Mozilla Data Collective

{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['id'], 'properties': {'id': {'type': 'string', 'maxLength': 500, 'minLength': 1, 'description': 'Dataset id or slug, as returned in the id field of search results.'}}}

{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {}}

{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['query'], 'properties': {'sort': {'enum': ['relevance', 'newest', 'size'], 'type': 'string', 'description': "Result ordering. Defaults to 'relevance'; use 'newest' or 'size' only when the user asks for it."}, 'task': {'type': 'array', 'items': {'enum': ['N/A', 'NLP', 'ASR', 'LID', 'TTS', 'MT', 'LM', 'LLM', 'NLU', 'NLG', 'CALL', 'RAG', 'CV', 'ML', 'OTH'], 'type': 'string'}, 'maxItems': 20, 'minItems': 1, 'description': "Restrict to these machine-learning tasks, e.g. ['ASR', 'TTS']."}, 'limit': {'type': 'integer', 'default': 10, 'maximum': 25, 'minimum': 1, 'description': 'Maximum number of results to return (1-25).'}, 'query': {'type': 'string', 'maxLength': 500, 'minLength': 1, 'description': "Natural-language search query describing the datasets you are looking for, e.g. 'Spanish speech recordings for TTS training'. Descriptive phrases retrieve better than single keywords."}, 'format': {'type': 'array', 'items': {'type': 'string', 'minLength': 1}, 'maxItems': 20, 'minItems': 1, 'description': "Restrict to these file formats, e.g. ['WAV', 'MP3']. Values must match exactly (case-sensitive); call the list_filters tool to get the valid ones."}, 'isPaid': {'type': 'boolean', 'description': 'true returns only paid datasets, false only free ones. Omit to include both.'}, 'locale': {'type': 'array', 'items': {'type': 'string', 'minLength': 1}, 'maxItems': 20, 'minItems': 1, 'description': "Restrict to these language/locale codes, e.g. ['sw', 'pt-BR']. Values must match exactly (case-sensitive); call the list_filters tool to get the valid ones."}, 'license': {'type': 'array', 'items': {'type': 'string', 'minLength': 1}, 'maxItems': 20, 'minItems': 1, 'description': "Restrict to these license abbreviations, e.g. ['CC0-1.0', 'CC-BY-4.0']. Values must match exactly (case-sensitive); call the list_filters tool to get the valid ones."}, 'hasSample': {'type': 'boolean', 'description': 'true returns only datasets that publish a downloadable sample, useful when the user wants to try data before committing. false behaves the same as omitting it.'}, 'uploadDate': {'enum': ['today', 'thisWeek', 'thisMonth', 'thisYear'], 'type': 'string', 'description': 'Restrict to datasets published within this recent window.'}, 'sortDirection': {'enum': ['asc', 'desc'], 'type': 'string', 'description': "Direction for the sort field. Only meaningful alongside sort='newest' or sort='size'."}}}