{ "openapi": "3.0.1", "info": { "title": "Saka NLP Actor", "description": "An Apify Actor that uses every feature of Saka-NLP to extract text from web pages and analyse it with Indonesian and regional-language NLP.", "version": "0.0", "x-build-id": "9X0t70CMEvLW6foyV" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ikhwan_fathulloh~Saka-NLP-Actor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ikhwan_fathulloh-Saka-NLP-Actor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ikhwan_fathulloh~Saka-NLP-Actor/runs": { "post": { "operationId": "runs-sync-ikhwan_fathulloh-Saka-NLP-Actor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ikhwan_fathulloh~Saka-NLP-Actor/run-sync": { "post": { "operationId": "run-sync-ikhwan_fathulloh-Saka-NLP-Actor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "url" ], "properties": { "url": { "title": "Web Page URL", "type": "string", "description": "URL of the web page to extract and analyse. Must be a publicly accessible HTTP/HTTPS URL. Example: https://www.kompas.com/tekno/read/2024/01/15/kecerdasan-buatan-indonesia" }, "lang": { "title": "Stopword Language", "enum": [ "id", "sunda", "jawa", "bali", "minang", "batak", "en", "jaksel", "all" ], "type": "string", "description": "Language used for stopword filtering. 'all' combines every supported language (id + sunda + jawa + bali + minang + batak + en + jaksel — 1 000+ words). Use 'id' for standard Indonesian news articles.", "default": "id" }, "topN": { "title": "Top N Words", "minimum": 5, "maximum": 100, "type": "integer", "description": "Number of highest-frequency clean tokens returned in top_words, top_bigrams, and top_trigrams.", "default": 20 }, "summaryLines": { "title": "Extractive Summary — Sentences", "minimum": 1, "maximum": 20, "type": "integer", "description": "Number of sentences selected for the extractive summary. Sentences are ranked by overlap with top-frequency words.", "default": 5 }, "kbbiLookup": { "title": "KBBI Lookup — Word Count", "minimum": 0, "maximum": 10, "type": "integer", "description": "Number of top words to look up in the official KBBI (Kamus Besar Bahasa Indonesia) online dictionary. Set to 0 to skip.", "default": 5 }, "aksaraWords": { "title": "Aksara Transliteration — Word Count", "minimum": 0, "maximum": 10, "type": "integer", "description": "Number of top words to transliterate into Sundanese, Javanese (Hanacaraka), and Balinese scripts. Set to 0 to skip.", "default": 5 }, "outputFormat": { "title": "Formatted Reports Format", "enum": [ "json", "markdown", "html", "csv", "table", "text" ], "type": "string", "description": "Rendering format for the formatted_reports output field. Primary output is always JSON regardless of this setting.", "default": "markdown" }, "includeFullText": { "title": "Include Full Extracted Text", "type": "boolean", "description": "When true, the complete extracted page text is included under full_text. Can significantly increase dataset item size for long articles.", "default": false }, "llmProvider": { "title": "LLM Provider", "enum": [ "openai", "gemini", "claude", "groq", "mistral", "together", "openrouter", "deepseek", "sumopod", "lmstudio", "ollama", "custom" ], "type": "string", "description": "LLM provider for AI-powered analysis (summary, sentiment, keywords, category). Select 'custom' to supply your own OpenAI-compatible endpoint. Leave llmApiKey empty to skip LLM entirely.", "default": "openai" }, "llmApiKey": { "title": "LLM API Key", "type": "string", "description": "Bearer token or API key for the selected LLM provider. Leave empty to skip all LLM tasks. For LM Studio and Ollama use any non-empty string (e.g. 'local')." }, "llmBaseUrl": { "title": "Custom LLM Base URL", "type": "string", "description": "Override the provider base URL. Required when llmProvider is 'custom'. Must point to an OpenAI-compatible /v1 endpoint. Example: https://ai.sumopod.com/v1" }, "llmModel": { "title": "LLM Model Name", "type": "string", "description": "Model identifier to use. Leave empty to use the provider default. Examples: gpt-4o, gpt-4o-mini, gemini-2.0-flash, claude-3-5-sonnet-20241022, llama3, deepseek-chat." }, "llmTasks": { "title": "LLM Tasks", "type": "string", "description": "Comma-separated LLM tasks: summary (AI-written summary), sentiment (positive/negative/neutral + score), keywords (refined top-10), category (topic classification). Leave empty to run all four when an API key is present." }, "llmTimeout": { "title": "LLM Request Timeout (seconds)", "minimum": 10, "maximum": 300, "type": "integer", "description": "Maximum time to wait for a single LLM API response. Increase for slow local models (LM Studio, Ollama).", "default": 60 }, "llmBatchMode": { "title": "LLM Batch Mode (Token-Saver)", "type": "boolean", "description": "When enabled (default), all LLM tasks run in ONE API call — saves ~65% input tokens vs four separate calls. Disable only if your provider rejects multi-task prompts.", "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 } } } } } } } } } }