{ "openapi": "3.0.1", "info": { "title": "42 Polars AI Data Transformer", "description": "Transform datasets using natural language. Upload CSV/Excel/JSON, describe your transformation in plain English, get results + reusable Python code. Powered by AI.", "version": "0.2", "x-build-id": "o3VKG4uzTtrR6Lw2Z" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/salesmart-srl~polars-ai-data-transformer/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-salesmart-srl-polars-ai-data-transformer", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/salesmart-srl~polars-ai-data-transformer/runs": { "post": { "operationId": "runs-sync-salesmart-srl-polars-ai-data-transformer", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/salesmart-srl~polars-ai-data-transformer/run-sync": { "post": { "operationId": "run-sync-salesmart-srl-polars-ai-data-transformer", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "prompt" ], "properties": { "datasetUrls": { "title": "📁 Dataset URLs", "type": "array", "description": "URLs to your data files (CSV, JSON, Excel, Parquet). Add multiple URLs to merge files together.", "items": { "type": "string" } }, "uploadedFiles": { "title": "📤 Upload Files", "type": "array", "description": "Or upload files directly (CSV, JSON, Excel, Parquet). Max 50MB per file." }, "apifyDatasetId": { "title": "📊 Apify Dataset ID", "type": "string", "description": "Or use an existing Apify dataset from another Actor run" }, "datasetId": { "title": "📊 Dataset ID (API/Integration)", "type": "string", "description": "Apify Dataset ID to transform. Simple alternative for API calls and integrations. Example: 'abc123def456'" }, "resource": { "title": "🔗 Webhook Payload", "type": "object", "description": "Auto-populated when triggered via webhook/integration from another Actor. Contains defaultDatasetId from the previous run. Leave empty - filled automatically by Apify." }, "inputData": { "title": "📋 Direct JSON Data", "type": "object", "description": "Pass data directly as JSON (no file upload needed).\n\n**Single table:** {\"data\": [{\"name\": \"A\", \"price\": 100}]}\n\n**Multi-table JOIN:** {\"contacts\": [{...}], \"companies\": [{...}]}\n\nMax ~9MB. Response includes full output_data if < 10MB." }, "prompt": { "title": "💬 Transformation Prompt", "type": "string", "description": "Describe your transformation in plain English. Be specific about column names, aggregations, filters, and sorting." }, "useAdvancedFeatures": { "title": "💎 Use Advanced Features", "type": "boolean", "description": "Enable Premium tier: Gemini 2.5 Pro + Google Search grounding + RAG memory. Works with hosted ($0.20) or BYOK Google API (same features, you pay Google directly). Basic tier uses Flash-Lite ($0.0015 hosted).", "default": false }, "llmProvider": { "title": "🤖 AI Provider (BYOK)", "enum": [ "groq", "anthropic", "openai", "google" ], "type": "string", "description": "Select AI provider for BYOK (Bring Your Own Key). Leave API key blank to use hosted tier instead. BYOK = $0.05 Apify fee + your API costs.", "default": "google" }, "groqApiKey": { "title": "🔑 Groq API Key (FREE)", "type": "string", "description": "Get your FREE API key at console.groq.com (takes 30 seconds). BYOK = $0.05 Apify fee + free Groq API." }, "anthropicApiKey": { "title": "🔑 Anthropic API Key", "type": "string", "description": "Required if using Claude. Get your key at console.anthropic.com. BYOK = $0.05 Apify fee + Claude API costs." }, "openaiApiKey": { "title": "🔑 OpenAI API Key", "type": "string", "description": "Required if using GPT-4o. Get your key at platform.openai.com. BYOK = $0.05 Apify fee + OpenAI API costs." }, "googleApiKey": { "title": "🔑 Google AI API Key", "type": "string", "description": "Get your key at aistudio.google.com. BYOK = $0.05 Apify fee + Google API costs (~$1.25/1M tokens). Enable 'Advanced Features' above for grounding (~$35/1K searches)." }, "outputFormat": { "title": "📄 Output Format", "enum": [ "csv", "json", "parquet", "xlsx" ], "type": "string", "description": "Choose the format for your transformed data", "default": "csv" }, "includeGeneratedCode": { "title": "📝 Include Generated Code", "type": "boolean", "description": "Include the generated Python/Polars code in output for reuse in your own projects", "default": true }, "fallbackProvider": { "title": "🔄 Fallback AI Model", "enum": [ "", "groq", "anthropic", "openai", "google" ], "type": "string", "description": "If primary model fails, try this one (requires corresponding API key)" }, "maxRetries": { "title": "🔄 Max Retries", "minimum": 1, "maximum": 5, "type": "integer", "description": "Number of attempts if code generation fails", "default": 3 }, "enableStreaming": { "title": "🌊 Enable Streaming", "type": "boolean", "description": "Process large files in chunks. Auto-enabled for files > 100MB.", "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 } } } } } } } } } }