{ "openapi": "3.0.1", "info": { "title": "Docs To Rag", "description": "Transform documentation websites into RAG-ready chunks with semantic understanding, quality scoring, and direct vector database integration.", "version": "2.0", "x-build-id": "7mca9TZUcwthQLO02" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/gabrielaxy~docs-to-rag/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-gabrielaxy-docs-to-rag", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/gabrielaxy~docs-to-rag/runs": { "post": { "operationId": "runs-sync-gabrielaxy-docs-to-rag", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/gabrielaxy~docs-to-rag/run-sync": { "post": { "operationId": "run-sync-gabrielaxy-docs-to-rag", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Documentation URLs", "type": "array", "description": "URLs of documentation sites to crawl", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxDepth": { "title": "Max Crawl Depth", "minimum": 0, "maximum": 50, "type": "integer", "description": "How many levels deep to crawl (0 = start page only)", "default": 10 }, "maxPages": { "title": "Max Pages", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of pages to crawl", "default": 1000 }, "includeGlobs": { "title": "Include Patterns", "type": "array", "description": "Only crawl URLs matching these glob patterns", "items": { "type": "string" } }, "excludeGlobs": { "title": "Exclude Patterns", "type": "array", "description": "Skip URLs matching these glob patterns", "items": { "type": "string" } }, "chunkSize": { "title": "Chunk Size (tokens)", "minimum": 100, "maximum": 2000, "type": "integer", "description": "Target size for each text chunk", "default": 500 }, "chunkOverlap": { "title": "Chunk Overlap (tokens)", "minimum": 0, "maximum": 500, "type": "integer", "description": "Overlap between consecutive chunks for context", "default": 50 }, "splitByHeaders": { "title": "Split by Headers", "type": "boolean", "description": "Create new chunks at H1/H2 headers", "default": true }, "includeCodeBlocks": { "title": "Include Code Blocks", "type": "boolean", "description": "Include code snippets in chunks", "default": true }, "chunkingStrategy": { "title": "Chunking Strategy", "enum": [ "simple", "semantic" ], "type": "string", "description": "Simple: token-based splitting. Semantic: preserves code blocks, paragraphs, lists, and document structure for better RAG retrieval.", "default": "semantic" }, "outputFormat": { "title": "Output Format", "enum": [ "json", "jsonl", "csv" ], "type": "string", "description": "Format for the output data", "default": "jsonl" }, "generateEmbeddings": { "title": "Generate Embeddings", "type": "boolean", "description": "Generate OpenAI embeddings for each chunk", "default": false }, "openaiApiKey": { "title": "OpenAI API Key", "type": "string", "description": "Your OpenAI API key for embeddings. Can also be set via OPENAI_API_KEY environment variable." }, "embeddingModel": { "title": "Embedding Model", "enum": [ "text-embedding-3-small", "text-embedding-3-large" ], "type": "string", "description": "OpenAI embedding model to use", "default": "text-embedding-3-small" }, "proxyConfig": { "title": "Proxy Configuration", "type": "object", "description": "Configure proxy to avoid IP blocking" }, "vectorDbProvider": { "title": "Vector Database", "enum": [ "none", "pinecone", "supabase", "qdrant" ], "type": "string", "description": "Select a vector database to push chunks directly after embedding generation", "default": "none" }, "vectorDbConfig": { "title": "Vector DB Configuration", "type": "object", "description": "Provider config (optional if using env vars). Pinecone: {indexName}. Supabase: {tableName}. Qdrant: {collectionName}. API keys can be set via environment variables." }, "vectorDbNamespace": { "title": "Namespace/Collection", "type": "string", "description": "Namespace (Pinecone) or collection name. Can also use VECTOR_DB_NAMESPACE env var." }, "upsertBatchSize": { "title": "Upsert Batch Size", "minimum": 10, "maximum": 1000, "type": "integer", "description": "Number of vectors to upsert in each batch", "default": 100 }, "enableQualityScoring": { "title": "Enable Quality Scoring", "type": "boolean", "description": "Enable quality scoring to filter low-value chunks", "default": true }, "minQualityScore": { "title": "Minimum Quality Score", "minimum": 0, "maximum": 100, "type": "integer", "description": "Chunks below this score will be filtered out (0-100)", "default": 40 }, "includeQualityInMetadata": { "title": "Include Quality in Metadata", "type": "boolean", "description": "Add quality scores to chunk metadata for retrieval optimization", "default": true }, "enrichMetadata": { "title": "Enrich Metadata", "type": "boolean", "description": "Add content type, topics, complexity, and relationship metadata", "default": true } } }, "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 } } } } } } } } } }