Note: We recommend using a virtual environment for your stack, see [this article](https://microsoft.github.io/autogen/docs/installation/#create-a-virtual-environment-optional) for guidance.
## Installing LiteLLM
Install LiteLLM with the proxy server functionality:
Ah, a classic question! The sky appears blue because of a phenomenon called Rayleigh scattering. When sunlight enters Earth's atmosphere, it encounters tiny molecules of gases such as nitrogen and oxygen. These molecules scatter the light in all directions, but they scatter shorter (blue) wavelengths more than longer (red) wavelengths. This is why the sky looks blue during the daytime, especially in the direction of the sun.
But wait, there's more! The color of the sky can also change depending on the time of day and atmospheric conditions. For example, during sunrise and sunset, the sky can take on hues of red, orange, and pink due to the way that light interacts with the Earth's atmosphere. And if you're in a location with a lot of dust or pollution, the sky may appear more hazy or gray.
So there you have it! The sky is blue because of the way that light interacts with the Earth's atmosphere, and there are many factors that can affect its appearance. Is there anything else you'd like to know?
Ah, an interesting question! To make the sky appear red, we need to look at the scattering of light in a different way. When the sun is low on the horizon, the light it emits has to travel through a longer distance in the atmosphere to reach our eyes. As a result, much of the shorter wavelength blue light is scattered away, leaving mainly the longer wavelength red and orange light to reach our eyes. This is why the sky can take on hues of red, orange, and pink during sunrise and sunset.
However, if we were to somehow change the composition of the atmosphere or add some additional particles into the air, we could potentially make the sky appear red even when the sun is high in the sky. For example, if we were to add a lot of dust or smoke into the atmosphere, the sky might take on a reddish hue due to the scattering of light by these particles. Or, if we were to create a situation where the air was filled with a high concentration of certain gases, such as nitrogen oxides or sulfur compounds, the sky could potentially appear red or orange as a result of the way that these gases interact with light.
So there you have it! While the sky is typically blue during the daytime due to Rayleigh scattering, there are many other factors that can affect its appearance, and with the right conditions, we can even make the sky appear red! Is there anything else you'd like to know?
Provide feedback to agent. Press enter to skip and use auto-reply, or type 'exit' to end the conversation: exit
````
## Example with Function Calling
Function calling (aka Tool calling) is a feature of OpenAI's API that AutoGen and LiteLLM support.
Below is an example of using function calling with LiteLLM and Ollama. Based on this [currency conversion](https://github.com/microsoft/autogen/blob/501f8d22726e687c55052682c20c97ce62f018ac/notebook/agentchat_function_call_currency_calculator.ipynb) notebook.
LiteLLM is loaded in the same way as the previous example, however the DolphinCoder model is used as it is better at constructing the
function calling message required.
In your terminal:
```bash
litellm --model ollama_chat/dolphincoder
```
```python
import autogen
from typing import Literal
from typing_extensions import Annotated
local_llm_config={
"config_list": [
{
"model": "NotRequired", # Loaded with LiteLLM command
"api_key": "NotRequired", # Not needed
"base_url": "http://0.0.0.0:4000" # Your LiteLLM URL
}
],
"cache_seed": None # Turns off caching, useful for testing different models
}
# Create the agent and include examples of the function calling JSON in the prompt
# to help guide the model
chatbot = autogen.AssistantAgent(
name="chatbot",
system_message="""For currency exchange tasks,
only use the functions you have been provided with.
Output 'TERMINATE' when an answer has been provided.
Do not include the function name or result in the JSON.
Example of the return JSON is:
{
"parameter_1_name": 100.00,
"parameter_2_name": "ABC",
"parameter_3_name": "DEF",
}.
Another example of the return JSON is:
{
"parameter_1_name": "GHI",
"parameter_2_name": "ABC",
"parameter_3_name": "DEF",
"parameter_4_name": 123.00,
}. """,
llm_config=local_llm_config,
)
user_proxy = autogen.UserProxyAgent(
name="user_proxy",
is_termination_msg=lambda x: x.get("content", "") and "TERMINATE" in x.get("content", ""),
