New intro

docs/examples/bank-support.md

@@ -0,0 +1,23 @@
+Small but complete example of using PydanticAI to build a support agent for a bank.
+
+Demonstrates:
+
+* [dynamic system prompt](../agents.md#system-prompts)
+* [structured `result_type`](../results.md#structured-result-validation)
+* [retrievers](../agents.md#retrievers)
+
+## Running the Example
+
+With [dependencies installed and environment variables set](./index.md#usage), run:
+
+```bash
+python/uv-run -m pydantic_ai_examples.bank_support
+```
+
+(or `PYDANTIC_AI_MODEL=gemini-1.5-flash ...`)
+
+## Example Code
+
+```py title="bank_support.py"
+#! pydantic_ai_examples/bank_support.py
+```

docs/examples/chat-app.md

@@ -3,8 +3,8 @@ Simple chat app example build with FastAPI.
 Demonstrates:
 
 * [reusing chat history](../message-history.md)
-* serializing messages
-* streaming responses
+* [serializing messages](../message-history.md#accessing-messages-from-results)
+* [streaming responses](../results.md#streamed-results)
 
 This demonstrates storing chat history between requests and using it to give the model context for new responses.
 

docs/examples/index.md

@@ -61,7 +61,17 @@ For examples, to run the very simple [`pydantic_model`](./pydantic-model.md) exa
 python/uv-run -m pydantic_ai_examples.pydantic_model
 ```
 
-But you'll probably want to edit examples in addition to just running them. You can copy the examples to a new directory with:
+If you like on-liners and you're using uv, you can run a pydantic-ai example with zero setup:
+
+```bash
+OPENAI_API_KEY='your-api-key' \
+  uv run --with 'pydantic-ai[examples]' \
+  -m pydantic_ai_examples.pydantic_model
+```
+
+---
+
+You'll probably want to edit examples in addition to just running them. You can copy the examples to a new directory with:
 
 ```bash
 python/uv-run -m pydantic_ai_examples --copy-to examples/

docs/examples/pydantic-model.md

@@ -2,7 +2,7 @@ Simple example of using Pydantic AI to construct a Pydantic model from a text in
 
 Demonstrates:
 
-* custom `result_type`
+* [structured `result_type`](../results.md#structured-result-validation)
 
 ## Running the Example
 

docs/examples/rag.md

@@ -4,7 +4,7 @@ RAG search example. This demo allows you to ask question of the [logfire](https:
 
 Demonstrates:
 
-* retrievers
+* [retrievers](../agents.md#retrievers)
 * [agent dependencies](../dependencies.md)
 * RAG search
 

docs/examples/sql-gen.md

@@ -4,9 +4,9 @@ Example demonstrating how to use Pydantic AI to generate SQL queries based on us
 
 Demonstrates:
 
-* custom `result_type`
-* dynamic system prompt
-* result validation
+* [dynamic system prompt](../agents.md#system-prompts)
+* [structured `result_type`](../results.md#structured-result-validation)
+* [result validation](../results.md#result-validators-functions)
 * [agent dependencies](../dependencies.md)
 
 ## Running the Example

docs/examples/weather-agent.md

@@ -2,8 +2,7 @@ Example of Pydantic AI with multiple tools which the LLM needs to call in turn t
 
 Demonstrates:
 
-* retrievers
-* multiple retrievers
+* [retrievers](../agents.md#retrievers)
 * [agent dependencies](../dependencies.md)
 
 In this case the idea is a "weather" agent — the user can ask for the weather in multiple locations,

docs/index.md

@@ -1,78 +1,135 @@
+# Introduction {.hide}
+
 --8<-- "docs/.partials/index-header.html"
 
-# PydanticAI {.hide}
+When I first found FastAPI, I got it immediately, I was excited to find something so genuinely innovative and yet ergonomic built on Pydantic.
+
+Virtually every Agent Framework and LLM library in Python uses Pydantic, but when we came to use Gen AI in [Pydantic Logfire](https://pydantic.dev/logfire), I couldn't find anything that gave me the same feeling.
+
+PydanticAI is a Python Agent Framework designed to make it less painful to build production grade applications with Generative AI.
 
-You can think of PydanticAI as an Agent Framework or a shim to use Pydantic with LLMs — they're the same thing.
+## Why use PydanticAI
 
-PydanticAI tries to make working with LLMs feel similar to building a web application.
+* Built by the team behind Pydantic (the validation layer of the OpenAI SDK, the Anthropic SDK, Langchain, LlamaIndex, AutoGPT, Transformers, Instructor and many more)
+* Multi-model — currently with OpenAI and Gemini are support, Anthropic [coming soon](https://github.com/pydantic/pydantic-ai/issues/63), simply interface to implement other models or adapt existing ones
+* Type-safe
+* Built on tried and tested best practices in Python
+* Structured response validation with Pydantic
+* Streamed responses, including validation of streamed structured responses with Pydantic
+* Novel, type-safe dependency injection system
+* Logfire integration
 
 !!! example "In Beta"
     PydanticAI is in early beta, the API is subject to change and there's a lot more to do.
     [Feedback](https://github.com/pydantic/pydantic-ai/issues) is very welcome!
 
