【InternLM 实战营第二期笔记】Lagent & AgentLego 智能体应用搭建

理论知识

Lagent 是什么

Lagent 是一个轻量级开源智能体框架，旨在让用户可以高效地构建基于大语言模型的智能体。同时它也提供了一些典型工具以增强大语言模型的能力。

Lagent 目前已经支持了包括 AutoGPT、ReAct 等在内的多个经典智能体范式，也支持了如下工具：

• Arxiv 搜索
• Bing 地图
• Google 学术搜索
• Google 搜索
• 交互式 IPython 解释器
• IPython 解释器
• PPT
• Python 解释器

AgentLego 是什么

AgentLego 是一个提供了多种开源工具 API 的多模态工具包，旨在像是乐高积木一样，让用户可以快速简便地拓展自定义工具，从而组装出自己的智能体。通过 AgentLego 算法库，不仅可以直接使用多种工具，也可以利用这些工具，在相关智能体框架（如 Lagent，Transformers Agent 等）的帮助下，快速构建可以增强大语言模型能力的智能体。

两者关系

Lagent 是一个智能体框架，而 AgentLego 与大模型智能体并不直接相关，而是作为工具包，在相关智能体的功能支持模块发挥作用。

实践部分

准备环境

拉取环境

studio-conda -t agent -o pytorch-2.1.2

安装 Lagent 和 AgentLego

cd /root/agent
conda activate agent
git clone https://gitee.com/internlm/lagent.git
cd lagent && git checkout 581d9fb && pip install -e . && cd ..
git clone https://gitee.com/internlm/agentlego.git
cd agentlego && git checkout 7769e0d && pip install -e . && cd ..

安装其他依赖

pip install lmdeploy==0.3.0

克隆Tutorial

git clone -b camp2 https://gitee.com/internlm/Tutorial.git

Lagent：轻量级智能体框架

Lagent Web Demo

启动api server

lmdeploy serve api_server /root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-7b \
                            --server-name 127.0.0.1 \
                            --model-name internlm2-chat-7b \
                            --cache-max-entry-count 0.1

启动并使用 Lagent Web Demo

cd /root/agent/lagent/examples
streamlit run internlm2_agent_web_demo.py --server.address 127.0.0.1 --server.port 7860

用 Lagent 自定义工具

创建工具文件

touch /root/agent/lagent/lagent/actions/weather.py

文件内容：

import json
import os
import requests
from typing import Optional, Type

from lagent.actions.base_action import BaseAction, tool_api
from lagent.actions.parser import BaseParser, JsonParser
from lagent.schema import ActionReturn, ActionStatusCode

class WeatherQuery(BaseAction):
    """Weather plugin for querying weather information."""
    
    def __init__(self,
                 key: Optional[str] = None,
                 description: Optional[dict] = None,
                 parser: Type[BaseParser] = JsonParser,
                 enable: bool = True) -> None:
        super().__init__(description, parser, enable)
        key = os.environ.get('WEATHER_API_KEY', key)
        if key is None:
            raise ValueError(
                'Please set Weather API key either in the environment '
                'as WEATHER_API_KEY or pass it as `key`')
        self.key = key
        self.location_query_url = 'https://geoapi.qweather.com/v2/city/lookup'
        self.weather_query_url = 'https://devapi.qweather.com/v7/weather/now'

    @tool_api
    def run(self, query: str) -> ActionReturn:
        """一个天气查询API。可以根据城市名查询天气信息。
        
        Args:
            query (:class:`str`): The city name to query.
        """
        tool_return = ActionReturn(type=self.name)
        status_code, response = self._search(query)
        if status_code == -1:
            tool_return.errmsg = response
            tool_return.state = ActionStatusCode.HTTP_ERROR
        elif status_code == 200:
            parsed_res = self._parse_results(response)
            tool_return.result = [dict(type='text', content=str(parsed_res))]
            tool_return.state = ActionStatusCode.SUCCESS
        else:
            tool_return.errmsg = str(status_code)
            tool_return.state = ActionStatusCode.API_ERROR
        return tool_return
    
    def _parse_results(self, results: dict) -> str:
        """Parse the weather results from QWeather API.
        
        Args:
            results (dict): The weather content from QWeather API
                in json format.
        
