site_name: Pydantic AI site_description: GenAI Agent Framework, the Pydantic way strict: true site_url: https://ai.pydantic.dev

repo_name: pydantic/pydantic-ai repo_url: https://github.com/pydantic/pydantic-ai edit_uri: edit/main/docs/

copyright: © Pydantic Services Inc. 2024 to present

nav:

• index.md

• install.md

• help.md

• troubleshooting.md

• Coding Agent Skills: coding-agent-skills.md

• Pydantic AI Gateway: gateway.md

• Documentation:

  • Core Concepts:
    • Agents: agent.md
    • dependencies.md
    • tools.md
    • output.md
    • capabilities.md
    • Hooks: hooks.md
    • Agent Specs: agent-spec.md
    • message-history.md
    • direct.md
  • Models & Providers:
    • Overview: models/overview.md
    • models/openai.md
    • models/anthropic.md
    • models/google.md
    • models/xai.md
    • models/bedrock.md
    • models/cerebras.md
    • models/cohere.md
    • models/groq.md
    • models/huggingface.md
    • models/mistral.md
    • models/ollama.md
    • models/openrouter.md
    • models/outlines.md
  • Tools & Toolsets:
    • tools.md
    • tools-advanced.md
    • toolsets.md
    • deferred-tools.md
    • native-tools.md
    • common-tools.md
    • third-party-tools.md
  • Advanced Features:
    • input.md
    • thinking.md
    • retries.md
  • MCP:
    • Overview: mcp/overview.md
    • mcp/client.md
    • mcp/fastmcp-client.md
    • mcp/server.md
  • Extensibility: extensibility.md
  • Multi-Agent Patterns: multi-agent-applications.md
  • Web Chat UI: web.md
  • Embeddings: embeddings.md
  • Testing: testing.md

• Pydantic AI Harness:

  • Overview: harness/overview.md
  • Code Mode: harness/code-mode.md

• Pydantic Evals:

  • Overview: evals.md
  • Getting Started:
    • Quick Start: evals/quick-start.md
    • Core Concepts: evals/core-concepts.md
  • Evaluators:
    • Overview: evals/evaluators/overview.md
    • Built-in Evaluators: evals/evaluators/built-in.md
    • LLM Judge: evals/evaluators/llm-judge.md
    • Third-Party Integrations: evals/evaluators/framework-integrations.md
    • Custom Evaluators: evals/evaluators/custom.md
    • Report Evaluators: evals/evaluators/report-evaluators.md
    • Span-Based: evals/evaluators/span-based.md
  • Online Evaluation: evals/online-evaluation.md
  • How-To Guides:
    • Logfire Integration: evals/how-to/logfire-integration.md
    • Dataset Management: evals/how-to/dataset-management.md
    • Dataset Serialization: evals/how-to/dataset-serialization.md
    • Concurrency & Performance: evals/how-to/concurrency.md
    • Multi-Run Evaluation: evals/how-to/multi-run.md
    • Retry Strategies: evals/how-to/retry-strategies.md
    • Metrics & Attributes: evals/how-to/metrics-attributes.md
    • Case Lifecycle Hooks: evals/how-to/lifecycle.md
  • Examples:
    • Simple Validation: evals/examples/simple-validation.md

• Pydantic Graph:

  • Overview: graph.md
  • Graph Builder:
    • Getting Started: graph/builder/index.md
    • Steps: graph/builder/steps.md
    • Joins & Reducers: graph/builder/joins.md
    • Decisions: graph/builder/decisions.md
    • Parallel Execution: graph/builder/parallel.md

• Integrations:

  • Debugging & Monitoring with Pydantic Logfire: logfire.md
  • Durable Execution:
    • Overview: durable_execution/overview.md
    • Temporal: durable_execution/temporal.md
    • DBOS: durable_execution/dbos.md
    • Prefect: durable_execution/prefect.md
    • Restate: durable_execution/restate.md
    • Kitaru: durable_execution/kitaru.md
  • UI Event Streams:
    • Overview: ui/overview.md
    • AG-UI: ui/ag-ui.md
    • Vercel AI: ui/vercel-ai.md
  • Agent2Agent (A2A): a2a.md

• Related Packages:

  • clai: cli.md

• Examples:

  • Setup: examples/setup.md
  • Getting Started:
    • examples/pydantic-model.md
    • examples/weather-agent.md
  • Conversational Agents:
    • examples/chat-app.md
    • examples/bank-support.md
  • Data & Analytics:
    • examples/sql-gen.md
    • examples/data-analyst.md
    • examples/rag.md
  • Streaming:
    • examples/stream-markdown.md
    • examples/stream-whales.md
  • Complex Workflows:
    • examples/flight-booking.md
    • examples/question-graph.md
  • Business Applications:
    • examples/slack-lead-qualifier.md
  • UI Examples:
    • examples/ag-ui.md

• API Reference:

  • pydantic_ai:
    • api/ag_ui.md
    • api/agent.md
    • api/native_tools.md
    • api/capabilities.md
    • api/common_tools.md
    • api/concurrency.md
    • api/direct.md
    • api/durable_exec.md
    • api/embeddings.md
    • api/exceptions.md
    • api/ext.md
    • api/format_prompt.md
    • api/function_signature.md
    • api/mcp.md
    • api/messages.md
    • api/models/anthropic.md
    • api/models/base.md
    • api/models/bedrock.md
    • api/models/cerebras.md
    • api/models/cohere.md
    • api/models/fallback.md
    • api/models/function.md
    • api/models/google.md
    • api/models/xai.md
    • api/models/groq.md
    • api/models/huggingface.md
    • api/models/instrumented.md
    • api/models/mcp-sampling.md
    • api/models/mistral.md
    • api/models/ollama.md
    • api/models/openai.md
    • api/models/openrouter.md
    • api/models/outlines.md
    • api/models/test.md
    • api/models/wrapper.md
    • api/output.md
    • api/profiles.md
    • api/providers.md
    • api/result.md
    • api/retries.md
    • api/run.md
    • api/settings.md
    • api/tools.md
    • api/toolsets.md
    • api/ui/ag_ui.md
    • api/ui/base.md
    • api/ui/vercel_ai.md
    • api/usage.md
  • pydantic_evals:
    • api/pydantic_evals/dataset.md
    • api/pydantic_evals/evaluators.md
    • api/pydantic_evals/lifecycle.md
    • api/pydantic_evals/online.md
    • api/pydantic_evals/online_capability.md
    • api/pydantic_evals/reporting.md
    • api/pydantic_evals/otel.md
    • api/pydantic_evals/generation.md
  • pydantic_graph:
    • api/pydantic_graph/basenode.md
    • api/pydantic_graph/graph_builder.md
    • api/pydantic_graph/step.md
    • api/pydantic_graph/join.md
    • api/pydantic_graph/decision.md
    • api/pydantic_graph/node.md
    • api/pydantic_graph/exceptions.md
  • fasta2a:
    • api/fasta2a.md

• Project:

  • contributing.md
  • changelog.md
  • version-policy.md

extra:

hide the "Made with Material for MkDocs" message

generator: false social: - icon: fontawesome/brands/github link: https://github.com/pydantic/pydantic-ai - icon: fontawesome/brands/bluesky link: https://bsky.app/profile/pydantic.dev - icon: fontawesome/brands/x-twitter link: https://x.com/pydantic - icon: fontawesome/brands/linkedin link: https://www.linkedin.com/company/pydantic

theme: name: "material" custom_dir: docs/.overrides palette: - media: "(prefers-color-scheme)" primary: pink accent: pink toggle: icon: material/brightness-auto name: "Switch to light mode" - media: "(prefers-color-scheme: light)" scheme: default primary: pink accent: pink toggle: icon: material/brightness-7 name: "Switch to dark mode" - media: "(prefers-color-scheme: dark)" scheme: slate primary: pink accent: pink toggle: icon: material/brightness-4 name: "Switch to system preference" features: - search.suggest - search.highlight - content.tabs.link - content.code.annotate - content.code.copy - content.code.select - navigation.path - navigation.indexes - navigation.sections - navigation.tracking - toc.follow - announce.dismiss logo: "img/logo-white.svg" favicon: "favicon.ico"

https://www.mkdocs.org/user-guide/configuration/#validation

validation: omitted_files: warn absolute_links: warn unrecognized_links: warn anchors: warn

extra_css:

• "extra/tweaks.css"

used for analytics

extra_javascript:

• "/flarelytics/client.js"
• "https://cdn.jsdelivr.net/npm/[email protected]/dist/lite/builds/browser.umd.js"
• "https://cdn.jsdelivr.net/npm/[email protected]/dist/instantsearch.production.min.js"
• "/javascripts/algolia-search.js"

markdown_extensions:

• tables
• admonition
• attr_list
• md_in_html
• pymdownx.details
• pymdownx.caret
• pymdownx.critic
• pymdownx.mark
• pymdownx.superfences
• pymdownx.snippets
• pymdownx.tilde
• pymdownx.inlinehilite
• pymdownx.highlight: pygments_lang_class: true
• pymdownx.extra: pymdownx.superfences: custom_fences: - name: mermaid class: mermaid format: !!python/name:pymdownx.superfences.fence_code_format
• pymdownx.emoji: emoji_index: !!python/name:material.extensions.emoji.twemoji emoji_generator: !!python/name:material.extensions.emoji.to_svg options: custom_icons: - docs/.overrides/.icons
• pymdownx.tabbed: alternate_style: true
• pymdownx.tasklist: custom_checkbox: true
• sane_lists # this means you can start a list from any number
• material.extensions.preview: targets: include: - '*'
• pydantic_docs.mdext

watch:

• pydantic_ai_slim
• pydantic_evals
• pydantic_graph
• examples

plugins:

• search
• social
• glightbox
• mkdocstrings: handlers: python: paths: [pydantic_ai_slim/pydantic_ai] options: docstring_options: # pydantic_graph/beta/graph.py uses "Type Parameters:" sections to document Generic type params # like StateT, OutputT, etc. Griffe can't extract these from Generic[T] base classes # (only from PEP 695 syntax), so we disable the validation warnings. warn_unknown_params: false relative_crossrefs: true members_order: source separate_signature: true show_signature_annotations: true signature_crossrefs: true group_by_category: false # 3 because docs are in pages with an H2 just above them heading_level: 3 extensions: - griffe_warnings_deprecated: kind: warning title: Deprecated inventories: - url: https://logfire.pydantic.dev/docs/objects.inv - url: https://docs.python.org/3/objects.inv - url: https://docs.pydantic.dev/latest/objects.inv - url: https://dirty-equals.helpmanual.io/latest/objects.inv - url: https://fastapi.tiangolo.com/objects.inv - url: https://typing-extensions.readthedocs.io/en/latest/objects.inv - url: https://rich.readthedocs.io/en/stable/objects.inv - url: https://modelcontextprotocol.github.io/python-sdk/objects.inv # waiting for https://github.com/encode/httpx/discussions/3091#discussioncomment-11205594
• llmstxt: enabled: !ENV [CI, false] full_output: llms-full.txt markdown_description: |- Pydantic AI is a Python agent framework designed to make it less painful to build production grade applications with Generative AI. sections: Introduction: - index.md - install.md - help.md - troubleshooting.md - coding-agent-skills.md Concepts documentation: - a2a.md - agent.md - agent-spec.md - native-tools.md - capabilities.md - dependencies.md - deferred-tools.md - direct.md - embeddings.md - gateway.md - input.md - tools.md - common-tools.md - output.md - retries.md - message-history.md - extensibility.md - hooks.md - multi-agent-applications.md - thinking.md - third-party-tools.md - tools-advanced.md - toolsets.md - web.md Models: - models/.md Graphs: - graph.md - graph/.md API Reference: - api/.md Evals: - evals.md - evals/.md Durable Execution: - durable_execution/.md MCP: - mcp/.md UI Event Streams: - ui/.md Optional: - testing.md - cli.md - logfire.md - contributing.md - changelog.md - version-policy.md Examples: - examples/.md

DON'T PUT REDIRECTS IN THIS FILE! Instead add them to docs-site/src/index.ts

hooks:

• "docs/.hooks/main.py"
• "docs/.hooks/algolia.py"