ohu
Turn Any Website Into Clean Fine-Tuning Data & RAG Context in Seconds.
Community: Submitted by a user or imported; check the owner before granting accessOnlineAPI key requiredGlobalFreeRead-only
What it can do
- Crawl: Crawl a URL and extract content in multiple formats (markdown, HTML, text, links, metadata)
- Markdown: Convert a URL to clean Markdown format
- Extract: Extract structured data from a URL using CSS selectors
What data it sees
Do you need an account
An API key from the service settings is required
Turn Any Website Into Clean Fine-Tuning Data & RAG Context in Seconds. Without Scraping Bans or Prompt Injections. Ohu handles the dirty work by bypassing DOM noise, parsing PDFs, auditing hidden AI injection attacks, and feeding your LLMs pristine JSONL datasets with a single API call.
Server tool list (17)
Raw names from tools/list. Only developers need these.
| crawl | Crawl a URL and extract content in multiple formats (markdown, HTML, text, links, metadata) |
| markdown | Convert a URL to clean Markdown format |
| extract | Extract structured data from a URL using CSS selectors |
| search | Search the web using multiple providers (Bing, DuckDuckGo, Wikipedia) |
| aeo | Analyze a URL for Answer Engine Optimization (AEO) readiness — scores AI crawler access, schema markup, semantic content, and machine readability |
| rag_chunk | Chunk content for RAG (Retrieval-Augmented Generation) with vector DB exports for Pinecone, Qdrant, Weaviate, and Chroma |
| llms_generator | Generate llms.txt and llms-full.txt manifests for a website — makes your site discoverable by LLMs |
| brand_mentions | Monitor brand mentions across the web with sentiment analysis |
| pdf_to_markdown | Convert a PDF URL to structured Markdown |
| table_extract | Extract HTML tables as structured JSON and Markdown |
| clean_article | Extract the main article body from a URL (reader-mode distillation) |
| code_extract | Extract code blocks from a URL, grouped by language |
| media_extractor | Find all media assets (video, audio, images, embeds) on a page |
| link_graph | Categorize and map all links on a page (internal, external, files, social) |
| geo_competitor | Head-to-head GEO (Generative Engine Optimization) competitor comparison |
| synthetic_dataset | Generate synthetic QA instruction pairs for LLM fine-tuning (JSONL, OpenAI, DPO formats) |
| security_audit | Scan a page for prompt injection vectors and leaked secrets/API keys |