mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
Python : Ollama Connector for Agent Framework (#1104)
* Initial Commit for Olama Connector * Added Olama Sample * Add Sample & Fixed Open Telemetry * Fixed Spelling from Olama to Ollama * remove"opentelemetry-semantic-conventions-ai ~=0.4.13" since its handled in a different pr * Added Tool Calling * Finalizing test cases * Adjust samples to be more reliable * Update python/packages/ollama/agent_framework_ollama/_chat_client.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update python/packages/ollama/pyproject.toml Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update python/packages/ollama/tests/test_ollama_chat_client.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update python/packages/ollama/agent_framework_ollama/_chat_client.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Improved Docstrings & Sample * Update python/packages/ollama/agent_framework_ollama/_chat_client.py Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com> * Integrate PR Feedback - Divided Streaming and Non-Streaming into independent Methods - Catch Ollama Validation Error - Add OTEL Provider Name - Checked Ollama Messages - Add Usage Statistics * Revert setting, so it can be none * Validate Message formatting between AF and Ollama * Catch Ollama Error and raise a ServiceResponse Error * Fix mypy error * remove .vscode comma * Add Reasoning support & adjust to new structure * Add Ollama Multimodality and Reasoning * Add test cases for reasoning * Add Tests for Error Handling in Ollama Client * Update python/samples/getting_started/multimodal_input/ollama_chat_multimodal.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Integrated Copilot Feedback * Implement first PR Feedback * Adjust Readme files for examples * Adjust argument passing via additional chat options * Implemented PR Feedback * Removing Ollama Package from Core and moving samples * Fix Link & Adding Samples to Main Sample Readme * Fixing Links in Readme * Moved Multimodal and Chat Example * Fixed Link in ChatClient to Ollama * Fix AgentFramework Links in Ollama Project * Fix observability breaking change --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com>
This commit is contained in:
Nico Möller
committed by
GitHub
Unverified
GitHub
parent
1dbf3fd5cf
commit
2f06fe557a
@@ -0,0 +1,38 @@
|
||||
# Ollama Examples
|
||||
|
||||
This folder contains examples demonstrating how to use Ollama models with the Agent Framework.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
1. **Install Ollama**: Download and install Ollama from [ollama.com](https://ollama.com/)
|
||||
2. **Start Ollama**: Ensure Ollama is running on your local machine
|
||||
3. **Pull a model**: Run `ollama pull mistral` (or any other model you prefer)
|
||||
- For function calling examples, use models that support tool calling like `mistral` or `qwen2.5`
|
||||
- For reasoning examples, use models that support reasoning like `qwen2.5:8b`
|
||||
- For Multimodality you can use models like `gemma3:4b`
|
||||
|
||||
> **Note**: Not all models support all features. Function calling and reasoning capabilities depend on the specific model you're using.
|
||||
|
||||
## Examples
|
||||
|
||||
| File | Description |
|
||||
|------|-------------|
|
||||
| [`ollama_agent_basic.py`](ollama_agent_basic.py) | Demonstrates basic Ollama agent usage with the native Ollama Chat Client. Shows both streaming and non-streaming responses with tool calling capabilities. |
|
||||
| [`ollama_agent_reasoning.py`](ollama_agent_reasoning.py) | Demonstrates Ollama agent with reasoning capabilities using the native Ollama Chat Client. Shows how to enable thinking/reasoning mode. |
|
||||
| [`ollama_chat_client.py`](ollama_chat_client.py) | Ollama Chat Client with native Ollama Chat Client |
|
||||
| [`ollama_chat_multimodal.py`](ollama_chat_multimodal.py) | Ollama Chat with multimodal native Ollama Chat Client |
|
||||
|
||||
## Configuration
|
||||
|
||||
The examples use environment variables for configuration. Set the appropriate variables based on which example you're running:
|
||||
|
||||
### For Native Ollama Examples (`ollama_agent_basic.py`, `ollama_agent_reasoning.py`)
|
||||
|
||||
Set the following environment variables:
|
||||
|
||||
- `OLLAMA_HOST`: The base URL for your Ollama server (optional, defaults to `http://localhost:11434`)
|
||||
- Example: `export OLLAMA_HOST="http://localhost:11434"`
|
||||
|
||||
- `OLLAMA_CHAT_MODEL_ID`: The model name to use
|
||||
- Example: `export OLLAMA_CHAT_MODEL_ID="qwen2.5:8b"`
|
||||
- Must be a model you have pulled with Ollama
|
||||
@@ -0,0 +1,68 @@
|
||||
# Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
import asyncio
|
||||
from datetime import datetime
|
||||
|
||||
from agent_framework_ollama import OllamaChatClient
|
||||
|
||||
"""
|
||||
Ollama Agent Basic Example
|
||||
|
||||
This sample demonstrates implementing a Ollama agent with basic tool usage.
|
||||
|
||||
Ensure to install Ollama and have a model running locally before running the sample
|
||||
Not all Models support function calling, to test function calling try llama3.2 or qwen3:4b
|
||||
Set the model to use via the OLLAMA_CHAT_MODEL_ID environment variable or modify the code below.
|
||||
https://ollama.com/
|
||||
|
||||
"""
|
||||
|
||||
|
||||
def get_time(location: str) -> str:
|
||||
"""Get the current time."""
|
||||
return f"The current time in {location} is {datetime.now().strftime('%I:%M %p')}."
|
||||
|
||||
|
||||
async def non_streaming_example() -> None:
|
||||
"""Example of non-streaming response (get the complete result at once)."""
|
||||
print("=== Non-streaming Response Example ===")
|
||||
|
||||
agent = OllamaChatClient().create_agent(
|
||||
name="TimeAgent",
|
||||
instructions="You are a helpful time agent answer in one sentence.",
|
||||
tools=get_time,
|
||||
)
|
||||
|
||||
query = "What time is it in Seattle? Use a tool call"
|
||||
print(f"User: {query}")
|
||||
result = await agent.run(query)
|
||||
print(f"Result: {result}\n")
|
||||
|
||||
|
||||
async def streaming_example() -> None:
|
||||
"""Example of streaming response (get results as they are generated)."""
|
||||
print("=== Streaming Response Example ===")
|
||||
|
||||
agent = OllamaChatClient().create_agent(
|
||||
name="TimeAgent",
|
||||
instructions="You are a helpful time agent answer in one sentence.",
|
||||
tools=get_time,
|
||||
)
|
||||
query = "What time is it in San Francisco? Use a tool call"
|
||||
print(f"User: {query}")
|
||||
print("Agent: ", end="", flush=True)
|
||||
async for chunk in agent.run_stream(query):
|
||||
if chunk.text:
|
||||
print(chunk.text, end="", flush=True)
|
||||
print("\n")
|
||||
|
||||
|
||||
async def main() -> None:
|
||||
print("=== Basic Ollama Chat Client Agent Example ===")
|
||||
|
||||
await non_streaming_example()
|
||||
await streaming_example()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
@@ -0,0 +1,46 @@
|
||||
# Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
import asyncio
|
||||
|
||||
from agent_framework import TextReasoningContent
|
||||
|
||||
from agent_framework_ollama import OllamaChatClient
|
||||
|
||||
"""
|
||||
Ollama Agent Reasoning Example
|
||||
|
||||
This sample demonstrates implementing a Ollama agent with reasoning.
|
||||
|
||||
Ensure to install Ollama and have a model running locally before running the sample
|
||||
Not all Models support reasoning, to test reasoning try qwen3:8b
|
||||
Set the model to use via the OLLAMA_CHAT_MODEL_ID environment variable or modify the code below.
|
||||
https://ollama.com/
|
||||
|
||||
"""
|
||||
|
||||
|
||||
async def reasoning_example() -> None:
|
||||
print("=== Response Reasoning Example ===")
|
||||
|
||||
agent = OllamaChatClient().create_agent(
|
||||
name="TimeAgent",
|
||||
instructions="You are a helpful agent answer in one sentence.",
|
||||
additional_chat_options={"think": True}, # Enable Reasoning on agent level
|
||||
)
|
||||
query = "Hey what is 3+4? Can you explain how you got to that answer?"
|
||||
print(f"User: {query}")
|
||||
# Enable Reasoning on per request level
|
||||
result = await agent.run(query)
|
||||
reasoning = "".join(c.text for c in result.messages[-1].contents if isinstance(c, TextReasoningContent))
|
||||
print(f"Reasoning: {reasoning}")
|
||||
print(f"Answer: {result}\n")
|
||||
|
||||
|
||||
async def main() -> None:
|
||||
print("=== Basic Ollama Chat Client Agent Reasoning ===")
|
||||
|
||||
await reasoning_example()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
@@ -0,0 +1,36 @@
|
||||
# Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
import asyncio
|
||||
from datetime import datetime
|
||||
|
||||
from agent_framework_ollama import OllamaChatClient
|
||||
|
||||
# Ensure to install Ollama and have a model running locally before running the sample
|
||||
# Not all Models support function calling, to test function calling try llama3.2
|
||||
# Set the model to use via the OLLAMA_CHAT_MODEL_ID environment variable or modify the code below.
|
||||
# https://ollama.com/
|
||||
|
||||
|
||||
def get_time():
|
||||
"""Get the current time."""
|
||||
return f"The current time is {datetime.now().strftime('%I:%M %p')}."
|
||||
|
||||
|
||||
async def main() -> None:
|
||||
client = OllamaChatClient()
|
||||
message = "What time is it? Use a tool call"
|
||||
stream = False
|
||||
print(f"User: {message}")
|
||||
if stream:
|
||||
print("Assistant: ", end="")
|
||||
async for chunk in client.get_streaming_response(message, tools=get_time):
|
||||
if str(chunk):
|
||||
print(str(chunk), end="")
|
||||
print("")
|
||||
else:
|
||||
response = await client.get_response(message, tools=get_time)
|
||||
print(f"Assistant: {response}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
@@ -0,0 +1,54 @@
|
||||
# Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
import asyncio
|
||||
|
||||
from agent_framework import ChatMessage, DataContent, Role, TextContent
|
||||
|
||||
from agent_framework_ollama import OllamaChatClient
|
||||
|
||||
"""
|
||||
Ollama Agent Multimodal Example
|
||||
|
||||
This sample demonstrates implementing a Ollama agent with multimodal input capabilities.
|
||||
|
||||
Ensure to install Ollama and have a model running locally before running the sample
|
||||
Not all Models support multimodal input, to test multimodal input try gemma3:4b
|
||||
Set the model to use via the OLLAMA_CHAT_MODEL_ID environment variable or modify the code below.
|
||||
https://ollama.com/
|
||||
|
||||
"""
|
||||
|
||||
|
||||
def create_sample_image() -> str:
|
||||
"""Create a simple 1x1 pixel PNG image for testing."""
|
||||
# This is a tiny red pixel in PNG format
|
||||
png_data = "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mP8/5+hHgAHggJ/PchI7wAAAABJRU5ErkJggg=="
|
||||
return f"data:image/png;base64,{png_data}"
|
||||
|
||||
|
||||
async def test_image() -> None:
|
||||
"""Test image analysis with Ollama."""
|
||||
|
||||
client = OllamaChatClient()
|
||||
|
||||
image_uri = create_sample_image()
|
||||
|
||||
message = ChatMessage(
|
||||
role=Role.USER,
|
||||
contents=[
|
||||
TextContent(text="What's in this image?"),
|
||||
DataContent(uri=image_uri, media_type="image/png"),
|
||||
],
|
||||
)
|
||||
|
||||
response = await client.get_response(message)
|
||||
print(f"Image Response: {response}")
|
||||
|
||||
|
||||
async def main() -> None:
|
||||
print("=== Testing Ollama Multimodal ===")
|
||||
await test_image()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
Reference in New Issue
Block a user