pinecone.io/guides/manage-data/back-up-an-index.md): Create backups of serverless indexes for protection - [Backups overview](https://docs.pinecone.io/guides/manage-data/backups-overview.md): Learn about backups of serverless indexes in Pinecone. - [Delete records](https://docs.pinecone.io/guides/manage-data/delete-data.md): Delete records by ID or metadata filter from indexes - [Fetch records](https://docs.pinecone.io/guides/manage-data/fetch-data.md): Retrieve complete records by ID or metadata filter. - [List record IDs](https://docs.pinecone.io/guides/manage-data/list-record-ids.md): List the IDS of records in an index namespace. - [Manage serverless indexes](https://docs.pinecone.io/guides/manage-data/manage-indexes.md): List, describe, and configure serverless indexes. - [Manage namespaces](https://docs.pinecone.io/guides/manage-data/manage-namespaces.md): Create and manage namespaces in serverless indexes. - [Restore an index](https://docs.pinecone.io/guides/manage-data/restore-an-index.md): Restore serverless indexes from backup snapshots. - [Target an index](https://docs.pinecone.io/guides/manage-data/target-an-index.md): Target an index by host or name for data operations such as upsert and query. - [Update records](https://docs.pinecone.io/guides/manage-data/update-data.md): Update vectors and metadata for existing records - [Integrate with Amazon S3](https://docs.pinecone.io/guides/operations/integrations/integrate-with-amazon-s3.md): Set up Amazon S3 integrationfor data import and audit logs. - [Integrate with Azure Blob Storage](https://docs.pinecone.io/guides/operations/integrations/integrate-with-azure-blob-storage.md): Set up Azure Blob Storage integration for data import. - [Integrate with Google Cloud Storage](https://docs.pinecone.io/guides/operations/integrations/integrate-with-google-cloud-storage.md): Integrate Google Cloud Storage for bulk data import - [Manage storage integrations](https://docs.pinecone.io/guides/operations/integrations/manage-storage-integrations.md): Update and manage cloud storage integrations. - [Local development with Pinecone Local](https://docs.pinecone.io/guides/operations/local-development.md): Develop locally with an in-memory Pinecone emulator. - [Use the Pinecone MCP server](https://docs.pinecone.io/guides/operations/mcp-server.md): Use Pinecone MCP server for AI agent integration. - [Decrease latency](https://docs.pinecone.io/guides/optimize/decrease-latency.md): Learn techniques to decrease latency for search and upsert operations. - [Increase search relevance](https://docs.pinecone.io/guides/optimize/increase-relevance.md): Learn techniques to improve search result quality. - [Increase throughput](https://docs.pinecone.io/guides/optimize/increase-throughput.md): Learn techniques to improve data operation performance and query throughput. - [Access your invoices](https://docs.pinecone.io/guides/organizations/manage-billing/access-your-invoices.md): View and download organization billing invoices. - [Change your payment method](https://docs.pinecone.io/guides/organizations/manage-billing/change-payment-method.md): Update your billing payment method. - [Downgrade your plan](https://docs.pinecone.io/guides/organizations/manage-billing/downgrade-billing-plan.md): Downgrade from a paid plan to the free Starter plan. - [Download a usage report](https://docs.pinecone.io/guides/organizations/manage-billing/download-usage-report.md): Download detailed usage and cost reports. - [Standard trial](https://docs.pinecone.io/guides/organizations/manage-billing/standard-trial.md): Get $300 credits for 21 days with the Standard plan trial. - [Upgrade your plan](https://docs.pinecone.io/guides/organizations/manage-billing/upgrade-billing-plan.md): Upgrade to a paid plan to access advanced features and limits. - [Manage organization members](https://docs.pinecone.io/guides/organizations/manage-organization-members.md): Add and manage organization members and roles. - [Manage service accounts at the organization-level](https://docs.pinecone.io/guides/organizations/manage-service-accounts.md): Create service accounts for organization-level API access. - [Understanding organizations](https://docs.pinecone.io/guides/organizations/understanding-organizations.md): Understand organization structure, projects, and billing. - [CI/CD with Pinecone Local and GitHub Actions](https://docs.pinecone.io/guides/production/automated-testing.md): Test Pinecone integration with CI/CD workflows. - [Bring your own cloud](https://docs.pinecone.io/guides/production/bring-your-own-cloud.md): Deploy Pinecone in your AWS or GCP account - [Configure audit logs](https://docs.pinecone.io/guides/production/configure-audit-logs.md): Enable audit logging to Amazon S3 for compliance - [Configure customer-managed encryption keys](https://docs.pinecone.io/guides/production/configure-cmek.md): Use customer-managed encryption keys with AWS KMS. - [Configure SSO with Okta](https://docs.pinecone.io/guides/production/configure-single-sign-on/okta.md): Configure SAML SSO with Okta for enterprise. - [Configure Private Endpoints for AWS PrivateLink](https://docs.pinecone.io/guides/production/connect-to-aws-privatelink.md): Secure Pinecone with private VPC endpoints. - [Data deletion on Pinecone](https://docs.pinecone.io/guides/production/data-deletion.md): Understand Pinecone's secure data deletion process. - [Error handling](https://docs.pinecone.io/guides/production/error-handling.md): Handle errors with retry logic and best practices. - [Monitor performance](https://docs.pinecone.io/guides/production/monitoring.md): Monitor performance metrics in the Pinecone console or with Prometheus or Datadog. - [Production checklist](https://docs.pinecone.io/guides/production/production-checklist.md): Prepare your indexes for production with best practices. - [Security overview](https://docs.pinecone.io/guides/production/security-overview.md): Understand Pinecone's security features, including authentication, encryption, and audit logs. - [Create a project](https://docs.pinecone.io/guides/projects/create-a-project.md): Create a new Pinecone project in your organization. - [Manage API keys](https://docs.pinecone.io/guides/projects/manage-api-keys.md): Create and manage API keys with custom permissions. - [Manage project members](https://docs.pinecone.io/guides/projects/manage-project-members.md): Add and manage project members with role-based access control. - [Manage projects](https://docs.pinecone.io/guides/projects/manage-projects.md): View, rename, and delete projects in your organization. - [Manage service accounts at the project-level](https://docs.pinecone.io/guides/projects/manage-service-accounts.md): Enable service accounts for programmatic API access. - [Understanding projects](https://docs.pinecone.io/guides/projects/understanding-projects.md): Learn about projects, environments, and member roles. - [Filter by metadata](https://docs.pinecone.io/guides/search/filter-by-metadata.md): Narrow search results with metadata filtering. - [Hybrid search](https://docs.pinecone.io/guides/search/hybrid-search.md): Combine semantic and lexical search for better results. - [Lexical search](https://docs.pinecone.io/guides/search/lexical-search.md): Perform keyword-based search on sparse indexes - [Rerank results](https://docs.pinecone.io/guides/search/rerank-results.md): Improve the quality of results with reranking. - [Search overview](https://docs.pinecone.io/guides/search/search-overview.md): Explore semantic, lexical, and hybrid search options. - [Semantic search](https://docs.pinecone.io/guides/search/semantic-search.md): Find semantically similar records using dense vectors. - [AI Engine](https://docs.pinecone.io/integrations/ai-engine.md) - [Airbyte](https://docs.pinecone.io/integrations/airbyte.md) - [Amazon Bedrock](https://docs.pinecone.io/integrations/amazon-bedrock.md): Pinecone as a Knowledge Base for Amazon Bedrock - [Amazon SageMaker](https://docs.pinecone.io/integrations/amazon-sagemaker.md) - [Anyscale](https://docs.pinecone.io/integrations/anyscale.md) - [Apify](https://docs.pinecone.io/integrations/apify.md) - [Aryn](https://docs.pinecone.io/integrations/aryn.md) - [AWS Marketplace](https://docs.pinecone.io/integrations/aws-marketplace.md) - [Box](https://docs.pinecone.io/integrations/box.md) - [Attribute usage to your integration](https://docs.pinecone.io/integrations/build-integration/attribute-usage-to-your-integration.md) - [Connect your users to Pinecone](https://docs.pinecone.io/integrations/build-integration/connect-your-users-to-pinecone.md) - [Integration ecosystem](https://docs.pinecone.io/integrations/build-integration/integration-ecosystem.md) - [Cloudera AI](https://docs.pinecone.io/integrations/cloudera.md): Vector embedding, RAG, and semantic search at scale - [Cohere](https://docs.pinecone.io/integrations/cohere.md): Using Cohere and Pinecone to generate and index high-quality vector embeddings - [Confluent](https://docs.pinecone.io/integrations/confluent.md) - [Context Data](https://docs.pinecone.io/integrations/context-data.md) - [Databricks](https://docs.pinecone.io/integrations/databricks.md): Using Databricks and Pinecone to create and index vector embeddings at scale - [Datadog](https://docs.pinecone.io/integrations/datadog.md): Monitoring Pinecone with Datadog - [Datavolo](https://docs.pinecone.io/integrations/datavolo.md) - [Estuary](https://docs.pinecone.io/integrations/estuary.md) - [Fleak](https://docs.pinecone.io/integrations/fleak.md) - [FlowiseAI](https://docs.pinecone.io/integrations/flowise.md) - [Gathr](https://docs.pinecone.io/integrations/gathr.md) - [Genkit](https://docs.pinecone.io/integrations/genkit.md) - [GitHub Copilot](https://docs.pinecone.io/integrations/github-copilot.md) - [Google Cloud Marketplace](https://docs.pinecone.io/integrations/google-cloud-marketplace.md) - [Haystack](https://docs.pinecone.io/integrations/haystack.md): 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.md): Using Hugging Face Inference Endpoints and Pinecone to generate and index high-quality vector embeddings - [Instill AI](https://docs.pinecone.io/integrations/instill.md) - [Jina AI](https://docs.pinecone.io/integrations/jina.md) - [LangChain](https://docs.pinecone.io/integrations/langchain.md): Using LangChain and Pinecone to add knowledge to LLMs - [Langtrace](https://docs.pinecone.io/integrations/langtrace.md) - [LlamaIndex](https://docs.pinecone.io/integrations/llamaindex.md): Using LlamaIndex and Pinecone to build semantic search and RAG applications - [Matillion](https://docs.pinecone.io/integrations/matillion.md) - [Microsoft Marketplace](https://docs.pinecone.io/integrations/microsoft-marketplace.md) - [n8n](https://docs.pinecone.io/integrations/n8n.md): n8n is a workflow automation platform offering technical teams code-level flexibility at no-code speed. - [New Relic](https://docs.pinecone.io/integrations/new-relic.md) - [Nexla](https://docs.pinecone.io/integrations/nexla.md) - [Nuclia](https://docs.pinecone.io/integrations/nuclia.md) - [OctoAI](https://docs.pinecone.io/integrations/octoai.md) - [OpenAI](https://docs.pinecone.io/integrations/openai.md): 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.md): 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.md) - [Redpanda](https://docs.pinecone.io/integrations/redpanda.md) - [Snowflake](https://docs.pinecone.io/integrations/snowflake.md) - [StreamNative](https://docs.pinecone.io/integrations/streamnative.md) - [Terraform](https://docs.pinecone.io/integrations/terraform.md) - [Traceloop](https://docs.pinecone.io/integrations/traceloop.md) - [TruLens](https://docs.pinecone.io/integrations/trulens.md): Using TruLens and Pinecone to evaluate grounded LLM applications - [Twelve Labs](https://docs.pinecone.io/integrations/twelve-labs.md) - [Unstructured](https://docs.pinecone.io/integrations/unstructured.md) - [Vercel](https://docs.pinecone.io/integrations/vercel.md) - [VoltAgent](https://docs.pinecone.io/integrations/voltagent.md) - [Voyage AI](https://docs.pinecone.io/integrations/voyage.md): Using Voyage AI and Pinecone to generate and index high-quality vector embeddings - [Zapier](https://docs.pinecone.io/integrations/zapier.md) - [Model Gallery](https://docs.pinecone.io/models/overview.md): 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. - [Create an API key](https://docs.pinecone.io/reference/api/2025-10/admin-assistant/create_api_key.md): Create a new API key for a project. Developers can use the API key to authenticate requests to Pinecone's Data Plane and Control Plane APIs. - [Create a new project](https://docs.pinecone.io/reference/api/2025-10/admin-assistant/create_project.md): Creates a new project. - [Delete an API key](https://docs.pinecone.io/reference/api/2025-10/admin-assistant/delete_api_key.md): Delete an API key from a project. - [Delete a project](https://docs.pinecone.io/reference/api/2025-10/admin-assistant/delete_project.md): Delete a project and all its associated configuration. Before deleting a project, you must delete all indexes, assistants, backups, and collections associated with the project. Other project resources, such as API keys, are automatically deleted when the project is deleted. - [Get API key details](https://docs.pinecone.io/reference/api/2025-10/admin-assistant/fetch_api_key.md): Get the details of an API key, excluding the API key secret. - [Get project details](https://docs.pinecone.io/reference/api/2025-10/admin-assistant/fetch_project.md): Get details about a project. - [Create an access token](https://docs.pinecone.io/reference/api/2025-10/admin-assistant/get_token.md): Obtain an access token for a service account using the OAuth2 client credentials flow. An access token is needed to authorize requests to the Pinecone Admin API. The host domain for OAuth endpoints is `login.pinecone.io`. - [List API keys](https://docs.pinecone.io/reference/api/2025-10/admin-assistant/list_api_keys.md): List all API keys in a project. - [List projects](https://docs.pinecone.io/reference/api/2025-10/admin-assistant/list_projects.md): List all projects in an organization. - [Update an API key](https://docs.pinecone.io/reference/api/2025-10/admin-assistant/update_api_key.md): Update the name and roles of an API key. - [Update a project](https://docs.pinecone.io/reference/api/2025-10/admin-assistant/update_project.md): Update a project's configuration details. You can update the project's name, maximum number of Pods, or enable encryption with a customer-managed encryption key (CMEK). - [Create an API key](https://docs.pinecone.io/reference/api/2025-10/admin/create_api_key.md): Create a new API key for a project. Developers can use the API key to authenticate requests to Pinecone's Data Plane and Control Plane APIs. - [Create a new project](https://docs.pinecone.io/reference/api/2025-10/admin/create_project.md): Creates a new project. - [Delete an API key](https://docs.pinecone.io/reference/api/2025-10/admin/delete_api_key.md): Delete an API key from a project. - [Delete a project](https://docs.pinecone.io/reference/api/2025-10/admin/delete_project.md): Delete a project and all its associated configuration. Before deleting a project, you must delete all indexes, assistants, backups, and collections associated with the project. Other project resources, such as API keys, are automatically deleted when the project is deleted. - [Get API key details](https://docs.pinecone.io/reference/api/2025-10/admin/fetch_api_key.md): Get the details of an API key, excluding the API key secret. - [Get project details](https://docs.pinecone.io/reference/api/2025-10/admin/fetch_project.md): Get details about a project. - [Create an access token](https://docs.pinecone.io/reference/api/2025-10/admin/get_token.md): Obtain an access token for a service account using the OAuth2 client credentials flow. An access token is needed to authorize requests to the Pinecone Admin API. The host domain for OAuth endpoints is `login.pinecone.io`. - [List API keys](https://docs.pinecone.io/reference/api/2025-10/admin/list_api_keys.md): List all API keys in a project. - [List projects](https://docs.pinecone.io/reference/api/2025-10/admin/list_projects.md): List all projects in an organization. - [Update an API key](https://docs.pinecone.io/reference/api/2025-10/admin/update_api_key.md): Update the name and roles of an API key. - [Update a project](https://docs.pinecone.io/reference/api/2025-10/admin/update_project.md): Update a project's configuration details. You can update the project's name, maximum number of Pods, or enable encryption with a customer-managed encryption key (CMEK). - [Chat with an assistant](https://docs.pinecone.io/reference/api/2025-10/assistant/chat_assistant.md): Chat with an 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 OpenAI-compatible chat interface. For guidance and examples, see [Chat with an assistant](https://docs.pinecone.io/guides/assistant/chat-with-assistant). - [Chat through an OpenAI-compatible interface](https://docs.pinecone.io/reference/api/2025-10/assistant/chat_completion_assistant.md): Chat with an 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 standard chat interface. For guidance and examples, see [Chat with an assistant](https://docs.pinecone.io/guides/assistant/chat-with-assistant). - [Retrieve context from an assistant](https://docs.pinecone.io/reference/api/2025-10/assistant/context_assistant.md): Retrieve context snippets from an assistant to use as part of RAG or any agentic flow. For guidance and examples, see [Retrieve context snippets](https://docs.pinecone.io/guides/assistant/retrieve-context-snippets). - [Create an assistant](https://docs.pinecone.io/reference/api/2025-10/assistant/create_assistant.md): Create an assistant. This is where you specify the underlying training model, which cloud provider you would like to deploy with, and more. For guidance and examples, see [Create an assistant](https://docs.pinecone.io/guides/assistant/create-assistant) - [Delete an assistant](https://docs.pinecone.io/reference/api/2025-10/assistant/delete_assistant.md): Delete an existing assistant. For guidance and examples, see [Manage assistants](https://docs.pinecone.io/guides/assistant/manage-assistants#delete-an-assistant) - [Delete an uploaded file](https://docs.pinecone.io/reference/api/2025-10/assistant/delete_file.md): Delete an uploaded file from an assistant. For guidance and examples, see [Manage files](https://docs.pinecone.io/guides/assistant/manage-files#delete-a-file). - [Check assistant status](https://docs.pinecone.io/reference/api/2025-10/assistant/describe_assistant.md): Get the status of an assistant. For guidance and examples, see [Manage assistants](https://docs.pinecone.io/guides/assistant/manage-assistants#get-the-status-of-an-assistant) - [Describe a file upload](https://docs.pinecone.io/reference/api/2025-10/assistant/describe_file.md): Get the status and metadata of a file uploaded to an assistant. For guidance and examples, see [Manage files](https://docs.pinecone.io/guides/assistant/manage-files#get-the-status-of-a-file). - [List assistants](https://docs.pinecone.io/reference/api/2025-10/assistant/list_assistants.md): List of all assistants in a project. For guidance and examples, see [Manage assistants](https://docs.pinecone.io/guides/assistant/manage-assistants#list-assistants-for-a-project). - [List Files](https://docs.pinecone.io/reference/api/2025-10/assistant/list_files.md): List all files in an assistant, with an option to filter files with metadata. For guidance and examples, see [Manage files](https://docs.pinecone.io/guides/assistant/manage-files#list-files-in-an-assistant). - [Evaluate an answer](https://docs.pinecone.io/reference/api/2025-10/assistant/metrics_alignment.md): Evaluate the correctness and completeness of a response from an assistant or a RAG system. 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. For guidance and examples, see [Evaluate answers](https://docs.pinecone.io/guides/assistant/evaluate-answers). - [Update an assistant](https://docs.pinecone.io/reference/api/2025-10/assistant/update_assistant.md): Update an existing assistant. You can modify the assistant's instructions. For guidance and examples, see [Manage assistants](https://docs.pinecone.io/guides/assistant/manage-assistants#add-instructions-to-an-assistant). - [Upload file to assistant](https://docs.pinecone.io/reference/api/2025-10/assistant/upload_file.md): Upload a file to the specified assistant. For guidance and examples, see [Manage files](https://docs.pinecone.io/guides/assistant/manage-files#upload-a-local-file). - [Configure an index](https://docs.pinecone.io/reference/api/2025-10/control-plane/configure_index.md): Configure an existing index. For guidance and examples, see [Manage indexes](https://docs.pinecone.io/guides/manage-data/manage-indexes). - [Create a backup of an index](https://docs.pinecone.io/reference/api/2025-10/control-plane/create_backup.md): Create a backup of an index. - [Create a collection](https://docs.pinecone.io/reference/api/2025-10/control-plane/create_collection.md): Create a Pinecone collection. Serverless indexes do not support collections. - [Create an index with integrated embedding](https://docs.pinecone.io/reference/api/2025-10/control-plane/create_for_model.md): Create an index with integrated embedding. With this type of index, you provide source text, and Pinecone uses a [hosted embedding model](https://docs.pinecone.io/guides/index-data/create-an-index#embedding-models) to convert the text automatically during [upsert](https://docs.pinecone.io/reference/api/2025-10/data-plane/upsert_records) and [search](https://docs.pinecone.io/reference/api/2025-10/data-plane/search_records). For guidance and examples, see [Create an index](https://docs.pinecone.io/guides/index-data/create-an-index#integrated-embedding). - [Create an index](https://docs.pinecone.io/reference/api/2025-10/control-plane/create_index.md): Create 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/index-data/create-an-index). - [Create an index from a backup](https://docs.pinecone.io/reference/api/2025-10/control-plane/create_index_from_backup.md): Create an index from a backup. - [Delete a backup](https://docs.pinecone.io/reference/api/2025-10/control-plane/delete_backup.md): Delete a backup. - [Delete a collection](https://docs.pinecone.io/reference/api/2025-10/control-plane/delete_collection.md): Delete an existing collection. Serverless indexes do not support collections. - [Delete an index](https://docs.pinecone.io/reference/api/2025-10/control-plane/delete_index.md): Delete an existing index. - [Describe a backup](https://docs.pinecone.io/reference/api/2025-10/control-plane/describe_backup.md): Get a description of a backup. - [Describe a collection](https://docs.pinecone.io/reference/api/2025-10/control-plane/describe_collection.md): Get a description of a collection. Serverless indexes do not support collections. - [Describe an index](https://docs.pinecone.io/reference/api/2025-10/control-plane/describe_index.md): Get a description of an index. - [Describe a restore job](https://docs.pinecone.io/reference/api/2025-10/control-plane/describe_restore_job.md): Get a description of a restore job. - [List collections](https://docs.pinecone.io/reference/api/2025-10/control-plane/list_collections.md): List all collections in a project. Serverless indexes do not support collections. - [List backups for an index](https://docs.pinecone.io/reference/api/2025-10/control-plane/list_index_backups.md): List