{ "openapi": "3.0.1", "info": { "title": "RagChunk: Semantic RAG Splitter & Markdown Cleaner", "description": "Extract, clean, and semantically split documentation URLs into token-safe chunks for Vector DBs. Built-in HTML boilerplate stripping saves up to 40% on LLM token costs.", "version": "0.0", "x-build-id": "e0NSTnALGdGCevnc2" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/flaretool~rag-semantic-chunker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-flaretool-rag-semantic-chunker", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/flaretool~rag-semantic-chunker/runs": { "post": { "operationId": "runs-sync-flaretool-rag-semantic-chunker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/flaretool~rag-semantic-chunker/run-sync": { "post": { "operationId": "run-sync-flaretool-rag-semantic-chunker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Target Website URL", "pattern": "^https?:\\/\\/[^\\s\\/$.?#].[^\\s]*$", "type": "string", "description": "The exact URL of the webpage or documentation link you want to scrape, extract, and chunk." }, "max_tokens": { "title": "Maximum Tokens Per Chunk", "minimum": 50, "maximum": 2000, "type": "integer", "description": "The max token allocation target for each sliding window slice using the cl100k_base (GPT-4) tokenizer footprint.", "default": 400 }, "overlap": { "title": "Token Overlap Window", "minimum": 0, "maximum": 500, "type": "integer", "description": "The number of trailing tokens carried over from the previous chunk to maintain semantic context boundaries.", "default": 40 }, "contentSelector": { "title": "Content CSS Selector", "type": "string", "description": "Optional CSS selector prioritizing specific wrapper elements for main content extraction (e.g. 'main', 'article', '#content')." }, "min_token_floor": { "title": "Minimum Token Floor", "minimum": 5, "maximum": 500, "type": "integer", "description": "The minimum number of tokens required to emit a chunk. Discards tiny, non-semantic fragments.", "default": 30 }, "prose_hard_multiplier": { "title": "Prose Hard Multiplier", "minimum": 1, "maximum": 2, "type": "number", "description": "Hard token limit multiplier for prose segments before splitting (1.0 - 2.0).", "default": 1.2 }, "table_hard_multiplier": { "title": "Table Hard Multiplier", "minimum": 1.5, "maximum": 5, "type": "number", "description": "Hard token limit multiplier inside tables to prevent data fragmentation (1.5 - 5.0).", "default": 3 } } }, "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 } } } } } } } } } }