{ "openapi": "3.0.1", "info": { "title": "RAG Corpus Provenance Packager", "description": "Package rights-declared HTML, Markdown, text, and born-digital PDFs into deterministic RAG pages, traceable chunks, and verified manifests.", "version": "0.1", "x-build-id": "DAygFK4VN9vNtr5KY" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/flintglade~rag-corpus-provenance-packager/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-flintglade-rag-corpus-provenance-packager", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/flintglade~rag-corpus-provenance-packager/runs": { "post": { "operationId": "runs-sync-flintglade-rag-corpus-provenance-packager", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/flintglade~rag-corpus-provenance-packager/run-sync": { "post": { "operationId": "run-sync-flintglade-rag-corpus-provenance-packager", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "sources" ], "properties": { "inputSchemaVersion": { "title": "Input schema version", "minimum": 1, "maximum": 1, "type": "integer", "description": "Versioned runtime input contract.", "default": 1 }, "sources": { "title": "Explicit source documents", "minItems": 1, "maxItems": 100, "type": "array", "description": "Each source selects one HTTPS URL or one user-authorized Apify KVS record and includes an explicit rights declaration. This declaration is recorded, not legally validated.", "items": { "type": "object", "additionalProperties": false, "properties": { "url": { "title": "Explicit HTTPS URL", "type": "string", "maxLength": 2048, "description": "One public or user-authorized source; links are not followed." }, "keyValueStoreId": { "title": "Key-value store ID", "type": "string", "maxLength": 128, "description": "A user-authorized Apify KVS selected instead of URL." }, "recordKey": { "title": "Record key", "type": "string", "maxLength": 256, "description": "Exact record key in the selected KVS." }, "rightsBasis": { "title": "Required rights declaration", "description": "Your declaration and evidence. This Actor does not provide legal advice or conclude that reuse is permitted.", "type": "object", "additionalProperties": false, "properties": { "type": { "title": "Basis", "description": "The user's declared basis for processing this source; metadata_only is recorded but cannot admit source text.", "type": "string", "enum": [ "user_owned", "licensed", "public_domain", "open_license", "metadata_only" ] }, "evidence": { "title": "Evidence text", "description": "Short non-secret evidence supporting the declaration.", "type": "string", "maxLength": 2000 }, "evidenceUrl": { "title": "Evidence URL", "description": "Optional HTTPS locator for evidence supporting the declaration.", "type": "string", "maxLength": 2048 } }, "required": [ "type" ] }, "formatHint": { "title": "Format hint", "description": "Optional parser selection when source metadata or file extension is insufficient.", "type": "string", "enum": [ "html", "markdown", "text", "pdf" ] }, "includeSelectors": { "title": "HTML include selectors", "description": "Optional bounded CSS selectors identifying HTML regions to include.", "type": "array", "editor": "stringList", "maxItems": 20, "items": { "type": "string", "maxLength": 200 } }, "excludeSelectors": { "title": "HTML exclude selectors", "description": "Optional bounded CSS selectors identifying HTML regions to remove.", "type": "array", "editor": "stringList", "maxItems": 20, "items": { "type": "string", "maxLength": 200 } } }, "required": [ "rightsBasis" ] } }, "chunking": { "title": "Deterministic chunking", "type": "object", "description": "Character chunking with a stable version, size, and overlap.", "properties": { "strategy": { "title": "Strategy", "description": "Version 1 supports deterministic character chunking only.", "type": "string", "enum": [ "character" ], "default": "character" }, "size": { "title": "Chunk size", "description": "Maximum characters per chunk.", "type": "integer", "minimum": 200, "maximum": 5000, "default": 1000 }, "overlap": { "title": "Chunk overlap", "description": "Characters repeated between adjacent chunks; runtime requires less than size.", "type": "integer", "minimum": 0, "maximum": 4999, "default": 150 } }, "default": { "strategy": "character", "size": 1000, "overlap": 150 }, "additionalProperties": false }, "dedupe": { "title": "Deduplication", "type": "object", "description": "Version 1 performs exact canonical-content deduplication only.", "properties": { "mode": { "title": "Mode", "description": "Exact hashing preserves similar-but-distinct documents.", "type": "string", "enum": [ "exact" ], "default": "exact" } }, "default": { "mode": "exact" }, "additionalProperties": false }, "baselineStoreId": { "title": "Baseline KVS", "type": "string", "description": "Optional existing KVS for page invalidation history. State commits only after a paid event is accepted." }, "retainRaw": { "title": "Retain raw source bytes", "type": "boolean", "description": "Store user-authorized raw bytes in KVS and the ZIP. Off by default.", "default": false }, "maxBytesPerSource": { "title": "Maximum bytes per source", "minimum": 1, "maximum": 50000000, "type": "integer", "description": "Reject a source before parsing when its response exceeds this byte limit.", "default": 20000000 }, "concurrency": { "title": "Source-read concurrency", "minimum": 1, "maximum": 4, "type": "integer", "description": "Maximum simultaneous source reads, reduced automatically by the remaining event budget.", "default": 2 } } }, "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 } } } } } } } } } }