Agently
Agently copied to clipboard
Maplemx
[AI Agent Application Development Framework] - 🚀 Build AI agent native application in very few code 💬 Easy to interact with AI agent in code using structure data and chained-calls syntax 🧩 Enhance...
Baichuan2-13B、Baichuan2-7B ChatGLM2-6B Qwen-14B、Qwen-7B
pycharm中执行样例总是报线程问题，这个异步是否需要优化一下 Exception ignored in: Traceback (most recent call last): File "D:\Python\Python39\lib\asyncio\proactor_events.py", line 116, in __del__ self.close() File "D:\Python\Python39\lib\asyncio\proactor_events.py", line 108, in close self._loop.call_soon(self._call_connection_lost, None) File "D:\Python\Python39\lib\asyncio\base_events.py", line 751, in call_soon...
1、中文版开发文档看了，没有看到workflow部分；我看最近开源的新闻整理有用到这个，是不是我没找对地方 2、之前看过langchain，这类开发框架偏向使用（自定义数据结构，规则）多一些，强行理解了一波（其实最后这些结构应该是组装成prompt）。agent其实是对prompt engineering的一种实践，如果能有方法直接输出传给llm的prompt以及响应，理解会更直观。 以上两个问题，当然可能我还没看到应该地方？
this project is exciting, but can you provide a use case for the function_call based on gemini-pro?
Because gemini-pro is fast and free.
Applying the GLM model to multi-agent game interaction, the scenario is based on identifying the culprit. ``` import Agently import ENV import json # 加载 JSON 配置文件 with open('glm.json', 'r',...
@must_call_agent.tool(tool_name="get_now") def get_current_datetime_decorated( timezone: ( "str", "[*Required] Timezone string used in pytz.timezone() in Python" ) ): """get current data and time""" tz = pytz.timezone(timezone) return datetime.now().astimezone(tz) 报错内容： [51](https://file+.vscode-resource.vscode-cdn.net/Users/lizhen/Documents/Projects/QueryCorrection/~/anaconda3/envs/py38/lib/python3.8/site-packages/Agently/plugins/agent_component/Decorator.py:51) if node.arg...
Agently.AgentFactory() .set_settings("current_model", "OAIClient") .set_settings("model.OAIClient.auth.api_key", "nothing") .set_settings("model.OAIClient.options", {"model": "my-llm"}) .set_settings("model.OAIClient.url", "http://127.0.0.1:9997/v1")
https://mermaid.live/代码： %%{ init: { 'flowchart': { 'curve': 'linear' }, 'theme': 'neutral' } }%% %% Rendered By Agently %% flowchart LR classDef chunk_style fill:#fbfcdb,stroke:#666,stroke-width:1px,color:#333; classDef condition_chunk_style fill:#ECECFF,stroke:#9370DB,stroke-width:1px,color:#333; classDef loop_style fill:#f5f7fa,stroke:#666,stroke-width:1px,color:#333,stroke-dasharray: 5...
有两个问题： 1. 使用百度千帆的 Access Token 方式报错 2. 看上去现在是通过 Erniebot 包实现的， 有考虑跟 lang-chain 一样使用 qianfan 的包实现吗？且能支持在百度千帆上发布的自训练的模型 agent 初始化方式： import Agently agent = ( Agently.create_agent() .set_settings("current_model", "ERNIE") .set_settings("model.ERNIE.auth", { # 使用AIStudio的Access Token...
