{ "openapi": "3.0.1", "info": { "title": "Rag Embedding Generator", "description": "Generate vector embeddings from text or chunked datasets using OpenAI or Cohere. Chains with RAG Content Chunker for end-to-end RAG pipelines. Outputs raw vectors ready for any vector database.", "version": "0.0", "x-build-id": "3cbxH6IEbEP3kI1aT" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/labrat011~rag-embedding-generator/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-labrat011-rag-embedding-generator", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/labrat011~rag-embedding-generator/runs": { "post": { "operationId": "runs-sync-labrat011-rag-embedding-generator", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/labrat011~rag-embedding-generator/run-sync": { "post": { "operationId": "run-sync-labrat011-rag-embedding-generator", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "api_key": { "title": "API Key", "type": "string", "description": "Your embedding provider API key (OpenAI or Cohere). Never logged or stored beyond this run." }, "provider": { "title": "Embedding Provider", "enum": [ "openai", "cohere" ], "type": "string", "description": "Which embedding provider to use.", "default": "openai" }, "model": { "title": "Embedding Model", "type": "string", "description": "Which embedding model to use. OpenAI: 'text-embedding-3-small' (1536 dims, cheapest), 'text-embedding-3-large' (3072 dims, best quality), 'text-embedding-ada-002' (1536 dims, legacy). Cohere: 'embed-english-v3.0' (1024 dims), 'embed-multilingual-v3.0' (1024 dims), 'embed-english-light-v3.0' (384 dims), 'embed-multilingual-light-v3.0' (384 dims).", "default": "text-embedding-3-small" }, "text": { "title": "Text to Embed", "type": "string", "description": "A single text string to embed. For bulk processing, use dataset_id instead." }, "texts": { "title": "Texts to Embed", "type": "array", "description": "A list of text strings to embed. For bulk processing from another actor, use dataset_id instead." }, "dataset_id": { "title": "Apify Dataset ID", "type": "string", "description": "ID of an existing Apify dataset (e.g., output from RAG Content Chunker or Website Content Crawler). Each item's text field will be embedded. Takes priority over text/texts inputs." }, "dataset_field": { "title": "Dataset Text Field", "type": "string", "description": "Which field to read from each dataset item. Default: 'text'. Supports dot notation for nested fields (e.g., 'metadata.content').", "default": "text" }, "batch_size": { "title": "Batch Size", "minimum": 1, "maximum": 2048, "type": "integer", "description": "Number of texts to send per API request. Higher values are faster but use more memory. OpenAI supports up to 2048. Cohere supports up to 96.", "default": 128 }, "include_text": { "title": "Include Source Text in Output", "type": "boolean", "description": "Whether to include the original text in each output item alongside the embedding vector. Useful for debugging but increases output size.", "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 } } } } } } } } } }