        Returns:
            str: The parsed weather results.
        """
        now = results['now']
        data = [
            f'数据观测时间: {now["obsTime"]}',
            f'温度: {now["temp"]}°C',
            f'体感温度: {now["feelsLike"]}°C',
            f'天气: {now["text"]}',
            f'风向: {now["windDir"]}，角度为 {now["wind360"]}°',
            f'风力等级: {now["windScale"]}，风速为 {now["windSpeed"]} km/h',
            f'相对湿度: {now["humidity"]}',
            f'当前小时累计降水量: {now["precip"]} mm',
            f'大气压强: {now["pressure"]} 百帕',
            f'能见度: {now["vis"]} km',
        ]
        return '\n'.join(data)

    def _search(self, query: str):
        # get city_code
        try:
            city_code_response = requests.get(
                self.location_query_url,
                params={'key': self.key, 'location': query}
            )
        except Exception as e:
            return -1, str(e)
        if city_code_response.status_code != 200:
            return city_code_response.status_code, city_code_response.json()
        city_code_response = city_code_response.json()
        if len(city_code_response['location']) == 0:
            return -1, '未查询到城市'
        city_code = city_code_response['location'][0]['id']
        # get weather
        try:
            weather_response = requests.get(
                self.weather_query_url,
                params={'key': self.key, 'location': city_code}
            )
        except Exception as e:
            return -1, str(e)
        return weather_response.status_code, weather_response.json()

获取 API KEY

开https://dev.qweather.com/docs/api/后，点击右上角控制台获取key

体验自定义工具效果

lmdeploy serve api_server /root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-7b \
                            --server-name 127.0.0.1 \
                            --model-name internlm2-chat-7b \
                            --cache-max-entry-count 0.1

设置

export WEATHER_API_KEY=在2.2节获取的API KEY
# 比如 export WEATHER_API_KEY=1234567890abcdef
cd /root/agent/Tutorial/agent
streamlit run internlm2_weather_web_demo.py --server.address 127.0.0.1 --server.port 7860

查询结果

AgentLego：组装智能体“乐高”

直接使用 AgentLego

下载demo

cd /root/agent
wget http://download.openmmlab.com/agentlego/road.jpg

安装依赖

pip install openmim==0.3.9
mim install mmdet==3.3.0

创建文件

touch /root/agent/direct_use.py

文件内容：

import re

import cv2
from agentlego.apis import load_tool

# load tool
tool = load_tool('ObjectDetection', device='cuda')

# apply tool
visualization = tool('/root/agent/road.jpg')
print(visualization)

# visualize
image = cv2.imread('/root/agent/road.jpg')

preds = visualization.split('\n')
pattern = r'(\w+) \((\d+), (\d+), (\d+), (\d+)\), score (\d+)'

for pred in preds:
    name, x1, y1, x2, y2, score = re.match(pattern, pred).groups()
    x1, y1, x2, y2, score = int(x1), int(y1), int(x2), int(y2), int(score)
    cv2.rectangle(image, (x1, y1), (x2, y2), (0, 255, 0), 1)
    cv2.putText(image, f'{name} {score}', (x1, y1), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 255, 0), 1)

cv2.imwrite('/root/agent/road_detection_direct.jpg', image)

执行推理

python /root/agent/direct_use.py

运行结果

Inference ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━   
truck (345, 428, 528, 599), score 83
car (771, 510, 837, 565), score 81
car (604, 518, 677, 569), score 75
person (866, 503, 905, 595), score 74
person (287, 513, 320, 596), score 74
person (964, 501, 999, 604), score 72
person (1009, 503, 1047, 602), score 69
person (259, 510, 279, 575), score 65
car (1074, 524, 1275, 691), score 64
person (993, 508, 1016, 597), score 62
truck (689, 483, 764, 561), score 62
bicycle (873, 551, 903, 602), score 60
person (680, 523, 699, 567), score 55
bicycle (968, 551, 996, 609), score 53
bus (826, 482, 930, 560), score 52
bicycle (1011, 551, 1043, 617), score 51

作为智能体工具使用

修改相关文件

文件路径：

/root/agent/agentlego/webui/modules/agents/lagent_agent.py

文件的第 105行位置，将 internlm2-chat-20b 修改为 internlm2-chat-7b

使用 LMDeploy 部署

lmdeploy serve api_server /root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-7b \
                            --server-name 127.0.0.1 \
                            --model-name internlm2-chat-7b \
                            --cache-max-entry-count 0.1 

启动 AgentLego WebUI

cd /root/agent/agentlego/webui
python one_click.py

连接

ssh -CNg -L 7860:127.0.0.1:7860 -L 23333:127.0.0.1:23333 root@ssh.intern-ai.org.cn -p 你的 ssh 端口号

使用 AgentLego WebUI

接下来在本地的浏览器页面中打开 http://localhost:7860 以使用 AgentLego WebUI。首先来配置 Agent，如下图所示。

1. 点击上方 Agent 进入 Agent 配置页面。
2. 点击 Agent 下方框，选择 New Agent。
3. 选择 Agent Class 为 lagent.InternLM2Agent。
4. 输入模型 URL 为 http://127.0.0.1:23333 。
5. 输入 Agent name，自定义即可，图中输入了 internlm2。
6. 点击 save to 以保存配置，这样在下次使用时只需在第2步时选择 Agent 为 internlm2 后点击 load 以加载就可以了。
7. 点击 load 以加载配置。

