Ohu Logo OHU
Home Use Cases Pricing FAQs Contact MCP Server Docs Dashboard

Ohu Developer API

High-performance REST API for Web Intelligence, RAG Ingestion, Synthetic Datasets, Prompt Injection Security Auditing, and Answer Engine Optimization (AEO).

Code Example Language

Base URL & Headers

All endpoints are served securely over HTTPS:

https://sluxia.com/ohu/api/v1

Request headers require Content-Type: application/json for all POST requests.

Rate Limiting

Requests are rate-limited per IP address. Standard limits allow up to 30 requests per 60 seconds. Exceeding this returns HTTP 429 Too Many Requests.

GET /health

Monitors system status, database connection health, memory usage, and application uptime.

Code Example

curl -s https://sluxia.com/ohu/api/v1/health

Response Payload (200 OK)

{ "status": "healthy", "version": "2.0.0", "system_health_score": 100, "uptime_seconds": 86400, "database": { "status": "connected", "ping_latency_ms": 2 }, "memory": { "rss_mb": 45.2, "heap_used_mb": 22.8, "cpanel_limit_mb": 120, "memory_usage_pct": 38 }, "environment": { "node_version": "v20.11.0", "platform": "darwin" }, "duration_ms": 3 }
POST /synthetic-dataset

Generates high-quality question and answer instruction pairs from web documentation for fine-tuning AI models, with automatic confidence filtering and multi-format exports.

Code Example

curl -X POST https://sluxia.com/ohu/api/v1/synthetic-dataset \ -H "Content-Type: application/json" \ -d '{ "url": "https://stripe.com/docs" }'

Response Payload (200 OK)

{ "source_url": "https://stripe.com/docs", "total_pairs_generated": 5, "dataset_health_score": 96, "strategy_used": "primary_semantic", "dataset": [ { "id": "pair_1", "question": "What details are specified regarding Payments?", "context_quote": "Accept payments online and collect payments with invoices...", "ideal_answer": "Stripe provides APIs to accept online payments, process credit cards...", "section_path": ["Payments", "Online Payments"], "complexity_level": "intermediate", "shannon_entropy_bits": 4.52, "tokens_estimated": 84, "confidence_score": 0.94 } ], "exporters": { "openai_jsonl_prompt": "{\"messages\":[{\"role\":\"user\",\"content\":\"...\"}]}" }, "duration_ms": 14 }
POST /security-audit

Scans webpages for security vulnerabilities, hidden prompt injection risks targeting AI models, and leaked API secret keys.

Code Example

curl -X POST https://sluxia.com/ohu/api/v1/security-audit \ -H "Content-Type: application/json" \ -d '{ "url": "https://github.com" }'

Response Payload (200 OK)

{ "url": "https://github.com", "security_score": 100, "risk_level": "clean", "audit_depth": "deep_nfkc_entropy", "findings_breakdown": { "total_leaked_secrets": 0, "total_prompt_injections": 0 }, "vulnerabilities": { "leaked_secrets": [], "prompt_injections": [] }, "sanitization_recommendations": [], "duration_ms": 4 }
POST /geo-competitor

Compares your website against a competitor for AI search visibility, analyzing semantic relevance, answer confidence, and content gaps to help you rank higher in AI recommendations.

Code Example

curl -X POST https://sluxia.com/ohu/api/v1/geo-competitor \ -H "Content-Type: application/json" \ -d '{ "your_url": "https://stripe.com", "competitor_url": "https://paypal.com", "topic": "Online Payments Infrastructure" }'

Response Payload (200 OK)

{ "topic": "Online Payments Infrastructure", "winner": "yours", "score_delta": 14, "your_site": { "url": "https://stripe.com", "domain": "stripe.com", "geo_score": 82, "citation_probability_pct": 88, "grade": "B", "topic_relevance": 90, "direct_answer_confidence": 85 }, "competitor_site": { "url": "https://paypal.com", "domain": "paypal.com", "geo_score": 68, "citation_probability_pct": 74, "grade": "C", "topic_relevance": 72, "direct_answer_confidence": 65 }, "advantage_matrix": [ { "category": "Topic Semantic Density", "your_score": 90, "competitor_score": 72, "advantage": "yours" }, { "category": "Direct Answer Confidence", "your_score": 85, "competitor_score": 65, "advantage": "yours" }, { "category": "AI Crawler Access", "your_score": 100, "competitor_score": 100, "advantage": "tie" }, { "category": "Knowledge Graph & Schema", "your_score": 80, "competitor_score": 60, "advantage": "yours" } ], "content_gaps_identified": [ "Your site leads competitor on core structural metrics. Expand H2/H3 semantic answer coverage to maintain advantage." ], "duration_ms": 22 }
POST /aeo

Analyzes how effectively AI search engines index and cite your website, providing an overall readiness score and ready-to-use structured schema code snippets.

Code Example

curl -X POST https://sluxia.com/ohu/api/v1/aeo \ -H "Content-Type: application/json" \ -d '{ "url": "https://stripe.com" }'

Response Payload (200 OK)

{ "url": "https://stripe.com", "domain": "stripe.com", "status_code": 200, "aeo_score": 82, "grade": "B", "breakdown": { "ai_crawler_access": { "score": 100, "weight": "30%" }, "entity_and_schema": { "score": 80, "weight": "25%" }, "semantic_content": { "score": 85, "weight": "30%" }, "machine_context": { "score": 60, "weight": "15%" } }, "instant_code_snippets": { "json_ld_organization": "", "llms_txt_boilerplate": "# stripe.com\n\n> Official LLM Context manifest...\n" }, "duration_ms": 24 }
POST /llms-generator

Generates standard `/llms.txt` and `/llms-full.txt` markdown manifests for your website to help AI models easily navigate and understand your core documentation.

Code Example

curl -X POST https://sluxia.com/ohu/api/v1/llms-generator \ -H "Content-Type: application/json" \ -d '{ "url": "https://stripe.com", "company_name": "Stripe", "description": "Financial infrastructure for the internet" }'

Response Payload (200 OK)

{ "domain": "stripe.com", "status_code": 200, "spec_version": "V1", "context_density_score": 95, "estimated_tokens": 420, "full_estimated_tokens": 1280, "is_budget_compliant": true, "llms_txt": "# Stripe\n\n> Official LLM Context manifest for stripe.com.\n\n## Key Sections & Documentation\n- [Documentation](https://stripe.com/docs): Official API guide.\n", "prompt_code_snippets": { "javascript_fetch": "const res = await fetch('https://stripe.com/llms.txt');", "python_requests": "import requests\nsystem_prompt = requests.get('https://stripe.com/llms.txt').text" }, "duration_ms": 22 }
POST /brand-mentions

Monitors online brand mentions across web and news sources while excluding your own domain, analyzing sentiment breakdown and market share of voice.

Code Example

curl -X POST https://sluxia.com/ohu/api/v1/brand-mentions \ -H "Content-Type: application/json" \ -d '{ "brand_name": "OpenAI", "brand_domain": "openai.com", "keywords": ["GPT-5", "Sora"], "recency": "30d", "max_results": 5 }'

Response Payload (200 OK)

{ "brand_name": "OpenAI", "brand_domain": "openai.com", "recency_filter": "30d", "total_mentions": 5, "share_of_voice_pct": 78, "crisis_risk_index": 0, "sentiment_breakdown": { "positive": 4, "neutral": 1, "negative": 0 }, "mentions": [ { "title": "OpenAI releases new intelligence model", "url": "https://techcrunch.com/openai-release", "source_domain": "techcrunch.com", "proximity_snippet": "...OpenAI releases new high speed intelligence model with fast latency...", "sentiment": "positive", "aspect_sentiment": { "speed": "positive", "reliability": "positive" } } ], "duration_ms": 280 }
POST /table-extract

Extracts tables from any webpage, automatically inferring data types and exporting formatted JSON, Markdown tables, and CSV data.

Code Example

curl -X POST https://sluxia.com/ohu/api/v1/table-extract \ -H "Content-Type: application/json" \ -d '{ "url": "https://en.wikipedia.org/wiki/List_of_programming_languages" }'

Response Payload (200 OK)

{ "source_url": "https://en.wikipedia.org/wiki/List_of_programming_languages", "total_tables_found": 1, "tables": [ { "table_index": 1, "column_count": 3, "row_count": 2, "table_quality_score": 100, "headers": ["Language", "Designed By", "Year"], "column_types": { "Language": "string", "Designed By": "string", "Year": "number" }, "structured_data": [ { "Language": "Python", "Designed By": "Guido van Rossum", "Year": 1991 } ], "exporters": { "gfm_markdown": "| Language | Designed By | Year |\n| --- | --- | --- |\n| Python | Guido van Rossum | 1991 |", "csv": "Language,Designed By,Year\nPython,Guido van Rossum,1991" } } ], "duration_ms": 12 }
POST /clean-article

Extracts clean article content from any webpage by removing ads, navigation menus, and sidebars—returning formatted text, lead summary, and hero images.

Code Example

curl -X POST https://sluxia.com/ohu/api/v1/clean-article \ -H "Content-Type: application/json" \ -d '{ "url": "https://news.ycombinator.com", "max_length": 5000 }'

Response Payload (200 OK)

{ "url": "https://news.ycombinator.com", "title": "Hacker News", "hero_image": "https://news.ycombinator.com/og-image.png", "lead_summary": "Hacker News provides technology news and discussions...", "reading_time_minutes": 2, "word_count": 340, "estimated_tokens": 425, "markdown": "# Hacker News\n\n1. [Show HN: Ohu Web Intelligence Engine](https://sluxia.com/ohu)...", "duration_ms": 15 }
POST /code-extract

Extracts code blocks from technical documentation and web pages, automatically identifying programming languages and separating code snippets from terminal commands.

Code Example

curl -X POST https://sluxia.com/ohu/api/v1/code-extract \ -H "Content-Type: application/json" \ -d '{ "url": "https://python.org" }'

Response Payload (200 OK)

{ "url": "https://python.org", "total_blocks": 3, "languages_found": ["python", "bash"], "blocks": [ { "block_index": 1, "language": "python", "category": "source_code", "line_count": 5, "character_length": 120, "estimated_tokens": 36, "code": "def hello():\n print('Hello World')" } ], "duration_ms": 8 }
POST /media-extractor

Extracts all media assets from a webpage, including video streams, audio podcasts, high-resolution images, video embeds, hero banner images, and image alt-text accessibility coverage.

Code Example

curl -X POST https://sluxia.com/ohu/api/v1/media-extractor \ -H "Content-Type: application/json" \ -d '{ "url": "https://github.com" }'

Response Payload (200 OK)

{ "url": "https://github.com", "video_count": 0, "audio_count": 0, "image_count": 12, "embed_count": 1, "alt_text_accessibility_pct": 92, "adaptive_streams": [], "images": [ { "type": "og:image", "url": "https://github.com/og.png", "alt": "GitHub Cover", "is_hero": true } ], "duration_ms": 12 }
POST /rag-chunk

Converts webpages or raw text into optimized chunks for RAG vector databases, preserving heading hierarchy and generating ready-to-use vector database export formats.

Code Example

curl -X POST https://sluxia.com/ohu/api/v1/rag-chunk \ -H "Content-Type: application/json" \ -d '{ "url": "https://news.ycombinator.com", "chunk_size": 250, "overlap": 30 }'

Response Payload (200 OK)

{ "source_url": "https://news.ycombinator.com", "total_chunks": 5, "total_estimated_tokens": 640, "vector_db_exporters": { "pinecone": [{ "id": "chunk_1", "metadata": { "section": "News > Top", "text": "Header: News > Top\n\n..." } }] }, "chunks": [ { "chunk_id": "chunk_1", "section_path": ["News", "Top"], "quality_score": 100, "text": "Header: News > Top\n\nShow HN: Ohu Web Intelligence Engine...", "word_count": 210, "estimated_tokens": 128 } ], "duration_ms": 8 }
POST /pdf-to-markdown

Converts PDF documents into clean, structured Markdown text while preserving multi-column layouts, tables, and document headings.

Code Example

curl -X POST https://sluxia.com/ohu/api/v1/pdf-to-markdown \ -H "Content-Type: application/json" \ -d '{ "url": "https://www.orimi.com/pdf-test.pdf", "max_length": 5000 }'

Response Payload (200 OK)

{ "url": "https://www.orimi.com/pdf-test.pdf", "page_count": 1, "scanned_pdf_warning_score": 0, "is_scanned_pdf": false, "info": { "title": "PDF Test Document", "author": "" }, "word_count": 58, "estimated_tokens": 72, "markdown": "# PDF Test Document\n\nCongratulations...", "duration_ms": 32 }
POST /crawl

Crawls website pages and returns content in multiple formats including Markdown, raw HTML, plain text, extracted links, and page metadata.

Code Example

curl -X POST https://sluxia.com/ohu/api/v1/crawl \ -H "Content-Type: application/json" \ -d '{ "url": "https://news.ycombinator.com", "formats": ["markdown", "metadata", "links"], "css_selector": "body", "max_length": 5000, "max_pages": 1 }'

Response Payload (200 OK)

{ "crawl_id": "crawl_98f7a61b", "seed_url": "https://news.ycombinator.com", "target_domain": "news.ycombinator.com", "status": "COMPLETED", "crawl_completeness_pct": 100, "total_pages_queued": 1, "total_pages_crawled": 1, "total_duplicates_skipped": 0, "total_estimated_tokens": 540, "pages": [ { "url": "https://news.ycombinator.com", "depth": 0, "status_code": 200, "content_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "results": { "markdown": "# Hacker News\n\n...", "metadata": { "title": "Hacker News", "description": "" } } } ], "duration_ms": 18 }
POST /markdown

Converts web pages or HTML elements into clean Markdown format, expanding relative links and retaining images and formatted callout boxes.

Code Example

curl -X POST https://sluxia.com/ohu/api/v1/markdown \ -H "Content-Type: application/json" \ -d '{ "url": "https://en.wikipedia.org/wiki/Node.js", "css_selector": "body", "max_length": 5000 }'

Response Payload (200 OK)

{ "url": "https://en.wikipedia.org/wiki/Node.js", "status_code": 200, "results": { "markdown": "# Node.js\n\n> [!NOTE]\n> Sub-15ms extraction with zero LLM API cost.\n\nNode.js is an open-source JavaScript runtime environment..." }, "duration_ms": 9 }
POST /extract

Extracts structured data from any webpage using CSS selectors, supporting attribute targets, typed values, and nested data schemas.

Code Example

curl -X POST https://sluxia.com/ohu/api/v1/extract \ -H "Content-Type: application/json" \ -d '{ "url": "https://news.ycombinator.com", "selectors": { "headlines": ".titleline > a", "scores": ".score" } }'

Response Payload (200 OK)

{ "url": "https://news.ycombinator.com", "status_code": 200, "extraction_fidelity_pct": 100, "matched_fields_count": 1, "total_fields_requested": 1, "results": { "headlines": ["Show HN: Ohu Web Intelligence Engine", "Stripe acquires Bridge"] }, "duration_ms": 4 }