volcengine/hiagent-python-sdk

최근 기록된 소스 활동: 2026년 5월 29일 03:26

SkillsMP 카탈로그 업데이트: 2026년 11월 2일 18:02

수집된 skills: 3

GitHub 스타: 30
GitHub 포크: 10

AI 어시스턴트로 설치

이 프롬프트를 복사해 사용 중인 AI 어시스턴트에 입력하세요.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/volcengine/hiagent-python-sdk.

저장소 README

README 원본 파일: README.md

README 원본 보기

README 전체 펼치기

# Overview English | [中文README](README.zh_CN.md) HiAgent-SDK is the SDK of the HiAgent product from Volcano Engine. Developers can use this SDK to quickly develop functions and improve development efficiency. HiAgent-SDK provides a complete AI native application development suite, including a rich set of development components and application example code. ## Architecture ![img.png](img.png) Documentation Access the document at [document address](https://bytedance.larkoffice.com/docx/EnpxdRL18oxsrqxubHjcylTDnif) to obtain the documentation. ## Quick Start ``` python import os from dotenv import load_dotenv from hiagent_api.chat import ChatService from hiagent_api.knowledgebase import KnowledgebaseService from hiagent_api.tool import ToolService from hiagent_components.agent import Agent from hiagent_components.integrations.langchain import LangChainTool from hiagent_components.retriever import KnowledgeRetriever from hiagent_components.tool import Tool from langchain.agents import AgentExecutor, create_structured_chat_agent from langchain.callbacks import StdOutCallbackHandler from langchain_openai import ChatOpenAI from langsmith import Client load_dotenv() def get_tool_svc() -> ToolService: svc = ToolService( endpoint=os.getenv("HIAGENT_TOP_ENDPOINT") or "", region="cn-north-1" ) return svc def get_chat_svc() -> ChatService: svc = ChatService( endpoint=os.getenv("HIAGENT_TOP_ENDPOINT") or "", region="cn-north-1" ) svc.set_app_base_url(os.getenv("HIAGENT_APP_BASE_URL") or "") return svc def get_knowledgebase_svc() -> KnowledgebaseService: svc = KnowledgebaseService( endpoint=os.getenv("HIAGENT_TOP_ENDPOINT") or "", region="cn-north-1" ) return svc if __name__ == "__main__": tool = Tool.init( svc=get_tool_svc(), workspace_id="cuq0pp9s7366bfl0cns0", tool_id="5njoa3j2m2t5cpaotjlg" ) app_key = os.getenv("HIAGENT_AGENT_APP_KEY") or "" agent = Agent.init( svc=get_chat_svc(), app_key=app_key, user_id="test", variables={"name": "weather_assistant"}, ) retriever = KnowledgeRetriever( svc=get_knowledgebase_svc(), name="knowledge_tool", description="knowledge retriever, used to search knowledge about pandas", workspace_id="cuq0pp9s7366bfl0cns0", dataset_ids=["019613e3-f37b-7b80-8e0a-579435bb9870"], top_k=3, score_threshold=0.4, retrieval_search_method=0, ) ocr_tool = LangChainTool.from_tool(tool) agent_tool = LangChainTool.from_tool(agent.as_tool()) retriever_tool = LangChainTool.from_tool(retriever.as_tool()) tools = [ocr_tool, agent_tool, retriever_tool] # Pull the prompt template from the hub # ReAct = Reason and Action # https://smith.langchain.com/hub/hwchase17/react client = Client() prompt = client.pull_prompt("hwchase17/structured-chat-agent") prompt.messages[0].prompt.template += "\n\n## Notice\n\n tool's action_input must be json object rather than string" callbacks = [StdOutCallbackHandler()] # export OPENAI_API_KEY=xxxx # Initialize a ChatOpenAI model llm = ChatOpenAI( model=os.getenv("OPENAI_MODEL"), # pro base_url="https://ark.cn-beijing.volces.com/api/v3", callbacks=callbacks, ) agent = create_structured_chat_agent( llm=llm, tools=tools, prompt=prompt, ) # Create an agent executor from the agent and tools agent_executor = AgentExecutor.from_agent_and_tools( agent=agent, tools=tools, verbose=False, callbacks=callbacks, ) # Run the agent with a test query response = agent_executor.invoke( {"input": "Is the weather in Shenzhen suitable for going out today?"}, ) # Print the response from the agent print("response:", response) ``` ## Code of Conduct Please check [Code of Conduct](CODE_OF_CONDUCT.md) for more details. ## Security and privacy This project takes security seriously. For vulnerability reporting and supported versions, see [SECURITY.md](SECURITY.md) ## License This project is licensed under the [Apache-2.0 License](LICENSE).

저장소 README를 불러오는 중…

이 저장소의 skills

소프트웨어 개발자 소프트웨어 품질 보증 분석가·테스터

직업 카테고리 2개 · 100% 분류됨

skill

직업 분류

설명

업데이트

cli-anything-hiagent

소프트웨어 개발자

Command-line interface for HiAgent Python SDK - Observe service (API Token, Trace Spans) via CLI

원문 언어: 영어

2026-05-29

hiagent-cli

소프트웨어 개발자

当用户想使用 HiAgent 观测(observe)能力（API Token、Trace Spans 查询）时，务必使用这个技能给出可直接执行的 cli-anything-hiagent observe 命令与排障步骤。尤其适用于用户提到 agent-harness、cli_anything、--json、workspace-id、custom-app-id、VOLC_ACCESSKEY/VOLC_SECRETKEY、observe token、observe…

원문 언어: 중국어

2026-05-29

e2e-runbook-skill

소프트웨어 품질 보증 분석가·테스터

Hibot Go SDK 端到端测试上传的最小可解析 Skill。当用户要求执行 pulse check / 心跳检查 / 排障状态查询时，Agent 应当调用本 skill 并返回结构化响应（包含字面量 PULSE_OK_E2E）。

원문 언어: 중국어

2026-05-26

수집된 skill 3개 중 3개를 표시합니다.