@exit 1

@echo 'installing insiders packages...'

@uv pip install -U mkdocs-material mkdocstrings-python \

--extra-index-url https://pydantic:${PPPR_TOKEN}@pppr.pydantic.dev/simple/

@uv pip install -U \

--extra-index-url https://pydantic:${PPPR_TOKEN}@pppr.pydantic.dev/simple/ \

mkdocs-material mkdocstrings-python

.PHONY: docs-insiders# Build the documentation using insiders packages

uv python install 3.12

uv sync --python 3.12 --frozen --group docs

uv pip install -U\

--extra-index-url https://pydantic:$(PPPR_TOKEN)@pppr.pydantic.dev/simple/\

--extra-index-url https://pydantic:${PPPR_TOKEN}@pppr.pydantic.dev/simple/\

mkdocs-material mkdocstrings-python

uv pip freeze

uv run --no-sync mkdocs build

uv run --no-sync mkdocs build -f mkdocs.insiders.yml

.PHONY: all

all: format lint typecheck testcov

Examples of how to usePydantic AI and what it can do.

Examples of how to usePydanticAI and what it can do.

Simple example of using Pydantic AI to construct a Pydantic model from a text input.

Simple example of using PydanticAI to construct a Pydantic model from a text input.

Demonstrates:

* RAG search

This is done by creating a database containing each section of the markdown documentation, then registering

the search tool as a retriever with thePydantic AI agent.

the search tool as a retriever with thePydanticAI agent.

Logic for extracting sections from markdown files and a JSON file with that data is available in

[this gist](https://gist.github.com/samuelcolvin/4b5bb9bb163b1122ff17e29e48c10992).

python/uv-run -m pydantic_ai_examples.rag build

(Note building the database doesn't usePydantic AI right now, instead it uses the OpenAI SDK directly.)

(Note building the database doesn't usePydanticAI right now, instead it uses the OpenAI SDK directly.)

You can then ask the agent a question with:

Example demonstrating how to usePydantic AI to generate SQL queries based on user input.

Example demonstrating how to usePydanticAI to generate SQL queries based on user input.

Demonstrates:

Example ofPydantic AI with multiple tools which the LLM needs to call in turn to answer a question.

Example ofPydanticAI with multiple tools which the LLM needs to call in turn to answer a question.

Demonstrates:

Examples of how to usePydantic AI and what it can do.

Examples of how to usePydanticAI and what it can do.

Full documentation of these examples and how to run them is available at[ai.pydantic.dev/examples/](https://ai.pydantic.dev/examples/).

[project]

name ="pydantic-ai-examples"

version ="0.0.6"

description ="Agent Framework / shimto usePydantic with LLMs"

description ="Examples of howto usePydanticAI and what it can do."

authors = [

{name ="Samuel Colvin",email ="samuel@pydantic.dev" },

]