+## Example — Hello World
+
+Here's a very minimal example of PydanticAI.
+
+```py title="hello_world.py"
+from pydantic_ai import Agent
+
+agent = Agent('gemini-1.5-flash', system_prompt='Be concise, reply with one sentence.')
+
+result = agent.run_sync('Where does "hello world" come from?')
+print(result.data)
+"""
+The first known use of "hello, world" was in a 1974 textbook about the C programming language.
+"""
+```
+_(This example is complete, it can be run "as is")_
+
+Not very interesting yet, but we can easily add retrievers, dynamic system prompts and structured responses to build more powerful agents.
+
 ## Example — Retrievers and Dependency Injection
 
-Partial example of using retrievers to help an LLM respond to a user's query about the weather:
+Small but complete example of using PydanticAI to build a support agent for a bank.
+
+```py title="bank_support.py"
+from dataclasses import dataclass
 
-```py title="weather_agent.py"
-import httpx
+from pydantic import BaseModel, Field
 
 from pydantic_ai import Agent, CallContext
 
-weather_agent = Agent(  # (1)!
+from bank_database import DatabaseConn
+
+
+@dataclass
+class SupportDependencies:  # (3)!
+    customer_id: int
+    db: DatabaseConn
+
+
+class SupportResult(BaseModel):
+    support_advice: str = Field(description='Advice returned to the customer')
+    block_card: bool = Field(description='Whether to block their')
+    risk: int = Field(description='Risk level of query', ge=0, le=10)
+
+
+support_agent = Agent(  # (1)!
     'openai:gpt-4o',  # (2)!
-    deps_type=httpx.AsyncClient,  # (3)!
-    system_prompt='Be concise, reply with one sentence.',  # (4)!
+    deps_type=SupportDependencies,
+    result_type=SupportResult,  # (9)!
+    system_prompt=(  # (4)!
+        'You are a support agent in our bank, give the '
+        'customer support and judge the risk level of their query. '
+        "Reply using the customer's name."
+    ),
 )
 
 
-@weather_agent.retriever_context  # (5)!
-async def get_location(
-    ctx: CallContext[httpx.AsyncClient],
-    location_description: str,
-) -> dict[str, float]:
-    """Get the latitude and longitude of a location by its description."""  # (6)!
-    response = await ctx.deps.get('https://api.geolocation...')
-    ...
-
-
-@weather_agent.retriever_context  # (7)!
-async def get_weather(
-    ctx: CallContext[httpx.AsyncClient],
-    lat: float,
-    lng: float,
-) -> dict[str, str]:
-    """Get the weather at a location by its latitude and longitude."""
-    response = await ctx.deps.get('https://api.weather...')
-    ...
-
-
-async def main():
-    async with httpx.AsyncClient() as client:
-        result = await weather_agent.run(  # (8)!
-            'What is the weather like in West London and in Wiltshire?',
-            deps=client,
-        )
-        print(result.data)  # (9)!
-        #> The weather in West London is raining, while in Wiltshire it is sunny.
-
-        messages = result.all_messages()  # (10)!
+@support_agent.system_prompt  # (5)!
+async def add_customer_name(ctx: CallContext[SupportDependencies]) -> str:
+    customer_name = await ctx.deps.db.customer_name(id=ctx.deps.customer_id)
+    return f"The customer's name is {customer_name!r}"
+
+
+@support_agent.retriever_context  # (6)!
+async def customer_balance(
+    ctx: CallContext[SupportDependencies], include_pending: bool
+) -> str:
+    """Returns the customer's current account balance."""  # (7)!
+    balance = await ctx.deps.db.customer_balance(
+        id=ctx.deps.customer_id,
+        include_pending=include_pending,
+    )
+    return f'${balance:.2f}'
+
+
+...  # (11)!
+
+
+deps = SupportDependencies(customer_id=123, db=DatabaseConn())
+result = support_agent.run_sync('What is my balance?', deps=deps)  # (8)!
+print(result.data)  # (10)!
+"""
+support_advice='Hello John, your current account balance, including pending transactions, is $123.45.' block_card=False risk=1
+"""
+
+result = support_agent.run_sync('I just lost my card!', deps=deps)
+print(result.data)
+"""
+support_advice="I'm sorry to hear that, John. We are temporarily blocking your card to prevent unauthorized transactions." block_card=True risk=8
+"""
 ```
 
-1. An agent that can tell users about the weather in a particular location. Agents combine a system prompt, a response type (here `str`) and "retrievers" (aka tools).
-2. Here we configure the agent to use OpenAI's GPT-4o model, you can also customise the model when running the agent.
-3. We specify the type dependencies for the agent, in this case an HTTP client, which retrievers will use to make requests to external services. PydanticAI's system of dependency injection provides a powerful, type safe way to customise the behaviour of your agents, including for unit tests and evals.
-4. Static system prompts can be registered as key word arguments to the agent, dynamic system prompts can be registered with the `@agent.system_prompot` decorator and benefit from dependency injection.
-5. Retrievers let you register "tools" which the LLM may call while to respond to a user. You inject dependencies into the retriever with `CallContext`, any other arguments become the tool schema passed to the LLM, Pydantic is used to validate these arguments, errors are passed back to the LLM so it can retry.
-6. This docstring is also passed to the LLM as a description of the tool.
-7. Multiple retrievers can be registered with the same agent, the LLM can choose which (if any) retrievers to call in order to respond to a user.
-8. Run the agent asynchronously, conducting a conversation with the LLM until a final response is reached. You can also run agents synchronously with `run_sync`. Internally agents are all async, so `run_sync` is a helper using `asyncio.run` to call `run()`.
-9. The response from the LLM, in this case a `str`, Agents are generic in both the type of `deps` and `result_type`, so calls are typed end-to-end.
-10. [`result.all_messages()`](message-history.md) includes details of messages exchanged, this is useful both to understand the conversation that took place and useful if you want to continue the conversation later — messages can be passed back to later `run/run_sync` calls.
+1. An [agent](agents.md) that acts as first-tier support in a bank, agents are generic in the type of dependencies they take and the type of result they return, in this case `Deps` and `SupportResult`.
+2. Here we configure the agent to use [OpenAI's GPT-4o model](api/models/openai.md), you can also customise the model when running the agent.
+3. The `SupportDependencies` dataclass is used to pass data and connections into the model that will be needed when running [system prompts](agents.md#system-prompts) and [retrievers](agents.md#retrievers). PydanticAI's system of dependency injection provides a powerful, type safe way to customise the behaviour of your agents, including for unit tests and evals.
+4. Static [system prompts](agents.md#system-prompts) can be registered as keyword arguments to the agent
+5. dynamic [system prompts](agents.md#system-prompts) can be registered with the `@agent.system_prompot` decorator and benefit from dependency injection.
+6. [Retrievers](agents.md#retrievers) let you register "tools" which the LLM may call while responding to a user. You inject dependencies into the retriever with [`CallContext`][pydantic_ai.dependencies.CallContext], any other arguments become the tool schema passed to the LLM, Pydantic is used to validate these arguments, errors are passed back to the LLM so it can retry.
+7. The docstring is also passed to the LLM as a description of the tool.
+8. [Run the agent](agents.md#running-agents) synchronously, conducting a conversation with the LLM until a final response is reached.
+9. The response from the agent will, be guaranteed to be a `SupportResult`, if validation fails [reflection](agents.md#reflection-and-self-correction) will mean the agent is prompted to try again.
+10. The result will be validated with Pydantic to guarantee it is a `SupportResult`, since the agent is generic, it'll also be typed as a `SupportResult` to aid with static type checking.
+11. In real use case, you'd add many more retrievers to the agent to extend the context it's equipped with and support it can provide.
 
-!!! tip "Complete `weather_agent.py` example"
-    This example is incomplete for the sake of brevity; you can find a complete `weather_agent.py` example [here](examples/weather-agent.md).
+!!! tip "Complete `bank_support.py` example"
+    This example is incomplete for the sake of brevity (the definition of `DatabaseConn` is missing); you can find a complete `bank_support.py` example [here](examples/bank-support.md).
 
-## Example — Result Validation
+## Next Steps
 
-TODO
+To try PydanticAI yourself, follow instructions [in examples](examples/index.md).

docs/install.md

@@ -36,4 +36,6 @@ To use Logfire with PydanticAI, install PydanticAI with the `logfire` optional g
 
 From there, follow the [Logfire documentation](https://logfire.pydantic.dev/docs/) to configure Logfire.
 
-TODO screenshot of Logfire with PydanticAI in action.
+## Next Steps
+
+To run PydanticAI, follow instructions [in examples](examples/index.md).

mkdocs.yml

@@ -23,6 +23,7 @@ nav:
     - examples/index.md
     - examples/pydantic-model.md
     - examples/weather-agent.md
+    - examples/bank-support.md
     - examples/sql-gen.md
     - examples/rag.md
     - examples/stream-markdown.md