# Pinecone Docs

> Official Pinecone documentation for the vector database, Assistant, inference APIs, SDKs, and building production search and AI applications.

- [Pinecone Database (488 pages)](https://docs.pinecone.io/_llms/pinecone-database.md): Documentation for Pinecone Database.
- [Pinecone Assistant (129 pages)](https://docs.pinecone.io/_llms/pinecone-assistant.md): Documentation for Pinecone Assistant.

## Pinecone Nexus

### Guides

#### Get started

- [Pinecone Nexus](https://docs.pinecone.io/guides/nexus/overview.md): Pinecone Nexus is the knowledge engine for agents. It compiles your data into queryable knowledge once, then serves grounded, cited answers to agents on every call.
- [Nexus quickstart](https://docs.pinecone.io/guides/nexus/quickstart.md): Deploy Pinecone Nexus with BYOC, curate a context from your own documents, and run KnowQL queries that return grounded, cited multi-document answers.
- [Nexus key concepts](https://docs.pinecone.io/guides/nexus/concepts.md): Learn the core Pinecone Nexus concepts: sources, workspaces, contexts, manifests, artifacts, tasks, sessions, and the Query API, and how they connect.

#### The knowledge engine

- [How Nexus works](https://docs.pinecone.io/guides/nexus/how-it-works.md): How Nexus distills curated artifacts for retrieval, then answers with code over a retrieval SDK.
- [Context design](https://docs.pinecone.io/guides/nexus/context-design.md): The manifest, the information stack (chunks, artifacts, and edges), and the artifact-kind reference.
- [Curation](https://docs.pinecone.io/guides/nexus/how-curation-works.md): The write path that turns sources into chunks and artifacts, incrementally, driven by the manifest.

##### Queries and sessions

- [Queries](https://docs.pinecone.io/guides/nexus/how-queries-work.md): The query runtime that gathers evidence and composes a grounded, cited answer.
- [Query tracing](https://docs.pinecone.io/guides/nexus/query-tracing.md): Inspect a Pinecone Nexus query trace to see reasoning steps, retrieval tool calls, token usage, latency, cost breakdown, and cache savings.

#### Tools

- [MCP server](https://docs.pinecone.io/guides/nexus/mcp-server.md): Query your Pinecone Nexus contexts from any Model Context Protocol client, such as Claude Desktop, over Streamable HTTP.

#### Bring your own cloud

- [Nexus BYOC overview](https://docs.pinecone.io/guides/nexus/byoc/overview.md): What Nexus bring your own cloud is, how it relates to Database BYOC, and its architecture.
- [Data residency and limits](https://docs.pinecone.io/guides/nexus/byoc/reference.md): Where your data lives and travels in Nexus BYOC, plus authentication, encryption, cluster footprint, and limitations.
- [Deploy Nexus BYOC](https://docs.pinecone.io/guides/nexus/byoc/deploy.md): Install and operate Pinecone Nexus in your own cloud account.

### Reference

#### APIs

- [Pinecone Nexus API](https://docs.pinecone.io/reference/api/nexus/introduction.md): Programmatic access to Nexus: manage contexts and sources, curate, and query with KnowQL.
- [Authentication](https://docs.pinecone.io/reference/api/nexus/authentication.md): Authenticate to the Nexus API with your Pinecone API key, sent directly or exchanged for a short-lived session token.

#### Endpoints

##### Auth

- [Exchange a Pinecone API key for a session token](https://docs.pinecone.io/api-reference/auth/exchange-a-pinecone-api-key-for-a-session-token.md)
- [Current identity (whoami)](https://docs.pinecone.io/api-reference/auth/current-identity-whoami.md)

##### Project

- [Get the active project](https://docs.pinecone.io/api-reference/project/get-the-active-project.md)
- [Project-wide task stats](https://docs.pinecone.io/api-reference/project/project-wide-task-stats.md): Aggregate task counters across the whole project (all contexts), broken down by state and workflow. The per-context equivalent is `GET /contexts/{slug}/tasks/stats`.

##### Connectors

- [List the project's linked connectors](https://docs.pinecone.io/api-reference/connectors/list-the-projects-linked-connectors.md)
- [Get a connector](https://docs.pinecone.io/api-reference/connectors/get-a-connector.md)
- [Unlink a connector](https://docs.pinecone.io/api-reference/connectors/unlink-a-connector.md)
- [Start the OAuth link flow for a provider](https://docs.pinecone.io/api-reference/connectors/start-the-oauth-link-flow-for-a-provider.md): Returns an `authorize_url` for the user to open in a browser. The connector is persisted by the provider's OAuth redirect callback once the user approves access.
- [Link a connector with an API key](https://docs.pinecone.io/api-reference/connectors/link-a-connector-with-an-api-key.md)
- [Browse a connector's folders/files](https://docs.pinecone.io/api-reference/connectors/browse-a-connectors-foldersfiles.md)
- [List a context's connectors (with per-context enabled flag)](https://docs.pinecone.io/api-reference/connectors/list-a-contexts-connectors-with-per-context-enabled-flag.md)
- [Enable or disable a connector for a context](https://docs.pinecone.io/api-reference/connectors/enable-or-disable-a-connector-for-a-context.md)

##### Contexts

- [List contexts (newest first, with stats)](https://docs.pinecone.io/api-reference/contexts/list-contexts-newest-first-with-stats.md)
- [Create a context](https://docs.pinecone.io/api-reference/contexts/create-a-context.md): The context is created empty and is not queryable until you import sources and curate them (curate is explicit — there is no auto-curate). Optionally seed a `manifest`. A `work` context is the exception: it is queryable from day zero and is built from traces of work rather than source documents.
- [Get a context](https://docs.pinecone.io/api-reference/contexts/get-a-context.md)
- [Update a context](https://docs.pinecone.io/api-reference/contexts/update-a-context.md): All fields optional; absent leaves untouched. Empty string clears description/guide; `{}` clears the manifest back to defaults. A supplied manifest is validated against the manifest schema.
- [Delete a context (and its Pinecone indexes)](https://docs.pinecone.io/api-reference/contexts/delete-a-context-and-its-pinecone-indexes.md)
- [Fork a context (copy manifest into a fresh target)](https://docs.pinecone.io/api-reference/contexts/fork-a-context-copy-manifest-into-a-fresh-target.md): Copies the source context's manifest and lifecycle metadata onto an **already-created** target context in the same project, so the target's query and curate gates pass. It does not create the target — create it first with `POST /contexts`. The target's index stays empty until curated. The source mus…
- [Per-context task statistics](https://docs.pinecone.io/api-reference/contexts/per-context-task-statistics.md)
- [Trigger an on-demand self-tuning optimize](https://docs.pinecone.io/api-reference/contexts/trigger-an-on-demand-self-tuning-optimize.md): Tunes the manifest from real query traffic and chains a forced re-curate. A body is required but every field in it is optional, so `{}` is valid — and a no-op when no `candidate_queries` are supplied. The context must have been curated, and only one optimize runs at a time.
- [Run the Design-flow explore agent (propose a manifest)](https://docs.pinecone.io/api-reference/contexts/run-the-design-flow-explore-agent-propose-a-manifest.md): Inspects the uploaded source and proposes manifest-template matches, returned in the task's `output` (see `ExploreOutput`). Persists nothing on the index — review the proposal, then apply it via the manifest update + a forced curate. Body is optional.
- [Estimate the token + time cost of curating the in-progress manifest](https://docs.pinecone.io/api-reference/contexts/estimate-the-token-+-time-cost-of-curating-the-in-progress-manifest.md): Spins up the `profile` runtime to estimate the token + time cost of curating the sources under the in-progress manifest (sent in the request body), returned as the task's `output` (see `ProfileEstimateOutput`). Persists nothing; the console polls it for the Design-page cost box. Body is optional.

##### Manifest

- [Get the context's manifest](https://docs.pinecone.io/api-reference/manifest/get-the-contexts-manifest.md): The context's pinned manifest document. A context with no pinned manifest returns `{}` — the runtime fills defaults. Writes go through the `manifest` field on `PUT /contexts/{slug}`.
- [List the built-in manifest templates](https://docs.pinecone.io/api-reference/manifest/list-the-built-in-manifest-templates.md): The catalog the console seeds new contexts from.

##### Curation

- [Get the curation ledger](https://docs.pinecone.io/api-reference/curation/get-the-curation-ledger.md): The full ledger: per-source hashes, edges, corpus groups, chunk-id lineage, version pin, reclaim intents, pointers, and glossary. This pays an O(corpus) chunk-id-lineage read — use `GET /contexts/{slug}/curate/version/pin` on the per-turn path.
- [(Re)build the context's index from its sources](https://docs.pinecone.io/api-reference/curation/rebuild-the-contexts-index-from-its-sources.md): Curate the staged sources under the active manifest. **Required before querying** — there is no auto-curate. Body is optional. Set `force: true` to do a full rebuild (use after editing the manifest); the default is an incremental curate. Search contexts only — a work context builds via `work`/`groom…
- [Drop named sources from the index + ledger](https://docs.pinecone.io/api-reference/curation/drop-named-sources-from-the-index-+-ledger.md)

##### Source Files

- [Import source documents from a project connector](https://docs.pinecone.io/api-reference/source-files/import-source-documents-from-a-project-connector.md): Pull source documents from a linked project connector (Box, ...) into the context. Supply either `folder` or `files`. Stages the source only — curate explicitly before querying.
- [Upload a source file or archive](https://docs.pinecone.io/api-reference/source-files/upload-a-source-file-or-archive.md): One file per request, max 2 GiB. Archives (`.zip`, `.tar`, `.tar.gz`, `.tgz`) are expanded by the import runtime. Stages the source only — it does not index anything. Curate explicitly with `POST /contexts/{slug}/curate` before querying.
- [List the source file tree (root)](https://docs.pinecone.io/api-reference/source-files/list-the-source-file-tree-root.md)
- [Source file/dir/size counts](https://docs.pinecone.io/api-reference/source-files/source-filedirsize-counts.md): Aggregate counts. Under preview mode the response also carries the per-context quota (`max_files_per_context`, `max_bytes_per_context`, `used_files`, `used_bytes`); those fields are absent otherwise.
- [Flat manifest of source files (path, size, last_modified)](https://docs.pinecone.io/api-reference/source-files/flat-manifest-of-source-files-path-size-last_modified.md): Flat source-object inventory used to render the source page without walking the tree. Excludes the `_inbox/` staging directory.
- [List the source file tree under a path](https://docs.pinecone.io/api-reference/source-files/list-the-source-file-tree-under-a-path.md)
- [Read a source file (raw bytes)](https://docs.pinecone.io/api-reference/source-files/read-a-source-file-raw-bytes.md)
- [Delete a source file](https://docs.pinecone.io/api-reference/source-files/delete-a-source-file.md)

##### Knowledge

- [List curated knowledge (root)](https://docs.pinecone.io/api-reference/knowledge/list-curated-knowledge-root.md)
- [Knowledge file/dir/size counts](https://docs.pinecone.io/api-reference/knowledge/knowledge-filedirsize-counts.md)
- [List curated knowledge under a path](https://docs.pinecone.io/api-reference/knowledge/list-curated-knowledge-under-a-path.md)
- [Read a curated knowledge file (raw bytes)](https://docs.pinecone.io/api-reference/knowledge/read-a-curated-knowledge-file-raw-bytes.md)

##### Query

- [Run one KnowQL query turn](https://docs.pinecone.io/api-reference/query/run-one-knowql-query-turn.md): Send `ask` (the natural-language question) and, when starting a new session, a `scope` of 1–10 contexts. Continue an existing session with `session_id` or `previous_query_id`. Scoped search contexts must be curated (work contexts are queryable immediately), and a scope may not mix work and search co…
- [Fetch one query (turn)](https://docs.pinecone.io/api-reference/query/fetch-one-query-turn.md)
- [Cancel an in-progress query turn](https://docs.pinecone.io/api-reference/query/cancel-an-in-progress-query-turn.md): Idempotent — an already-terminal query is returned unchanged. On success the turn's `status` becomes `cancelled`.
- [Fetch the recorded trace for a query turn](https://docs.pinecone.io/api-reference/query/fetch-the-recorded-trace-for-a-query-turn.md): The per-turn debug trace (steps, tool calls, strategy, cost, rollup). Trace persistence is unconditional — every turn lands a trace blob — so this is available once the turn is terminal.
- [Stream a query turn's events (SSE)](https://docs.pinecone.io/api-reference/query/stream-a-query-turns-events-sse.md): Server-sent event stream of the turn's events as they land — the same `type`-named events POST /query emits with `stream: true`, but as a standalone, resumable subscription. Reconnect with `Last-Event-ID` to replay from where the stream dropped.
- [Record thumbs-up/down feedback on a query turn](https://docs.pinecone.io/api-reference/query/record-thumbs-updown-feedback-on-a-query-turn.md)
- [List the selectable query models](https://docs.pinecone.io/api-reference/query/list-the-selectable-query-models.md): The model catalog the `model` field on `POST /query` draws from. Returns the default model, every catalog entry, the tier → model-id map, per-phase defaults, and the curate-capable model ids. Only entries with `available: true` are selectable (others are coming soon and rejected with `400`).
- [List project-wide query sessions (newest first)](https://docs.pinecone.io/api-reference/query/list-project-wide-query-sessions-newest-first.md)
- [Get a session with its queries (conversation order)](https://docs.pinecone.io/api-reference/query/get-a-session-with-its-queries-conversation-order.md)
- [Delete a session and its queries](https://docs.pinecone.io/api-reference/query/delete-a-session-and-its-queries.md)

##### Tasks

- [List tasks (project-wide, paginated)](https://docs.pinecone.io/api-reference/tasks/list-tasks-project-wide-paginated.md)
- [Get a task (with steps)](https://docs.pinecone.io/api-reference/tasks/get-a-task-with-steps.md)
- [Cancel/terminate a task](https://docs.pinecone.io/api-reference/tasks/cancelterminate-a-task.md): Body is optional. Max body 1 MiB.
- [Live token + runtime stats for a task](https://docs.pinecone.io/api-reference/tasks/live-token-+-runtime-stats-for-a-task.md)

##### Task Files

- [Read a task file (raw bytes)](https://docs.pinecone.io/api-reference/task-files/read-a-task-file-raw-bytes.md): Serves from the live container while the task runs, and from the archived blob store afterwards. This is how a finished pack's `<slug>.context.zip` is downloaded.
- [Stat a task file](https://docs.pinecone.io/api-reference/task-files/stat-a-task-file.md)
- [List a task's files under a path](https://docs.pinecone.io/api-reference/task-files/list-a-tasks-files-under-a-path.md)
- [List a task's working-directory files](https://docs.pinecone.io/api-reference/task-files/list-a-tasks-working-directory-files.md)
- [Delete a task file](https://docs.pinecone.io/api-reference/task-files/delete-a-task-file.md)

## Pinecone Marketplace

### Guides

#### Get started

- [Pinecone Marketplace](https://docs.pinecone.io/guides/marketplace/overview.md): Pinecone Marketplace is a no-code platform for building, publishing, and operating grounded knowledge applications from vertical templates and connectors.
- [Marketplace quickstart](https://docs.pinecone.io/guides/marketplace/quickstart.md): Pinecone Marketplace quickstart: pick a template app, connect a Google Drive folder, configure the deployment, and publish your first knowledge app.
- [Marketplace concepts](https://docs.pinecone.io/guides/marketplace/concepts.md): Learn Pinecone Marketplace concepts including knowledge applications, deployments, templates, manifests, KAT routing, layouts, and visual components.
- [Marketplace pricing and limits](https://docs.pinecone.io/guides/marketplace/pricing-and-limits.md): How Pinecone Marketplace usage is billed through Assistant and index consumption, plus deployment limits on connectors, files, and consumer auth.

#### Templates

- [Templates overview](https://docs.pinecone.io/guides/marketplace/templates-overview.md): How Pinecone Marketplace templates work, what they define, and how operators customize a deployment after creating it from a template.
- [Template catalog](https://docs.pinecone.io/guides/marketplace/template-catalog.md): Browse the vertical apps in the Pinecone Marketplace template catalog, including Customer Support, HR Benefits, Deal Desk, and Financial Filings Analyzer.

#### Build a knowledge application

- [Create a deployment](https://docs.pinecone.io/guides/marketplace/create-a-deployment.md): Create a new Pinecone Marketplace deployment from a vertical template, name it, choose a layout, and configure operating parameters for your use case.
- [Configure operating parameters](https://docs.pinecone.io/guides/marketplace/configure-operating-parameters.md): Tune the system prompt, starter prompts, and response style of a Pinecone Marketplace knowledge application through operating parameter settings.
- [Configure layouts](https://docs.pinecone.io/guides/marketplace/configure-layouts.md): Choose a chat, search, structured, or hybrid consumer layout for a Pinecone Marketplace knowledge application to match your end-user experience.
- [Configure components](https://docs.pinecone.io/guides/marketplace/configure-components.md): Enable visual components like comparison tables, timelines, and coverage matrices in a Pinecone Marketplace knowledge application interface.

#### Connect data sources

- [Connectors overview](https://docs.pinecone.io/guides/marketplace/connectors-overview.md): How Pinecone Marketplace connectors ingest documents, keep them in sync with source systems, and let operators add manually uploaded files.

#### Multi-domain orchestration

- [Knowledge Agent Toolkit (KAT) overview](https://docs.pinecone.io/guides/marketplace/kat-overview.md): How the Knowledge Agent Toolkit (KAT) orchestrates multi-domain Pinecone Marketplace apps with manifests, disambiguation, slot filling, and guardrails.
- [Multi-domain routing](https://docs.pinecone.io/guides/marketplace/multi-domain-routing.md): How the Knowledge Agent Toolkit (KAT) routes queries across multiple knowledge bases in a Pinecone Marketplace deployment for multi-domain answers.

#### Publish and operate

- [Publish a deployment](https://docs.pinecone.io/guides/marketplace/publish-a-deployment.md): Publish a Pinecone Marketplace deployment to promote a building version to active, run introspection, generate starter prompts, and evaluate quality.
- [Manage versions and rollback](https://docs.pinecone.io/guides/marketplace/manage-versions-and-rollback.md): Use versioned publishing in Pinecone Marketplace to stage edits, compare active and building versions, and roll back a deployment when needed.
- [Evaluations](https://docs.pinecone.io/guides/marketplace/evaluations.md): How Pinecone Marketplace runs automatic evaluations on every publish, scoring faithfulness and relevance to catch regressions in a new version.
- [Analytics and event logs](https://docs.pinecone.io/guides/marketplace/analytics-and-event-logs.md): Track end-user activity, refusal rates, feedback, and event logs in a Pinecone Marketplace deployment for analytics, auditing, and debugging.

#### Access control

- [Deployer authentication](https://docs.pinecone.io/guides/marketplace/deployer-auth.md): Sign in to Pinecone Marketplace as an operator to create deployments, manage sessions across devices, and audit deployer actions in the event log.
- [Consumer authentication](https://docs.pinecone.io/guides/marketplace/consumer-auth-overview.md): Configure consumer sign-in for a Pinecone Marketplace deployment using link access or Google sign-in to control who can use your knowledge application.

