# Ecommerce RAG Ingestion Engine (`blukaze/ecommerce-rag-ingestion-engine`) Actor Stop feeding your LLMs noisy HTML and irrelevant UI clutter. The Ecommerce RAG Ingestion Engine is a production-ready Apify Actor designed to transform entire ecommerce domains with a specialized focus on Shopify into clean, AI-ready knowledge bases. - **URL**: https://apify.com/blukaze/ecommerce-rag-ingestion-engine.md - **Developed by:** [Blukaze Automations](https://apify.com/blukaze) (community) - **Categories:** AI, E-commerce, Agents - **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, NaN bookmarks - **User rating**: No ratings yet ## Pricing from $3.00 / 1,000 results 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 ## Ecommerce Store Knowledgebase Scraper An advanced, production-ready Apify Actor designed to scrape ecommerce websites (with a strong focus on Shopify) to extract both **structured product catalogs** and **AI-ready RAG chunks**. This actor is purpose-built for AI teams, agencies, and ecommerce brands that need to ingest a domain’s content into LLM support bots, semantic search pipelines, merchandising copilots, or internal vector databases. ### Why use this over a generic crawler? * **Ecommerce-Aware**: It automatically identifies and classifies URLs into Product, Collection, Policy, FAQ, and Blog page types. * **Shopify Optimized**: Employs specific logic to dig into native Shopify payload structures (e.g. `product.json` payloads, variant variables) enabling reliable, resilient extractions compared to CSS selectors. * **LLM & RAG Native**: It doesn't just dump HTML. It cleans pages, stripping headers, footers, and noise, and intelligently chunks the main text content via Markdown boundary detection, estimating token sizes automatically. * **Configurable Outputs**: Choose to output catalog data, knowledge chunks, or both depending on your pipeline requirements. ### Ideal Use Cases - **AI Support Bots**: Train OpenAI, Anthropic, or dialogue systems on the exact latest return policies, shipping times, and FAQs directly from the source. - **Semantic Product Search**: Ingest `products` datasets into Pinecone, Weaviate, or Qdrant to enable rich natural language querying over catalogs. - **Knowledge Ingestion Pipelines**: Integrate directly with Make, n8n, or Langchain to automatically synchronize website knowledge to your enterprise RAG stack. ### Output Modes The actor allows you to selectively choose what output formats you desire via `outputMode` using the `includeSections` controls: #### 1. Catalog Only Extracts clean, normalized product data pushed to the `products` dataset. ```json { "url": "https://example.com/products/cool-shirt", "title": "Cool Graphic T-Shirt", "price": 29.99, "currency": "USD", "availability": "in_stock", "brand": "Example Brand", "variants": [ {"title": "Small", "price": 29.99, "sku": "SHIRT-S"}, {"title": "Large", "price": 29.99, "sku": "SHIRT-L"} ] } ```` #### 2. Knowledge Only (RAG Chunks) Pushes clean text chunks properly bounded and estimated for tokens into the `knowledge_chunks` dataset. ```json { "url": "https://example.com/policies/shipping-policy", "title": "Shipping Policy - International Shipping", "section_type": "policy_section", "source_kind": "policy", "text": "We offer international shipping to over 100 countries. Standard international shipping takes 10-15 business days...", "token_estimate": 45 } ``` ### Input Configuration | Field | Type | Description | |---|---|---| | `startUrls` | Array | URLs or Sitemaps to begin crawling. | | `includeSections` | Array | Types of pages to process (`products`, `policies`, `faq`, etc.) | | `outputMode` | String | `catalog_only`, `knowledge_only`, or `both`. | | `maxPages` | Integer | Hard limit of pages to traverse (cost control). | | `chunkSizeTokens` | Integer | Target maximum token size for RAG chunks. | ### Limitations - **Render Heavy Sites**: Currently operates on a high-speed `CheerioCrawler`. Highly complex SPAs without Server-Side Rendering (SSR) might have some data hidden. Shopify and most modern ecommerce platforms provide SSR or JSON-LD which this actor consumes natively. - **Paywalls/Logins**: Does not support bypassing logins or captchas outside of Apify's standard proxy rotation parameters. # Actor input Schema ## `startUrls` (type: `array`): List of ecommerce store URLs or sitemaps to start crawling from. ## `includeSections` (type: `array`): Which types of pages should be extracted and chunked? (e.g. products, collections, faq, policies, reviews\_qna, blog, general\_pages) ## `maxPages` (type: `integer`): Maximum number of pages the crawler will visit. ## `maxProducts` (type: `integer`): Limit the number of products extracted. Leave empty for no limit. ## `maxDepth` (type: `integer`): How deep to follow links from the start URL. (0 means only start URLs). ## `chunkSizeTokens` (type: `integer`): The approximate maximum number of tokens per RAG chunk. ## `outputMode` (type: `string`): What data should the actor output? ## `respectRobotsTxt` (type: `boolean`): If enabled, crawler will not visit pages blocked by robots.txt. ## `proxyConfiguration` (type: `object`): Select proxies to be used. ## `debugMode` (type: `boolean`): Enable verbose logging for troubleshooting. ## Actor input object example ```json { "startUrls": [ { "url": "https://vault-demo-store.myshopify.com/" } ], "includeSections": [ "products", "collections", "faq", "policies" ], "maxPages": 500, "maxProducts": 100, "maxDepth": 10, "chunkSizeTokens": 500, "outputMode": "both", "respectRobotsTxt": false, "proxyConfiguration": { "useApifyProxy": true }, "debugMode": false } ``` # Actor output Schema ## `dataset` (type: `string`): The master dataset containing both product JSON catalog entries and formatted Markdown RAG chunks. # 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://vault-demo-store.myshopify.com/" } ], "includeSections": [ "products", "collections", "faq", "policies" ], "maxPages": 500, "maxProducts": 100, "maxDepth": 10, "chunkSizeTokens": 500, "outputMode": "both", "respectRobotsTxt": false, "proxyConfiguration": { "useApifyProxy": true }, "debugMode": false }; // Run the Actor and wait for it to finish const run = await client.actor("blukaze/ecommerce-rag-ingestion-engine").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://vault-demo-store.myshopify.com/" }], "includeSections": [ "products", "collections", "faq", "policies", ], "maxPages": 500, "maxProducts": 100, "maxDepth": 10, "chunkSizeTokens": 500, "outputMode": "both", "respectRobotsTxt": False, "proxyConfiguration": { "useApifyProxy": True }, "debugMode": False, } # Run the Actor and wait for it to finish run = client.actor("blukaze/ecommerce-rag-ingestion-engine").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://vault-demo-store.myshopify.com/" } ], "includeSections": [ "products", "collections", "faq", "policies" ], "maxPages": 500, "maxProducts": 100, "maxDepth": 10, "chunkSizeTokens": 500, "outputMode": "both", "respectRobotsTxt": false, "proxyConfiguration": { "useApifyProxy": true }, "debugMode": false }' | apify call blukaze/ecommerce-rag-ingestion-engine --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=blukaze/ecommerce-rag-ingestion-engine", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "Ecommerce RAG Ingestion Engine", "description": "Stop feeding your LLMs noisy HTML and irrelevant UI clutter. The Ecommerce RAG Ingestion Engine is a production-ready Apify Actor designed to transform entire ecommerce domains with a specialized focus on Shopify into clean, AI-ready knowledge bases.", "version": "0.0", "x-build-id": "tVp2HozlO2i8OpFT7" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/blukaze~ecommerce-rag-ingestion-engine/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-blukaze-ecommerce-rag-ingestion-engine", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/blukaze~ecommerce-rag-ingestion-engine/runs": { "post": { "operationId": "runs-sync-blukaze-ecommerce-rag-ingestion-engine", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/blukaze~ecommerce-rag-ingestion-engine/run-sync": { "post": { "operationId": "run-sync-blukaze-ecommerce-rag-ingestion-engine", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "outputMode" ], "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "List of ecommerce store URLs or sitemaps to start crawling from.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "includeSections": { "title": "Sections to Include", "type": "array", "description": "Which types of pages should be extracted and chunked? (e.g. products, collections, faq, policies, reviews_qna, blog, general_pages)", "default": [ "products", "collections", "faq", "policies" ], "items": { "type": "string" } }, "maxPages": { "title": "Max Pages to Crawl", "type": "integer", "description": "Maximum number of pages the crawler will visit.", "default": 1000 }, "maxProducts": { "title": "Max Products to Extract", "type": "integer", "description": "Limit the number of products extracted. Leave empty for no limit." }, "maxDepth": { "title": "Max Crawl Depth", "type": "integer", "description": "How deep to follow links from the start URL. (0 means only start URLs).", "default": 10 }, "chunkSizeTokens": { "title": "Target Chunk Size (Tokens)", "type": "integer", "description": "The approximate maximum number of tokens per RAG chunk.", "default": 500 }, "outputMode": { "title": "Output Mode", "enum": [ "catalog_only", "knowledge_only", "both" ], "type": "string", "description": "What data should the actor output?", "default": "both" }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "If enabled, crawler will not visit pages blocked by robots.txt.", "default": false }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Select proxies to be used.", "default": { "useApifyProxy": true } }, "debugMode": { "title": "Debug Mode", "type": "boolean", "description": "Enable verbose logging for troubleshooting.", "default": false } } }, "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 } } } } } } } } } } ```