LLM 大模型学习必知必会系列(十)：基于AgentFabric实现交互式智能体应用,Agent实战

    # 设置pip全局镜像 (加速下载)
    pip config set global.index-url https://mirrors.aliyun.com/pypi/simple/
    # 安装ms-swift
    git clone https://github.com/modelscope/swift.git
    cd swift
    pip install -e .[llm]
    
    # 环境对齐 (通常不需要运行. 如果你运行错误, 可以跑下面的代码, 仓库使用最新环境测试)
    pip install -r requirements/framework.txt  -U
    pip install -r requirements/llm.txt  -U

    Answer the following questions as best you can. You have access to the following APIs:
    1. fire_recognition: Call this tool to interact with the fire recognition API. This API is used to recognize whether there is fire in the image. Parameters: [{"name": "image", "description": "The input image to recognize fire", "required": "True"}]
    
    Use the following format:
    
    Thought: you should always think about what to do
    Action: the action to take, should be one of the above tools[fire_recognition, fire_alert, call_police, call_fireman]
    Action Input: the input to the action
    Observation: the result of the action
    ... (this Thought/Action/Action Input/Observation can be repeated zero or more times)
    Thought: I now know the final answer
    Final Answer: the final answer to the original input question
    Begin!
    
    输入图片是/tmp/2.jpg，协助判断图片中是否存在着火点

    # 工具

    ## 你拥有如下工具：
    
    amap_weather: amap_weather API。获取对应城市的天气数据 输入参数: {"type": "object", "properties": {"location": {"type": "string", "description": "城市/区具体名称，如`北京市海淀区`请描述为`海淀区`"}}, "required": ["location"]} Format the arguments as a JSON object.
    
    ## 当你需要调用工具时，请在你的回复中穿插如下的工具调用命令，可以根据需求调用零次或多次：
    
    工具调用
    Action: 工具的名称，必须是[amap_weather]之一
    Action Input: 工具的输入
    Observation: <result>工具返回的结果</result>
    Answer: 根据Observation总结本次工具调用返回的结果，如果结果中出现url，请使用如下格式展示出来：![图片](url)
    
    
    # 指令
    
    你扮演一个天气预报助手，你需要查询相应地区的天气，并调用给你的画图工具绘制一张城市的图。
    
    请注意：你具有图像和视频的展示能力，也具有运行代码的能力，不要在回复中说你做不到。
    
    (。你可以使用工具：[amap_weather])朝阳区天气怎样？

    import json
    import re
    
    sys_prefix = "\n# 工具\n\n## 你拥有如下工具：\n\n"
    
    def _process_system(text):
        apis_info = []
        api_pattern = r"(?<=\n\d\.)(.*?})(?=])"
        apis = re.findall(api_pattern,text,re.DOTALL)
        sys_prompt = sys_prefix
        func_names = []
        for api in apis:
            func_name = re.search(r'(.*?):', api).group(1).strip()
            func_names.append(func_name)
            api_name = re.search(r'(\S+)\sAPI', api).group(1)
            api_desc = re.search(r"useful for\?\s(.*?)\.",api).group(1)
            sys_prompt += f"{func_name}: {api_name} API。{api_desc}" + "输入参数: {\"type\": \"object\", \"properties\": {"
            paras = re.findall(r"Parameters: \[({.*})",api,re.DOTALL)
            required_paras = []
            for para in paras:
                para_name = re.search(r'"name": "(.*?)"',para).group(1)
                desc = re.search(r'"description": "(.*?)"',para).group(1)
                if re.search(r'"required": "(.*)"',para).group(1).strip().lower() == "true": required_paras.append(para_name)
                sys_prompt += f'"\{para_name}\": {{\"type\": \"string\", \"description\": \"{desc}\"}}' 
            sys_prompt += "},\"required\": " + json.dumps(required_paras) + "} Format the arguments as a JSON object." + "\n\n"
        func_names = json.dumps(func_names)
        sys_prompt += f"## 当你需要调用工具时，请在你的回复中穿插如下的工具调用命令，可以根据需求调用零次或多次：\n\n工具调用\nAction: 工具的名称，必须是{func_names}之一\nAction Input: 工具的输入\nObservation: <result>工具返回的结果</result>\nAnswer: 根据Observation总结本次工具调用返回的结果，如果结果中出现url，请使用如下格式展示出来：![图片](url)\n\n\n# 指令\n\n你扮演AI-Agent，\n你具有下列具体功能：\n下面你将开始扮演\n\n请注意：你具有图像和视频的展示能力，也具有运行代码的能力，不要在回复中说你做不到。\n"
    
        return sys_prompt
    
    jsonl_file_path = 'ms_agent/train_agent_react.jsonl'
    target_file_path = 'new_ms_agent.jsonl'
    
    modified_data = []
    
    with open(jsonl_file_path, 'r', encoding='utf-8') as file:
        for line in file:
            json_obj = json.loads(line)
            system_prompt = json_obj["conversations"][0]["value"]
            json_obj["conversations"][0]["value"] = _process_system(system_prompt)
            modified_data.append(json_obj)
    
    with open(target_file_path, 'w', encoding='utf-8') as file:
        for json_obj in modified_data:
            file.write(json.dumps(json_obj, ensure_ascii=False) + '\n')

    # Experimental environment: A100
    
    cd examples/pytorch/llm
    
    # 如果使用1张卡则配置nproc_per_node=1
    nproc_per_node=8
    
    export PYTHONPATH=../../..
    