### End user guide

#### Use a knowledge application

- [End user guide](https://docs.pinecone.io/guides/marketplace/end-user/overview.md): End-user overview of Pinecone Marketplace knowledge applications, including how to sign in with link access or Google and read grounded citations.
- [Ask questions](https://docs.pinecone.io/guides/marketplace/end-user/ask-questions.md): Tips for end users on asking clear, specific questions in a Pinecone Marketplace knowledge application, using follow-ups, and handling clarifications.
- [Understand answers](https://docs.pinecone.io/guides/marketplace/end-user/citations.md): Read citations, work with visual components, export and share answers, and give feedback in a Pinecone Marketplace knowledge application.

### Reference

#### APIs

- [Pinecone Marketplace API](https://docs.pinecone.io/reference/api/marketplace/introduction.md): Pinecone Marketplace API reference overview covering deployments, templates, connectors, versions, evaluations, and analytics endpoints.
- [Authentication](https://docs.pinecone.io/reference/api/marketplace/authentication.md): Authenticate to the Pinecone Marketplace API using project-scoped API keys, including the Api-Key header, key scoping, and deployment permissions.

#### Deployments

- [Deployments](https://docs.pinecone.io/reference/api/marketplace/deployments.md): Marketplace Deployments API reference for listing, creating, updating, and deleting knowledge application deployments programmatically.

#### Templates

- [Templates](https://docs.pinecone.io/reference/api/marketplace/templates.md): Marketplace Templates API reference for listing vertical template catalogs and retrieving default operating parameters for deployments.

#### Connectors

- [Connectors](https://docs.pinecone.io/reference/api/marketplace/connectors.md): Marketplace Connectors API reference for attaching source connectors, updating configuration, and triggering syncs across deployments.

#### Versions and publishing

- [Versions and publishing](https://docs.pinecone.io/reference/api/marketplace/versions.md): Marketplace Versions API reference for publishing building versions, listing version history, and rolling back deployments programmatically.

#### Evaluations

- [Evaluations](https://docs.pinecone.io/reference/api/marketplace/evaluations.md): Marketplace Evaluations API reference for triggering evaluation runs, retrieving scores, and inspecting per-question detail per version.

#### Events and analytics

- [Events and analytics](https://docs.pinecone.io/reference/api/marketplace/events.md): Marketplace Events and Analytics API reference for streaming deployment event logs and reading conversation and feedback counters.

## Changelog

- [Pinecone 2026 changelog](https://docs.pinecone.io/release-notes/2026.md): Every change to Pinecone in 2026, including new features, API updates, deprecations, and pricing and plan changes.
- [Pinecone 2025 changelog](https://docs.pinecone.io/release-notes/2025.md): Every change to Pinecone in 2025, including new features, API updates, deprecations, and pricing and plan changes.
- [Pinecone 2024 changelog](https://docs.pinecone.io/release-notes/2024.md): Every change to Pinecone in 2024, including new features, API updates, deprecations, and pricing and plan changes.
- [Pinecone 2023 changelog](https://docs.pinecone.io/release-notes/2023.md): Every change to Pinecone in 2023, including new features, API updates, deprecations, and pricing and plan changes.
- [Pinecone 2022 changelog](https://docs.pinecone.io/release-notes/2022.md): Every change to Pinecone in 2022, including new features, API updates, deprecations, and pricing and plan changes.
- [Pinecone feature availability](https://docs.pinecone.io/release-notes/feature-availability.md): Pinecone feature availability across public preview, general availability, and limited availability releases, with links to the relevant changelog entries.

## Other

- [AGENTS JAVASCRIPT](https://docs.pinecone.io/AGENTS-JAVASCRIPT.md)
- [AGENTS PYTHON](https://docs.pinecone.io/AGENTS-PYTHON.md)
- [Semantic search](https://docs.pinecone.io/examples/sample-apps/legal-semantic-search.md): Next.js sample app for semantic search over PDF legal documents using Pinecone serverless indexes and Voyage AI voyage-law-2 embeddings.
- [Multi-tenant RAG](https://docs.pinecone.io/examples/sample-apps/namespace-notes.md): Next.js multi-tenant RAG sample app that uses Pinecone namespaces to isolate document context and chatbot memory per workspace tenant.
- [Pinecone Assistant](https://docs.pinecone.io/examples/sample-apps/pinecone-assistant.md): Next.js sample chat app that connects to a Pinecone Assistant for grounded answers over uploaded PDFs with citations and file references.
- [Multimodal search](https://docs.pinecone.io/examples/sample-apps/shop-the-look.md): Sample Next.js + FastAPI app for multimodal search across text, images, and videos using Pinecone and Google Vertex AI multimodal embeddings.
- [Monitor assistants](https://docs.pinecone.io/guides/assistant/monitor-assistants.md): Track Pinecone Assistant performance in the console with time-series metrics for requests, error counts, chat and context latency, and file processing.
- [Create and load private datasets](https://docs.pinecone.io/guides/data/create-and-load-private-datasets.md): Create custom Pinecone datasets with the pinecone-datasets library, define metadata schema, and upload to your own S3, GCS, or local storage bucket.
- [Use public Pinecone datasets](https://docs.pinecone.io/guides/data/use-public-pinecone-datasets.md): Browse Pinecone's catalog of public benchmark datasets like ANN, MSMARCO, and Quora, then load and upsert them with the pinecone-datasets Python library.
- [Use sample datasets](https://docs.pinecone.io/guides/data/use-sample-datasets.md): Load a pre-built movies sample dataset from the Pinecone console to quickly test indexing, similarity search, and quickstart workflows without uploading your own data.
- [Build a RAG chatbot](https://docs.pinecone.io/guides/get-started/build-a-rag-chatbot.md): Build a Python RAG chatbot with Pinecone, OpenAI, and LangChain that retrieves context from private data to reduce LLM hallucinations.
- [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.
- [all-MiniLM-L12-v2](https://docs.pinecone.io/models/all-MiniLM-L12-v2.md): Use the all-MiniLM-L12-v2 embedding or reranking model with Pinecone: specs and index setup. all-MiniLM-L12-v2 is a sentence and short paragraph encoder.
- [all-mpnet-base-v2](https://docs.pinecone.io/models/all-mpnet-base-v2.md): Use the all-mpnet-base-v2 embedding or reranking model with Pinecone: specs and index setup. all-mpnet-base-v2 is a sentence and short paragraph encoder.
- [bge-reranker-v2-m3](https://docs.pinecone.io/models/bge-reranker-v2-m3.md): Use the bge-reranker-v2-m3 embedding or reranking model with Pinecone: specs and index setup. This is an open source, high performance, multilingual model.
- [CLIP](https://docs.pinecone.io/models/clip.md): CLIP (Contrastive Language–Image Pre-training) builds on a large body of work on zero-shot transfer, natural language supervision, and multimodal learning.
- [CLIP-ViT-B-32-laion2B-s34B-b79K](https://docs.pinecone.io/models/CLIP-ViT-B-32-laion2B-s34B-b79K.md): It's particularly well-suited for tasks like: - **Zero-Shot Image Classification:** Classify images based on text descriptions without further training.
- [embed-english-light-v3.0](https://docs.pinecone.io/models/cohere-embed-english-light-v3.0.md): Cohere embed-english-light-v3.0 on Pinecone: 384-dim text embeddings, 512-token context, low-dimensional storage for fast semantic search.
- [embed-english-v3.0](https://docs.pinecone.io/models/cohere-embed-english-v3.0.md): Use Cohere embed-english-v3.0 with Pinecone for English embeddings: 1024 dimensions, cosine or dot product, and query vs document input types.
- [embed-multilingual-v3.0](https://docs.pinecone.io/models/cohere-embed-multilingual-v3.0.md): Use the embed-multilingual-v3.0 embedding or reranking model with Pinecone: specs and index setup. Multilingual embedding model ideal for easy to use text.
- [cohere-rerank-3.5](https://docs.pinecone.io/models/cohere-rerank-3.5.md): Rerank has improved dramatically in cases where the user is expressing explicitly or implicitly constraints on what they would like returned.
- [cohere-rerank-4-fast](https://docs.pinecone.io/models/cohere-rerank-4-fast.md): Cohere Rerank 4.0 Fast is Cohere's latest reranking model, providing high-quality relevance scoring across enterprise search workloads.
- [e5-base-v2](https://docs.pinecone.io/models/e5-base-v2.md): Use the e5-base-v2 embedding or reranking model with Pinecone: specs and index setup. Ideal model for good performance while keeping with open source and.
- [e5-large-v2](https://docs.pinecone.io/models/e5-large-v2.md): Use the e5-large-v2 embedding or reranking model with Pinecone: specs and index setup. Ideal model for high performance while keeping with open source. Works.
- [gte-base](https://docs.pinecone.io/models/gte-base.md): Use the gte-base embedding or reranking model with Pinecone: specs and index setup. Ideal model for good performance while keeping with open source and.
- [gte-large](https://docs.pinecone.io/models/gte-large.md): Use the gte-large embedding or reranking model with Pinecone: specs and index setup. Larger GTE variant for more high quality embeddings. Ideal model for.
- [instructor-large](https://docs.pinecone.io/models/instructor-large.md): Use the instructor-large embedding or reranking model with Pinecone: specs and index setup. An instruction-finetuned text embedding model that can generate.
- [instructor-xl](https://docs.pinecone.io/models/instructor-xl.md): Use the instructor-xl embedding or reranking model with Pinecone: specs and index setup. An instruction-finetuned text embedding model that can generate text.
- [jina-clip-v2](https://docs.pinecone.io/models/jina-clip-v2.md): Use the jina-clip-v2 embedding or reranking model with Pinecone: specs and index setup. Jina CLIP v2 is a state-of-the-art **multilingual and multimodal.