all backups for an index. - [List indexes](https://docs.pinecone.io/reference/api/2025-10/control-plane/list_indexes.md): List all indexes in a project. - [List backups for all indexes in a project](https://docs.pinecone.io/reference/api/2025-10/control-plane/list_project_backups.md): List all backups for a project. - [List restore jobs](https://docs.pinecone.io/reference/api/2025-10/control-plane/list_restore_jobs.md): List all restore jobs for a project. - [Cancel an import](https://docs.pinecone.io/reference/api/2025-10/data-plane/cancel_import.md): Cancel 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/index-data/import-data). - [Create a namespace](https://docs.pinecone.io/reference/api/2025-10/data-plane/createnamespace.md): Create a namespace in a serverless index. For guidance and examples, see [Manage namespaces](https://docs.pinecone.io/guides/manage-data/manage-namespaces). **Note:** This operation is not supported for pod-based indexes. - [Delete vectors](https://docs.pinecone.io/reference/api/2025-10/data-plane/delete.md): Delete vectors by id from a single namespace. For guidance and examples, see [Delete data](https://docs.pinecone.io/guides/manage-data/delete-data). - [Delete a namespace](https://docs.pinecone.io/reference/api/2025-10/data-plane/deletenamespace.md): Delete a namespace from a serverless index. Deleting a namespace is irreversible; all data in the namespace is permanently deleted. For guidance and examples, see [Manage namespaces](https://docs.pinecone.io/guides/manage-data/manage-namespaces). **Note:** This operation is not supported for pod-based indexes. - [Describe an import](https://docs.pinecone.io/reference/api/2025-10/data-plane/describe_import.md): Return details of a specific import operation. For guidance and examples, see [Import data](https://docs.pinecone.io/guides/index-data/import-data). - [Get index stats](https://docs.pinecone.io/reference/api/2025-10/data-plane/describeindexstats.md): Return 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. - [Describe a namespace](https://docs.pinecone.io/reference/api/2025-10/data-plane/describenamespace.md): Describe a namespace in a serverless index, including the total number of vectors in the namespace. For guidance and examples, see [Manage namespaces](https://docs.pinecone.io/guides/manage-data/manage-namespaces). **Note:** This operation is not supported for pod-based indexes. - [Fetch vectors](https://docs.pinecone.io/reference/api/2025-10/data-plane/fetch.md): Look up and return vectors by ID from a single namespace. The returned vectors include the vector data and/or metadata. For on-demand indexes, since vector values are retrieved from object storage, fetch operations may have increased latency. If you only need metadata or IDs, consider using the query operation with `includeValues` set to `false` instead. For guidance and examples, see [Fetch data](https://docs.pinecone.io/guides/manage-data/fetch-data). - [Fetch vectors by metadata](https://docs.pinecone.io/reference/api/2025-10/data-plane/fetch_by_metadata.md): Look up and return vectors by metadata filter 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/manage-data/fetch-data). - [List vector IDs](https://docs.pinecone.io/reference/api/2025-10/data-plane/list.md): List 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. 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/manage-data/list-record-ids). **Note:** `list` is supported only for serverless indexes. - [List imports](https://docs.pinecone.io/reference/api/2025-10/data-plane/list_imports.md): List 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/index-data/import-data). - [List namespaces](https://docs.pinecone.io/reference/api/2025-10/data-plane/listnamespaces.md): List all namespaces in a serverless index. Up to 100 namespaces are returned at a time by default, in sorted order (bitwise “C” collation). If the `limit` parameter is set, up to that number of namespaces are returned instead. Whenever there are additional namespaces to return, the response also includes a `pagination_token` that you can use to get the next batch of namespaces. When the response does not include a `pagination_token`, there are no more namespaces to return. For guidance and examples, see [Manage namespaces](https://docs.pinecone.io/guides/manage-data/manage-namespaces). **Note:** This operation is not supported for pod-based indexes. - [Search with a vector](https://docs.pinecone.io/reference/api/2025-10/data-plane/query.md): Search 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, examples, and limits, see [Search](https://docs.pinecone.io/guides/search/search-overview). - [Search with text](https://docs.pinecone.io/reference/api/2025-10/data-plane/search_records.md): Search a namespace with a query text, query vector, or record ID and return the most similar records, along with their similarity scores. Optionally, rerank the initial results based on their relevance to the query. Searching with text is supported only for indexes with [integrated embedding](https://docs.pinecone.io/guides/index-data/indexing-overview#vector-embedding). Searching with a query vector or record ID is supported for all indexes. For guidance and examples, see [Search](https://docs.pinecone.io/guides/search/search-overview). - [Start import](https://docs.pinecone.io/reference/api/2025-10/data-plane/start_import.md): Start an asynchronous import of vectors from object storage into an index. For guidance and examples, see [Import data](https://docs.pinecone.io/guides/index-data/import-data). - [Update a vector](https://docs.pinecone.io/reference/api/2025-10/data-plane/update.md): Update 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/manage-data/update-data). - [Upsert vectors](https://docs.pinecone.io/reference/api/2025-10/data-plane/upsert.md): Upsert vectors into a namespace. If a new value is upserted for an existing vector ID, it will overwrite the previous value. For guidance, examples, and limits, see [Upsert data](https://docs.pinecone.io/guides/index-data/upsert-data). - [Upsert text](https://docs.pinecone.io/reference/api/2025-10/data-plane/upsert_records.md): Upsert text into a namespace. Pinecone converts the text to vectors automatically using the hosted embedding model associated with the index. Upserting text is supported only for [indexes with integrated embedding](https://docs.pinecone.io/reference/api/2025-01/control-plane/create_for_model). For guidance, examples, and limits, see [Upsert data](https://docs.pinecone.io/guides/index-data/upsert-data). - [Describe a model](https://docs.pinecone.io/reference/api/2025-10/inference/describe_model.md): Get a description of a model hosted by Pinecone. You can use hosted models as an integrated part of Pinecone operations or for standalone embedding and reranking. For more details, see [Vector embedding](https://docs.pinecone.io/guides/index-data/indexing-overview#vector-embedding) and [Rerank results](https://docs.pinecone.io/guides/search/rerank-results). - [Generate vectors](https://docs.pinecone.io/reference/api/2025-10/inference/generate-embeddings.md): Generate vector embeddings for input data. This endpoint uses Pinecone's [hosted embedding models](https://docs.pinecone.io/guides/index-data/create-an-index#embedding-models). - [List available models](https://docs.pinecone.io/reference/api/2025-10/inference/list_models.md): List the embedding and reranking models hosted by Pinecone. You can use hosted models as an integrated part of Pinecone operations or for standalone embedding and reranking. For more details, see [Vector embedding](https://docs.pinecone.io/guides/index-data/indexing-overview#vector-embedding) and [Rerank results](https://docs.pinecone.io/guides/search/rerank-results). - [Rerank results](https://docs.pinecone.io/reference/api/2025-10/inference/rerank.md): Rerank results according to their relevance to a query. For guidance and examples, see [Rerank results](https://docs.pinecone.io/guides/search/rerank-results). - [Pinecone Assistant limits](https://docs.pinecone.io/reference/api/assistant/assistant-limits.md) - [Authentication](https://docs.pinecone.io/reference/api/assistant/authentication.md) - [Assistant API reference](https://docs.pinecone.io/reference/api/assistant/introduction.md) - [Authentication](https://docs.pinecone.io/reference/api/authentication.md) - [Pinecone Database limits](https://docs.pinecone.io/reference/api/database-limits.md) - [Errors](https://docs.pinecone.io/reference/api/errors.md) - [API reference](https://docs.pinecone.io/reference/api/introduction.md) - [Known limitations](https://docs.pinecone.io/reference/api/known-limitations.md) - [API versioning](https://docs.pinecone.io/reference/api/versioning.md) - [Pinecone Assistant architecture](https://docs.pinecone.io/reference/architecture/assistant-architecture.md) - [CLI authentication](https://docs.pinecone.io/reference/cli/authentication.md) - [CLI command reference](https://docs.pinecone.io/reference/cli/command-reference.md) - [CLI quickstart](https://docs.pinecone.io/reference/cli/quickstart.md) - [CLI target context](https://docs.pinecone.io/reference/cli/target-context.md) - [Introduction](https://docs.pinecone.io/reference/pinecone-sdks.md) - [Pinecone .NET SDK](https://docs.pinecone.io/reference/sdks/dotnet/overview.md) - [Reference](https://docs.pinecone.io/reference/sdks/dotnet/reference.md) - [Pinecone