# RAG Data Ingestion: Website to AI Knowledge Base (`0xysn/rag-data-ingestion-website-to-ai-knowledge-base`) Actor Master complex documentation with a premium scraper that flattens Shadow DOM and handles modern web components. Delivers clean, token-accurate Markdown pre-chunked for immediate RAG ingestion into Pinecone, Weaviate, or LangChain. Optimized for high-fidelity LLM training data. - **URL**: https://apify.com/0xysn/rag-data-ingestion-website-to-ai-knowledge-base.md - **Developed by:** [tekk](https://apify.com/0xysn) (community) - **Categories:** AI, Automation - **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, NaN bookmarks - **User rating**: No ratings yet ## Pricing from $1.00 / 1,000 premium scraped pages This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Actors are written with capital "A". ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## Universal AI Knowledge Scraper β€” Premium RAG Ingestion Engine > **The high-fidelity bridge between the complex web and your LLM.** Convert any website or documentation portal into cleaned, chunked, and token-accurate Markdown optimized for RAG pipelines. Build production-grade RAG (Retrieval-Augmented Generation) datasets with a single Actor run. Feed the output directly into **Pinecone, Weaviate, Qdrant, ChromaDB**, or any vector store. --- ### πŸ›‘οΈ Why Use This Actor? Most scrapers return empty strings on modern documentation sites. This Actor was built to solve the "Invisible Web" problem. | Feature | Standard Scrapers | This Actor | | :--- | :---: | :---: | | **Vanilla HTML** | βœ… | βœ… | | **Shadow DOM / Web Components** | ❌ (Empty Output) | βœ… (Full Flattening) | | **Token Tracking** | ❌ (Manual Regex) | βœ… (Native Tiktoken) | | **Modern Code Blocks** | ❌ (Garbled) | βœ… (Clean GFM) | - **Built-in Token Counting for Budget Management** β€” Every record includes a `usage` object with exact token counts, encoding type, and chunk parameters. Enterprise teams can calculate embedding costs *before* hitting the OpenAI API. - **Shadow DOM Extraction** β€” Successfully captures content from Shadow DOM-heavy sites (like Shoelace Web Components) where standard crawlers see nothing. - **Zero-Config Extraction** β€” No CSS selectors to maintain. The density-based Readability algorithm adapts to any site layout automatically. - **Antifragile Stealth** β€” BΓ©zier-curve mouse simulation and fingerprint rotation make this Actor invisible to Cloudflare, Akamai, and behavioral detection systems. - **CU-Optimized** β€” Resource interception blocks images, fonts, and media. You get lower memory usage and higher concurrency at the same price. --- ### πŸš€ Key Features - **Hybrid Discovery** β€” Priority parsing of `sitemap.xml` with fallback to recursive `` tag extraction. - **Universal Extraction** β€” Powered by Mozilla's Readability algorithm with recursive Shadow DOM flattening. - **Clean Markdown Output** β€” Converts HTML to Markdown via Turndown with GFM support (tables, code blocks). - **Token-Aware Chunking** β€” Splits content using `tiktoken` (GPT-4o / o1 encodings) into configurable chunk sizes with overlap. - **Bloom Filter Dedup** β€” O(1) URL deduplication prevents infinite loops and duplicate scraping. --- ### πŸ“¦ Output Format Each record is a standardized JSON object ready for vector database ingestion: ```json { "metadata": { "source_url": "[https://docs.example.com/api/auth](https://docs.example.com/api/auth)", "title": "Authentication β€” API Docs", "crawled_at": "2026-04-30T13:00:00Z", "site_name": "Example Docs", "lang": "en" }, "usage": { "total_tokens": 1010, "total_chunks": 2, "encoding": "o200k_base", "chunk_size": 512, "chunk_overlap": 50 }, "content": [ { "chunk_id": 1, "token_count": 512, "text": "#### Authentication\n\nAll API requests require a Bearer token..." } ], "raw_markdown": "#### Authentication\n\nAll API requests require a Bearer token..." } # Actor input Schema ## `startUrls` (type: `array`): One or more URLs to begin crawling from. ## `maxCrawlDepth` (type: `integer`): Maximum link-following depth. Set to 0 to only scrape start URLs. ## `maxRequestsPerCrawl` (type: `integer`): Hard limit on total pages scraped in a single run. ## `maxConcurrency` (type: `integer`): Maximum parallel pages. 5-10 is recommended for 2GB memory. ## `chunkSize` (type: `integer`): Target number of tokens per content chunk. ## `chunkOverlap` (type: `integer`): Overlapping tokens between chunks for context. ## `tiktokenEncoding` (type: `string`): The tokenizer encoding to use. ## `useSitemap` (type: `boolean`): Disable this for faster quality tests. Discovers sitemap.xml before crawling. ## `includeGlobs` (type: `array`): Only crawl URLs matching these glob patterns. ## `excludeGlobs` (type: `array`): Skip URLs matching these glob patterns. ## `minTextLength` (type: `integer`): Discard pages with text shorter than this threshold. ## `maxRedirects` (type: `integer`): Maximum number of redirects to follow per request. ## `proxyConfiguration` (type: `object`): Proxy settings for anti-bot bypass. ## `fingerprintRotationInterval` (type: `integer`): Rotate browser fingerprints every N requests. ## `waitForSelector` (type: `string`): Optional CSS selector to wait for before extracting content. ## `customCodeBlockSelectors` (type: `array`): CSS selectors for non-standard code containers. ## `outputFormat` (type: `string`): Choose the output structure format. ## Actor input object example ```json { "startUrls": [ { "url": "https://example.com" } ], "maxCrawlDepth": 1, "maxRequestsPerCrawl": 10, "maxConcurrency": 5, "chunkSize": 512, "chunkOverlap": 50, "tiktokenEncoding": "o200k_base", "useSitemap": false, "includeGlobs": [], "excludeGlobs": [], "minTextLength": 150, "maxRedirects": 5, "proxyConfiguration": { "useApifyProxy": true }, "fingerprintRotationInterval": 15, "waitForSelector": "", "customCodeBlockSelectors": [], "outputFormat": "chunked" } ```` # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "startUrls": [ { "url": "https://example.com" } ], "proxyConfiguration": { "useApifyProxy": true } }; // Run the Actor and wait for it to finish const run = await client.actor("0xysn/rag-data-ingestion-website-to-ai-knowledge-base").