github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-22 13:42:25 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #3927] function calling with autogen does not work #2433

New Issue
Closed
opened 2026-04-12 12:44:54 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 12:44:54 -05:00
Owner
Copy Link

Originally created by @patrickwasp on GitHub (Apr 26, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3927

What is the issue?

#!/usr/local/bin/python3.12

from typing import Literal

from pydantic import BaseModel, Field
from typing_extensions import Annotated

import autogen
from autogen.cache import Cache

# MODEL_NAME = "gpt-3.5-turbo"
# API_URL = "https://api.openai.com/v1/"
# API_KEY = "sk-XYZ"

MODEL_NAME = "llama3:8k"
API_URL = "http://10.4.4.207:11434/v1"
API_KEY = "ollama"

config_list = [
    {
        "model": MODEL_NAME,
        "base_url": API_URL,
        "api_key": API_KEY,
    }
]

llm_config = {
    "config_list": config_list,
    "timeout": 120,
}

user_proxy = autogen.UserProxyAgent(
    name="user_proxy",
    is_termination_msg=lambda x: x.get("content", "")
    and x.get("content", "").rstrip().endswith("TERMINATE"),
    human_input_mode="NEVER",
    max_consecutive_auto_reply=10,
)

chatbot = autogen.AssistantAgent(
    name="chatbot",
    system_message="For currency exchange tasks, only use the functions you have been provided with. Reply TERMINATE when the task is done.",
    llm_config=llm_config,
)

CurrencySymbol = Literal["USD", "EUR"]


def exchange_rate(
    base_currency: CurrencySymbol, quote_currency: CurrencySymbol
) -> float:
    if base_currency == quote_currency:
        return 1.0
    elif base_currency == "USD" and quote_currency == "EUR":
        return 1 / 1.1
    elif base_currency == "EUR" and quote_currency == "USD":
        return 1.1
    else:
        raise ValueError(f"Unknown currencies {base_currency}, {quote_currency}")


class Currency(BaseModel):
    currency: Annotated[CurrencySymbol, Field(..., description="Currency symbol")]
    amount: Annotated[float, Field(0, description="Amount of currency", ge=0)]


@user_proxy.register_for_execution()
@chatbot.register_for_llm(description="Currency exchange calculator.")
def currency_calculator(
    base: Annotated[Currency, "Base currency: amount and currency symbol"],
    quote_currency: Annotated[CurrencySymbol, "Quote currency symbol"] = "USD",
) -> Currency:
    quote_amount = exchange_rate(base.currency, quote_currency) * base.amount
    return Currency(amount=quote_amount, currency=quote_currency)


def main():
    with Cache.disk() as cache:
        user_proxy.initiate_chat(
            chatbot,
            message="How much is 112.23 Euros in US Dollars?",
            summary_method="last_msg",
            cache=cache,
        )


if __name__ == "__main__":
    main()

output using gpt-3.5-turbo:

user_proxy (to chatbot):

How much is 112.23 Euros in US Dollars?

--------------------------------------------------------------------------------
chatbot (to user_proxy):

***** Suggested tool call (call_TdfMydJ9TeKBbz8QRE5ZHl2k): currency_calculator *****
Arguments: 
{"base":{"currency":"EUR","amount":112.23},"quote_currency":"USD"}
************************************************************************************

--------------------------------------------------------------------------------

>>>>>>>> EXECUTING FUNCTION currency_calculator...
user_proxy (to chatbot):

user_proxy (to chatbot):

***** Response from calling tool (call_TdfMydJ9TeKBbz8QRE5ZHl2k) *****
{"currency":"USD","amount":123.45300000000002}
**********************************************************************

--------------------------------------------------------------------------------
chatbot (to user_proxy):

112.23 Euros is equivalent to 123.45 US Dollars.

--------------------------------------------------------------------------------
user_proxy (to chatbot):



--------------------------------------------------------------------------------
chatbot (to user_proxy):

TERMINATE

--------------------------------------------------------------------------------

output using llama3 running with ollama:

user_proxy (to chatbot):

How much is 112.23 Euros in US Dollars?

--------------------------------------------------------------------------------
chatbot (to user_proxy):

To convert 112.23 Euros to US Dollars, I can use the provided function:

According to the exchange rate, 1 EUR is approximately equal to 1.22 USD.

Converting 112.23 EUR, we get:
112.23 EUR * 1.22 USD/EUR = 136.88 USD

So, 112.23 Euros are equivalent to approximately 136.88 US Dollars.

Please let me know if I should continue with the next task or reply TERMINATE when the currency exchange is done.

--------------------------------------------------------------------------------
user_proxy (to chatbot):



--------------------------------------------------------------------------------

followed by a bunch of other empty messages from user_proxy (to chatbot) before exiting.

OS

Docker

GPU

Nvidia

CPU

Intel

Ollama version

ollama/ollama:0.1.32

Originally created by @patrickwasp on GitHub (Apr 26, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3927 ### What is the issue? ```python #!/usr/local/bin/python3.12 from typing import Literal from pydantic import BaseModel, Field from typing_extensions import Annotated import autogen from autogen.cache import Cache # MODEL_NAME = "gpt-3.5-turbo" # API_URL = "https://api.openai.com/v1/" # API_KEY = "sk-XYZ" MODEL_NAME = "llama3:8k" API_URL = "http://10.4.4.207:11434/v1" API_KEY = "ollama" config_list = [ { "model": MODEL_NAME, "base_url": API_URL, "api_key": API_KEY, } ] llm_config = { "config_list": config_list, "timeout": 120, } user_proxy = autogen.UserProxyAgent( name="user_proxy", is_termination_msg=lambda x: x.get("content", "") and x.get("content", "").rstrip().endswith("TERMINATE"), human_input_mode="NEVER", max_consecutive_auto_reply=10, ) chatbot = autogen.AssistantAgent( name="chatbot", system_message="For currency exchange tasks, only use the functions you have been provided with. Reply TERMINATE when the task is done.", llm_config=llm_config, ) CurrencySymbol = Literal["USD", "EUR"] def exchange_rate( base_currency: CurrencySymbol, quote_currency: CurrencySymbol ) -> float: if base_currency == quote_currency: return 1.0 elif base_currency == "USD" and quote_currency == "EUR": return 1 / 1.1 elif base_currency == "EUR" and quote_currency == "USD": return 1.1 else: raise ValueError(f"Unknown currencies {base_currency}, {quote_currency}") class Currency(BaseModel): currency: Annotated[CurrencySymbol, Field(..., description="Currency symbol")] amount: Annotated[float, Field(0, description="Amount of currency", ge=0)] @user_proxy.register_for_execution() @chatbot.register_for_llm(description="Currency exchange calculator.") def currency_calculator( base: Annotated[Currency, "Base currency: amount and currency symbol"], quote_currency: Annotated[CurrencySymbol, "Quote currency symbol"] = "USD", ) -> Currency: quote_amount = exchange_rate(base.currency, quote_currency) * base.amount return Currency(amount=quote_amount, currency=quote_currency) def main(): with Cache.disk() as cache: user_proxy.initiate_chat( chatbot, message="How much is 112.23 Euros in US Dollars?", summary_method="last_msg", cache=cache, ) if __name__ == "__main__": main() ``` output using gpt-3.5-turbo: ```python3.12 autogen_tools_example.py user_proxy (to chatbot): How much is 112.23 Euros in US Dollars? -------------------------------------------------------------------------------- chatbot (to user_proxy): ***** Suggested tool call (call_TdfMydJ9TeKBbz8QRE5ZHl2k): currency_calculator ***** Arguments: {"base":{"currency":"EUR","amount":112.23},"quote_currency":"USD"} ************************************************************************************ -------------------------------------------------------------------------------- >>>>>>>> EXECUTING FUNCTION currency_calculator... user_proxy (to chatbot): user_proxy (to chatbot): ***** Response from calling tool (call_TdfMydJ9TeKBbz8QRE5ZHl2k) ***** {"currency":"USD","amount":123.45300000000002} ********************************************************************** -------------------------------------------------------------------------------- chatbot (to user_proxy): 112.23 Euros is equivalent to 123.45 US Dollars. -------------------------------------------------------------------------------- user_proxy (to chatbot): -------------------------------------------------------------------------------- chatbot (to user_proxy): TERMINATE -------------------------------------------------------------------------------- ``` output using llama3 running with ollama: ``` user_proxy (to chatbot): How much is 112.23 Euros in US Dollars? -------------------------------------------------------------------------------- chatbot (to user_proxy): To convert 112.23 Euros to US Dollars, I can use the provided function: According to the exchange rate, 1 EUR is approximately equal to 1.22 USD. Converting 112.23 EUR, we get: 112.23 EUR * 1.22 USD/EUR = 136.88 USD So, 112.23 Euros are equivalent to approximately 136.88 US Dollars. Please let me know if I should continue with the next task or reply TERMINATE when the currency exchange is done. -------------------------------------------------------------------------------- user_proxy (to chatbot): -------------------------------------------------------------------------------- ``` followed by a bunch of other empty messages from `user_proxy (to chatbot)` before exiting. ### OS Docker ### GPU Nvidia ### CPU Intel ### Ollama version ollama/ollama:0.1.32
GiteaMirror added the bug label 2026-04-12 12:44:54 -05:00
GiteaMirror commented 2026-04-12 12:44:56 -05:00
Author
Owner
Copy Link

@marklysze commented on GitHub (Apr 28, 2024):

I believe Ollama doesn't support function calling directly. I use LiteLLM + Ollama.

See this page for an example.

<!-- gh-comment-id:2081430435 --> @marklysze commented on GitHub (Apr 28, 2024): I believe Ollama doesn't support function calling directly. I use LiteLLM + Ollama. [See this page for an example](https://microsoft.github.io/autogen/docs/topics/non-openai-models/local-litellm-ollama/#example-with-function-calling).
GiteaMirror commented 2026-04-12 12:44:56 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Jul 26, 2024):

Hi there, this should be supported now - note that OpenAI-compatible endpoint does not support streaming yet but it is being worked on

<!-- gh-comment-id:2251744068 --> @jmorganca commented on GitHub (Jul 26, 2024): Hi there, this should be supported now - note that OpenAI-compatible endpoint does not support streaming yet but it is being worked on
GiteaMirror commented 2026-04-12 12:44:57 -05:00
Author
Owner
Copy Link

@opqpop commented on GitHub (Jul 30, 2024):

Thanks @jmorganca, we're trying to move away from LiteLLM + Ollama to support function calling in autogen. Do you perhaps have a link or example on how to get it working?

I tried following the "Autogen" example @ https://ollama.com/blog/openai-compatibility but it just hangs. I was only able to get chat completions working.

<!-- gh-comment-id:2257331366 --> @opqpop commented on GitHub (Jul 30, 2024): Thanks @jmorganca, we're trying to move away from LiteLLM + Ollama to support function calling in autogen. Do you perhaps have a link or example on how to get it working? I tried following the "Autogen" example @ https://ollama.com/blog/openai-compatibility but it just hangs. I was only able to get chat completions working.
GiteaMirror commented 2026-04-12 12:44:58 -05:00
Author
Owner
Copy Link

@marklysze commented on GitHub (Jul 30, 2024):

Thanks @jmorganca, we're trying to move away from LiteLLM + Ollama to support function calling in autogen. Do you perhaps have a link or example on how to get it working?

I tried following the "Autogen" example @ https://ollama.com/blog/openai-compatibility but it just hangs. I was only able to get chat completions working.

Hey @opqpop, I'm working on an Ollama client class in AutoGen, it has tool calling using Ollama's tool calling as well as a manually handled tool calling option.

See:
https://github.com/microsoft/autogen/pull/3056

<!-- gh-comment-id:2257357255 --> @marklysze commented on GitHub (Jul 30, 2024): > Thanks @jmorganca, we're trying to move away from LiteLLM + Ollama to support function calling in autogen. Do you perhaps have a link or example on how to get it working? > > I tried following the "Autogen" example @ https://ollama.com/blog/openai-compatibility but it just hangs. I was only able to get chat completions working. Hey @opqpop, I'm working on an Ollama client class in AutoGen, it has tool calling using Ollama's tool calling as well as a manually handled tool calling option. See: https://github.com/microsoft/autogen/pull/3056
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#2433
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?