Tuesday, June 11, 2024

Qwen-Agents to Build AI Agents with Qwen Models Locally - Step by Step Tutorial

 This video is a quick easy tutorial to install Qwen-Agent locally and create agentic applications with Qwen2 and Ollama for function calling and RAG.


conda create -n qwenagent python=3.11 -y

pip install -U qwen-agent

import json
import os

from qwen_agent.llm import get_chat_model

# Example dummy function hard coded to return the same weather
# In production, this could be your backend API or an external API
def get_current_weather(location, unit='fahrenheit'):
    """Get the current weather in a given location"""
    if 'tokyo' in location.lower():
        return json.dumps({'location': 'Tokyo', 'temperature': '10', 'unit': 'celsius'})
    elif 'san francisco' in location.lower():
        return json.dumps({'location': 'San Francisco', 'temperature': '72', 'unit': 'fahrenheit'})
    elif 'paris' in location.lower():
        return json.dumps({'location': 'Paris', 'temperature': '22', 'unit': 'celsius'})
        return json.dumps({'location': location, 'temperature': 'unknown'})

def test():
    llm = get_chat_model({
        'model': 'qwen2:7b',
        'model_server': 'http://localhost:11434/v1',  # api_base
        'api_key': 'EMPTY',

    # Step 1: send the conversation and available functions to the model
    messages = [{'role': 'user', 'content': "What's the weather like in San Francisco?"}]
    functions = [{
        'name': 'get_current_weather',
        'description': 'Get the current weather in a given location',
        'parameters': {
            'type': 'object',
            'properties': {
                'location': {
                    'type': 'string',
                    'description': 'The city and state, e.g. San Francisco, CA',
                'unit': {
                    'type': 'string',
                    'enum': ['celsius', 'fahrenheit']
            'required': ['location'],

    print('# Assistant Response 1:')
    responses = []
    for responses in llm.chat(messages=messages, functions=functions, stream=True):

    messages.extend(responses)  # extend conversation with assistant's reply

    # Step 2: check if the model wanted to call a function
    last_response = messages[-1]
    if last_response.get('function_call', None):

        # Step 3: call the function
        # Note: the JSON response may not always be valid; be sure to handle errors
        available_functions = {
            'get_current_weather': get_current_weather,
        }  # only one function in this example, but you can have multiple
        function_name = last_response['function_call']['name']
        function_to_call = available_functions[function_name]
        function_args = json.loads(last_response['function_call']['arguments'])
        function_response = function_to_call(
        print('# Function Response:')

        # Step 4: send the info for each function call and function response to the model
            'role': 'function',
            'name': function_name,
            'content': function_response,
        })  # extend conversation with function response

        print('# Assistant Response 2:')
        for responses in llm.chat(
        ):  # get a new response from the model where it can see the function response

if __name__ == '__main__':

No comments: