{ "openapi": "3.0.1", "info": { "title": "Rag Vector Store Writer", "description": "Apify Actor that writes embedding vectors to Pinecone or Qdrant vector databases. Chains directly with RAG Embedding Generator output or accepts raw vectors with metadata. Handles batching, retries, collection creation, metadata mapping, and ID generation. Bring your own vector DB API key.", "version": "0.0", "x-build-id": "9Rry7wqnjSHPjo0gS" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/labrat011~rag-vector-store-writer/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-labrat011-rag-vector-store-writer", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/labrat011~rag-vector-store-writer/runs": { "post": { "operationId": "runs-sync-labrat011-rag-vector-store-writer", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/labrat011~rag-vector-store-writer/run-sync": { "post": { "operationId": "run-sync-labrat011-rag-vector-store-writer", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Vector DB API Key", "type": "string", "description": "Your Pinecone or Qdrant API key. Never logged or stored beyond this run." }, "provider": { "title": "Vector Database Provider", "enum": [ "pinecone", "qdrant" ], "type": "string", "description": "Which vector database to write to.", "default": "pinecone" }, "index_name": { "title": "Index / Collection Name", "type": "string", "description": "Pinecone: the index name (used to resolve the host). Qdrant: the collection name. Will be auto-created for Qdrant if it doesn't exist." }, "environment": { "title": "Qdrant Cluster URL", "type": "string", "description": "Qdrant Cloud only: your full cluster URL (e.g., 'https://xyz-example.us-east-1.aws.cloud.qdrant.io:6333'). Not needed for Pinecone." }, "namespace": { "title": "Namespace (Pinecone only)", "type": "string", "description": "Pinecone namespace to write vectors into. Leave empty for the default namespace. Ignored for Qdrant.", "default": "" }, "distance_metric": { "title": "Distance Metric (Qdrant only)", "enum": [ "Cosine", "Dot", "Euclid" ], "type": "string", "description": "Distance metric for Qdrant collection creation. Only used when auto-creating a new collection. Ignored for Pinecone.", "default": "Cosine" }, "dataset_id": { "title": "Apify Dataset ID (from Embedding Generator)", "type": "string", "description": "ID of an Apify dataset containing embedding vectors (e.g., output from RAG Embedding Generator). Each item should have an 'embedding' field. Takes priority over 'vectors' input." }, "vectors": { "title": "Raw Vectors (JSON)", "type": "array", "description": "Direct vector input as a JSON array. Each item: {\"id\": \"optional-id\", \"embedding\": [0.1, ...], \"metadata\": {\"key\": \"value\"}}. Use dataset_id for chaining with Embedding Generator instead." }, "batch_size": { "title": "Batch Size", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Number of vectors to upsert per API request. Pinecone max: 1000 (recommended: 100-200 for 1536d vectors). Qdrant: no hard limit (recommended: 100).", "default": 100 }, "id_field": { "title": "ID Field", "type": "string", "description": "Which field from dataset items to use as the vector ID. Default: 'chunk_id' (from RAG Content Chunker). Falls back to UUID generation if the field is missing.", "default": "chunk_id" } } }, "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 } } } } } } } } } }