运行结果

用 AgentLego 自定义工具

创建工具文件

touch /root/agent/agentlego/agentlego/tools/magicmaker_image_generation.py

文件内容

import json
import requests

import numpy as np

from agentlego.types import Annotated, ImageIO, Info
from agentlego.utils import require
from .base import BaseTool


class MagicMakerImageGeneration(BaseTool):

    default_desc = ('This tool can call the api of magicmaker to '
                    'generate an image according to the given keywords.')

    styles_option = [
        'dongman',  # 动漫
        'guofeng',  # 国风
        'xieshi',   # 写实
        'youhua',   # 油画
        'manghe',   # 盲盒
    ]
    aspect_ratio_options = [
        '16:9', '4:3', '3:2', '1:1',
        '2:3', '3:4', '9:16'
    ]

    @require('opencv-python')
    def __init__(self,
                 style='guofeng',
                 aspect_ratio='4:3'):
        super().__init__()
        if style in self.styles_option:
            self.style = style
        else:
            raise ValueError(f'The style must be one of {self.styles_option}')
        
        if aspect_ratio in self.aspect_ratio_options:
            self.aspect_ratio = aspect_ratio
        else:
            raise ValueError(f'The aspect ratio must be one of {aspect_ratio}')

    def apply(self,
              keywords: Annotated[str,
                                  Info('A series of Chinese keywords separated by comma.')]
        ) -> ImageIO:
        import cv2
        response = requests.post(
            url='https://magicmaker.openxlab.org.cn/gw/edit-anything/api/v1/bff/sd/generate',
            data=json.dumps({
                "official": True,
                "prompt": keywords,
                "style": self.style,
                "poseT": False,
                "aspectRatio": self.aspect_ratio
            }),
            headers={'content-type': 'application/json'}
        )
        image_url = response.json()['data']['imgUrl']
        image_response = requests.get(image_url)
        image = cv2.imdecode(np.frombuffer(image_response.content, np.uint8), cv2.IMREAD_COLOR)
        return ImageIO(image)
 

注册新工具

接下来修改 /root/agent/agentlego/agentlego/tools/__init__.py 文件，将我们的工具注册在工具列表中。如下所示，我们将 MagicMakerImageGeneration 通过 from .magicmaker_image_generation import MagicMakerImageGeneration 导入到了文件中，并且将其加入了 __all__ 列表中。

from .base import BaseTool
from .calculator import Calculator
from .func import make_tool
from .image_canny import CannyTextToImage, ImageToCanny
from .image_depth import DepthTextToImage, ImageToDepth
from .image_editing import ImageExpansion, ImageStylization, ObjectRemove, ObjectReplace
from .image_pose import HumanBodyPose, HumanFaceLandmark, PoseToImage
from .image_scribble import ImageToScribble, ScribbleTextToImage
from .image_text import ImageDescription, TextToImage
from .imagebind import AudioImageToImage, AudioTextToImage, AudioToImage, ThermalToImage
from .object_detection import ObjectDetection, TextToBbox
from .ocr import OCR
from .scholar import *  # noqa: F401, F403
from .search import BingSearch, GoogleSearch
from .segmentation import SegmentAnything, SegmentObject, SemanticSegmentation
from .speech_text import SpeechToText, TextToSpeech
from .translation import Translation
from .vqa import VQA
from .magicmaker_image_generation import MagicMakerImageGeneration

__all__ = [
    'CannyTextToImage', 'ImageToCanny', 'DepthTextToImage', 'ImageToDepth',
    'ImageExpansion', 'ObjectRemove', 'ObjectReplace', 'HumanFaceLandmark',
    'HumanBodyPose', 'PoseToImage', 'ImageToScribble', 'ScribbleTextToImage',
    'ImageDescription', 'TextToImage', 'VQA', 'ObjectDetection', 'TextToBbox', 'OCR',
    'SegmentObject', 'SegmentAnything', 'SemanticSegmentation', 'ImageStylization',
    'AudioToImage', 'ThermalToImage', 'AudioImageToImage', 'AudioTextToImage',
    'SpeechToText', 'TextToSpeech', 'Translation', 'GoogleSearch', 'Calculator',
    'BaseTool', 'make_tool', 'BingSearch', 'MagicMakerImageGeneration'
]

体验自定义工具效果

lmdeploy serve api_server /root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-7b \
                            --server-name 127.0.0.1 \
                            --model-name internlm2-chat-7b \
                            --cache-max-entry-count 0.1

启动

cd /root/agent/agentlego/webui
python one_click.py