22 Commits

Author SHA1 Message Date
Eric Zhu
9fd8eefc55
fix: Structured output with tool calls for OpenAIChatCompletionClient (#5671)
Resolves: #5568

Also, refactored some unit tests.

Integration tests against OpenAI endpoint passed:
https://github.com/microsoft/autogen/actions/runs/13484492096

Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
2025-02-24 14:18:46 +00:00
Eric Zhu
7784f44ea6
feat: Add thought process handling in tool calls and expose ThoughtEvent through stream in AgentChat (#5500)
Resolves #5192

Test

```python
import asyncio
import os
from random import randint
from typing import List
from autogen_core.tools import BaseTool, FunctionTool
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.ui import Console

async def get_current_time(city: str) -> str:
    return f"The current time in {city} is {randint(0, 23)}:{randint(0, 59)}."

tools: List[BaseTool] = [
    FunctionTool(
        get_current_time,
        name="get_current_time",
        description="Get current time for a city.",
    ),
]

model_client = OpenAIChatCompletionClient(
    model="anthropic/claude-3.5-haiku-20241022",
    base_url="https://openrouter.ai/api/v1",
    api_key=os.environ["OPENROUTER_API_KEY"],
    model_info={
        "family": "claude-3.5-haiku",
        "function_calling": True,
        "vision": False,
        "json_output": False,
    }
)

agent = AssistantAgent(
    name="Agent",
    model_client=model_client,
    tools=tools,
    system_message= "You are an assistant with some tools that can be used to answer some questions",
)

async def main() -> None:
    await Console(agent.run_stream(task="What is current time of Paris and Toronto?"))

asyncio.run(main())
```

```
---------- user ----------
What is current time of Paris and Toronto?
---------- Agent ----------
I'll help you find the current time for Paris and Toronto by using the get_current_time function for each city.
---------- Agent ----------
[FunctionCall(id='toolu_01NwP3fNAwcYKn1x656Dq9xW', arguments='{"city": "Paris"}', name='get_current_time'), FunctionCall(id='toolu_018d4cWSy3TxXhjgmLYFrfRt', arguments='{"city": "Toronto"}', name='get_current_time')]
---------- Agent ----------
[FunctionExecutionResult(content='The current time in Paris is 1:10.', call_id='toolu_01NwP3fNAwcYKn1x656Dq9xW', is_error=False), FunctionExecutionResult(content='The current time in Toronto is 7:28.', call_id='toolu_018d4cWSy3TxXhjgmLYFrfRt', is_error=False)]
---------- Agent ----------
The current time in Paris is 1:10.
The current time in Toronto is 7:28.
```

---------

Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
2025-02-21 13:58:32 -08:00
Eric Zhu
ec314c586c
feat: Add strict mode support to BaseTool, ToolSchema and FunctionTool (#5507)
Resolves #4447

For `openai` client's structured output support is through its beta
client, which requires the function JSON schema to be strict when in
structured output mode.

Reference:
https://platform.openai.com/docs/guides/function-calling#strict-mode
2025-02-13 19:44:55 +00:00
wistuba
7a772a2fcd
feat: add indictor for tool failure to FunctionExecutionResult (#5428)
Some LLMs recieve an explicit signal about tool use failures. 

Closes #5273

Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
2025-02-09 21:57:50 -08:00
Eric Zhu
9a028acf9f
feat: enhance Gemini model support in OpenAI client and tests (#5461) 2025-02-09 10:12:59 -08:00
afourney
0b659de36d
Mitigates #5401 by optionally prepending names to messages. (#5448)
Mitigates #5401 by optionally prepending names to messages.

Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
2025-02-08 07:04:24 +00:00
Eric Zhu
569bc19769
feat: add gemini model families, enhance group chat selection for Gemini model and add tests (#5334)
Resolves #5322
2025-02-03 18:32:35 +00:00
Eric Zhu
f656ff1e01
feat: Support R1 reasoning text in model create result; enhance API docs (#5262)
Resolves #5255 

---------

Co-authored-by: afourney <adamfo@microsoft.com>
2025-01-30 11:03:54 -08:00
Eric Zhu
44db2cc1fb
fix: handle non-string function arguments in tool calls and add corresponding warnings (#5260) 2025-01-30 16:49:22 +00:00
Eric Zhu
b441d5b43a
fix: Enhance OpenAI client to handle additional stop reasons and improve tool call validation in tests to address empty tool_calls list. (#5223)
Resolves #5222
2025-01-27 21:16:47 +00:00
Eric Zhu
da1c2bf12e
fix: use tool_calls field to detect tool calls in OpenAI client; add integration tests for OpenAI and Gemini (#5122)
* fix: use tool_calls field to detect tool calls in OpenAI client

* Add unit tests for tool calling; and integration tests for openai and gemini
2025-01-21 09:06:19 -05:00
Eric Zhu
af420a83e2
fix: ensure proper handling of structured output in OpenAI client and improve test coverage for structured output (#5116) 2025-01-20 20:54:39 +00:00
Jack Gerrits
cb1633b501
feat!: Add support for model family specification (#4856)
* Add support for model family specification

* spelling mistake

* lint, etc

* fixes
2024-12-30 15:09:21 -05:00
Sachin Joglekar
3b4dd6e050
Support custom models with OpenAI client (#4808) 2024-12-24 13:04:23 -08:00
Leonardo Pinheiro
253fe216fd
Add models.openai and tools.langchain namespaces (#4601)
* add models.openai namespace

* refactor tools namespace

* update lock file

* revert pyproject changes

* update docs and add cast

* update ext models doc ref

* increase underline

* add reply models namespace

* update imports

* fix test

* linting

* fix missing conflicts

* revert pydantic changes

* rename to replay

* replay

* fix reply

* Fix test

* formatting

* example

---------

Co-authored-by: Leonardo Pinheiro <lpinheiro@microsoft.com>
Co-authored-by: Jack Gerrits <jack@jackgerrits.com>
Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
2024-12-09 19:18:09 -08:00
Jack Gerrits
218e84fd8e
Migrate remaining components (#4626) 2024-12-09 18:39:07 -08:00
Jack Gerrits
87011ae01b
Migrate model context and models modules out of components (#4613)
* Move model context out of components

* move models out of components

* rename docs file
2024-12-09 10:00:08 -08:00
Jack Gerrits
3022369eeb
Flatten core base and components (#4513)
* Flatten core base and components

* remove extra files

* dont export from deprecated locations

* format

* fmt
2024-12-03 17:00:44 -08:00
Jack Gerrits
b2ae4d1203
Add warnings for deprecated azure oai config changes (#4317)
* Add warnings for deprecated azure oai config changes

* Update docs and usages, simplify capabilities
2024-11-25 09:34:52 -08:00
Leonardo Pinheiro
ac53961bc8
Delete autogen-ext refactor deprecations (#4305)
* delete files and update dependencies

* add explicit config exports

* ignore mypy error on nb

---------

Co-authored-by: Leonardo Pinheiro <lpinheiro@microsoft.com>
Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
2024-11-22 11:29:39 -05:00
Anthony Uphof
87bd1de396
Fix: provide valid Prompt and Completion Token usage counts from create_stream (#3972)
* Fix: `create_stream` to return valid usage token counts
* documentation

---------

Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
2024-10-29 16:20:03 -07:00
Leonardo Pinheiro
38f62e1609
migrate models (#3848)
* migrate models

* Update python/packages/autogen-agentchat/src/autogen_agentchat/agents/_tool_use_assistant_agent.py

Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>

* refactor missing imports

* ignore type check errors

* Update python/packages/autogen-ext/src/autogen_ext/models/_openai/_model_info.py

Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>

* update packages index page

---------

Co-authored-by: Leonardo Pinheiro <lpinheiro@microsoft.com>
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
2024-10-22 11:40:41 -04:00