- [jina-embeddings-v2-base-en](https://docs.pinecone.io/models/jina-embeddings-v2-base-en.md): Use the jina-embeddings-v2-base-en embedding or reranking model with Pinecone: specs and index setup. Ideal for text embeddings where short queries are.
- [jina-embeddings-v3](https://docs.pinecone.io/models/jina-embeddings-v3.md): Jina embeddings v3 on Pinecone: multilingual text embeddings with 1024/512 dims, 8192-token context, task adapters, and Matryoshka support.
- [jina-embeddings-v4](https://docs.pinecone.io/models/jina-embeddings-v4.md): Jina embeddings v4 on Pinecone: multimodal text and image embeddings with 32k tokens, flexible 128-2048 dims, and multi-vector retrieval.
- [llama-text-embed-v2](https://docs.pinecone.io/models/llama-text-embed-v2.md): Developed by NVIDIA Research, it is built on the Llama 3.2 1B architecture and optimized for high retrieval quality with low-latency inference.
- [Marengo-retrieval-2.6](https://docs.pinecone.io/models/marengo-retrieval-2-6.md): Use the Marengo-retrieval-2.6 embedding or reranking model with Pinecone: specs and index setup. The video understanding engine generates embeddings for all.
- [mistral-embed](https://docs.pinecone.io/models/mistral-embed.md): Use the mistral-embed embedding or reranking model with Pinecone: specs and index setup. High performance embedding model from Mistral AI, with a context.
- [multilingual-e5-large](https://docs.pinecone.io/models/multilingual-e5-large.md): Use the multilingual-e5-large embedding or reranking model with Pinecone: specs and index setup. Ideal multilingual model for high performance while keeping.
- [pinecone-rerank-v0](https://docs.pinecone.io/models/pinecone-rerank-v0.md): Pinecone rerank v0 on Pinecone Inference: reranking model for RAG relevance scoring with 512-token context and query-document pair scores.
- [pinecone-sparse-english-v0](https://docs.pinecone.io/models/pinecone-sparse-english-v0.md): Use the pinecone-sparse-english-v0 embedding or reranking model with Pinecone: specs and index setup. Built on the innovations of the DeepImpact.
- [rerank-2](https://docs.pinecone.io/models/rerank-2.md): Voyage AI rerank-2 on Pinecone: quality-focused multilingual reranker with 16000-token context for RAG relevance scoring and search reorder.
- [rerank-2-lite](https://docs.pinecone.io/models/rerank-2-lite.md): Voyage AI rerank-2-lite on Pinecone: multilingual reranker balancing latency and quality with 8000-token context for RAG search results.
- [rerank-english-v2](https://docs.pinecone.io/models/rerank-english-v2.md): Use the rerank-english-v2 embedding or reranking model with Pinecone: specs and index setup. Good reranking model, consumes both a query and a list of.
- [text-embedding-3-large](https://docs.pinecone.io/models/text-embedding-3-large.md): Use the text-embedding-3-large embedding or reranking model with Pinecone: specs and index setup. Most powerful OpenAI embedding model, with a larger.
- [text-embedding-3-small](https://docs.pinecone.io/models/text-embedding-3-small.md): Use the text-embedding-3-small embedding or reranking model with Pinecone: specs and index setup. Most cost effective OpenAI embedding model, great for.
- [text-embedding-ada-002](https://docs.pinecone.io/models/text-embedding-ada-002.md): Use the text-embedding-ada-002 embedding or reranking model with Pinecone: specs and index setup. Legacy embedding model from OpenAI, great for general.
- [voyage-01](https://docs.pinecone.io/models/voyage-01.md): Use the voyage-01 embedding or reranking model with Pinecone: specs and index setup. The highest-quality text embedding model from the first generation of.
- [voyage-2](https://docs.pinecone.io/models/voyage-02.md): Use the voyage-2 embedding or reranking model with Pinecone: specs and index setup. The base-size text embedding model from the second generation of Voyage.
- [voyage-3](https://docs.pinecone.io/models/voyage-3.md): Voyage AI voyage-3 on Pinecone: general-purpose multilingual text embeddings with 1024 dimensions and 32k-token context for retrieval RAG.
- [voyage-3-large](https://docs.pinecone.io/models/voyage-3-large.md): Voyage AI voyage-3-large on Pinecone: top-quality multilingual text embeddings with 32k context and flexible 256/512/1024/2048 dimensions.
- [voyage-3-lite](https://docs.pinecone.io/models/voyage-3-lite.md): Voyage AI voyage-3-lite on Pinecone: cost- and latency-optimized 512-dim text embeddings with 32k-token context for high-throughput search.
- [voyage-code-2](https://docs.pinecone.io/models/voyage-code-2.md): Voyage AI voyage-code-2 on Pinecone: 1536-dim code embeddings with 16k-token context, optimized for source code search and code retrieval.
- [voyage-code-3](https://docs.pinecone.io/models/voyage-code-3.md): Voyage AI voyage-code-3 on Pinecone: code embeddings with 32k context and flexible 256/512/1024/2048 dims for source code search and RAG.
- [voyage-finance-2](https://docs.pinecone.io/models/voyage-finance-2.md): Voyage AI voyage-finance-2 on Pinecone: 1024-dim finance-domain embeddings with 32k-token context for financial RAG and document retrieval.
- [voyage-large-2](https://docs.pinecone.io/models/voyage-large-2.md): Use the voyage-large-2 embedding or reranking model with Pinecone: specs and index setup. The highest-quality text embedding model from the second generation.
- [voyage-law-2](https://docs.pinecone.io/models/voyage-law-2.md): Voyage AI voyage-law-2 on Pinecone: 1024-dim legal-domain embeddings with 16k-token context for legal document retrieval and contract RAG.
- [voyage-lite-02-instruct](https://docs.pinecone.io/models/voyage-lite-02-instruct.md): Use the voyage-lite-02-instruct embedding or reranking model with Pinecone: specs and index setup. The base-size text embedding model from the second.
- [voyage-multimodal-3](https://docs.pinecone.io/models/voyage-multimodal-3.md): Voyage AI voyage-multimodal-3 on Pinecone: 1024-dim embeddings for interleaved text and images like PDFs, slides, tables, and screenshots.
- [Pinecone datasets](https://docs.pinecone.io/reference/tools/pinecone-datasets.md): Use the pinecone-datasets Python library to load public Pinecone example datasets and iterate over vectors to automate benchmark queries.

## OpenAPI Specs

- [db_control_2026-01.alpha.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2026-01.alpha/db_control_2026-01.alpha.oas.yaml)
- [db_data_2026-01.alpha.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2026-01.alpha/db_data_2026-01.alpha.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_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)
- [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)
- [assistant_control_2026-04.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2026-04/assistant_control_2026-04.oas.yaml)
- [assistant_data_2026-04.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2026-04/assistant_data_2026-04.oas.yaml)
- [assistant_evaluation_2026-04.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2026-04/assistant_evaluation_2026-04.oas.yaml)
- [assistant_control_2025-10.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2025-10/assistant_control_2025-10.oas.yaml)
- [assistant_data_2025-10.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2025-10/assistant_data_2025-10.oas.yaml)
- [assistant_evaluation_2025-10.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2025-10/assistant_evaluation_2025-10.oas.yaml)
- [assistant_control_2025-04.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2025-04/assistant_control_2025-04.oas.yaml)
- [assistant_data_2025-04.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2025-04/assistant_data_2025-04.oas.yaml)
- [assistant_evaluation_2025-04.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2025-04/assistant_evaluation_2025-04.oas.yaml)
- [assistant_control_2025-01.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2025-01/assistant_control_2025-01.oas.yaml)
- [assistant_data_2025-01.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2025-01/assistant_data_2025-01.oas.yaml)
- [assistant_evaluation_2025-01.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2025-01/assistant_evaluation_2025-01.oas.yaml)
- [nexus_2026-07.oas](https://raw.githubusercontent.com/pinecone-io/pinecone-api/refs/heads/main/2026-07/nexus_2026-07.oas.yaml)
- [control_plane_api](/control_plane_api.json)
- [data_plane_api](/data_plane_api.json)
- [pinecone](/pinecone.json)

> The links below point to documentation indexes. Follow each `/_llms/` index recursively until you reach documentation pages.

## Indexes

- [Pinecone Database (488 pages)](https://docs.pinecone.io/_llms/pinecone-database.md): Documentation for Pinecone Database.
- [Pinecone Database / Guides (86 pages)](https://docs.pinecone.io/_llms/pinecone-database/guides.md): Documentation for Pinecone Database / Guides.
- [Pinecone Database / Reference (315 pages)](https://docs.pinecone.io/_llms/pinecone-database/reference.md): Documentation for Pinecone Database / Reference.
- [Pinecone Database / Reference / 2026-04 (latest) (96 pages)](https://docs.pinecone.io/_llms/pinecone-database/reference/2026-04-latest.md): Documentation for Pinecone Database / Reference / 2026-04 (latest).
- [Pinecone Assistant (129 pages)](https://docs.pinecone.io/_llms/pinecone-assistant.md): Documentation for Pinecone Assistant.
- [Pinecone Assistant / Reference (92 pages)](https://docs.pinecone.io/_llms/pinecone-assistant/reference.md): Documentation for Pinecone Assistant / Reference.