> ## Documentation Index > Fetch the complete documentation index at: https://docs.getlimina.ai/llms.txt > Use this file to discover all available pages before exploring further. # Process Files Base64 > Detect entities such as PII, PHI or PCI in a base64-encoded file using Private AI's entity detection engine. After entity detection, a copy of the file with all entities removed is created and returned. This route is similar to `/v3/process/files/uri`, but passes the file in the POST request itself. This route allows for simple setup and testing, as no folders or volumes need to be mounted to the container. This route supports the following content types: application/dicom, application/json, application/msword, application/pdf, application/vnd.ms-excel, application/vnd.ms-powerpoint, application/vnd.openxmlformats-officedocument.presentationml.presentation, application/vnd.openxmlformats-officedocument.spreadsheetml.sheet, application/vnd.openxmlformats-officedocument.wordprocessingml.document, application/xml, audio/m4a, audio/mp3, audio/mp4, audio/mp4a-latm, audio/mpeg, audio/wav, audio/webm, audio/x-wav, image/bmp, image/jpeg, image/jpg, image/png, image/tif, image/tiff, image/x-ms-bmp, message/rfc822, text/csv, text/plain ## OpenAPI ````yaml /openapi/privateai_3.8.2.json post /v3/process/files/base64 openapi: 3.1.0 info: title: API Reference description: Private AI API Reference termsOfService: https://www.private-ai.com/terms-of-use/ contact: url: https://www.private-ai.com/contact/ email: info@private-ai.com version: 3.8.2 servers: - url: https://api.private-ai.com/deid description: Private AI Community API - url: https://api.private-ai.com/cloud description: Private AI Cloud API - url: http://localhost:8080 description: Local Server security: [] paths: /v3/process/files/base64: post: summary: Process Files Base64 description: >- Detect entities such as PII, PHI or PCI in a base64-encoded file using Private AI's entity detection engine. After entity detection, a copy of the file with all entities removed is created and returned. This route is similar to `/v3/process/files/uri`, but passes the file in the POST request itself. This route allows for simple setup and testing, as no folders or volumes need to be mounted to the container. This route supports the following content types: application/dicom, application/json, application/msword, application/pdf, application/vnd.ms-excel, application/vnd.ms-powerpoint, application/vnd.openxmlformats-officedocument.presentationml.presentation, application/vnd.openxmlformats-officedocument.spreadsheetml.sheet, application/vnd.openxmlformats-officedocument.wordprocessingml.document, application/xml, audio/m4a, audio/mp3, audio/mp4, audio/mp4a-latm, audio/mpeg, audio/wav, audio/webm, audio/x-wav, image/bmp, image/jpeg, image/jpg, image/png, image/tif, image/tiff, image/x-ms-bmp, message/rfc822, text/csv, text/plain operationId: process_files_base64_v3_process_files_base64_post parameters: - name: x-api-key in: header required: false schema: type: string default: '' title: X-Api-Key requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ProcessFileRequestBase64' examples: process_file: summary: Process File with base64-encoded payload value: file: data: >- JVBERi0xLjQKJdPr6eEKMSAwIG9iago8PC9UaXRsZSAoc2FtcGxlKQovUHJvZHVj... content_type: application/pdf or image/jpeg entity_detection: return_entity: true pdf_options: density: 150 max_resolution: 2000 audio_options: bleep_start_padding: 0 bleep_end_padding: 0 responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ProcessFileResponseBase64' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' components: schemas: ProcessFileRequestBase64: properties: file: allOf: - $ref: '#/components/schemas/File' description: >- This section contains a set of parameters to control the PII detection process. All fields have sensible default that can be changed for specific needs. entity_detection: allOf: - $ref: '#/components/schemas/PIIDetectionParams' description: >- This section contains a set of parameters to control the PII detection process. All fields have sensible default that can be changed for specific needs. pdf_options: allOf: - $ref: '#/components/schemas/PDFOptions' description: >- Options to process PDF files, such as the rendering quality when each page is turned into an image. image_options: allOf: - $ref: '#/components/schemas/ImageOptions' description: Options to process image files, such as the masking mode. audio_options: allOf: - $ref: '#/components/schemas/AudioOptions' description: >- Options to process audio files, such as the padding to add while redacting audio segments. project_id: anyOf: - type: string maxLength: 60 pattern: ^[a-zA-Z0-9\-_\:]*$ - type: 'null' title: Project Id description: >- Used to categorize requests for reporting purposes. Limited to alphanumeric characters or the following special characters :_- additionalProperties: false type: object required: - file title: ProcessFileRequestBase64 ProcessFileResponseBase64: properties: processed_file: type: string title: Processed File description: the base64 encoded file content of the redacted file. processed_text: type: string title: Processed Text description: >- This field contains the redacted version of any text that was extracted from the input file. It corresponds to a redacted ASR transcript for audio files and any text found inside a document such as a PDF or image file. entities: items: $ref: '#/components/schemas/FileEntityItem' type: array title: Entities description: A list of all entities found in the provided file. entities_present: type: boolean title: Entities Present description: Returns `True` if the list of detected entities is not empty. languages_detected: additionalProperties: type: number type: object title: Languages Detected description: >- A dictionary containing ISO 639-1 language labels and the likelihood of their detection in the request payload. type: object required: - processed_file - processed_text - entities - entities_present - languages_detected title: ProcessFileResponseBase64 HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError File: properties: data: type: string title: Data description: Base64 encoded ASCII text data of the file to process. content_type: type: string title: Content Type description: >- Content type of the file. Currently ['application/dicom', 'application/json', 'application/msword', 'application/pdf', 'application/vnd.ms-excel', 'application/vnd.ms-powerpoint', 'application/vnd.openxmlformats-officedocument.presentationml.presentation', 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'application/vnd.openxmlformats-officedocument.wordprocessingml.document', 'application/xml', 'audio/m4a', 'audio/mp3', 'audio/mp4', 'audio/mp4a-latm', 'audio/mpeg', 'audio/wav', 'audio/webm', 'audio/x-wav', 'image/bmp', 'image/jpeg', 'image/jpg', 'image/png', 'image/tif', 'image/tiff', 'image/x-ms-bmp', 'message/rfc822', 'text/csv', 'text/plain'] are supported. additionalProperties: false type: object required: - data - content_type title: File PIIDetectionParams: properties: accuracy: allOf: - $ref: '#/components/schemas/AccuracyMode' description: >- Selects the model used to identify PII in the input text. By default, the `high_automatic` accuracy model is used. This default automatically chooses either the high or high_multilingual model. While the models used by the Private AI solution are highly optimized (~25X faster than a reference transformer implementation), in high-throughput cases it is possible to trade accuracy for speed by selecting either the `standard` or `standard_high` accuracy modes. Multilingual support can be enabled by using one of the multilingual models, namely `standard_high_multilingual` (GPU container only) and `high_multilingual`. The multilingual models process all supported languages including English, without the need to specify language. It is advisable to use the English-only models where possible, as they perform slightly better on English. Automatic Models can determine which model to use (English or Multilingual) depending on the languages detected, provided Multilingual models are available. entity_types: items: anyOf: - $ref: '#/components/schemas/EnableEntityTypeSelector' - $ref: '#/components/schemas/DisableEntityTypeSelector' type: array title: Entity Types description: >- Controls which entity types and legislation sets are detected. See [Supported Entity Types](https://docs.private-ai.com/entities/#supported-entities) for the list of possible entities and legislation sets. By default, all entities are detected and removed. You can specify one of many selectors, which can be either an individual entity type such as `LOCATION_CITY` or a legislation like `GDPR`. `EnableEntityTypeSelector` selectors will add entity types to detect. On the contrary, `DisableEntityTypeSelector` selectors will ignore entities of the specified types. If only `DisableEntityTypeSelector` selectors are specified, they are assumed to be ignoring entity types from the entire supported list of entity types. filter: items: anyOf: - $ref: '#/components/schemas/AllowFilter' - $ref: '#/components/schemas/BlockFilter' - $ref: '#/components/schemas/AllowTextFilter' type: array title: Filter description: >- This field contains a list of filters expressed as regular expressions. These regular expressions can help users customize PII detection in a few ways. `ALLOW` filters can disabled redaction of entities containing specific text (e.g. a document id with format ID-1212 that is not sensitive). On the other hand, the `BLOCK` filters can augment the existing set of entities with custom entities (e.g. detecting sensitive medical code with format A18.32 as IDC_NUMBER). Finally, the `ALLOW_TEXT` filters can select a section of text in a document that should not be redacted (e.g. author names in scientific references or dates in an audit trail log). return_entity: type: boolean title: Return Entity description: >- Controls whether the PII list in the response contains the `text` field. Turning this off means that no sensitive PII is returned in the response. default: true enable_non_max_suppression: type: boolean title: Enable Non Max Suppression description: >- When set, if the best label of an entity is disabled then the entity will not be redacted. This could be useful to minimize false-positives when disabling an entity label like `ACCOUNT_NUMBER` that is closely related to another entity like `BANK_ACCOUNT`. Note that, the effect of that flag is difficult to predict when disabling labels like `LOCATION_COUNTRY` or `NAME_GIVEN` that are hierarchical by nature (i.e. a `NAME_GIVEN` entity is also a `NAME` entity). We don't recommend setting that flag to true when some of these hierarchical entities are disabled. default: false additionalProperties: false type: object title: PIIDetectionParams PDFOptions: properties: density: type: integer title: Density description: >- PDFs are converted into images using this DPI value. Smaller values result in images with smaller resolutions, which will take up less storage space and process faster, at the cost of output quality & redaction accuracy. default: 200 max_resolution: type: integer title: Max Resolution description: >- PDFs are converted into images using the `density` DPI value. Any resulting images with maximum size length larger than this will be resized to this value, while preserving aspect ratio. default: 3000 enable_pdf_text_layer: type: boolean title: Enable Pdf Text Layer description: >- This PDF option controls whether a text layer is included in the PDF files generated by the process. When set to `true`, the application will include a text layer in the PDFs, allowing for text selection, search, and accessibility features. If set to any other value or not set at all, the text layer will be disabled, potentially resulting in smaller file sizes, faster processing, but with reduced functionality regarding text selection and search. The default value is `True`, but can be adjusted via `PAI_ENABLE_PDF_TEXT_LAYER` environment variable by setting it to `False` default: true additionalProperties: false type: object title: PDFOptions ImageOptions: properties: masking_method: allOf: - $ref: '#/components/schemas/MaskMode' description: >- Masking Mode for Image Deidentification. Available options are ['blur', 'blackbox'] default: blur additionalProperties: false type: object title: ImageOptions AudioOptions: properties: bleep_start_padding: type: number minimum: 0 title: Bleep Start Padding description: Additional padding at the start of bleep, in seconds. default: 0.5 bleep_end_padding: type: number minimum: 0 title: Bleep End Padding description: Additional padding at the end of bleep, in seconds. default: 0.2 distortion_steps: type: integer title: Distortion Steps description: >- Specifies how the distortion will be made. Providing a number more than 0 will result in a higher tone and a coefficient less than 0 will result in a lower tone. default: 0 bleep_frequency: type: integer title: Bleep Frequency description: >- The `bleep_frequency` parameter configures the frequency of the sine wave used for the bleep sound in an audio segment. This setting allows users to adjust the pitch of the bleep, with higher values resulting in a higher pitch and vice versa. Ideal for customizing the bleep tone to suit various audio environments, it is expressed in Hertz (Hz) and should be chosen considering the balance and clarity needed in the audio. The default setting is 600 Hz, which represents a standard bleep tone. default: 600 bleep_gain: type: number title: Bleep Gain description: >- The `bleep_gain` parameter sets the gain level, in decibels (dB), for the bleep sound within the audio segment. It controls the relative loudness of the bleep, allowing for precise volume adjustments. A value of 0.0 dB maintains the original amplitude of the bleep, positive values increase its loudness, and negative values decrease it. default: -3 additionalProperties: false type: object title: AudioOptions FileEntityItem: properties: processed_text: type: string title: Processed Text description: >- The corresponding marker in the de-identified text (result field), where the entity exists. Note that this field is only populated for text-based formats such as `.txt` text: type: string title: Text description: >- The text corresponding to the entity. For images the text is obtained using OCR, while for audio the text is obtained using ASR. location: anyOf: - $ref: '#/components/schemas/TextLocation' - $ref: '#/components/schemas/ImageLocation' - $ref: '#/components/schemas/AudioLocation' title: Location best_label: type: string title: Best Label description: The entity label with the highest likelihood. labels: additionalProperties: type: number type: object title: Labels description: >- A dictionary of all possible labels, together with associated likelihoods. Note that these are not strictly probabilities and do not sum to 1, as a word can belong to multiple classes. The scores have also been thresholded, so no additional thresholding is necessary. type: object required: - processed_text - text - location - best_label - labels title: FileEntityItem description: Empty ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError AccuracyMode: type: string enum: - standard - standard_high - standard_high_multilingual - standard_high_automatic - high - high_multilingual - high_automatic title: AccuracyMode description: >- Selects the model used to identify PII in the input text. By default, the "high_automatic" accuracy model is used. This default automatically chooses either the high or high_multilingual model. While the models used by the Private AI solution are highly optimized (~25X faster than a reference transformer implementation), in high-throughput cases it is possible to trade accuracy for speed by selecting either the "standard" or "standard_high" accuracy modes. Multilingual support can be enabled by using one of the multilingual models, namely "standard_high_multilingual" (GPU container only) and "standard_high_multilingual". The multilingual models process all supported languages including English, without the need to specify language. It is advisable to use the English-only models where possible, as they perform slightly better on English. Automatic Models can determine which model to use (English or Multilingual) depending on the languages detected, provided Multilingual models are available. EnableEntityTypeSelector: properties: type: const: ENABLE title: Type default: ENABLE value: items: type: string type: array title: Value description: >- A list of entity types to detect and remove. See [Supported Entity Types](https://docs.private-ai.com/entities/#supported-entities) for a complete list of entity types. This can also be one or many legislations. We currently support these legislations ['APPI', 'APPI_SENSITIVE', 'CPRA', 'GDPR', 'GDPR_SENSITIVE', 'HIPAA', 'LIDI', 'PCI', 'PHI', 'QUEBEC_PRIVACY_ACT', 'CORE_ENTITIES', 'NUMERICAL_EXCL_PCI']. additionalProperties: false type: object title: EnableEntityTypeSelector DisableEntityTypeSelector: properties: type: const: DISABLE title: Type default: DISABLE value: items: type: string type: array title: Value description: >- A list of entity types to ignore. See [Supported Entity Types](https://docs.private-ai.com/entities/#supported-entities) for a complete list of entity types. additionalProperties: false type: object title: DisableEntityTypeSelector AllowFilter: properties: type: const: ALLOW title: Type description: >- Entities with text matching the provided regex pattern will be discarded. It is also possible to set this option via environment variable. See [Environment Variables](https://docs.private-ai.com/environment-variables). default: ALLOW pattern: type: string title: Pattern description: >- A python regex pattern (e.g. `r"^ID-[\d]{4}$"`). This pattern will be used to match the entity text. If it matches zero or more characters at the **beginning of the entity text**, the entity will be ignored. Be sure to use the end of string character `$` if you want to only allow entities when the entirety of the text matches. It is also important to note that regex patterns may require escaping when used in JSON objects. additionalProperties: false type: object required: - pattern title: AllowFilter BlockFilter: properties: type: const: BLOCK title: Type description: >- The block feature allows you to extend the functionality of the Private AI models by using regular expressions. This way, you can define a Python regex pattern that will be used to identify additional tokens with the given PII label. Several block list filters can be specified with their own regex pattern. Lastly,for supported labels, if you would like the model to pick up only the tokens from the block list, you can use the enabled entity type feature together with the block list feature. This can be done by defining a list of enabled entity types and not including the supported label you are adding to the block list. For example, if you would like the label `ORGANIZATION` to only pick up Microsoft, you can define the enabled entity types as `[{"type":"ENABLE", "value": "NAME"}, {"type": "ENABLE", "value": "LOCATION"}, {"type": "ENABLE", "value": "AGE"}, ...]` (and omitting `ORGANIZATION`) and the block list as `[{"type": "BLOCK", "entitiy_type": "ORGANIZATION", "pattern": "Microsoft"}]`. default: BLOCK entity_type: type: string title: Entity Type description: >- Name of the custom entity type. It can either be a completely new entity type such as `CUSTOM_ID` or an existing entity, such as `NAME`. pattern: type: string title: Pattern description: >- This is a pattern to match in the text. This feature uses regex patterns, you can either pass a word (e.g. the, word, custom, etc.) or you can pass a valid Python regex pattern. It is important to note that regex patterns may require escaping when used in JSON objects. To give an example, if you would like to send the regex pattern `r"\b\w{4}\b"` which will catch every 4-character word, you need to send it as `"\\b\\w{4}\\b"`. A complete JSON grammar is found here: https://www.json.org/json-en.html. More information on how to write a python regex is found here: https://docs.python.org/3/library/re.html It is important to note also that only non-overlapping matches are returned. threshold: type: number title: Threshold description: >- This is defining a likelihood threshold for custom entity. This likelihood is compared against the predicted model likelihood and if it is greater then the custom entity is outputted instead of the model predicted entity. By default this threshold is set to 1.0 which will ensure that the blocked entities will always be preferred over a matching model predicted entity. This can be any value between 0 and 1. default: 1 additionalProperties: false type: object required: - entity_type - pattern title: BlockFilter AllowTextFilter: properties: type: const: ALLOW_TEXT title: Type description: >- Input text matching the provided regex pattern will not be redacted. It is currently not possible to set this option via environment variable. default: ALLOW_TEXT pattern: type: string title: Pattern description: >- A python regex pattern (e.g. `r"^ID-[\d]{4}$"`). This pattern will be used to match the input text. Entities detected **inside the matched text** will be ignored. Note that capturing groups can be used in the regex pattern. If present, only the text matching a capturing group will be left unredacted. It is also important to note that regex patterns may require escaping when used in JSON objects. additionalProperties: false type: object required: - pattern title: AllowTextFilter MaskMode: type: string enum: - blur - blackbox title: MaskMode TextLocation: properties: stt_idx: type: integer title: Stt Idx description: Start character index of the entity in the original text. end_idx: type: integer title: End Idx description: >- Index of the character immediately following the entity, such that end_idx - stt_idx = number of characters in the entity. stt_idx_processed: type: integer title: Stt Idx Processed description: Start character index of the entity in the processed text. end_idx_processed: type: integer title: End Idx Processed description: >- Index of the character immediately following the entity in the processed text. type: object required: - stt_idx - end_idx - stt_idx_processed - end_idx_processed title: TextLocation description: >- Start and end indices of the entity in a text-based file format such as `.txt`. ImageLocation: properties: page: type: integer title: Page description: >- The page or layer that the entity occurs on. This corresponds to page in a PDF document or layer in a TIFF image. x0: type: number title: X0 description: X coordinate of the upper left point of the entity bounding box. x1: type: number title: X1 description: X coordinate of the lower right point of the entity bounding box. y0: type: number title: Y0 description: Y coordinate of the upper left point of the entity bounding box. y1: type: number title: Y1 description: Y coordinate of the lower right point of the entity bounding box. type: object required: - page - x0 - x1 - y0 - y1 title: ImageLocation description: >- Bounding box of the entity in an image or PDF file (PDF files are converted to images). The origin is the upper left pixel of the image. Coordinates are given as a fraction of the X and Y image dimensions. AudioLocation: properties: stt_time: type: number title: Stt Time description: The start timestamp of the entity, in seconds end_time: type: number title: End Time description: The end timestamp of the entity, in seconds type: object required: - stt_time - end_time title: AudioLocation description: Timestamp of the entity in an audio file such as `.wav`. ````