mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
Eduard van Valkenburg
838a7fd61d
* Replace Role and FinishReason classes with NewType + Literal
- Remove EnumLike metaclass from _types.py
- Replace Role class with NewType('Role', str) + RoleLiteral
- Replace FinishReason class with NewType('FinishReason', str) + FinishReasonLiteral
- Update all usages across codebase to use string literals
- Remove .value access patterns (direct string comparison now works)
- Add backward compatibility for legacy dict serialization format
- Update tests to reflect new string-based types
Addresses #3591, #3615
* Simplify ChatResponse and AgentResponse type hints (#3592)
- Remove overloads from ChatResponse.__init__
- Remove text parameter from ChatResponse.__init__
- Remove | dict[str, Any] from finish_reason and usage_details params
- Remove **kwargs from AgentResponse.__init__
- Both now accept ChatMessage | Sequence[ChatMessage] | None for messages
- Update docstrings and examples to reflect changes
- Fix tests that were using removed kwargs
- Fix Role type hint usage in ag-ui utils
* Remove text parameter from ChatResponseUpdate and AgentResponseUpdate (#3597)
- Remove text parameter from ChatResponseUpdate.__init__
- Remove text parameter from AgentResponseUpdate.__init__
- Remove **kwargs from both update classes
- Simplify contents parameter type to Sequence[Content] | None
- Update all usages to use contents=[Content.from_text(...)] pattern
- Fix imports in test files
- Update docstrings and examples
* Rename from_chat_response_updates to from_updates (#3593)
- ChatResponse.from_chat_response_updates โ ChatResponse.from_updates
- ChatResponse.from_chat_response_generator โ ChatResponse.from_update_generator
- AgentResponse.from_agent_run_response_updates โ AgentResponse.from_updates
* Remove try_parse_value method from ChatResponse and AgentResponse (#3595)
- Remove try_parse_value method from ChatResponse
- Remove try_parse_value method from AgentResponse
- Remove try_parse_value calls from from_updates and from_update_generator methods
- Update samples to use try/except with response.value instead
- Update tests to use response.value pattern
- Users should now use response.value with try/except for safe parsing
* Add agent_id to AgentResponse and clarify author_name documentation (#3596)
- Add agent_id parameter to AgentResponse class
- Document that author_name is on ChatMessage objects, not responses
- Update ChatResponse docstring with author_name note
- Update AgentResponse docstring with author_name note
* Simplify ChatMessage.__init__ signature (#3618)
- Make contents a positional argument accepting Sequence[Content | str]
- Auto-convert strings in contents to TextContent
- Remove overloads, keep text kwarg for backward compatibility with serialization
- Update _parse_content_list to handle string items
- Update all usages across codebase to use new format: ChatMessage("role", ["text"])
* Allow Content as input on run and get_response
- Update prepare_messages and normalize_messages to accept Content
- Update type signatures in _agents.py and _clients.py
- Add tests for Content input handling
* Fix ChatMessage usage across packages and samples
Update all remaining ChatMessage(role=..., text=...) to use new
ChatMessage('role', ['text']) signature.
* Fix Role string usage and response format parsing
- Fix redis provider: remove .value access on string literals
- Fix durabletask ensure_response_format: set _response_format before accessing .value
* Fix ollama .value and ai_model_id issues, handle None in content list
- Fix ollama _chat_client: remove .value on string literals
- Fix ollama _chat_client: rename ai_model_id to model_id
- Fix _parse_content_list: skip None values gracefully
* Fix A2AAgent type signature to include Content
* Fix Role/FinishReason NewType dict annotations and improve test coverage to 95%
* Fix mypy errors for Role/FinishReason NewType usage
* Fix Role.TOOL and Role.ASSISTANT usage in _orchestrator_helpers.py
* Fix Role NewType usage in durabletask _models.py
838a7fd61d
ยท
2026-02-04 10:13:23 +00:00
History
Ollama Examples
This folder contains examples demonstrating how to use Ollama models with the Agent Framework.
Prerequisites
- Install Ollama: Download and install Ollama from ollama.com
- Start Ollama: Ensure Ollama is running on your local machine
- Pull a model: Run
ollama pull mistral(or any other model you prefer)- For function calling examples, use models that support tool calling like
mistralorqwen2.5 - For reasoning examples, use models that support reasoning like
qwen3:8b - For multimodal examples, use models like
gemma3:4b
- For function calling examples, use models that support tool calling like
Note
: Not all models support all features. Function calling, reasoning, and multimodal capabilities depend on the specific model you're using.
Recommended Approach
The recommended way to use Ollama with Agent Framework is via the native OllamaChatClient from the agent-framework-ollama package. This provides full support for Ollama-specific features like reasoning mode.
Alternatively, you can use the OpenAIChatClient configured to point to your local Ollama server, which may be useful if you're already familiar with the OpenAI client interface.
Examples
| File | Description |
|---|---|
ollama_agent_basic.py |
Basic Ollama agent with tool calling using native Ollama Chat Client. Shows both streaming and non-streaming responses. |
ollama_agent_reasoning.py |
Ollama agent with reasoning capabilities using native Ollama Chat Client. Shows how to enable thinking/reasoning mode. |
ollama_chat_client.py |
Direct usage of the native Ollama Chat Client with tool calling. |
ollama_chat_multimodal.py |
Ollama Chat Client with multimodal (image) input capabilities. |
ollama_with_openai_chat_client.py |
Alternative approach using OpenAI Chat Client configured to use local Ollama models. |
Configuration
The examples use environment variables for configuration. Set the appropriate variables based on which example you're running:
For Native Ollama Examples
Set the following environment variables:
-
OLLAMA_HOST: The base URL for your Ollama server (optional, defaults tohttp://localhost:11434)- Example:
export OLLAMA_HOST="http://localhost:11434"
- Example:
-
OLLAMA_MODEL_ID: The model name to use- Example:
export OLLAMA_MODEL_ID="qwen2.5:8b" - Must be a model you have pulled with Ollama
- Example:
For OpenAI Client with Ollama (ollama_with_openai_chat_client.py)
Set the following environment variables:
-
OLLAMA_ENDPOINT: The base URL for your Ollama server with/v1/suffix- Example:
export OLLAMA_ENDPOINT="http://localhost:11434/v1/"
- Example:
-
OLLAMA_MODEL: The model name to use- Example:
export OLLAMA_MODEL="mistral" - Must be a model you have pulled with Ollama
- Example: