{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Corpus Audit & RAG Readiness", "description": "Extract public YouTube captions, audit transcript coverage, score RAG readiness, and create timestamped supporting chunks without double charging report mode.", "version": "0.1", "x-build-id": "w22dHb35dy4pd0eUQ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/taroyamada~youtube-channel-transcript-rag-intelligence/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-taroyamada-youtube-channel-transcript-rag-intelligence", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/taroyamada~youtube-channel-transcript-rag-intelligence/runs": { "post": { "operationId": "runs-sync-taroyamada-youtube-channel-transcript-rag-intelligence", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/taroyamada~youtube-channel-transcript-rag-intelligence/run-sync": { "post": { "operationId": "run-sync-taroyamada-youtube-channel-transcript-rag-intelligence", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "videoUrls": { "title": "Video URLs", "type": "array", "description": "YouTube watch, Shorts, embed, live, or youtu.be URLs.", "default": [ "https://www.youtube.com/watch?v=dQw4w9WgXcQ" ], "items": { "type": "string" } }, "videoIds": { "title": "Video IDs", "type": "array", "description": "Direct 11-character YouTube video IDs.", "default": [], "items": { "type": "string" } }, "channelUrls": { "title": "Channel URLs or @handles", "type": "array", "description": "YouTube channel URLs or bare @handles. The actor expands public channel pages into visible video IDs.", "default": [], "items": { "type": "string" } }, "playlistUrls": { "title": "Playlist URLs", "type": "array", "description": "Optional public playlist URLs to expand into visible video IDs.", "default": [], "items": { "type": "string" } }, "language": { "title": "Preferred Caption Language", "type": "string", "description": "Preferred caption language code such as en, ja, or es.", "default": "en" }, "includeAutoGenerated": { "title": "Include Auto-generated Captions", "type": "boolean", "description": "Allow YouTube auto-generated captions when manual captions are unavailable.", "default": true }, "translationLanguage": { "title": "Translation Language", "type": "string", "description": "Optional YouTube transcript translation target language code.", "default": "" }, "maxVideos": { "title": "Max Videos", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum videos to process in one run.", "default": 5 }, "chunkSize": { "title": "Chunk Size", "minimum": 250, "maximum": 8000, "type": "integer", "description": "Approximate maximum transcript characters per RAG chunk.", "default": 1200 }, "chunkOverlap": { "title": "Chunk Overlap", "minimum": 0, "maximum": 2000, "type": "integer", "description": "Approximate overlap characters carried from the previous chunk, segment-aligned.", "default": 150 }, "maxTranscriptChars": { "title": "Max Transcript Characters", "minimum": 500, "maximum": 500000, "type": "integer", "description": "Maximum transcript text characters to chunk per video.", "default": 100000 }, "timeoutMs": { "title": "HTTP Timeout", "minimum": 3000, "maximum": 60000, "type": "integer", "description": "Request timeout in milliseconds.", "default": 15000 }, "reportTier": { "title": "Report Tier", "enum": [ "corpus_snapshot", "rag_readiness", "chunks" ], "type": "string", "description": "Public report tiers produce one decision-ready audit report. Use chunks only when you need legacy per-chunk output; watch summaries are planned and proof-gated.", "default": "corpus_snapshot" }, "maxChargeUsd": { "title": "Max Charge USD", "minimum": 0, "maximum": 500, "type": "number", "description": "Safety cap checked before report-tier charging. If the selected report price exceeds this cap, the actor returns a no-charge limit_reached row.", "default": 9 }, "maxReports": { "title": "Max Reports", "minimum": 1, "maximum": 10, "type": "integer", "description": "Report-mode safety limit. V1 emits one corpus report per run.", "default": 1 }, "demoMode": { "title": "Demo Mode", "type": "boolean", "description": "Return a no-charge sample report without external requests.", "default": false }, "dedupeVideos": { "title": "Dedupe Videos", "type": "boolean", "description": "Remove duplicate video IDs after combining video, playlist, and channel sources.", "default": true }, "limit": { "title": "Result Row Limit", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum chunk/warning rows to emit.", "default": 50 }, "delivery": { "title": "Delivery Mode", "enum": [ "dataset", "webhook", "dataset_and_webhook" ], "type": "string", "description": "Choose whether to write rows to the dataset, post the final payload to webhookUrl, or both.", "default": "dataset" }, "webhookUrl": { "title": "Webhook URL", "type": "string", "description": "HTTPS endpoint used when delivery is webhook or dataset_and_webhook.", "default": "" }, "dryRun": { "title": "Dry Run", "type": "boolean", "description": "Validate input and emit sample RAG rows without fetching YouTube or delivering dataset/webhook output.", "default": true } } }, "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 } } } } } } } } } }