searching-mlflow-docs
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseMLflow Documentation Search
MLflow文档搜索
Workflow
工作流程
- Fetch to find relevant page paths
https://mlflow.org/docs/latest/llms.txt - Fetch the file at the identified path
.md - Present results with verbatim code examples
- 获取以找到相关页面路径
https://mlflow.org/docs/latest/llms.txt - 获取已识别路径下的文件
.md - 附带逐字代码示例展示结果
Step 1: Fetch llms.txt Index
步骤1:获取llms.txt索引
WebFetch(
url: "https://mlflow.org/docs/latest/llms.txt",
prompt: "Find links or references to [TOPIC]. List all relevant URLs."
)WebFetch(
url: "https://mlflow.org/docs/latest/llms.txt",
prompt: "查找与[TOPIC]相关的链接或引用。列出所有相关URL。"
)Step 2: Fetch Target Documentation
步骤2:获取目标文档
Use the path from Step 1, always with extension:
.mdWebFetch(
url: "https://mlflow.org/docs/latest/[path].md",
prompt: "Return all code blocks verbatim. Do not summarize."
)使用步骤1中的路径,始终使用扩展名:
.mdWebFetch(
url: "https://mlflow.org/docs/latest/[path].md",
prompt: "逐字返回所有代码块。请勿总结。"
)Anti-Patterns
反模式
Do not use files — Fetch source files only.
.html.mdDo not use WebSearch — Always start from llms.txt; web search returns outdated or third-party content.
Do not use vague prompts — "Extract complete documentation" allows summarization. Use "Return all code blocks verbatim. Do not summarize."
Do not use versioned paths — Always use , never or other versions unless the user explicitly requests a specific version.
/docs/latest//docs/3.8/Do not guess URLs — Always verify paths exist in llms.txt before fetching. Never construct documentation paths from assumptions.
Do not follow external links — Stay within mlflow.org/docs. Do not follow links to GitHub, PyPI, or third-party sites.
Do not mix sources — Use only MLflow docs. Do not combine with LangChain docs, OpenAI docs, or other external documentation.
Do not use llms.txt for non-GenAI topics — The llms.txt index covers LLM/GenAI documentation only. For classic ML tracking features, paths may differ.
请勿使用文件 — 仅获取源文件。
.html.md请勿使用WebSearch — 始终从llms.txt开始;网页搜索会返回过时或第三方内容。
请勿使用模糊提示 — “提取完整文档”允许进行总结。请使用“逐字返回所有代码块。请勿总结。”
请勿使用带版本的路径 — 始终使用,除非用户明确要求特定版本,否则绝不要使用或其他版本路径。
/docs/latest//docs/3.8/请勿猜测URL — 在获取之前始终确认路径存在于llms.txt中。绝不要凭假设构建文档路径。
请勿跟随外部链接 — 仅在mlflow.org/docs范围内操作。请勿跟随指向GitHub、PyPI或第三方站点的链接。
请勿混合来源 — 仅使用MLflow文档。请勿与LangChain文档、OpenAI文档或其他外部文档结合使用。
请勿将llms.txt用于非生成式AI主题 — llms.txt索引仅覆盖LLM/生成式AI相关文档。对于经典机器学习跟踪功能,路径可能不同。