Go SDK](https://docs.pinecone.io/reference/sdks/go/overview.md) - [Reference](https://docs.pinecone.io/reference/sdks/go/reference.md) - [Pinecone Java SDK](https://docs.pinecone.io/reference/sdks/java/overview.md) - [Reference](https://docs.pinecone.io/reference/sdks/java/reference.md) - [Pinecone Node.js SDK](https://docs.pinecone.io/reference/sdks/node/overview.md) - [Reference](https://docs.pinecone.io/reference/sdks/node/reference.md) - [Pinecone Python SDK](https://docs.pinecone.io/reference/sdks/python/overview.md) - [Reference](https://docs.pinecone.io/reference/sdks/python/reference.md) - [Pinecone Rust SDK](https://docs.pinecone.io/reference/sdks/rust/overview.md) - [Reference](https://docs.pinecone.io/reference/sdks/rust/reference.md) - [Spark-Pinecone connector](https://docs.pinecone.io/reference/tools/pinecone-spark-connector.md) - [2022 releases](https://docs.pinecone.io/release-notes/2022.md) - [2023 releases](https://docs.pinecone.io/release-notes/2023.md) - [2024 releases](https://docs.pinecone.io/release-notes/2024.md) - [2025 releases](https://docs.pinecone.io/release-notes/2025.md) - [2026 releases](https://docs.pinecone.io/release-notes/2026.md) - [Feature availability](https://docs.pinecone.io/release-notes/feature-availability.md) - [Billing disputes and refunds](https://docs.pinecone.io/troubleshooting/billing-disputes-and-refunds.md) - [Contact Support](https://docs.pinecone.io/troubleshooting/contact-support.md) - [CORS Issues](https://docs.pinecone.io/troubleshooting/cors-issues.md) - [Create and manage vectors with metadata](https://docs.pinecone.io/troubleshooting/create-and-manage-vectors-with-metadata.md) - [Custom data processing agreements](https://docs.pinecone.io/troubleshooting/custom-data-processing-agreements.md) - [Debug model vs. Pinecone recall issues](https://docs.pinecone.io/troubleshooting/debug-model-vs-pinecone-recall-issues.md) - [Delete your account](https://docs.pinecone.io/troubleshooting/delete-your-account.md) - [Delete your organization](https://docs.pinecone.io/troubleshooting/delete-your-organization.md) - [Differences between Lexical and Semantic Search regarding relevancy](https://docs.pinecone.io/troubleshooting/differences-between-lexical-semantic-search.md) - [Embedding values changed when upserted](https://docs.pinecone.io/troubleshooting/embedding-values-changed-when-upserted.md) - [Error: Cannot import name 'Pinecone' from 'pinecone'](https://docs.pinecone.io/troubleshooting/error-cannot-import-name-pinecone.md) - [Error: Handshake read failed when connecting](https://docs.pinecone.io/troubleshooting/error-handshake-read-failed.md) - [Export indexes](https://docs.pinecone.io/troubleshooting/export-indexes.md) - [How to work with Support](https://docs.pinecone.io/troubleshooting/how-to-work-with-support.md) - [Serverless index creation error - max serverless indexes](https://docs.pinecone.io/troubleshooting/index-creation-error-max-serverless.md) - [Index creation error - missing spec parameter](https://docs.pinecone.io/troubleshooting/index-creation-error-missing-spec.md) - [Keep customer data separate in Pinecone](https://docs.pinecone.io/troubleshooting/keep-customer-data-separate.md) - [Limitations of querying by ID](https://docs.pinecone.io/troubleshooting/limitations-of-querying-by-id.md) - [Login code issues](https://docs.pinecone.io/troubleshooting/login-code-issues.md) - [Minimize latencies](https://docs.pinecone.io/troubleshooting/minimize-latencies.md) - [Python AttributeError: module pinecone has no attribute init](https://docs.pinecone.io/troubleshooting/module-pinecone-has-no-attribute-init.md) - [Node.js Troubleshooting](https://docs.pinecone.io/troubleshooting/nodejs-troubleshooting.md) - [Parallel queries](https://docs.pinecone.io/troubleshooting/parallel-queries.md) - [PineconeAttribute errors with LangChain](https://docs.pinecone.io/troubleshooting/pinecone-attribute-errors-with-langchain.md) - [Pinecone Support SLAs](https://docs.pinecone.io/troubleshooting/pinecone-support-slas.md) - [Remove a metadata field from a record](https://docs.pinecone.io/troubleshooting/remove-metadata-field.md) - [Restrictions on index names](https://docs.pinecone.io/troubleshooting/restrictions-on-index-names.md) - [Return all vectors in an index](https://docs.pinecone.io/troubleshooting/return-all-vectors-in-an-index.md) - [Serverless index connection errors](https://docs.pinecone.io/troubleshooting/serverless-index-connection-errors.md) - [Unable to pip install](https://docs.pinecone.io/troubleshooting/unable-to-pip-install.md) - [Wait for index creation to be complete](https://docs.pinecone.io/troubleshooting/wait-for-index-creation.md)