AutoGen

AutoGen is a framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks. To learn more, please visit the AutoGen.

AutoGen with DeepInfra endpoints

# install autogen
pip install pyautogen

Here is how you can configure autogen to use DeepInfra endpoints.

The base_url is https://api.deepinfra.com/v1/openai. You can use any model which is OpenAI compatible. For example, meta-llama/Meta-Llama-3-70B-Instruct is a model that can be used to solve coding tasks.

import autogen

config_list = [
    {
        "model": "meta-llama/Meta-Llama-3-70B-Instruct",
        "base_url": "https://api.deepinfra.com/v1/openai",
        "api_key": "<your DeepInfra API key here>"
    }
]

llm_config={"config_list": config_list, "seed": 42}

assistant = autogen.AssistantAgent("assistant", llm_config=llm_config)
user_proxy = autogen.UserProxyAgent("user_proxy", code_execution_config={"work_dir": "coding"})
user_proxy.initiate_chat(assistant, message="What time is it right now?")

In the example, two agents converse and solve the task. The assistant agent provides a python code snippet which then gets executed on your local machine. In AutoGen, code execution is triggered automatically by the UserProxyAgent when it detects an executable code block in a received message.

Here is the output of the above code:

user_proxy (to assistant):

What time is it now?

--------------------------------------------------------------------------------
assistant (to user_proxy):

To get the current time, you can use the `datetime` module in Python. Here's an example code:
```python
import datetime

current_time = datetime.datetime.now()
print(current_time.strftime("%I:%M %p"))
```
This code will print the current time in a 12-hour format with the AM/PM designation. If you want to print the time in a 24-hour format, you can use the `%H:%M` format specifier instead of `%I:%M %p`.

You can save this code in a file with a `.py` extension and run it in a terminal or command prompt to see the current time.

Note: This code assumes that you have Python installed on your computer. If you don't have Python installed, you can download it from the official Python website.

--------------------------------------------------------------------------------
Provide feedback to assistant. Press enter to skip and use auto-reply, or type 'exit' to end the conversation: 

>>>>>>>> NO HUMAN INPUT RECEIVED.

>>>>>>>> USING AUTO REPLY...

>>>>>>>> EXECUTING CODE BLOCK 0 (inferred language is python)...
execute_code was called without specifying a value for use_docker. Since the python docker package is not available, code will be run natively. Note: this fallback behavior is subject to change
user_proxy (to assistant):

exitcode: 0 (execution succeeded)
Code output: 
02:20 PM


--------------------------------------------------------------------------------
assistant (to user_proxy):

It looks like the code you provided ran successfully and returned the current time in a 12-hour format with the AM/PM designation. Here's the output:

02:20 PM

If you have any other questions or need further assistance, feel free to ask!

--------------------------------------------------------------------------------
Provide feedback to assistant. Press enter to skip and use auto-reply, or type 'exit' to end the conversation: exit