Logo
  • 🚀 Getting started
    • Install the Tonic Textual SDK
    • Set up a Textual API key
    • Creating a Textual client
  • Parse
    • 🧮 Parsing files
      • Parsing a local file
      • Parsing a file from Amazon S3
      • Understanding the parsed result
    • 👨‍🔧 Pipelines
      • Creating a pipeline
      • Creating a local pipeline
      • Creating and configuring an Amazon S3 pipeline
      • Creating and configuring an Azure pipeline
      • Create a Databricks pipeline
      • Deleting a pipeline
      • Getting pipelines
      • Uploading files
      • Enumerating files in a pipeline
      • Enumerating file deltas
    • 🧞‍♂️ Working with parsed files
  • Redact
    • Redacting text
      • Redact raw text
      • Bulk redact raw text
      • Redact JSON data
      • Redact XML data
      • Redact HTML data
      • Choosing tokenization or synthesis raw text
      • Using LLM synthesis
      • Recording API requests
      • Working with DataFrames
      • Working with large data sets
      • Replacing values in your redaction response
    • Redacting files
      • 📄 Files
        • Redact a file
        • Configure how to handle specific entity types
    • Redacting audio
      • Redact audio files
      • Generate redacted audio
      • Additional Remarks
    • Working with datasets
      • 📁 Datasets
        • Creating a dataset
        • Retrieving an existing dataset
        • Editing a dataset
        • Uploading files to a dataset
        • Deleting a file from a dataset
        • Viewing the list of files in a dataset
        • Downloading a redacted dataset file
        • Viewing the PII information for a dataset
    • Conversations stored in JSON
      • Conversation data stored in JSON
    • CSV helper with examples
      • Processing data in CSV files
  • 📖 Redact API documentation
    • TextualNer class
      • TextualNer
        • TextualNer.create_dataset()
        • TextualNer.delete_dataset()
        • TextualNer.download_redacted_file()
        • TextualNer.get_all_datasets()
        • TextualNer.get_audio_transcription()
        • TextualNer.get_dataset()
        • TextualNer.get_files()
        • TextualNer.llm_synthesis()
        • TextualNer.redact()
        • TextualNer.redact_audio()
        • TextualNer.redact_audio_file()
        • TextualNer.redact_bulk()
        • TextualNer.redact_html()
        • TextualNer.redact_json()
        • TextualNer.redact_xml()
        • TextualNer.send_redact_bulk_request()
        • TextualNer.send_redact_request()
        • TextualNer.start_file_redaction()
        • TextualNer.unredact()
        • TextualNer.unredact_bulk()
      • RecordApiRequestOptions
    • Dataset class
      • Dataset
        • Dataset.add_file()
        • Dataset.delete_file()
        • Dataset.describe()
        • Dataset.edit()
        • Dataset.fetch_all_df()
        • Dataset.fetch_all_json()
        • Dataset.files
        • Dataset.get_failed_files()
        • Dataset.get_processed_files()
        • Dataset.get_queued_files()
        • Dataset.get_running_files()
        • Dataset.pii_info
    • DatasetFile class
      • DatasetFile
        • DatasetFile.describe()
        • DatasetFile.download()
    • Redaction response
      • RedactionResponse
      • Replacement
    • Helper classes
      • ReplaceTextHelper
      • JsonConversationHelper
        • JsonConversationHelper.redact()
  • 📖 Parse API documentation
    • TextualParse class
      • TextualParse
        • TextualParse.create_azure_pipeline()
        • TextualParse.create_databricks_pipeline()
        • TextualParse.create_local_pipeline()
        • TextualParse.create_s3_pipeline()
        • TextualParse.delete_pipeline()
        • TextualParse.get_pipeline_by_id()
        • TextualParse.get_pipelines()
        • TextualParse.parse_file()
        • TextualParse.parse_s3_file()
    • Pipeline class
      • Pipeline
        • Pipeline.describe()
        • Pipeline.enumerate_files()
        • Pipeline.get_delta()
        • Pipeline.get_runs()
        • Pipeline.run()
        • Pipeline.set_synthesize_files()
        • Pipeline.upload_file()
    • Local Pipeline class
      • LocalPipeline
        • LocalPipeline.add_file()
    • S3 Pipeline class
      • S3Pipeline
        • S3Pipeline.add_files()
        • S3Pipeline.add_prefixes()
        • S3Pipeline.set_output_location()
    • Azure Pipeline class
      • AzurePipeline
        • AzurePipeline.add_files()
        • AzurePipeline.add_prefixes()
        • AzurePipeline.set_output_location()
    • File enumerators
      • PipelineFileEnumerator
        • PipelineFileEnumerator.next()
      • FileParseResultsDiffEnumerator
        • FileParseResultsDiffEnumerator.next()
    • Pipeline file results
      • FileParseResult
        • FileParseResult.describe()
        • FileParseResult.download_results()
        • FileParseResult.get_all_entities()
        • FileParseResult.get_chunks()
        • FileParseResult.get_entities()
        • FileParseResult.get_json()
        • FileParseResult.get_markdown()
        • FileParseResult.get_tables()
        • FileParseResult.is_sensitive()
      • FileParseDiffAction
        • FileParseDiffAction.Added
        • FileParseDiffAction.Deleted
        • FileParseDiffAction.Modified
        • FileParseDiffAction.NonModified
      • FileParseResultsDiff
        • FileParseResultsDiff.deconstruct()
        • FileParseResultsDiff.describe()
Tonic Textual
  • Search

© Copyright 2025, Tonic AI.