{ "openapi": "3.0.1", "info": { "title": "Vertical Corpora Builder - Domain Datasets for LLM Fine-Tuning", "description": "Build domain-specific text corpora (legal, medical, financial) for LLM fine-tuning: crawl seed sources, strip boilerplate, dedupe, and emit token-aware chunks as JSONL with full provenance. Outputs a ready-to-train dataset.", "version": "0.1", "x-build-id": "wUdCOeDqYXTrU4RWR" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/darknezz~vertical-corpus-builder/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-darknezz-vertical-corpus-builder", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/darknezz~vertical-corpus-builder/runs": { "post": { "operationId": "runs-sync-darknezz-vertical-corpus-builder", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/darknezz~vertical-corpus-builder/run-sync": { "post": { "operationId": "run-sync-darknezz-vertical-corpus-builder", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "domain": { "title": "Domain", "enum": [ "legal", "medical", "financial" ], "type": "string", "description": "Vertical domain of the corpus. Controls the `domain` field in every output record and the crawl profile.", "default": "legal" }, "sources": { "title": "Seed sources", "type": "array", "description": "Seed URLs to crawl. Each URL is treated as a starting point; same-domain links are followed up to maxPagesPerSource pages.", "items": { "type": "string" }, "default": [ "https://www.law.cornell.edu/supremecourt/text/19-1392" ] }, "outputFormat": { "title": "Output format", "enum": [ "jsonl", "json" ], "type": "string", "description": "jsonl = dataset records are JSON Lines with one chunk per line (plus a downloadable output.jsonl in the key-value store). json = plain dataset records without the key-value file.", "default": "jsonl" }, "chunkSize": { "title": "Chunk size (tokens)", "minimum": 64, "maximum": 4096, "type": "integer", "description": "Target chunk size in tokens (estimated at ~4 chars/token). Text is split at paragraph boundaries to stay under the budget.", "default": 512 }, "maxPagesPerSource": { "title": "Max pages per source", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum pages to crawl per seed URL (1 = the seed page only). Same-domain links are followed breadth-first up to this limit.", "default": 1 }, "maxChunksPerPage": { "title": "Max chunks per page", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Maximum chunks kept per page (0 = unlimited). Caps dataset size when crawling long documents.", "default": 0 }, "dedupeSimilarity": { "title": "Dedupe similarity (0-1)", "minimum": 0.5, "maximum": 1, "type": "number", "description": "Near-duplicate threshold: chunks whose similarity is >= this value are collapsed. 1.0 = exact-duplicate removal only.", "default": 0.95 } } }, "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 } } } } } } } } } }