    # 时间比较久，8*A100需要 2+小时，nohup运行
    nohup torchrun \
        --nproc_per_node=$nproc_per_node \
        --master_port 29500 \
        llm_sft.py \
        --model_id_or_path qwen/Qwen-7B-Chat \
        --model_revision master \
        --sft_type lora \
        --tuner_backend swift \
        --dtype AUTO \
        --output_dir output \
        --custom_train_dataset_path ms_agent_for_agentfabric/new_ms_agent.jsonl ms_agent_for_agentfabric/addition.jsonl
        --train_dataset_mix_ratio 2.0 \
        --train_dataset_sample -1 \
        --num_train_epochs 2 \
        --max_length 2048 \
        --check_dataset_strategy warning \
        --lora_rank 8 \
        --lora_alpha 32 \
        --lora_dropout_p 0.05 \
        --lora_target_modules ALL \
        --self_cognition_sample 3000 \
        --model_name 卡卡罗特 \
        --model_author 陶白白 \
        --gradient_checkpointing true \
        --batch_size 2 \
        --weight_decay 0.01 \
        --learning_rate 5e-5 \
        --gradient_accumulation_steps $(expr 1 / $nproc_per_node) \
        --max_grad_norm 0.5 \
        --warmup_ratio 0.03 \
        --eval_steps 100 \
        --save_steps 100 \
        --save_total_limit 2 \
        --logging_steps 10 &

[INFO:swift] best_model_checkpoint: /home/workspace/swift/examples/pytorch/llm/output/qwen-7b-chat/v0-20240314-211944/checkpoint-2828
[INFO:swift] images_dir: /home/workspace/swift/examples/pytorch/llm/output/qwen-7b-chat/v0-20240314-211944/images
[INFO:swift] End time of running main: 2024-03-14 23:33:54.658745

    python tools/merge_lora_weights_to_model.py --model_id_or_path /dir/to/your/base/model --model_revision master --ckpt_dir /dir/to/your/lora/model

    from modelscope import snapshot_download
    base_model_path = snapshot_download('qwen/Qwen-7B-Chat')
    print(base_model_path)

    [INFO:swift] Saving merged weights...
    [INFO:swift] Successfully merged LoRA and saved in /home/workspace/swift/examples/pytorch/llm/output/qwen-7b-chat/v0-20240314-211944/checkpoint-2828-merged.
    [INFO:swift] End time of running main: 2024-03-18 10:34:54.307471

    nohup python -m vllm.entrypoints.openai.api_server --model /dir/to/your/model-merged --trust-remote-code &

INFO:     Started server process [531583]
INFO:     Waiting for application startup.
INFO:     Application startup complete.
INFO:     Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)

    curl http://localhost:8000/v1/completions -H "Content-Type: application/json" -d '{"model": "/dir/to/your/model-merged", "prompt": "San Francisco is a", "max_tokens": 7, "temperature": 0}'

    from modelscope_agent.agents.role_play import RolePlay  # NOQA
    
    
    def test_weather_role():
        role_template = '你扮演一个天气预报助手，你需要查询相应地区的天气，并调用给你的画图工具绘制一张城市的图。'
    
        llm_config =  {
            "model_server": "openai",
            "model": "/dir/to/your/model-merged",
            "api_base": "http://localhost:8000/v1",
            "is_chat": True,
            "is_function_call": False,
            "support_stream": False
        }
        #llm_config = {"model": "qwen-max", "model_server": "dashscope"}
    
        # input tool name
        function_list = ['amap_weather']
    
        bot = RolePlay(
            function_list=function_list, llm=llm_config, instruction=role_template)
    
        response = bot.run('朝阳区天气怎样？')
    
        text = ''
        for chunk in response:
            text += chunk
        print(text)
        assert isinstance(text, str)
    
    
    test_weather_role()

    cd modelscope-agent/apps/agentfabric

"my-qwen-7b-chat": {
    "type": "openai",
    "model": "/dir/to/your/model-merged",
    "api_base": "http://localhost:8000/v1",
    "is_chat": true,
    "is_function_call": false,
    "support_stream": false
}

    GRADIO_SERVER_NAME=0.0.0.0 PYTHONPATH=../../  python app.py