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`πŸ’Ύ Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // πŸ“š Want to learn more πŸ“–? Go to β†’ https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "startUrls": [{ "url": "https://example.com" }], "proxyConfiguration": { "useApifyProxy": True }, } # Run the Actor and wait for it to finish run = client.actor("0xysn/rag-data-ingestion-website-to-ai-knowledge-base").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("πŸ’Ύ Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # πŸ“š Want to learn more πŸ“–? Go to β†’ https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "startUrls": [ { "url": "https://example.com" } ], "proxyConfiguration": { "useApifyProxy": true } }' | apify call 0xysn/rag-data-ingestion-website-to-ai-knowledge-base --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=0xysn/rag-data-ingestion-website-to-ai-knowledge-base", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "RAG Data Ingestion: Website to AI Knowledge Base", "description": "Master complex documentation with a premium scraper that flattens Shadow DOM and handles modern web components. Delivers clean, token-accurate Markdown pre-chunked for immediate RAG ingestion into Pinecone, Weaviate, or LangChain. Optimized for high-fidelity LLM training data.", "version": "1.0", "x-build-id": "i8Rvh64h6LwGGGB2g" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/0xysn~rag-data-ingestion-website-to-ai-knowledge-base/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-0xysn-rag-data-ingestion-website-to-ai-knowledge-base", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/0xysn~rag-data-ingestion-website-to-ai-knowledge-base/runs": { "post": { "operationId": "runs-sync-0xysn-rag-data-ingestion-website-to-ai-knowledge-base", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/0xysn~rag-data-ingestion-website-to-ai-knowledge-base/run-sync": { "post": { "operationId": "run-sync-0xysn-rag-data-ingestion-website-to-ai-knowledge-base", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "One or more URLs to begin crawling from.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxCrawlDepth": { "title": "Max Crawl Depth", "minimum": 0, "maximum": 50, "type": "integer", "description": "Maximum link-following depth. Set to 0 to only scrape start URLs.", "default": 1 }, "maxRequestsPerCrawl": { "title": "Max Pages Per Run", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Hard limit on total pages scraped in a single run.", "default": 10 }, "maxConcurrency": { "title": "Max Concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum parallel pages. 5-10 is recommended for 2GB memory.", "default": 5 }, "chunkSize": { "title": "Chunk Size (tokens)", "minimum": 64, "maximum": 8192, "type": "integer", "description": "Target number of tokens per content chunk.", "default": 512 }, "chunkOverlap": { "title": "Chunk Overlap (tokens)", "minimum": 0, "maximum": 512, "type": "integer", "description": "Overlapping tokens between chunks for context.", "default": 50 }, "tiktokenEncoding": { "title": "Tiktoken Encoding", "enum": [ "o200k_base", "cl100k_base" ], "type": "string", "description": "The tokenizer encoding to use.", "default": "o200k_base" }, "useSitemap": { "title": "Use Sitemap Discovery", "type": "boolean", "description": "Disable this for faster quality tests. Discovers sitemap.xml before crawling.", "default": false }, "includeGlobs": { "title": "Include URL Patterns", "type": "array", "description": "Only crawl URLs matching these glob patterns.", "default": [], "items": { "type": "object", "required": [ "glob" ], "properties": { "glob": { "type": "string", "title": "Glob of a web page" } } } }, "excludeGlobs": { "title": "Exclude URL Patterns", "type": "array", "description": "Skip URLs matching these glob patterns.", "default": [], "items": { "type": "object", "required": [ "glob" ], "properties": { "glob": { "type": "string", "title": "Glob of a web page" } } } }, "minTextLength": { "title": "Min Text Length (chars)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Discard pages with text shorter than this threshold.", "default": 150 }, "maxRedirects": { "title": "Max Redirects", "minimum": 0, "maximum": 20, "type": "integer", "description": "Maximum number of redirects to follow per request.", "default": 5 }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Proxy settings for anti-bot bypass." }, "fingerprintRotationInterval": { "title": "Fingerprint Rotation Interval", "minimum": 1, "maximum": 100, "type": "integer", "description": "Rotate browser fingerprints every N requests.", "default": 15 }, "waitForSelector": { "title": "Wait For Selector", "type": "string", "description": "Optional CSS selector to wait for before extracting content.", "default": "" }, "customCodeBlockSelectors": { "title": "Custom Code Block Selectors", "type": "array", "description": "CSS selectors for non-standard code containers.", "default": [], "items": { "type": "string" } }, "outputFormat": { "title": "Output Format", "enum": [ "chunked", "full" ], "type": "string", "description": "Choose the output structure format.", "default": "chunked" } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } } ```