firecrawl-knowledge-base

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Firecrawl Knowledge Base

Firecrawl知识库

Use this to turn URLs or topics into organized LLM-ready content.

使用此工具将URL或主题转换为结构化的LLM就绪内容。

Onboarding Interview

引导访谈

Infer the source, goal, depth, and output location from context. If the source and goal are clear, proceed immediately.

Ask at most 1-3 concise questions only if blocked, such as the source URL/topic, whether the output is reference/RAG/training/docs, or training format if training is requested.

从上下文推断来源、目标、深度和输出位置。如果来源和目标明确，立即开始执行。

仅在遇到阻碍时提出最多1-3个简洁问题，例如来源URL/主题、输出类型是参考文档/RAG/训练数据/文档镜像，或者如果要求生成训练数据，询问训练格式。

Firecrawl Collection Plan

Firecrawl采集方案

Use Firecrawl map for documentation sites, search for topic-based corpora, scrape pages into markdown, and preserve code examples and tables.

For files, follow the Firecrawl download-style convention:

text

.firecrawl/
  <hostname>/
    <path>/
      index.md

针对文档站点使用Firecrawl地图，搜索基于主题的语料库，将页面抓取为markdown格式，并保留代码示例和表格。

对于文件，遵循Firecrawl下载式命名规范：

text

.firecrawl/
  <hostname>/
    <path>/
      index.md

Parallel Work

并行工作

If appropriate, use sub-agents or equivalent parallel task runners:

one docs section per researcher
official docs, tutorials, community discussions, and references by source type
source scraping vs chunk generation vs manifest generation

如果合适，使用子Agent或等效的并行任务运行器：

每个研究员负责一个文档板块
按来源类型区分官方文档、教程、社区讨论和参考资料
来源抓取、块生成和清单生成并行处理

Output Modes

输出模式

Reference: markdown files,
```
index.md
```
, and
```
sources.json
```
.
RAG: markdown files plus chunk files and
```
manifest.json
```
.

Training: scraped source files plus

training-data.jsonl

and

training-metadata.json

Docs mirror: complete markdown mirror with a table of contents.

参考模式：markdown文件、
```
index.md
```
和
```
sources.json
```
。
RAG模式：markdown文件加上块文件和
```
manifest.json
```
。
训练模式：抓取的源文件加上
```
training-data.jsonl
```
和
```
training-metadata.json
```
。
文档镜像：带目录的完整markdown镜像。

Final Deliverable

最终交付物

markdown

undefined

markdown

undefined

Knowledge Base: [Source]

知识库：[来源]

Summary

摘要

[What was collected and why]

[采集内容及原因]

Output Structure

输出结构

[Files/directories created]

[创建的文件/目录]

Coverage

覆盖范围

[Sections, source types, counts]

[板块、来源类型、数量]

Usage Notes

使用说明

[How to use in RAG, docs, training, or agent context]

[如何在RAG、文档、训练或Agent场景中使用]

Sources

来源

[URLs collected]

[采集的URL]

Rerun Inputs

重新运行参数

workflow: firecrawl-knowledge-base source: [url/topic] goal: [reference/rag/train/docs] depth: [quick/thorough/exhaustive] output_dir: [.firecrawl/]

undefined

workflow: firecrawl-knowledge-base source: [url/主题] goal: [reference/rag/train/docs] depth: [quick/thorough/exhaustive] output_dir: [.firecrawl/]

undefined

Quality Bar

质量标准

Preserve code examples and formatting.
Remove boilerplate navigation where possible.
Include source URLs in frontmatter or metadata.

保留代码示例和格式。
尽可能移除冗余导航内容。
在前置元数据或元数据中包含来源URL。