Mistral Support (#173)

Co-authored-by: Samuel Colvin <[email protected]>
Co-authored-by: David Montague <[email protected]>

Author: 3 people

README.md

@@ -32,7 +32,7 @@ PydanticAI is a Python Agent Framework designed to make it less painful to build
 ## Why use PydanticAI
 
 * Built by the team behind Pydantic (the validation layer of the OpenAI SDK, the Anthropic SDK, LangChain, LlamaIndex, AutoGPT, Transformers, CrewAI, Instructor and many more)
-* Model-agnostic — currently OpenAI, Gemini, Anthropic, and Groq are supported. And there is a simple interface to implement support for other models.
+* Model-agnostic — currently OpenAI, Gemini, Anthropic, Groq, and Mistral are supported. And there is a simple interface to implement support for other models.
 * [Type-safe](https://ai.pydantic.dev/agents/#static-type-checking)
 * Control flow and agent composition is done with vanilla Python, allowing you to make use of the same Python development best practices you'd use in any other (non-AI) project
 * [Structured response](https://ai.pydantic.dev/results/#structured-result-validation) validation with Pydantic

docs/api/models/mistral.md

@@ -0,0 +1,3 @@
+# `pydantic_ai.models.mistral`
+
+::: pydantic_ai.models.mistral

docs/index.md

@@ -11,7 +11,7 @@ PydanticAI is a Python Agent Framework designed to make it less painful to build
 ## Why use PydanticAI
 
 * Built by the team behind Pydantic (the validation layer of the OpenAI SDK, the Anthropic SDK, LangChain, LlamaIndex, AutoGPT, Transformers, CrewAI, Instructor and many more)
-* Model-agnostic — currently OpenAI, Gemini, Anthropic, and Groq are supported, and there is a simple interface to implement support for other models.
+* Model-agnostic — currently OpenAI, Gemini, Anthropic, Groq, and Mistral are supported, and there is a simple interface to implement support for other models.
 * [Type-safe](agents.md#static-type-checking)
 * Control flow and agent composition is done with vanilla Python, allowing you to make use of the same Python development best practices you'd use in any other (non-AI) project
 * [Structured response](results.md#structured-result-validation) validation with Pydantic

mkdocs.yml

@@ -40,12 +40,13 @@ nav:
     - api/exceptions.md
     - api/settings.md
     - api/models/base.md
-    - api/models/anthropic.md
     - api/models/openai.md
-    - api/models/ollama.md
+    - api/models/anthropic.md
     - api/models/gemini.md
     - api/models/vertexai.md
     - api/models/groq.md
+    - api/models/mistral.md
+    - api/models/ollama.md
     - api/models/test.md
     - api/models/function.md
 

pydantic_ai_slim/pydantic_ai/models/__init__.py

@@ -52,6 +52,12 @@
     'gemini-2.0-flash-exp',
     'vertexai:gemini-1.5-flash',
     'vertexai:gemini-1.5-pro',
+    # since mistral models are supported by other providers (e.g. ollama), and some of their models (e.g. "codestral")
+    # don't start with "mistral", we add the "mistral:" prefix to all to be explicit
+    'mistral:mistral-small-latest',
+    'mistral:mistral-large-latest',
+    'mistral:codestral-latest',
+    'mistral:mistral-moderation-latest',
     'ollama:codellama',
     'ollama:gemma',
     'ollama:gemma2',
@@ -280,6 +286,10 @@ def infer_model(model: Model | KnownModelName) -> Model:
         from .vertexai import VertexAIModel
 
         return VertexAIModel(model[9:])  # pyright: ignore[reportArgumentType]
+    elif model.startswith('mistral:'):
+        from .mistral import MistralModel
+
+        return MistralModel(model[8:])
     elif model.startswith('ollama:'):
         from .ollama import OllamaModel