PDF Text Extractor for AI Agents

{'type': 'object', 'required': ['runId'], 'properties': {'runId': {'type': 'string', 'minLength': 1, 'description': 'The ID of the Actor run to abort.'}, 'gracefully': {'type': 'boolean', 'description': 'If true, the Actor run will abort gracefully with a 30-second timeout.'}}, 'additionalProperties': False}

{'type': 'object', 'anyOf': [{'type': 'object', 'required': ['runId', 'actorId', 'status', 'storages', 'summary', 'nextStep'], 'properties': {'runId': {'type': 'string', 'description': 'Actor run ID'}, 'stats': {'type': 'object', 'properties': {'memMaxBytes': {'type': 'number'}, 'runTimeSecs': {'type': 'number'}, 'computeUnits': {'type': 'number'}}, 'description': 'Run statistics'}, 'status': {'type': 'string', 'description': 'Run status: READY | RUNNING | TIMING-OUT | TIMED-OUT | ABORTING | ABORTED | SUCCEEDED | FAILED'}, 'actorId': {'type': 'string', 'description': 'Stable Apify Actor ID from the run record'}, 'summary': {'type': 'string', 'description': 'Past-tense summary of the run state'}, 'exitCode': {'type': 'number', 'description': 'Actor process exit code; populated for terminal states (especially FAILED)'}, 'nextStep': {'type': 'string', 'description': 'One primary follow-up action with identifiers interpolated'}, 'storages': {'type': 'object', 'properties': {'datasets': {'type': 'object', 'required': ['default'], 'properties': {'default': {'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Dataset ID'}, 'name': {'type': 'string'}, 'title': {'type': 'string'}, 'fields': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Dataset field paths in dot notation (e.g. ["metadata.url"])'}, 'itemCount': {'type': 'number'}, 'inflatedBytes': {'type': 'number', 'description': 'Approximate uncompressed byte size of the dataset. Use with itemCount to pick limit/fields before fetching.'}, 'apifyConsoleUrl': {'type': 'string', 'description': 'Personalized Apify Console link to the dataset; present only for Console sessions'}}}}, 'description': 'Map of dataset alias â\x86\x92 metadata. Key "default" is always the run\'s primary dataset.', 'additionalProperties': {'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Dataset ID'}, 'name': {'type': 'string'}, 'title': {'type': 'string'}, 'fields': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Dataset field paths in dot notation (e.g. ["metadata.url"])'}, 'itemCount': {'type': 'number'}, 'inflatedBytes': {'type': 'number', 'description': 'Approximate uncompressed byte size of the dataset. Use with itemCount to pick limit/fields before fetching.'}, 'apifyConsoleUrl': {'type': 'string', 'description': 'Personalized Apify Console link to the dataset; present only for Console sessions'}}}}, 'keyValueStores': {'type': 'object', 'required': ['default'], 'properties': {'default': {'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Key-value store ID'}, 'keys': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Up to 50 key names'}, 'name': {'type': 'string'}, 'title': {'type': 'string'}, 'keyCount': {'type': 'number', 'description': 'Total number of keys (omitted when truncated)'}, 'apifyConsoleUrl': {'type': 'string', 'description': 'Personalized Apify Console link to the store; present only for Console sessions'}}}}, 'description': 'Map of key-value store alias â\x86\x92 metadata. Key "default" is always the run\'s primary store.', 'additionalProperties': {'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Key-value store ID'}, 'keys': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Up to 50 key names'}, 'name': {'type': 'string'}, 'title': {'type': 'string'}, 'keyCount': {'type': 'number', 'description': 'Total number of keys (omitted when truncated)'}, 'apifyConsoleUrl': {'type': 'string', 'description': 'Personalized Apify Console link to the store; present only for Console sessions'}}}}}, 'description': 'Dataset and key-value store metadata, keyed by alias. "default" is always the primary entry.'}, 'actorName': {'type': 'string', 'description': '"username/actor-name"'}, 'startedAt': {'type': 'string', 'description': 'ISO timestamp when the run started'}, 'finishedAt': {'type': 'string', 'description': 'ISO timestamp when the run finished (terminal states only)'}, 'statusMessage': {'type': 'string', 'description': 'Pass-through from Apify run.statusMessage'}, 'apifyConsoleUrl': {'type': 'string', 'description': 'Personalized Apify Console link to the run; present only for Console sessions'}}}, {'type': 'object', 'required': ['x402Version', 'accepts'], 'properties': {'error': {'type': 'string'}, 'accepts': {'type': 'array', 'items': {'type': 'object'}}, 'resource': {'type': 'object'}, 'x402Version': {'type': 'number'}}}]}

{'type': 'object', 'required': ['runId'], 'properties': {'runId': {'type': 'string', 'minLength': 1, 'description': 'The ID of the Actor run.'}, 'waitSecs': {'type': 'integer', 'default': 30, 'maximum': 45, 'minimum': 0, 'description': 'Maximum seconds to wait for the run to reach a terminal state (SUCCEEDED, FAILED, ABORTED, TIMED-OUT).\n0 returns immediately with the current status. Cap: 45. Default: 30.'}}, 'additionalProperties': False}

{'type': 'object', 'anyOf': [{'type': 'object', 'required': ['runId', 'actorId', 'status', 'storages', 'summary', 'nextStep'], 'properties': {'runId': {'type': 'string', 'description': 'Actor run ID'}, 'stats': {'type': 'object', 'properties': {'memMaxBytes': {'type': 'number'}, 'runTimeSecs': {'type': 'number'}, 'computeUnits': {'type': 'number'}}, 'description': 'Run statistics'}, 'status': {'type': 'string', 'description': 'Run status: READY | RUNNING | TIMING-OUT | TIMED-OUT | ABORTING | ABORTED | SUCCEEDED | FAILED'}, 'actorId': {'type': 'string', 'description': 'Stable Apify Actor ID from the run record'}, 'summary': {'type': 'string', 'description': 'Past-tense summary of the run state'}, 'exitCode': {'type': 'number', 'description': 'Actor process exit code; populated for terminal states (especially FAILED)'}, 'nextStep': {'type': 'string', 'description': 'One primary follow-up action with identifiers interpolated'}, 'storages': {'type': 'object', 'properties': {'datasets': {'type': 'object', 'required': ['default'], 'properties': {'default': {'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Dataset ID'}, 'name': {'type': 'string'}, 'title': {'type': 'string'}, 'fields': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Dataset field paths in dot notation (e.g. ["metadata.url"])'}, 'itemCount': {'type': 'number'}, 'inflatedBytes': {'type': 'number', 'description': 'Approximate uncompressed byte size of the dataset. Use with itemCount to pick limit/fields before fetching.'}, 'apifyConsoleUrl': {'type': 'string', 'description': 'Personalized Apify Console link to the dataset; present only for Console sessions'}}}}, 'description': 'Map of dataset alias â\x86\x92 metadata. Key "default" is always the run\'s primary dataset.', 'additionalProperties': {'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Dataset ID'}, 'name': {'type': 'string'}, 'title': {'type': 'string'}, 'fields': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Dataset field paths in dot notation (e.g. ["metadata.url"])'}, 'itemCount': {'type': 'number'}, 'inflatedBytes': {'type': 'number', 'description': 'Approximate uncompressed byte size of the dataset. Use with itemCount to pick limit/fields before fetching.'}, 'apifyConsoleUrl': {'type': 'string', 'description': 'Personalized Apify Console link to the dataset; present only for Console sessions'}}}}, 'keyValueStores': {'type': 'object', 'required': ['default'], 'properties': {'default': {'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Key-value store ID'}, 'keys': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Up to 50 key names'}, 'name': {'type': 'string'}, 'title': {'type': 'string'}, 'keyCount': {'type': 'number', 'description': 'Total number of keys (omitted when truncated)'}, 'apifyConsoleUrl': {'type': 'string', 'description': 'Personalized Apify Console link to the store; present only for Console sessions'}}}}, 'description': 'Map of key-value store alias â\x86\x92 metadata. Key "default" is always the run\'s primary store.', 'additionalProperties': {'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Key-value store ID'}, 'keys': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Up to 50 key names'}, 'name': {'type': 'string'}, 'title': {'type': 'string'}, 'keyCount': {'type': 'number', 'description': 'Total number of keys (omitted when truncated)'}, 'apifyConsoleUrl': {'type': 'string', 'description': 'Personalized Apify Console link to the store; present only for Console sessions'}}}}}, 'description': 'Dataset and key-value store metadata, keyed by alias. "default" is always the primary entry.'}, 'actorName': {'type': 'string', 'description': '"username/actor-name"'}, 'startedAt': {'type': 'string', 'description': 'ISO timestamp when the run started'}, 'finishedAt': {'type': 'string', 'description': 'ISO timestamp when the run finished (terminal states only)'}, 'statusMessage': {'type': 'string', 'description': 'Pass-through from Apify run.statusMessage'}, 'apifyConsoleUrl': {'type': 'string', 'description': 'Personalized Apify Console link to the run; present only for Console sessions'}}}, {'type': 'object', 'required': ['x402Version', 'accepts'], 'properties': {'error': {'type': 'string'}, 'accepts': {'type': 'array', 'items': {'type': 'object'}}, 'resource': {'type': 'object'}, 'x402Version': {'type': 'number'}}}]}

{'type': 'object', 'required': ['datasetId'], 'properties': {'desc': {'type': 'boolean', 'description': 'If true, results are returned in reverse order (newest to oldest).'}, 'omit': {'type': 'string', 'description': 'Comma-separated list of fields to exclude from results.'}, 'clean': {'type': 'boolean', 'description': 'If true, returns only non-empty items and skips hidden fields (starting with #). Shortcut for skipHidden=true and skipEmpty=true.'}, 'limit': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': 1, 'description': 'Maximum number of items to return. Default is 20.'}, 'fields': {'type': 'string', 'description': 'Comma-separated list of fields to include in results. Fields in output are sorted as specified. Use dot notation for nested objects (e.g. "metadata.url"); the server auto-flattens parent prefixes.'}, 'offset': {'type': 'number', 'description': 'Number of items to skip at the start. Default is 0.'}, 'flatten': {'type': 'string', 'description': 'Comma-separated list of fields to flatten (e.g. flatten="metadata" turns {"metadata":{"url":"x"}} into {"metadata.url":"x"}). Normally derived automatically from dot-notation in `fields`; specify only as a diagnostic override.'}, 'datasetId': {'type': 'string', 'minLength': 1, 'description': 'Dataset ID or username~dataset-name.'}}, 'additionalProperties': False}

{'type': 'object', 'anyOf': [{'type': 'object', 'required': ['datasetId', 'items', 'itemCount', 'totalItemCount', 'offset', 'limit', 'summary', 'nextStep'], 'properties': {'items': {'type': 'array', 'items': {'type': 'object'}, 'description': 'Dataset items'}, 'limit': {'type': 'number', 'description': 'Limit used for pagination'}, 'offset': {'type': 'number', 'description': 'Offset used for pagination'}, 'summary': {'type': 'string', 'description': 'Summary of the result'}, 'nextStep': {'type': 'string', 'description': 'One follow-up action with tool name'}, 'datasetId': {'type': 'string', 'description': 'Dataset ID'}, 'itemCount': {'type': 'number', 'description': 'Number of items returned'}, 'totalItemCount': {'type': 'number', 'description': 'Total items in dataset'}, 'apifyConsoleUrl': {'type': 'string', 'description': 'Personalized Apify Console link to the dataset; present only for Console sessions'}}}, {'type': 'object', 'required': ['x402Version', 'accepts'], 'properties': {'error': {'type': 'string'}, 'accepts': {'type': 'array', 'items': {'type': 'object'}}, 'resource': {'type': 'object'}, 'x402Version': {'type': 'number'}}}]}

{'type': 'object', 'required': ['keyValueStoreId', 'recordKey'], 'properties': {'recordKey': {'type': 'string', 'minLength': 1, 'description': 'Key of the record to retrieve.'}, 'keyValueStoreId': {'type': 'string', 'minLength': 1, 'description': 'Key-value store ID or username~store-name.'}}, 'additionalProperties': False}

{'type': 'object', 'anyOf': [{'type': 'object', 'required': ['keyValueStoreId', 'key', 'value', 'summary'], 'properties': {'key': {'type': 'string', 'description': 'Record key'}, 'value': {'description': 'The stored value (JSON, text, or binary)'}, 'summary': {'type': 'string', 'description': 'Summary of the result'}, 'contentType': {'type': 'string', 'description': 'MIME type of the stored value'}, 'keyValueStoreId': {'type': 'string', 'description': 'Key-value store ID'}}}, {'type': 'object', 'required': ['x402Version', 'accepts'], 'properties': {'error': {'type': 'string'}, 'accepts': {'type': 'array', 'items': {'type': 'object'}}, 'resource': {'type': 'object'}, 'x402Version': {'type': 'number'}}}]}

{'$id': 'https://apify.com/mcp/industrial_platform--pdf-text-intelligence/schema.json', 'type': 'object', 'title': 'PDF Text Intelligence input', 'required': ['urls'], 'properties': {'urls': {'type': 'array', 'items': {'type': 'string', 'maxLength': 2048}, 'title': 'PDF URLs', 'prefill': ['https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf'], 'examples': ['https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf'], 'description': '**REQUIRED** Public HTTP/HTTPS PDF URLs to process. Up to 50 unique PDFs per run.\nExample values: ["https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"]'}, 'waitSecs': {'type': 'integer', 'default': 30, 'maximum': 45, 'minimum': 0, 'description': 'Max seconds (0â\x80\x9345, default 30) to cap the wait for the Actor run to reach terminal state. For long-running Actors the response returns at the cap with the current run status; follow `nextStep` to poll via get-actor-run. Set to 0 to fire-and-forget.'}, 'max_pages': {'type': 'integer', 'title': 'Maximum pages', 'default': 200, 'examples': [200], 'description': 'Maximum pages extracted from each PDF.\nExample values: 200'}, 'concurrency': {'type': 'integer', 'title': 'Concurrency', 'default': 5, 'examples': [5], 'description': 'Maximum number of PDFs downloaded and parsed concurrently.\nExample values: 5'}, 'max_text_chars': {'type': 'integer', 'title': 'Maximum text characters', 'default': 500000, 'examples': [500000], 'description': 'Maximum retained text characters per PDF.\nExample values: 500000'}, 'timeout_seconds': {'type': 'integer', 'title': 'Per-PDF timeout', 'default': 45, 'examples': [45], 'description': 'Maximum time allowed to download each PDF.\nExample values: 45'}}, 'additionalProperties': False}

{'type': 'object', 'anyOf': [{'type': 'object', 'required': ['runId', 'actorId', 'status', 'storages', 'summary', 'nextStep'], 'properties': {'runId': {'type': 'string', 'description': 'Actor run ID'}, 'stats': {'type': 'object', 'properties': {'memMaxBytes': {'type': 'number'}, 'runTimeSecs': {'type': 'number'}, 'computeUnits': {'type': 'number'}}, 'description': 'Run statistics'}, 'status': {'type': 'string', 'description': 'Run status: READY | RUNNING | TIMING-OUT | TIMED-OUT | ABORTING | ABORTED | SUCCEEDED | FAILED'}, 'actorId': {'type': 'string', 'description': 'Stable Apify Actor ID from the run record'}, 'summary': {'type': 'string', 'description': 'Past-tense summary of the run state'}, 'exitCode': {'type': 'number', 'description': 'Actor process exit code; populated for terminal states (especially FAILED)'}, 'nextStep': {'type': 'string', 'description': 'One primary follow-up action with identifiers interpolated'}, 'storages': {'type': 'object', 'properties': {'datasets': {'type': 'object', 'required': ['default'], 'properties': {'default': {'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Dataset ID'}, 'name': {'type': 'string'}, 'title': {'type': 'string'}, 'fields': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Dataset field paths in dot notation (e.g. ["metadata.url"])'}, 'itemCount': {'type': 'number'}, 'itemsSchema': {'type': 'object', 'properties': {'url': {'type': 'string'}, 'text': {'type': 'string'}, 'pages': {'type': 'array', 'items': {'type': 'object', 'properties': {'text': {'type': 'string'}, 'page_number': {'type': 'number'}, 'text_length': {'type': 'number'}}}}, 'author': {'type': 'string'}, 'status': {'type': 'string'}, 'creator': {'type': 'string'}, 'producer': {'type': 'string'}, 'final_url': {'type': 'string'}, 'fetched_at': {'type': 'string'}, 'latency_ms': {'type': 'number'}, 'page_count': {'type': 'number'}, 'http_status': {'type': 'number'}, 'text_length': {'type': 'number'}, 'content_type': {'type': 'string'}, 'creation_date': {'type': 'string'}, 'response_bytes': {'type': 'number'}, 'text_truncated': {'type': 'boolean'}, 'extracted_pages': {'type': 'number'}}, 'description': "JSON Schema for rows in the dataset at `storages.datasets.default.id` â\x80\x94 describes row shape only; the rows themselves are NOT returned inline in this response. Inferred from this Actor's historical successful runs. To fetch actual rows, call `get-dataset-items` with the dataset id and a `fields` projection drawn from this schema."}, 'inflatedBytes': {'type': 'number', 'description': 'Approximate uncompressed byte size of the dataset. Use with itemCount to pick limit/fields before fetching.'}, 'apifyConsoleUrl': {'type': 'string', 'description': 'Personalized Apify Console link to the dataset; present only for Console sessions'}}}}, 'description': 'Map of dataset alias â\x86\x92 metadata. Key "default" is always the run\'s primary dataset.', 'additionalProperties': {'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Dataset ID'}, 'name': {'type': 'string'}, 'title': {'type': 'string'}, 'fields': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Dataset field paths in dot notation (e.g. ["metadata.url"])'}, 'itemCount': {'type': 'number'}, 'inflatedBytes': {'type': 'number', 'description': 'Approximate uncompressed byte size of the dataset. Use with itemCount to pick limit/fields before fetching.'}, 'apifyConsoleUrl': {'type': 'string', 'description': 'Personalized Apify Console link to the dataset; present only for Console sessions'}}}}, 'keyValueStores': {'type': 'object', 'required': ['default'], 'properties': {'default': {'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Key-value store ID'}, 'keys': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Up to 50 key names'}, 'name': {'type': 'string'}, 'title': {'type': 'string'}, 'keyCount': {'type': 'number', 'description': 'Total number of keys (omitted when truncated)'}, 'apifyConsoleUrl': {'type': 'string', 'description': 'Personalized Apify Console link to the store; present only for Console sessions'}}}}, 'description': 'Map of key-value store alias â\x86\x92 metadata. Key "default" is always the run\'s primary store.', 'additionalProperties': {'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Key-value store ID'}, 'keys': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Up to 50 key names'}, 'name': {'type': 'string'}, 'title': {'type': 'string'}, 'keyCount': {'type': 'number', 'description': 'Total number of keys (omitted when truncated)'}, 'apifyConsoleUrl': {'type': 'string', 'description': 'Personalized Apify Console link to the store; present only for Console sessions'}}}}}, 'description': 'Dataset and key-value store metadata, keyed by alias. "default" is always the primary entry.'}, 'actorName': {'type': 'string', 'description': '"username/actor-name"'}, 'startedAt': {'type': 'string', 'description': 'ISO timestamp when the run started'}, 'finishedAt': {'type': 'string', 'description': 'ISO timestamp when the run finished (terminal states only)'}, 'statusMessage': {'type': 'string', 'description': 'Pass-through from Apify run.statusMessage'}, 'apifyConsoleUrl': {'type': 'string', 'description': 'Personalized Apify Console link to the run; present only for Console sessions'}}}, {'type': 'object', 'required': ['x402Version', 'accepts'], 'properties': {'error': {'type': 'string'}, 'accepts': {'type': 'array', 'items': {'type': 'object'}}, 'resource': {'type': 'object'}, 'x402Version': {'type': 'number'}}}]}