Document the Outlines model

Author: RobinPicard

docs/api/models/outlines.md

@@ -0,0 +1,7 @@
+# `pydantic_ai.models.outlines`
+
+## Setup
+
+For details on how to set up this model, see [model configuration for Outlines](../../models/outlines.md).
+
+::: pydantic_ai.models.outlines

docs/builtin-tools.md

@@ -32,6 +32,7 @@ making it ideal for queries that require up-to-date data.
 | Mistral | ❌ | Not supported |
 | Cohere | ❌ | Not supported |
 | HuggingFace | ❌ | Not supported |
+| Outlines | ❌ | Not supported |
 
 !!! note "Groq Support"
     To use web search capabilities with Groq, you need to use the [compound models](https://console.groq.com/docs/compound).
@@ -107,6 +108,7 @@ in a secure environment, making it perfect for computational tasks, data analysi
 | Mistral | ❌ |
 | Cohere | ❌ |
 | HuggingFace | ❌ |
+| Outlines | ❌ |
 
 ### Usage
 
@@ -136,6 +138,7 @@ allowing it to pull up-to-date information from the web.
 | Mistral | ❌ |
 | Cohere | ❌ |
 | HuggingFace | ❌ |
+| Outlines | ❌ |
 
 ### Usage
 

docs/index.md

@@ -24,7 +24,7 @@ We built Pydantic AI with one simple aim: to bring that FastAPI feeling to GenAI
   Built by the team behind [Pydantic Validation](https://docs.pydantic.dev/latest/) (the validation layer of the OpenAI SDK, the Anthropic SDK, LangChain, LlamaIndex, AutoGPT, Transformers, CrewAI, Instructor and many more).
 
 - **Model-agnostic**:
-  Supports OpenAI, Anthropic, Gemini, Deepseek, Ollama, Groq, Cohere, and Mistral, and there is a simple interface to implement support for [other models](models/overview.md).
+  Supports OpenAI, Anthropic, Gemini, Deepseek, Ollama, Groq, Cohere, Mistral, and Outlines, and there is a simple interface to implement support for [other models](models/overview.md).
 
 - **Pydantic Logfire Integration**:
   Seamlessly [integrates](logfire.md) with [Pydantic Logfire](https://pydantic.dev/logfire) for real-time debugging, performance monitoring, and behavior tracking of your LLM-powered applications.

docs/install.md

@@ -51,6 +51,7 @@ pip/uv-add "pydantic-ai-slim[openai]"
 * `cohere` - installs `cohere` [PyPI ↗](https://pypi.org/project/cohere){:target="_blank"}
 * `bedrock` - installs `boto3` [PyPI ↗](https://pypi.org/project/boto3){:target="_blank"}
 * `huggingface` - installs `huggingface-hub[inference]` [PyPI ↗](https://pypi.org/project/huggingface-hub){:target="_blank"}
+* `outlines` - installs `outlines` [PyPI ↗](https://pypi.org/project/outlines){:target="_blank"}
 * `duckduckgo` - installs `ddgs` [PyPI ↗](https://pypi.org/project/ddgs){:target="_blank"}
 * `tavily` - installs `tavily-python` [PyPI ↗](https://pypi.org/project/tavily-python){:target="_blank"}
 * `cli` - installs `rich` [PyPI ↗](https://pypi.org/project/rich){:target="_blank"}, `prompt-toolkit` [PyPI ↗](https://pypi.org/project/prompt-toolkit){:target="_blank"}, and `argcomplete` [PyPI ↗](https://pypi.org/project/argcomplete){:target="_blank"}

docs/models/outlines.md

@@ -0,0 +1,73 @@
+# Outlines
+
+## Install
+
+To use `OutlinesModel`, you need to either install `pydantic-ai`, or install `pydantic-ai-slim` with the `outlines` optional group:
+
+```bash
+pip/uv-add "pydantic-ai-slim[outlines]"
+```
+
+As Outlines is a library allowing you to run model from various different providers, it does not include the necessary dependencies for any model, but instead requires you to install the optional group for the provider you want to use. For instance:
+
+```bash
+pip/uv-add "outlines[transformers]"
+```
+
+Or
+
+```bash
+pip/uv-add "outlines[mlxlm]"
+```
+
+## Model Initialization
+
+As Outlines is not an inference provider, but instead a library allowing you to run bith local and API-based models, instantiating the model is a bit different from the other models available on Pydantic-AI.
+
+To initialize the `OutlinesModel` through the `__init__` method, the first argument you must provide has to be an `outlines.Model` or an `outlines.AsyncModel` instance.
+
+For instance:
+
+```python
+import outlines
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+from pydantic_ai.models.outlines import OutlinesModel
+
+outlines_model = outlines.from_transformers(
+    AutoModelForCausalLM.from_pretrained('erwanf/gpt2-mini'),
+    AutoTokenizer.from_pretrained('erwanf/gpt2-mini')
+)
+model = OutlinesModel(outlines_model)
+```
+
+Alternatively, you can use some `OutlinesModel` class methods made to load a specific type of Outlines model directly. To do so, you must provide as argument the same arguments you would have given to the associated Outlines model loading function.
+
+For instance:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+from pydantic_ai.models.outlines import OutlinesModel
+
+model = OutlinesModel.from_transformers(
+    AutoModelForCausalLM.from_pretrained('erwanf/gpt2-mini'),
+    AutoTokenizer.from_pretrained('erwanf/gpt2-mini')
+)
+```
+
+There are methods for the 6 Outlines models that are officially supported in the integration into Pydantic-AI:
+- `from_transformers`
+- `from_llama_cpp`
+- `from_mlxlm`
+- `from_sglang`
+- `from_dottxt`
+- `from_vllm_offline`
+
+As you already providing an Outlines model instance, there is no need to provide an `OutlinesProvider` yourself.
+
+## Running the model
+
+Once you have initialized an `OutlinesModel`, you can use it with an Agent as with all other Pydantic-AI models.
+
+Outlines does not support tools yet, but support for that feature will be added in the near future.

docs/models/overview.md

@@ -10,6 +10,7 @@ Pydantic AI is model-agnostic and has built-in support for multiple model provid
 * [Cohere](cohere.md)
 * [Bedrock](bedrock.md)
 * [Hugging Face](huggingface.md)
+* [Outlines](outlines.md)
 
 ## OpenAI-compatible Providers
 

docs/thinking.md

@@ -89,6 +89,6 @@ agent = Agent(model, model_settings=settings)
 ...
 ```
 
-## Mistral / Cohere
+## Mistral / Cohere / Outlines
 
-Neither Mistral nor Cohere generate thinking parts.
+Neither Mistral, nor Cohere, nor Outlines generate thinking parts.