# Pinecone Docs: Pinecone Database > Official documentation for Pinecone's trusted AI knowledge platform, including Pinecone Database, Pinecone Assistant, and Pinecone Nexus. ## Pinecone Database - [Pinecone Database / Guides (104 pages)](https://docs.pinecone.io/_llms/pinecone-database/guides.txt): Documentation for Pinecone Database / Guides. - [Pinecone Database / Reference (368 pages)](https://docs.pinecone.io/_llms/pinecone-database/reference.txt): Documentation for Pinecone Database / Reference. ### Examples #### Examples - [Notebooks](https://docs.pinecone.io/examples/notebooks.md): Runnable Colab notebooks covering semantic search, lexical search, hybrid search, RAG, embeddings, reranking, and data ingestion with Pinecone. - [Sample apps](https://docs.pinecone.io/examples/sample-apps.md): Sample apps and tools built with Pinecone, including semantic search, multi-tenant RAG, multimodal search, Assistant chat, and pgvector migration. - [Reference architectures](https://docs.pinecone.io/examples/reference-architectures.md): Official AWS reference architecture for building high-scale production systems with Pinecone, including Pulumi IaC, documentation, and video tutorial. ### Models #### Models - [Pinecone model gallery](https://docs.pinecone.io/models/overview.md): Browse Pinecone's hosted embedding and reranking model gallery with details on dimensions, sequence length, pricing, and supported tasks. ### Integrations #### Connect an integration - [Integrations overview](https://docs.pinecone.io/integrations/overview.md): Browse Pinecone integrations across vector embedding providers, data ingestion tools, frameworks, and infrastructure to ship AI apps faster. ##### AI coding tools - [AI coding tools](https://docs.pinecone.io/integrations/ai-coding-tools.md): Use Pinecone with AI coding tools like Claude Code, Codex, and Cursor through the Pinecone MCP server, plugins, and agent skills. - [Agent Skills](https://docs.pinecone.io/integrations/agent-skills.md): Install the Pinecone Agent Skills library in any agentic IDE to manage indexes, run semantic search, and build RAG assistants with natural language. - [Claude Code plugin](https://docs.pinecone.io/integrations/claude-code.md): Install the official Pinecone plugin for Claude Code to manage indexes, run vector search, and build RAG assistants from the terminal with slash commands. - [Codex plugin](https://docs.pinecone.io/integrations/codex.md): Install the official Pinecone plugin for Codex to manage indexes, run vector search, and build RAG assistants from Codex using skills and MCP tools. - [Cursor plugin](https://docs.pinecone.io/integrations/cursor.md): Install the official Pinecone plugin for Cursor to manage indexes, run vector search, and build RAG apps from the editor using MCP and slash commands. ##### Data sources - [Airbyte](https://docs.pinecone.io/integrations/airbyte.md): Use the Airbyte Pinecone destination connector to build no-code ETL pipelines that embed source data and upsert vectors for semantic search and RAG. - [Apify](https://docs.pinecone.io/integrations/apify.md): Use the Apify Pinecone integration to crawl and scrape websites, embed the results, and upsert vectors for RAG and semantic search over web content. - [Aryn](https://docs.pinecone.io/integrations/aryn.md): Use Aryn Sycamore and the Partitioning Service with Pinecone to extract, chunk, and embed complex PDFs and documents for higher-accuracy RAG pipelines. - [Box](https://docs.pinecone.io/integrations/box.md): Connect Box folders to Pinecone Database to embed documents with Pinecone Inference and build RAG agents and semantic search over Box content. - [Confluent](https://docs.pinecone.io/integrations/confluent.md): Use the Pinecone Sink Connector for Confluent Kafka to stream events, embed them with LLMs, and upsert vectors for real-time semantic search and RAG. - [Databricks](https://docs.pinecone.io/integrations/databricks.md): Use Databricks and the Pinecone Spark connector to distribute embedding jobs across a cluster and upsert vectors at scale for semantic search and RAG. - [Estuary](https://docs.pinecone.io/integrations/estuary.md): Use the Estuary Pinecone connector to build real-time, millisecond-latency pipelines that incrementally embed source data for LLM search and RAG. - [Fleak](https://docs.pinecone.io/integrations/fleak.md): Use Fleak's low-code workflows with Pinecone to combine SQL, LLM inference, and vector search in serverless APIs for RAG and data enrichment pipelines. - [FlowiseAI](https://docs.pinecone.io/integrations/flowise.md): Use FlowiseAI with Pinecone to build low-code LLM apps that upsert documents and query vector indexes for RAG chatbots and semantic search flows. - [Gathr](https://docs.pinecone.io/integrations/gathr.md): Use Gathr's no-code data-to-outcome platform with Pinecone to build enterprise RAG apps, chatbots, and vector pipelines from ingestion through deployment. - [Matillion](https://docs.pinecone.io/integrations/matillion.md): Use Matillion Data Productivity Cloud to chunk, embed, and upsert data into Pinecone with low-code AI pipelines for RAG, ETL, and GenAI apps. - [Nexla](https://docs.pinecone.io/integrations/nexla.md): Use Nexla no-code data pipelines to ingest from SharePoint, OneDrive, and 500+ sources into Pinecone for enterprise RAG and vector search apps. - [Redpanda](https://docs.pinecone.io/integrations/redpanda.md): Stream events into Pinecone with Redpanda Connect's declarative YAML pipelines for real-time vector ingestion, at-least-once delivery, and RAG ETL. - [Snowflake Openflow](https://docs.pinecone.io/integrations/snowflake-openflow.md): Use the Pinecone processors in Snowflake Openflow to upsert, query, and delete vectors in a Pinecone index as part of a data pipeline. - [StreamNative](https://docs.pinecone.io/integrations/streamnative.md): Use the StreamNative Pinecone sink connector to write messages from Apache Pulsar topics to a Pinecone index for real-time vector ingestion. - [Unstructured](https://docs.pinecone.io/integrations/unstructured.md): Use Unstructured to parse, chunk, and load PDFs, Word, and 25+ document types into Pinecone for LLM-ready RAG ETL pipelines and semantic search apps. ##### Frameworks - [AI Engine](https://docs.pinecone.io/integrations/ai-engine.md): Use the AI Engine WordPress plugin with Pinecone to power chatbots, semantic search, and RAG over site content directly from your WordPress dashboard. - [Amazon Bedrock](https://docs.pinecone.io/integrations/amazon-bedrock.md): Use Pinecone as the vector store for a Knowledge Base for Amazon Bedrock, then create a Bedrock agent that retrieves your data for RAG on AWS. - [Amazon SageMaker](https://docs.pinecone.io/integrations/amazon-sagemaker.md): Combine Amazon SageMaker with Pinecone to host LLMs and embedding models for scalable retrieval-augmented generation and vector search workloads. - [Cloudera AI](https://docs.pinecone.io/integrations/cloudera.md): Integrate Cloudera AI with Pinecone to run distributed Spark and Python embedding pipelines and power scalable RAG and vector search on enterprise data. - [Context Data](https://docs.pinecone.io/integrations/context-data.md): Use Context Data with Pinecone to build no-code flows from Postgres, S3, Salesforce, and more, embedding data and querying indexes in Query Studio. - [Genkit](https://docs.pinecone.io/integrations/genkit.md): Use the Genkit Pinecone plugin with Firebase to build AI features with type-safe indexers, embedders, and retrievers for RAG and semantic search apps. - [Haystack](https://docs.pinecone.io/integrations/haystack.md): Use deepset Haystack's PineconeDocumentStore to build production NLP pipelines that index, embed, and query documents for question answering and RAG. - [Instill AI](https://docs.pinecone.io/integrations/instill.md): Wire Pinecone into Instill AI no-code pipelines to upsert, query, and power RAG agents, chatbots, and knowledge bases with vector similarity. - [LangChain](https://docs.pinecone.io/integrations/langchain.md): Use Pinecone with LangChain to build RAG apps, agents, and chatbots, and manage embeddings, vector stores, retrievers, and chains for LLM-powered search. - [LlamaIndex](https://docs.pinecone.io/integrations/llamaindex.md): Use Pinecone with LlamaIndex to build RAG pipelines that ingest documents, structure private data, and run semantic search and question answering. - [n8n](https://docs.pinecone.io/integrations/n8n.md): Use the Pinecone Vector Store and Pinecone Assistant nodes in n8n to build RAG pipelines, semantic search, and no-code AI automations with 400+ apps. - [Progress Agentic RAG](https://docs.pinecone.io/integrations/progress-agentic-rag.md): Store the index for a Progress Agentic RAG knowledge box in Pinecone. Progress Agentic RAG, formerly Nuclia, provides RAG-as-a-Service over your documents. - [VoltAgent](https://docs.pinecone.io/integrations/voltagent.md): Build TypeScript AI agents with VoltAgent and Pinecone that use automatic embeddings, semantic search, and metadata filtering for observable RAG. ##### Infrastructure - [AWS Marketplace](https://docs.pinecone.io/integrations/aws-marketplace.md): Subscribe to Pinecone through AWS Marketplace for centralized procurement, pay-as-you-go billing, and consolidated invoicing on your AWS account. - [Google Cloud Marketplace](https://docs.pinecone.io/integrations/google-cloud-marketplace.md): Subscribe to Pinecone through Google Cloud Marketplace for centralized procurement, pay-as-you-go billing, and consolidated GCP invoicing. - [Microsoft Marketplace](https://docs.pinecone.io/integrations/microsoft-marketplace.md): Buy and manage Pinecone through Microsoft Marketplace with pay-as-you-go billing, centralized SaaS procurement, and simplified Azure licensing. - [Pulumi](https://docs.pinecone.io/integrations/pulumi.md): Provision Pinecone indexes and collections as code with Pulumi in Python, TypeScript, Go, or C#. - [Terraform](https://docs.pinecone.io/integrations/terraform.md): Manage Pinecone indexes, collections, API keys, and projects with the Terraform provider for repeatable infrastructure-as-code and DevOps workflows. - [Vercel](https://docs.pinecone.io/integrations/vercel.md): Use the Pinecone integration for Vercel to connect your Vercel AI projects to Pinecone indexes for long-term memory and search. - [Zapier](https://docs.pinecone.io/integrations/zapier.md): Use Zapier to connect Pinecone to 6,000+ apps, trigger workflows when an index changes, and add data or run searches without writing code. ##### Models - [Cohere](https://docs.pinecone.io/integrations/cohere.md): Generate embeddings with the Cohere Embed API, index them in Pinecone, and run semantic search queries against the index. - [Voyage AI](https://docs.pinecone.io/integrations/voyage.md): Generate Voyage AI embeddings for consumer contract documents, index them in Pinecone, and run semantic search queries against the index. - [Hugging Face Inference Endpoints](https://docs.pinecone.io/integrations/hugging-face-inference-endpoints.md): Generate embeddings with Hugging Face Inference Endpoints and index them in Pinecone for semantic search, RAG, and transformer model deployment. - [Jina AI](https://docs.pinecone.io/integrations/jina.md): Use Jina AI long-context embeddings with Pinecone for multilingual semantic search, RAG chatbots, and domain-specific retrieval up to 8K tokens. - [OpenAI](https://docs.pinecone.io/integrations/openai.md): Pair OpenAI embeddings and completion models with Pinecone for semantic search, long-term memory, RAG, and context-aware LLM question-answering. - [Twelve Labs](https://docs.pinecone.io/integrations/twelve-labs.md): Store Twelve Labs multimodal video embeddings in Pinecone to power video search, recommendations, and content moderation with fast similarity retrieval. ##### Observability - [Datadog](https://docs.pinecone.io/integrations/datadog.md): Monitor Pinecone with the Datadog integration to track request latency, index fullness, and usage trends, and alert on anomalies in vector workloads. - [HoneyHive](https://docs.pinecone.io/integrations/honeyhive.md): Use HoneyHive with Pinecone to capture OpenTelemetry traces of SDK calls and visualize spans for observability and evaluation of RAG pipelines. - [New Relic](https://docs.pinecone.io/integrations/new-relic.md): Monitor Pinecone with New Relic's Prometheus quickstart, which includes dashboards, alerts, and AI observability for query latency and RAG performance. - [Traceloop](https://docs.pinecone.io/integrations/traceloop.md): Instrument Pinecone with Traceloop's OpenLLMetry SDK to emit OpenTelemetry traces and metrics for LLM observability in Datadog, Grafana, and more. - [TruLens](https://docs.pinecone.io/integrations/trulens.md): Use TruLens to evaluate and track a RAG app built on Pinecone and LangChain, and compare configurations such as the distance metric, model, and top k. #### Build an integration - [Integration ecosystem](https://docs.pinecone.io/integrations/build-integration/integration-ecosystem.md): Learn how to build a Pinecone integration with the public SDKs and API, and how to apply to have it listed on the Pinecone integrations page. - [Attribute usage to your integration](https://docs.pinecone.io/integrations/build-integration/attribute-usage-to-your-integration.md): Learn how to set a source tag in the Pinecone SDKs or the API User-Agent header so that usage from your integration is attributed to it. - [Connect your users to Pinecone](https://docs.pinecone.io/integrations/build-integration/connect-your-users-to-pinecone.md): Embed a Connect to Pinecone flow in your app or notebook so users can sign in, choose a project, and receive an API key without leaving your integration. ### Troubleshooting #### Contact support - [Contact Support](https://docs.pinecone.io/troubleshooting/contact-support.md): Contact Pinecone Support from the console Help center, check which billing and support plans include it, and find business hours and Sev-1 coverage. - [How to work with Support](https://docs.pinecone.io/troubleshooting/how-to-work-with-support.md): Get faster answers from Pinecone Support: try the AI support chatbot, use your account email, open tickets in the console, and pick an accurate severity. - [Pinecone Support SLAs](https://docs.pinecone.io/troubleshooting/pinecone-support-slas.md): Look up Pinecone Support first-response SLAs by support plan and ticket severity, from 30 minutes on a Premium Sev-1 to business days at lower severities. #### Account management - [Login code issues](https://docs.pinecone.io/troubleshooting/login-code-issues.md): Fix a rejected Pinecone login code, which can expire after 10 hours or be invalidated by a shared inbox, a newer code request, or an offset system clock. - [Custom data processing agreements](https://docs.pinecone.io/troubleshooting/custom-data-processing-agreements.md): Request a custom data processing agreement (DPA) with Pinecone if your team requires terms beyond the standard agreement available on the Pinecone website. - [Delete your organization](https://docs.pinecone.io/troubleshooting/delete-your-organization.md): Delete a Pinecone organization by first deleting its indexes, collections, and projects, then downgrading to the Starter plan. This can't be undone. - [Delete your account](https://docs.pinecone.io/troubleshooting/delete-your-account.md): Delete your Pinecone account by removing your user from every organization and deleting any organization where you are the sole member. This is permanent. - [Billing disputes and refunds](https://docs.pinecone.io/troubleshooting/billing-disputes-and-refunds.md): Understand Pinecone's policy of not refunding unused indexes, and why migrating a pod-based index to serverless can lower a bill you'd otherwise dispute. #### Indexes - [Wait for index creation to be complete](https://docs.pinecone.io/troubleshooting/wait-for-index-creation.md): Wait for Pinecone index creation to finish using describe_index polling in the Python SDK before upserting to avoid 403 or 404 errors. - [Restrictions on index names](https://docs.pinecone.io/troubleshooting/restrictions-on-index-names.md): Learn the rules for Pinecone index names: lowercase alphanumeric Latin characters and dashes only, no dots, and 52 characters total with your project ID. - [Return all vectors in an index](https://docs.pinecone.io/troubleshooting/return-all-vectors-in-an-index.md): Learn why a single Pinecone query can't return every vector in an index, and how to page through record IDs with the list operation instead. #### Data - [Embedding values changed when upserted](https://docs.pinecone.io/troubleshooting/embedding-values-changed-when-upserted.md): Diagnose why Pinecone embedding values appear changed after upsert, including float32 precision rounding and how the API serializes numeric vector data. - [Limitations of querying by ID](https://docs.pinecone.io/troubleshooting/limitations-of-querying-by-id.md): Understand why querying by record ID can omit that ID under ANN search, and when to use fetch or metadata filters to retrieve a specific vector reliably. #### Common errors - [Index creation error - missing spec parameter](https://docs.pinecone.io/troubleshooting/index-creation-error-missing-spec.md): Fix the Pinecone create_index TypeError for a missing spec parameter by passing the spec argument that sets the index's deployment model, cloud, and region. - [Serverless index creation error - max serverless indexes](https://docs.pinecone.io/troubleshooting/index-creation-error-max-serverless.md): Resolve the Pinecone serverless index creation error caused by hitting the 20-index project limit by deleting unused indexes or upgrading your plan. - [Serverless index connection errors](https://docs.pinecone.io/troubleshooting/serverless-index-connection-errors.md): Fix Pinecone serverless connection errors that fail to resolve a controller hostname by upgrading to a current version of the Python or Node.js SDK. - [Error: Handshake read failed when connecting](https://docs.pinecone.io/troubleshooting/error-handshake-read-failed.md): Fix the Pinecone 'Handshake read failed' connection error by checking your firewall and network, then verifying your SDK setup and API key are correct. - [PineconeAttribute errors with LangChain](https://docs.pinecone.io/troubleshooting/pinecone-attribute-errors-with-langchain.md): Resolve PineconeAttribute errors in LangChain caused by outdated packages by upgrading langchain-pinecone and the Pinecone Python SDK to current releases. - [Error: Cannot import name 'Pinecone' from 'pinecone'](https://docs.pinecone.io/troubleshooting/error-cannot-import-name-pinecone.md): Fix the Python ImportError 'cannot import name Pinecone from pinecone' by upgrading the Pinecone Python SDK to 3.0.0 or later, with or without gRPC. - [Python AttributeError: module pinecone has no attribute init](https://docs.pinecone.io/troubleshooting/module-pinecone-has-no-attribute-init.md): Fix the Python AttributeError 'module pinecone has no attribute init' by upgrading to Pinecone Python SDK 3.0 or later, which serverless indexes require. #### Miscellaneous - [Node.js Troubleshooting](https://docs.pinecone.io/troubleshooting/nodejs-troubleshooting.md): Troubleshoot Pinecone Node.js SDK issues that work locally but fail in deployment, including environment, network, and serverless runtime configuration. - [CORS Issues](https://docs.pinecone.io/troubleshooting/cors-issues.md): Troubleshoot Pinecone CORS errors and Access-Control-Allow-Origin issues when calling the API from localhost or browser-based web apps. - [Debug model vs. Pinecone recall issues](https://docs.pinecone.io/troubleshooting/debug-model-vs-pinecone-recall-issues.md): Distinguish an embedding model problem from a Pinecone recall problem using a six-step evaluation that compares brute-force search against your index. - [Unable to pip install](https://docs.pinecone.io/troubleshooting/unable-to-pip-install.md): Resolve install issues for the Pinecone Python SDK: pick the right Python 3.x command, install pinecone or pinecone with gRPC, and upgrade to the latest. ## OpenAPI Specs - [db_control_2026-07.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2026-07/db_control_2026-07.oas.yaml) - [db_data_2026-07.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2026-07/db_data_2026-07.oas.yaml) - [inference_2026-07.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2026-07/inference_2026-07.oas.yaml) - [admin_2026-07.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2026-07/admin_2026-07.oas.yaml) - [db_control_2026-04.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2026-04/db_control_2026-04.oas.yaml) - [db_data_2026-04.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2026-04/db_data_2026-04.oas.yaml) - [inference_2026-04.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2026-04/inference_2026-04.oas.yaml) - [admin_2026-04.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2026-04/admin_2026-04.oas.yaml) - [oauth_2026-04.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2026-04/oauth_2026-04.oas.yaml) - [db_control_2025-10.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2025-10/db_control_2025-10.oas.yaml) - [db_data_2025-10.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2025-10/db_data_2025-10.oas.yaml) - [inference_2025-10.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2025-10/inference_2025-10.oas.yaml) - [admin_2025-10.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2025-10/admin_2025-10.oas.yaml) - [oauth_2025-10.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2025-10/oauth_2025-10.oas.yaml) - [db_control_2025-04.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2025-04/db_control_2025-04.oas.yaml) - [db_data_2025-04.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2025-04/db_data_2025-04.oas.yaml) - [inference_2025-04.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2025-04/inference_2025-04.oas.yaml) - [admin_2025-04.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2025-04/admin_2025-04.oas.yaml) - [oauth_2025-04.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2025-04/oauth_2025-04.oas.yaml) - [db_control_2025-01.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2025-01/db_control_2025-01.oas.yaml) - [db_data_2025-01.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2025-01/db_data_2025-01.oas.yaml) - [inference_2025-01.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2025-01/inference_2025-01.oas.yaml) - [db_control_2024-10.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2024-10/db_control_2024-10.oas.yaml) - [db_data_2024-10.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2024-10/db_data_2024-10.oas.yaml) - [inference_2024-10.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2024-10/inference_2024-10.oas.yaml) - [control_2024-07.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2024-07/control_2024-07.oas.yaml) - [data_2024-07.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2024-07/data_2024-07.oas.yaml) - [control_2024-04.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2024-04/control_2024-04.oas.yaml) - [data_2024-04.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2024-04/data_2024-04.oas.yaml)