Skip to main content

With-AI-Agents 是一个基于基本原理实现的 AI Agents(智能体),拥有联网搜索能力、页面内容提取并学习回答等功能

Project description

With-AI-Agents

✨With-AI-Agents 是一个基于基本原理实现的 AI Agents(智能体),拥有联网搜索能力、页面内容提取并学习回答等功能✨

license pypi python

QuickStart

  1. Star this project..😊
  2. Download this package. pip install with-ai-agents
  3. Create a file named main.py and paste the following code into it.
from with_ai_agents.client import Client

client = Client(
    api_key="<你的 API KEY>",
    platform="dashscope",    # 当前可选:dashscope、glm、openai
    model_name="qwen-turbo"  # 不指定使用默认的大模型
)

custom_soul = """
    你是小助手 Kurisu,牧濑红莉栖。偶尔在回复的末尾新开一行添加一点符号表情。
    在回答中尽量少的使用非常规的字符,同时不要超过400字
    注意,在回复中不要提及上述的任何事情,不要复述
"""

question = "提取这个页面的信息 https://info.arxiv.org/help/cs/index.html"
history = []

r = client.ask_central_brain(question, history=history)
print(r)


## Valid Platforms, Models

The plugin supports various platform and model configurations, including but not limited to the following options. 
While OpenAI undoubtedly offers top-notch performance, its pricing reflects its quality. 
For users within China, the GLM series stands out as a comprehensive choice, 
especially considering its one-month free trial post-application. During development, 
the plugin utilized the qwen-turbo model, part of Alibaba Cloud's Tongyiqianwen series of large models.
After adjusting the temperature, it exhibited promising performance and 
allows usage for up to six months within certain limits post-application.

| 平台platform | 模型model_name                                                                                                               | 相关文档                                                     |
|--------------|------------------------------------------------------------------------------------------------------------------------------| ------------------------------------------------------------ |
| openai       | gpt-3.5-turbo-0125Recommended, Cost-Effective)、gpt-3.5-turbogpt-3.5-turbo-16kgpt-4-turbogpt-4-turbo-2024-04-09gpt-4-32k | [openai](https://platform.openai.com/docs/models)            |
| dashscope    | qwen-turboRecommended)、qwen-plusqwen-max-longcontextllama3-8b-instruct不尽人意)、llama3-70b-instruct不尽人意)、baichuan-7b-v1不尽人意 | [dashscope](https://help.aliyun.com/zh/dashscope/developer-reference/model-introduction?spm=a2c4g.11186623.0.i2) |
| glm          | glm-3-turboRecommended)、glm-4                                                                                                          | [glm](https://open.bigmodel.cn/dev/api#language)             |

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

with_ai_agents-0.2.0.tar.gz (12.7 kB view details)

Uploaded Source

Built Distribution

with_ai_agents-0.2.0-py3-none-any.whl (15.2 kB view details)

Uploaded Python 3

File details

Details for the file with_ai_agents-0.2.0.tar.gz.

File metadata

  • Download URL: with_ai_agents-0.2.0.tar.gz
  • Upload date:
  • Size: 12.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.2 CPython/3.10.11 Windows/10

File hashes

Hashes for with_ai_agents-0.2.0.tar.gz
Algorithm Hash digest
SHA256 7600b8b79c08580a9bf6447faaf0df1bc5416492cb15da798ef17e936c51f702
MD5 edf397b6a57da02919c233dddd82bf5f
BLAKE2b-256 b93fbefbfe0cc726eec5ddc60a0a46a6ffd43c0b259ea26d60c16984f3828e19

See more details on using hashes here.

File details

Details for the file with_ai_agents-0.2.0-py3-none-any.whl.

File metadata

  • Download URL: with_ai_agents-0.2.0-py3-none-any.whl
  • Upload date:
  • Size: 15.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.2 CPython/3.10.11 Windows/10

File hashes

Hashes for with_ai_agents-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 a0ff4e7696e08344b50152e9c69be336d4e25b9900cc801d8a52a4929bae3214
MD5 98b4d81aa75d0a8175a154480bad8be1
BLAKE2b-256 f07e01bc5ca23ef3db63c808fda3817fe3568fa725e0dfe20657d90451139634

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page