Concepts docs

docs/api/messages.md

@@ -1,3 +1,17 @@
 # `pydantic_ai.messages`
 
 ::: pydantic_ai.messages
+    options:
+      members:
+        - Message
+        - SystemPrompt
+        - UserPrompt
+        - ToolReturn
+        - RetryPrompt
+        - ModelAnyResponse
+        - ModelTextResponse
+        - ModelStructuredResponse
+        - ToolCall
+        - ArgsJson
+        - ArgsObject
+        - MessagesTypeAdapter

docs/concepts/dependencies.md

@@ -0,0 +1,339 @@
+# Dependencies
+
+PydanticAI uses a dependency injection system to provide data and services to your agent's [system prompts](system-prompt.md), [retrievers](retrievers.md) and [result validators](result-validation.md#TODO).
+
+Matching PydanticAI's design philosophy, our dependency system tries to use existing best practice in Python development rather than inventing esoteric "magic", this should make dependencies type-safe, understandable easier to test and ultimately easier to deploy in production.
+
+## Defining Dependencies
+
+Dependencies can be any python type. While in simple cases you might be able to pass a single object
+as a dependency (e.g. an HTTP connection), [dataclasses][] are generally a convenient container when your dependencies included multiple objects.
+
+Here's an example of defining an agent that requires dependencies.
+
+(**Note:** dependencies aren't actually used in this example, see [Accessing Dependencies](#accessing-dependencies) below)
+
+```python title="unused_dependencies.py"
+from dataclasses import dataclass
+
+import httpx
+
+from pydantic_ai import Agent
+
+
+@dataclass
+class MyDeps:  # (1)!
+    api_key: str
+    http_client: httpx.AsyncClient
+
+
+agent = Agent(
+    'openai:gpt-4o',
+    deps_type=MyDeps,  # (2)!
+)
+
+
+async def main():
+    async with httpx.AsyncClient() as client:
+        deps = MyDeps('foobar', client)
+        result = await agent.run(
+            'Tell me a joke.',
+            deps=deps,  # (3)!
+        )
+        print(result.data)
+```
+
+1. Define a dataclass to hold dependencies.
+2. Pass the dataclass type to the `deps_type` argument of the [`Agent` constructor][pydantic_ai.Agent.__init__]. **Note**: we're passing the type here, NOT an instance, this parameter is not actually used at runtime, it's here so we can get full type checking of the agent.
+3. When running the agent, pass an instance of the dataclass to the `deps` parameter.
+
+_(This example is complete, it can be run "as is" inside an async context)_
+
+## Accessing Dependencies
+
+Dependencies are accessed through the [`CallContext`][pydantic_ai.dependencies.CallContext] type, this should be the first parameter of system prompt functions etc.
+
+
+```python title="system_prompt_dependencies.py" hl_lines="20-27"
+from dataclasses import dataclass
+
+import httpx
+
+from pydantic_ai import Agent, CallContext
+
+
+@dataclass
+class MyDeps:
+    api_key: str
+    http_client: httpx.AsyncClient
+
+
+agent = Agent(
+    'openai:gpt-4o',
+    deps_type=MyDeps,
+)
+
+
+@agent.system_prompt  # (1)!
+async def get_system_prompt(ctx: CallContext[MyDeps]) -> str:  # (2)!
+    response = await ctx.deps.http_client.get(  # (3)!
+        'https://example.com',
+        headers={'Authorization': f'Bearer {ctx.deps.api_key}'}  # (4)!
+    )
+    response.raise_for_status()
+    return f'Prompt: {response.text}'
+
+
+async def main():
+    async with httpx.AsyncClient() as client:
+        deps = MyDeps('foobar', client)
+        result = await agent.run('Tell me a joke.', deps=deps)
+        print(result.data)
+```
+
+1. [`CallContext`][pydantic_ai.dependencies.CallContext] may optionally be passed to a [`system_prompt`][pydantic_ai.Agent.system_prompt] function as the only argument.
+2. [`CallContext`][pydantic_ai.dependencies.CallContext] is parameterized with the type of the dependencies, if this type is incorrect, static type checkers will raise an error.
+3. Access dependencies through the [`.deps`][pydantic_ai.dependencies.CallContext.deps] attribute.
+4. Access dependencies through the [`.deps`][pydantic_ai.dependencies.CallContext.deps] attribute.
+
+_(This example is complete, it can be run "as is" inside an async context)_
+
+### Asynchronous vs. Synchronous dependencies
+
+System prompt functions, retriever functions and result validator are all run in the async context of an agent run.
+
+If these functions are not coroutines (e.g. `async def`) they are called with
+[`run_in_executor`][asyncio.loop.run_in_executor] in a thread pool, it's therefore marginally preferable
+to use `async` methods where dependencies perform IO, although synchronous dependencies should work fine too.
+
+!!! note "`run` vs. `run_sync` and Asynchronous vs. Synchronous dependencies"
+    Whether you use synchronous or asynchronous dependencies, is completely independent of whether you use `run` or `run_sync` — `run_sync` is just a wrapper around `run` and agents are always run in an async context.
+
+Here's the same example as above, but with a synchronous dependency:
+
+```python title="sync_dependencies.py"
+from dataclasses import dataclass
+
+import httpx
+
+from pydantic_ai import Agent, CallContext
+
+
+@dataclass
+class MyDeps:
+    api_key: str
+    http_client: httpx.Client  # (1)!
+
+
+agent = Agent(
+    'openai:gpt-4o',
+    deps_type=MyDeps,
+)
+
+
+@agent.system_prompt
+def get_system_prompt(ctx: CallContext[MyDeps]) -> str:  # (2)!
+    response = ctx.deps.http_client.get(
+        'https://example.com',
+        headers={'Authorization': f'Bearer {ctx.deps.api_key}'}
+    )
+    response.raise_for_status()
+    return f'Prompt: {response.text}'
+
+
+async def main():
+    deps = MyDeps('foobar', httpx.Client())
+    result = await agent.run(
+        'Tell me a joke.',
+        deps=deps,
+    )
+    print(result.data)
+```
+
+1. Here we use a synchronous `httpx.Client` instead of an asynchronous `httpx.AsyncClient`.
+2. To match the synchronous dependency, the system prompt function is now a plain function, not a coroutine.
+
+_(This example is complete, it can be run "as is")_
+
+## Full Example
+
+As well as system prompts, dependencies can be used in [retrievers](retrievers.md) and [result validators](result-validation.md#TODO).
+
+```python title="full_example.py" hl_lines="27-35 38-48"
+from dataclasses import dataclass
+
+import httpx
+
+from pydantic_ai import Agent, CallContext, ModelRetry
+
+
+@dataclass
+class MyDeps:
+    api_key: str
+    http_client: httpx.AsyncClient
+
+
+agent = Agent(
+    'openai:gpt-4o',
+    deps_type=MyDeps,
+)
+
+
+@agent.system_prompt
+async def get_system_prompt(ctx: CallContext[MyDeps]) -> str:
+    response = await ctx.deps.http_client.get('https://example.com')
+    response.raise_for_status()
+    return f'Prompt: {response.text}'
+
+
+@agent.retriever_context  # (1)!
+async def get_joke_material(ctx: CallContext[MyDeps], subject: str) -> str:
+    response = await ctx.deps.http_client.get(
+        'https://example.com#jokes',
+        params={'subject': subject},
+        headers={'Authorization': f'Bearer {ctx.deps.api_key}'},
+    )
+    response.raise_for_status()
+    return response.text
+
+
+@agent.result_validator  # (2)!
+async def validate_result(ctx: CallContext[MyDeps], final_response: str) -> str:
+    response = await ctx.deps.http_client.post(
+        'https://example.com#validate',
+        headers={'Authorization': f'Bearer {ctx.deps.api_key}'},
+        params={'query': final_response},
+    )
+    if response.status_code == 400:
+        raise ModelRetry(f'invalid response: {response.text}')
+    response.raise_for_status()
+    return final_response
+
+
+async def main():
+    async with httpx.AsyncClient() as client:
+        deps = MyDeps('foobar', client)
+        result = await agent.run('Tell me a joke.', deps=deps)
+        print(result.data)
+```
+
+1. To pass `CallContext` and to a retriever, us the [`retriever_context`][pydantic_ai.Agent.retriever_context] decorator.
+2. `CallContext` may optionally be passed to a [`result_validator`][pydantic_ai.Agent.result_validator] function as the first argument.
+
+## Overriding Dependencies
+
+When testing agents, it's useful to be able to customise dependencies.
+
+While this can sometimes be done by calling the agent directly within unit tests, we can also override dependencies
+while calling application code which in turn calls the agent.
+
+This is done via the [`override_deps`][pydantic_ai.Agent.override_deps] method on the agent.
+
+```py title="joke_app.py"
+from dataclasses import dataclass
+
+import httpx
+
+from pydantic_ai import Agent, CallContext
+
+
+@dataclass
+class MyDeps:
+    api_key: str
+    http_client: httpx.AsyncClient
+
+    async def system_prompt_factory(self) -> str:  # (1)!
+        response = await self.http_client.get('https://example.com')
+        response.raise_for_status()
+        return f'Prompt: {response.text}'
+
+
+joke_agent = Agent('openai:gpt-4o', deps_type=MyDeps)
+
+
+@joke_agent.system_prompt
+async def get_system_prompt(ctx: CallContext[MyDeps]) -> str:
+    return await ctx.deps.system_prompt_factory()  # (2)!
+
+
+async def application_code(prompt: str) -> str:  # (3)!
+    ...
+    ...
+    # now deep within application code we call our agent
+    async with httpx.AsyncClient() as client:
+        app_deps = MyDeps('foobar', client)
+        result = await joke_agent.run(prompt, deps=app_deps)  # (4)!
+    return result.data
+
+```
+
+1. Define a method on the dependency to make the system prompt easier to customise.
+2. Call the system prompt factory from within the system prompt function.
+3. Application code that calls the agent, in a real application this might be an API endpoint.
+4. Call the agent from within the application code, in a real application this call might be deep within a call stack. Note `app_deps` here will NOT be used when deps are overridden.
+
+```py title="test_joke_app.py" hl_lines="10-12"
+from joke_app import application_code, joke_agent, MyDeps
+
+
+class TestMyDeps(MyDeps):  # (1)!
+    async def system_prompt_factory(self) -> str:
+        return 'test prompt'
+
+
+async def test_application_code():
+    test_deps = TestMyDeps('test_key', None)  # (2)!
+    with joke_agent.override_deps(test_deps):  # (3)!
+        joke = application_code('Tell me a joke.')  # (4)!
+    assert joke == 'funny'
+```
+
+1. Define a subclass of `MyDeps` in tests to customise the system prompt factory.
+2. Create an instance of the test dependency, we don't need to pass an `http_client` here as it's not used.
+3. Override the dependencies of the agent for the duration of the `with` block, `test_deps` will be used when the agent is run.
+4. Now we can safely call our application code, the agent will use the overridden dependencies.
+
+## Agents as dependencies of other Agents
+
+Since dependencies can be any python type, and agents are just python objects, agents can be dependencies of other agents.
+
+```py title="agents_as_dependencies.py"
+from dataclasses import dataclass
+
+from pydantic_ai import Agent, CallContext
+
+
+@dataclass
+class MyDeps:
+    factory_agent: Agent[None, list[str]]
+
+
+joke_agent = Agent(
+    'openai:gpt-4o',
+    deps_type=MyDeps,
+    system_prompt=(
+        'Use the "joke_factory" to generate some jokes, then choose the best. '
+        'You must return just a single joke.'
+    )
+)
+
+factory_agent = Agent('gemini-1.5-pro', result_type=list[str])
+
+
+@joke_agent.retriever_context
+async def joke_factory(ctx: CallContext[MyDeps], count: int) -> str:
+    r = await ctx.deps.factory_agent.run(f'Please generate {count} jokes.')
+    return '\n'.join(r.data)
+
+
+result = joke_agent.run_sync('Tell me a joke.', deps=MyDeps(factory_agent))
+print(result.data)
+```
+
+## Examples
+
+The following examples demonstrate how to use dependencies in PydanticAI:
+
+- [Weather Agent](../examples/weather-agent.md)
+- [SQL Generation](../examples/sql-gen.md)
+- [RAG](../examples/rag.md)