Use for RAGFlow dataset tasks: create, list, inspect, update, or delete datasets; upload, list, update, or delete documents; start or stop parsing; check par...
72 次安装8 星标
记忆
LangChain
Builds and debugs LangChain apps in Python: LCEL chains, agents, tools, retrievers, streaming, and structured output. Use when writing or reviewing a chain, agent, tool, retriever, or prompt template; when a prompt raises KeyError or "missing variables"; when streaming arrives as one blob or astream_events yields nothing; when an agent loops until GraphRecursionError or repeats a tool; when tool calls fail validation or the provider rejects a tool_call_id; when chat history disappears or the context window overflows; when with_structured_output returns None or a parser crashes on valid JSON; when retrieval returns the wrong chunks; when LangSmith traces are empty; when retries, rate limits, or token cost need bounding; or when imports break after an upgrade. Covers LangGraph state, checkpointers, and middleware. Not for framework-agnostic agent architecture (agents), retrieval design (rag), or chunk tuning (rag-chunking).
它能做什么
Builds and debugs LangChain apps in Python: LCEL chains, agents, tools, retrievers, streaming, and structured output. Use when writing or reviewing a chain, agent, tool, retriever, or prompt template; when a prompt raises KeyError or "missing variables"; when streaming arrives as one blob or astream_events yields nothing; when an agent loops until GraphRecursionError or repeats a tool; when tool calls fail validation or the provider rejects a tool_call_id; when chat history disappears or the context window overflows; when with_structured_output returns None or a parser crashes on valid JSON; when retrieval returns the wrong chunks; when LangSmith traces are empty; when retries, rate limits, or token cost need bounding; or when imports break after an upgrade. Covers LangGraph state, checkpointers, and middleware. Not for framework-agnostic agent architecture (agents), retrieval design (rag), or chunk tuning (rag-chunking).
技能文档
这个技能的完整文档还没被收录，可以先到原始来源页查看。
相关技能
产出可复用的工作流蓝图,包含触发器、步骤、依赖关系和可导出产物。
362 次安装11 星标
按症状路由到 FastAPI 子指南，排查卡顿、验证错误与异步陷阱。
120 次安装7 星标
按文档化的 Python 规则手册和固定检查清单排查、审阅与编写代码。
156 次安装6 星标
压缩任意来源,保留每一条论断、对冲、数值与归属。
239 次安装4 星标
通过自然语言提示生成交互式仪表盘、数据可视化与网页应用。
155 次安装5 星标