mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
Eduard van Valkenburg
1e350ea22f
* PR2: Wire context provider pipeline and update all internal consumers - Replace AgentThread with AgentSession across all packages - Replace ContextProvider with BaseContextProvider across all packages - Replace context_provider param with context_providers (Sequence) - Replace thread= with session= in run() signatures - Replace get_new_thread() with create_session() - Add get_session(service_session_id) to agent interface - DurableAgentThread -> DurableAgentSession - Remove _notify_thread_of_new_messages from WorkflowAgent - Wire before_run/after_run context provider pipeline in RawAgent - Auto-inject InMemoryHistoryProvider when no providers configured * fix: update all tests for context provider pipeline, fix lazy-loaders, remove old test files * refactor: update all sample files for context provider pipeline (AgentThread→AgentSession, ContextProvider→BaseContextProvider) * fix: update remaining ag-ui references (client docstring, getting_started sample) * fix: make get_session service_session_id keyword-only to avoid confusion with session_id * refactor: rename _RunContext.thread_messages to session_messages * refactor: remove _threads.py, _memory.py, and old provider files; migrate devui to use plain message lists * rename: remove _new_ prefix from test files * refactor: rewrite SlidingWindowChatMessageStore as SlidingWindowHistoryProvider(InMemoryHistoryProvider) * fix: read full history from session state directly instead of reaching into provider internals * fix: update stale .pyi stubs, sample imports, and README references for new provider types * fix: remove stale message_store, _notify_thread_of_new_messages, and session_id.key references in samples * refactor: merge context_providers and sessions sample folders into sessions, remove aggregate_context_provider * refactor: UserInfoMemory stores state in session.state instead of instance attributes * feat: add Pydantic BaseModel support to session state serialization Pydantic models stored in session.state are now automatically serialized via model_dump() and restored via model_validate() during to_dict()/from_dict() round-trips. Models are auto-registered on first serialization; use register_state_type() for cold-start deserialization. Also export register_state_type as a public API. * fix mem0 * Update sample README links and descriptions for session terminology - Replace 'thread' with 'session' in sample descriptions across all READMEs - Update file links for renamed samples (mem0_sessions, redis_sessions, etc.) - Fix Threads section → Sessions section in main samples/README.md - Update tools, middleware, workflows, durabletask, azure_functions READMEs - Update architecture diagrams in concepts/tools/README.md - Update migration guides (autogen, semantic-kernel) * Fix broken Redis README link to renamed sample * Fix Mem0 OSS client search: pass scoping params as direct kwargs AsyncMemory (OSS) expects user_id/agent_id/run_id as direct kwargs, while AsyncMemoryClient (Platform) expects them in a filters dict. Adds tests for both client types. Port of fix from #3844 to new Mem0ContextProvider. * Fix rebase issues: restore missing _conversation_state.py and checkpoint decode logic - Add back _conversation_state.py (encode/decode_chat_messages) lost in rebase - Fix on_checkpoint_restore to decode cache/conversation with decode_chat_messages - Fix on_checkpoint_restore to use decode_checkpoint_value for pending requests - Add tests/workflow/__init__.py for relative import support - Fix test_agent_executor checkpoint selection (checkpoints[1] not superstep) * Add STORES_BY_DEFAULT ClassVar to skip redundant InMemoryHistoryProvider injection Chat clients that store history server-side by default (OpenAI Responses API, Azure AI Agent) now declare STORES_BY_DEFAULT = True. The agent checks this during auto-injection and skips InMemoryHistoryProvider unless the user explicitly sets store=False. * Fix broken markdown links in azure_ai and redis READMEs * Fix getting-started samples to use session API instead of removed thread/ContextProvider API * updates to workflow as agent * fix group chat import * Rename Thread→Session throughout, fix service_session_id propagation, remove stale AGUIThread - Fix: Propagate conversation_id from ChatResponse back to session.service_session_id in both streaming and non-streaming paths in _agents.py - Rename AgentThreadException → AgentSessionException - Remove stale AGUIThread from ag_ui lazy-loader - Rename use_service_thread → use_service_session in ag-ui package - Rename test functions from *_thread_* to *_session_* - Rename sample files from *_thread* to *_session* - Update docstrings and comments: thread → session - Update _mcp.py kwargs filter: add 'session' alongside 'thread' - Fix ContinuationToken docstring example: thread=thread → session=session - Fix _clients.py docstring: 'Agent threads' → 'Agent sessions' * Fix broken markdown links after thread→session file renames * fix azure ai test
1e350ea22f
·
2026-02-12 21:00:32 +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: