{ "openapi": "3.0.1", "info": { "title": "HF Model License Drift Monitor", "description": "Monitor public Hugging Face model watchlists for license, gating, model-card, and governance-risk changes.", "version": "0.0", "x-build-id": "nNrgzaBRX6jzMkMJx" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/defenestrator~hf-model-license-drift-monitor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-defenestrator-hf-model-license-drift-monitor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/defenestrator~hf-model-license-drift-monitor/runs": { "post": { "operationId": "runs-sync-defenestrator-hf-model-license-drift-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/defenestrator~hf-model-license-drift-monitor/run-sync": { "post": { "operationId": "run-sync-defenestrator-hf-model-license-drift-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "modelIds": { "title": "Hugging Face model IDs", "minItems": 1, "maxItems": 200, "type": "array", "description": "Public Hugging Face model IDs to check, e.g. Qwen/Qwen2.5-7B-Instruct. This Actor is unofficial and only supports public model metadata; it does not download model weights.", "items": { "type": "string", "minLength": 3, "maxLength": 256, "pattern": "^(?:https://huggingface\\.co/)?(?:[A-Za-z0-9][A-Za-z0-9._-]{0,127}/)?[A-Za-z0-9][A-Za-z0-9._-]{0,127}(?:/(?:tree|blob|resolve|raw)/.+)?$" }, "default": [ "Qwen/Qwen2.5-7B-Instruct", "mistralai/Mistral-7B-Instruct-v0.3", "meta-llama/Llama-3.1-8B-Instruct", "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B" ] }, "previousSnapshots": { "title": "Previous snapshot rows for drift detection", "maxItems": 200, "type": "array", "description": "Optional rows from a previous run of this Actor. When supplied, the Actor flags changes to license, gating, model-card hash/terms, risk level, repository SHA, and download counts.", "items": { "type": "object" }, "default": [] }, "includeReadmeSignals": { "title": "Scan model card README risk terms", "type": "boolean", "description": "Fetch and scan the public README/model card for governance terms such as non-commercial, acceptable use, prohibited uses, attribution, and research-only. The README text itself is not stored, only a hash and matched terms.", "default": true }, "maxReadmeChars": { "title": "Maximum README characters to scan", "minimum": 0, "maximum": 250000, "type": "integer", "description": "Safety cap for model card text scanning. Larger cards are truncated before risk-term scanning and hashing.", "default": 60000 }, "includeAllRows": { "title": "Include non-alert rows", "type": "boolean", "description": "When false, only alert rows are pushed to the dataset; the run summary still reports every checked model.", "default": true }, "alertSeverityThreshold": { "title": "Alert severity threshold", "minimum": 1, "maximum": 100, "type": "integer", "description": "Rows at or above this score are marked alert=true. License/gating/risk drift can also force an alert.", "default": 45 }, "allowedLicenses": { "title": "Licenses treated as low-risk", "type": "array", "description": "SPDX-style license IDs treated as generally permissive for the Actor's coarse risk scoring. This is not legal advice.", "items": { "type": "string" }, "default": [ "apache-2.0", "mit", "bsd-2-clause", "bsd-3-clause", "isc", "cc0-1.0", "unlicense" ] }, "reviewLicenses": { "title": "Licenses treated as review-needed", "type": "array", "description": "License IDs or substrings that should be reviewed before production/commercial use.", "items": { "type": "string" }, "default": [ "llama", "gemma", "openrail", "bigscience", "creativeml-openrail-m", "cc-by", "gpl", "agpl", "lgpl", "other" ] }, "highRiskLicenseTerms": { "title": "License or card terms treated as high-risk", "type": "array", "description": "Case-insensitive substrings that raise license risk when found in license IDs or model-card text.", "items": { "type": "string" }, "default": [ "non-commercial", "noncommercial", "cc-by-nc", "no derivatives", "no-derivatives", "research only", "evaluation only", "not for commercial", "proprietary", "restricted use" ] }, "minDownloadDeltaPercent": { "title": "Download change percentage alert", "minimum": 0, "maximum": 10000, "type": "number", "description": "When previousSnapshots include downloads, flag a notable adoption change at or above this absolute percentage.", "default": 25 }, "maxModels": { "title": "Maximum models per run", "minimum": 1, "maximum": 200, "type": "integer", "description": "Upper bound to keep scheduled runs cheap and predictable.", "default": 50 }, "timeoutMs": { "title": "Fetch timeout milliseconds", "minimum": 5000, "maximum": 60000, "type": "integer", "description": "Per-request timeout for Hugging Face public API and model-card fetches.", "default": 30000 } } }, "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 } } } } } } } } } }