{ "openapi": "3.0.1", "info": { "title": "Dataset Enrich — structure any dataset with your own LLM key", "description": "Structure and enrich any dataset with YOUR OWN LLM key (OpenAI, Anthropic or OpenRouter). Define a target JSON schema and an instruction; every item is transformed to match, with JSON repair, retries and per-item error isolation. You control model choice and token cost.", "version": "0.1", "x-build-id": "lpXTM9JCLeMfIl9kW" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/multiplex~dataset-enrich/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-multiplex-dataset-enrich", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/multiplex~dataset-enrich/runs": { "post": { "operationId": "runs-sync-multiplex-dataset-enrich", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/multiplex~dataset-enrich/run-sync": { "post": { "operationId": "run-sync-multiplex-dataset-enrich", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "instruction", "outputSchema", "provider", "apiKey", "model" ], "properties": { "datasetId": { "title": "Source dataset ID", "type": "string", "description": "The Apify dataset to read, e.g. the default dataset of another actor's run. Leave empty and paste rows into `items` instead. Give one or the other, not both." }, "items": { "title": "Items (JSON array)", "type": "array", "description": "Rows to enrich, as a JSON array of objects. Used only when `datasetId` is empty. Handy for a trial run before you point this at a full dataset." }, "instruction": { "title": "Instruction", "type": "string", "description": "What the model should do with each row, in plain English. Be specific about how to derive each field and what to do when a value is missing." }, "outputSchema": { "title": "Target output schema (JSON Schema)", "type": "object", "description": "A JSON Schema describing ONE output row. Every enriched row is produced against it, and its properties become the dataset's columns. Keep it flat and typed for the cleanest CSV/Excel export." }, "provider": { "title": "LLM provider", "enum": [ "openai", "anthropic", "openrouter" ], "type": "string", "description": "Whose API to call. The key you supply below is sent only to this provider, over HTTPS, and is never written to the dataset, the logs or the key-value store.", "default": "openai" }, "apiKey": { "title": "API key", "type": "string", "description": "Your own API key for the provider above. Stored encrypted by Apify, held in memory only during the run, and never logged or pushed to any storage. Use a key scoped to this job and rotate it as you would any other." }, "model": { "title": "Model", "type": "string", "description": "The model id exactly as your provider spells it — e.g. `gpt-4o-mini` (OpenAI), `claude-3-5-haiku-latest` (Anthropic), `openai/gpt-4o-mini` (OpenRouter). Model ids change; check your provider's own model list. A small, cheap model is usually plenty for structuring." }, "batchSize": { "title": "Items per request", "minimum": 1, "maximum": 25, "type": "integer", "description": "How many rows to send in one model call. Larger batches cost fewer tokens overall but risk hitting the model's output limit, which shows up as repaired or failed rows. 1-5 is the safe range.", "default": 1 }, "concurrency": { "title": "Concurrent requests", "minimum": 1, "maximum": 5, "type": "integer", "description": "How many model calls to run at once. Capped at 5. Lower it if your provider returns 429s (the actor already backs off and honours Retry-After).", "default": 2 }, "maxItems": { "title": "Max items", "minimum": 0, "type": "integer", "description": "Stop after this many source rows. 0 = every row. Set it to 10 for a cheap trial run before committing your key to a full dataset.", "default": 0 }, "includeSourceItem": { "title": "Include the original item", "type": "boolean", "description": "Keep the untouched source row under `_source` on every output row. Off by default so the dataset stays narrow and exports cleanly.", "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 } } } } } } } } } }