{ "openapi": "3.0.1", "info": { "title": "AI Dataset Enricher - Bulk LLM Classify, Tag & Summarise", "description": "Run one AI prompt over every row of an Apify dataset, CSV/Excel/JSON file or pasted rows: classify, tag, score sentiment, summarise, translate or extract into typed fields you define. Cheap LLM via Apify's OpenRouter, billed at cost to your account. $0.70 per 1,000 rows plus tokens.", "version": "0.1", "x-build-id": "W4d4ZtRGXUZ0NEHA9" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/actor-forge~ai-dataset-enricher/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-actor-forge-ai-dataset-enricher", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/actor-forge~ai-dataset-enricher/runs": { "post": { "operationId": "runs-sync-actor-forge-ai-dataset-enricher", "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/actor-forge~ai-dataset-enricher/run-sync": { "post": { "operationId": "run-sync-actor-forge-ai-dataset-enricher", "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": { "rows": { "title": "Rows (JSON)", "type": "array", "description": "Rows pasted as a JSON array of objects. You can also (or instead) pick a dataset or give a file URL below." }, "datasetId": { "title": "Dataset", "type": "string", "description": "An Apify dataset to enrich, e.g. the output of a reviews, jobs or leads scraper. Picking it here gives this run read access to it." }, "fileUrl": { "title": "File URL (CSV, JSON, Excel)", "type": "string", "description": "A public CSV/TSV, JSON, JSON Lines or XLSX file (first row = column names, up to 50 MB)." }, "prompt": { "title": "What should the AI do with each row?", "type": "string", "description": "Plain-English instruction applied to every row, e.g. \"Classify the review's sentiment and main topic\", \"Write a 20-word summary\", \"Translate the title to English\", \"Extract the company name and job seniority\" or \"Is this lead a B2B SaaS company? Answer true/false with a reason\"." }, "outputSchema": { "title": "Output fields", "type": "object", "description": "The fields to add, as {\"field\": \"description or type\"} (types number, integer, boolean and array are converted), or a full JSON Schema (also sent as a structured-output schema). Empty: the model returns any JSON object." }, "inputFields": { "title": "Fields sent to the model", "type": "array", "description": "Only send these fields of each row (dot paths allowed), to save tokens and keep private columns out of the prompt. Empty: the whole row.", "items": { "type": "string" } }, "outputMode": { "title": "Output", "enum": [ "merge", "enrichedOnly" ], "type": "string", "description": "Merge: the original row plus the new fields. Enriched only: just the new fields and _rowIndex.", "default": "merge" }, "outputPrefix": { "title": "Prefix for new fields", "type": "string", "description": "Optional prefix such as ai_ so new fields never overwrite existing columns.", "default": "" }, "model": { "title": "AI model", "type": "string", "description": "Any OpenRouter model id (openrouter.ai/models), e.g. google/gemini-2.5-flash-lite (default: cheap and fast), openai/gpt-5-nano, openai/gpt-4o-mini or google/gemini-2.5-flash (smarter). Tokens are billed to your Apify account at OpenRouter rates.", "default": "google/gemini-2.5-flash-lite" }, "maxLlmCostUsd": { "title": "Max AI token cost per run (USD)", "minimum": 0, "maximum": 100, "type": "number", "description": "Hard cap on the AI token charges this run may cause on your Apify account (estimated, including the 10× free-plan rate when it applies). The worst case of each row (its prompt plus maxOutputTokens) is reserved before the call; the run stops cleanly when the next row would pass the cap. Separate from this actor's per-row fee, which the run's maximum total charge limits.", "default": 0.1 }, "maxRows": { "title": "Max rows", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Process at most this many rows.", "default": 1000 }, "maxInputTokensPerRow": { "title": "Max input tokens per row", "minimum": 100, "maximum": 50000, "type": "integer", "description": "Rows larger than this (≈3 characters per token) are skipped with a free row; select fewer fields to fit.", "default": 2000 }, "maxOutputTokens": { "title": "Max output tokens per row", "minimum": 20, "maximum": 16000, "type": "integer", "description": "max_tokens for each reply. A few labels need ~50; a summary ~150; long extractions more.", "default": 400 }, "estimateOnly": { "title": "Estimate cost only", "type": "boolean", "description": "Read the rows and report the expected AI token cost and this actor's fee without calling the model (one free row).", "default": false }, "allowPersonalData": { "title": "Allow personal contact data", "type": "boolean", "description": "Off (default): the model is told not to output private individuals' personal contact details and personal-looking email addresses in its output are replaced. Switch on only if you have a lawful basis.", "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }