书生浦语第二期实战营系列—综述加技术报告研读
书生浦语第二期实战营系列—Tutorial1:demo体验
书生浦语第二期实战营系列—Tutorial2:RAG
书生浦语第二期实战营系列—Tutorial3:Xtuner微调
书生浦语第二期实战营系列—Tutorial4:Lmdeploy量化部署
书生浦语第二期实战营系列—Tutorial5:Agent
书生浦语第二期实战营系列—Tutorial6:OpenCompass
书生浦语第二期实战营学习笔记(作业)(第六节课)
1 背景知识
1.1 智能体的定义
1.2 为什么需要智能体
1.模型容易产生幻觉
2.模型训练有时效性
3.模型的输出有可靠性的问题
1.3 智能体实现的几种范式
1.3.1 AutoGPT
1.3.2 ReWoo
1.3.3 RaAct
1.4 智能体实现工具
- 智能体实现工具Lagent
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。
2. 多智能体实现工具AgentLego
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
3. Lagent 和 AgentLego 的关系
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。
2 Lagent和AgentLego使用
2.1 安装依赖
conda activate internlm
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 ..
pip install lmdeploy==0.3.0
2.2 完成 Lagent Web Demo 使用(基础作业)
2.2.1 下载代码
git clone -b camp2 https://gitee.com/internlm/Tutorial.git
2.2.2 启动server
lmdeploy serve api_server xxx/Shanghai_AI_Laboratory/internlm2-chat-7b \
--server-name 127.0.0.1 \
--model-name internlm2-chat-7b \
--cache-max-entry-count 0.1
2.2.3启动Lagent Web Demo
1.启动代码
cd xxx/agent/lagent/examples
streamlit run internlm2_agent_web_demo.py --server.address 127.0.0.1 --server.port 7860
2.映射端口
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
3.打开浏览器http://localhost:7860,在模型ip选择127.0.0.1:23333,插件选择Arxivsearch
2.3 完成 AgentLego 直接使用部分(基础作业)
2.3.1 安装依赖
pip install openmim==0.3.9
mim install mmdet==3.3.0
2.3.2 下载数据
wget http://download.openmmlab.com/agentlego/road.jpg
2.3.4 编辑直接启动脚本
使用python直接调用
touch xxx/agent/direct_use.py
import re
import cv2
from agentlego.apis import load_tool
# load tool
tool = load_tool('ObjectDetection', device='cuda')
# apply tool
visualization = tool('xxx/agent/road.jpg')
print(visualization)
# visualize
image = cv2.imread('xxx/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('xxx/agent/road_detection_direct.jpg', image)
2.3.5 运行demo
python xxx/agent/direct_use.py
2.4 完成 AgentLego WebUI 使用(进阶作业)
2.4.1 修改代码
由于 AgentLego 算法库默认使用 InternLM2-Chat-20B 模型,因此我们首先需要修改 /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,即
def llm_internlm2_lmdeploy(cfg):
url = cfg['url'].strip()
llm = LMDeployClient(
- model_name='internlm2-chat-20b',
+ model_name='internlm2-chat-7b',
url=url,
meta_template=INTERNLM2_META,
top_p=0.8,
top_k=100,
temperature=cfg.get('temperature', 0.7),
repetition_penalty=1.0,
stop_words=['<|im_end|>'])
return llm
2.4.2 启动server
lmdeploy serve api_server xxx/Shanghai_AI_Laboratory/internlm2-chat-7b \
--server-name 127.0.0.1 \
--model-name internlm2-chat-7b \
--cache-max-entry-count 0.1
2.4.3 启动demo
1.运行webui
cd xxx/agent/agentlego/webui
python one_click.py
2.填写标题栏Agent
点击:标题栏Agent
Agent:写入一个自定义的agent的名字
Agent class:lagent.InternLM2Agent
URL:127.0.0.1:23333
依次点击:save–load
3.填写标题栏Tools
点击:标题栏Tools
Tools:ObjectDetection
点击:save
4.填写标题栏Chat
点击:标题栏Chat
Select tools:ObjectDetection
对话框:输入–请检测图中物体
依次点击:打开文件夹图标,选择一张图片–Generate
2.5 使用AgentLego 实现自定义工具并完成调用(进阶作业)
2.5.1 创建tools文件
touch xxx/agentlego/agentlego/tools/magicmaker_image_generation.py
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)
2.5.2 注册新工具
修改init文件xxx/agent/agentlego/agentlego/tools/init.py
++19
++29
2.5.3 开启server
lmdeploy serve api_server xxx/Shanghai_AI_Laboratory/internlm2-chat-7b \
--server-name 127.0.0.1 \
--model-name internlm2-chat-7b \
--cache-max-entry-count 0.1
2.5.4 运行demo
1.运行webui
cd xxx/agent/agentlego/webui
python one_click.py
2.填写标题栏Agent
点击:标题栏Agent
Agent:写入一个自定义的agent的名字
Agent class:lagent.InternLM2Agent
URL:127.0.0.1:23333
依次点击:save–load
3.填写标题栏Tools
点击:标题栏Tools
Tools:MagicMakerImageGeneration
点击:save
4.填写标题栏Chat
点击:标题栏Chat
Select tools:MagicMakerImageGeneration
对话框:输入–请帮我生成一张可爱的宠物照片
依次点击:Generate
2.6 使用 Lagent 实现自定义工具并完成调用(进阶作业)
2.6.1 创建tools
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()
2.6.2 获取 API KEY
为了获得稳定的天气查询服务,我们首先要获取 API KEY。
1.首先打开 https://dev.qweather.com/docs/api/ (如下图所示)。
依次点击–控制台–项目管理–创建项目
2.获取API KEY
2.6.3 启动server
lmdeploy serve api_server xxx/Shanghai_AI_Laboratory/internlm2-chat-7b \
--server-name 127.0.0.1 \
--model-name internlm2-chat-7b \
--cache-max-entry-count 0.1
2.6.4 启动Lagent Web Demo
1.启动代码
export WEATHER_API_KEY=1234567890abcdef
cd xxx/agent/Tutorial/agent
streamlit run internlm2_weather_web_demo.py --server.address 127.0.0.1 --server.port 7860
2.映射端口
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
3.打开浏览器http://localhost:7860,在模型ip选择127.0.0.1:23333,插件选择weatherquery
参考链接:
1.https://github.com/InternLM/Tutorial/blob/camp2/agent/lagent.md
2.https://github.com/InternLM/Tutorial/blob/camp2/agent/agentlego.md