{ "openapi": "3.0.1", "info": { "title": "Pinecone All-in-One Integration", "description": "Crawl websites, store datasets, run semantic searches, delete vectors, and check index stats — all in one actor. Uses Pinecone Integrated Inference by default — no OpenAI key needed. Bring your own Pinecone API key and start in minutes.", "version": "1.0", "x-build-id": "bopn1XRJA3jNtnta9" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/brilliant_gum~pinecone-integration/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-brilliant_gum-pinecone-integration", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/brilliant_gum~pinecone-integration/runs": { "post": { "operationId": "runs-sync-brilliant_gum-pinecone-integration", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/brilliant_gum~pinecone-integration/run-sync": { "post": { "operationId": "run-sync-brilliant_gum-pinecone-integration", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "mode", "pineconeApiKey", "pineconeIndexName" ], "properties": { "mode": { "title": "Mode", "enum": [ "crawl-and-store", "store-dataset", "query", "delete", "index-stats" ], "type": "string", "description": "Operation mode: crawl-and-store (crawl URLs and store in Pinecone), store-dataset (store Apify dataset), query (semantic search), delete (remove vectors), index-stats (index info).", "default": "crawl-and-store" }, "pineconeApiKey": { "title": "Pinecone API Key", "type": "string", "description": "Your Pinecone API key. Get it from https://app.pinecone.io/" }, "pineconeIndexName": { "title": "Pinecone Index Name", "type": "string", "description": "Name of the Pinecone index to use. Will be auto-created if it doesn't exist (when autoCreateIndex is enabled)." }, "pineconeNamespace": { "title": "Namespace", "type": "string", "description": "Pinecone namespace to target. Leave empty for the default namespace.", "default": "" }, "startUrls": { "title": "Start URLs", "type": "array", "description": "URLs to start crawling from. Supports direct URLs or request list sources.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "sitemapUrl": { "title": "Sitemap URL", "type": "string", "description": "URL to an XML sitemap. All URLs from the sitemap will be crawled." }, "maxPages": { "title": "Max Pages", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Maximum number of pages to crawl.", "default": 100 }, "maxDepth": { "title": "Max Crawl Depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "Maximum link depth to follow from start URLs. 0 = only start URLs.", "default": 3 }, "contentSelector": { "title": "Content CSS Selector", "type": "string", "description": "CSS selectors for the main content area. Multiple selectors separated by commas. The first match is used.", "default": "main, article, .content, .post, #content" }, "excludeSelectors": { "title": "Exclude CSS Selectors", "type": "array", "description": "CSS selectors for elements to remove before extracting content.", "default": [ "nav", "footer", "header", "aside", ".sidebar", ".menu", ".cookie", "script", "style", "noscript" ], "items": { "type": "string" } }, "renderJavaScript": { "title": "Render JavaScript", "type": "boolean", "description": "Use a headless browser to render JavaScript. Needed for SPAs and dynamic content.", "default": true }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Proxy settings for crawling.", "default": { "useApifyProxy": true } }, "datasetId": { "title": "Dataset ID", "type": "string", "description": "Apify dataset ID or name to load data from." }, "datasetFields": { "title": "Text Fields", "type": "array", "description": "Dataset fields to extract text from. Content from all specified fields is concatenated.", "default": [ "text" ], "items": { "type": "string" } }, "metadataFields": { "title": "Metadata Field Mapping", "type": "object", "description": "Map of dataset field names to Pinecone metadata keys. Example: {\"pageUrl\": \"url\", \"pageTitle\": \"title\"}", "default": {} }, "embeddingProvider": { "title": "Embedding Provider", "enum": [ "pinecone", "openai", "cohere" ], "type": "string", "description": "Which embedding provider to use. 'pinecone' uses Pinecone Integrated Inference (no extra API key needed!). 'openai' and 'cohere' require their respective API keys.", "default": "pinecone" }, "embeddingModel": { "title": "Embedding Model", "type": "string", "description": "Embedding model name. Leave empty for auto-selection: Pinecone → multilingual-e5-large, OpenAI → text-embedding-3-small, Cohere → embed-english-v3.0", "default": "" }, "embeddingsApiKey": { "title": "Embeddings API Key", "type": "string", "description": "API key for OpenAI or Cohere. Not needed when using Pinecone Integrated Inference." }, "pineconeCloud": { "title": "Cloud Provider", "enum": [ "aws", "gcp", "azure" ], "type": "string", "description": "Cloud provider for index creation (only used when auto-creating a new index).", "default": "aws" }, "pineconeRegion": { "title": "Cloud Region", "type": "string", "description": "Cloud region for index creation (only used when auto-creating a new index).", "default": "us-east-1" }, "autoCreateIndex": { "title": "Auto-Create Index", "type": "boolean", "description": "Automatically create the Pinecone index if it doesn't exist.", "default": true }, "chunkSize": { "title": "Chunk Size (chars)", "minimum": 200, "maximum": 10000, "type": "integer", "description": "Maximum number of characters per text chunk.", "default": 2000 }, "chunkOverlap": { "title": "Chunk Overlap (chars)", "minimum": 0, "maximum": 2000, "type": "integer", "description": "Number of overlapping characters between consecutive chunks.", "default": 200 }, "prependContext": { "title": "Prepend Source Context", "type": "boolean", "description": "Prepend the page title and URL to each chunk for better search relevance.", "default": true }, "queryText": { "title": "Search Query", "type": "string", "description": "The text to search for in your Pinecone index." }, "topK": { "title": "Number of Results", "minimum": 1, "maximum": 100, "type": "integer", "description": "How many results to return.", "default": 10 }, "metadataFilter": { "title": "Metadata Filter", "type": "object", "description": "Pinecone metadata filter in JSON format. Example: {\"url\": {\"$eq\": \"https://example.com\"}}" }, "includeMetadata": { "title": "Include Metadata", "type": "boolean", "description": "Include metadata in query results.", "default": true }, "rerankModel": { "title": "Rerank Model", "enum": [ "none", "bge-reranker-v2-m3", "pinecone-rerank-v0" ], "type": "string", "description": "Optional reranking model to improve result relevance.", "default": "none" }, "rerankTopN": { "title": "Results After Reranking", "minimum": 1, "maximum": 50, "type": "integer", "description": "Number of results to return after reranking.", "default": 5 }, "deleteMode": { "title": "Delete Mode", "enum": [ "by-ids", "by-filter", "all-namespace" ], "type": "string", "description": "How to select vectors for deletion." }, "deleteIds": { "title": "Vector IDs to Delete", "type": "array", "description": "List of vector IDs to delete.", "items": { "type": "string" } }, "deleteFilter": { "title": "Delete Filter", "type": "object", "description": "Metadata filter for deletion in JSON format. Example: {\"url\": {\"$eq\": \"https://example.com\"}}" } } }, "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 } } } } } } } } } }