> ## Documentation Index
> Fetch the complete documentation index at: https://docs.nvisy.com/llms.txt
> Use this file to discover all available pages before exploring further.

# FAQ

> Frequently asked questions about Nvisy

## General

<AccordionGroup>
  <Accordion title="What is Nvisy?">
    Nvisy is an open-source multimodal redaction platform. It detects and removes sensitive information across documents, images, and audio, combining deterministic patterns, NER, computer vision, and LLM-driven classification into auditable, policy-driven pipelines.
  </Accordion>

  <Accordion title="Is Nvisy open-source?">
    Yes, Nvisy is open-source. You can find our code on [GitHub](https://github.com/nvisycom) and contribute to the project.
  </Accordion>

  <Accordion title="What types of sensitive information can Nvisy detect?">
    Nvisy can detect:

    * **PII**: Names, addresses, SSN, phone numbers, email addresses
    * **PHI**: Medical records, diagnoses, prescriptions, patient data
    * **Financial**: Credit card numbers, bank accounts, tax IDs
    * **Custom patterns**: Your organization-specific sensitive data
  </Accordion>

  <Accordion title="How accurate is the detection?">
    Each detection carries a calibrated confidence score and a provenance chain showing how it was recognized. Runs stop after analysis so findings can be reviewed before anything is modified — detection informs a decision rather than replacing one.
  </Accordion>

  <Accordion title="What file formats are supported?">
    Documents (`pdf`, `docx`, `rtf`, `txt`, `log`, `html`, `xml`, `json`), tabular data (`csv`, `xlsx`), images (`png`, `jpg`, `tiff`), and audio (`wav`).

    [View complete list →](/features/supported-formats)
  </Accordion>
</AccordionGroup>

## Pricing & Plans

<AccordionGroup>
  <Accordion title="How much does Nvisy cost?">
    Nvisy is in private beta. [Contact us](mailto:support@nvisy.com) to discuss pricing and access.
  </Accordion>

  <Accordion title="Can I use Nvisy on-premises?">
    Yes. Nvisy is open-source and can be self-hosted, which is the right choice for strict data-residency requirements.

    [On-premise deployment →](/deployment/on-premise/requirements)
  </Accordion>
</AccordionGroup>

## Technical

<AccordionGroup>
  <Accordion title="Do you have an API?">
    Yes. Nvisy provides a REST API and official SDKs for TypeScript, Python, and Rust.

    [View API documentation →](/api-reference/introduction)
  </Accordion>

  <Accordion title="How long are documents stored?">
    There is no fixed default. Retention is set per workspace and can be overridden per pipeline.

    A workspace sets retention for three scopes — original documents, redacted documents, and audit logs. Each is `forever`, `zeroDays` (delete as soon as processing finishes), or a fixed number of days.

    A pipeline may override retention for the scopes it produces: redacted documents and audit logs. Original documents are ingested rather than produced, so they always follow the workspace baseline.

    [Audit trails →](/features/audit-trails)
  </Accordion>

  <Accordion title="Can I integrate Nvisy with my existing tools?">
    Workspaces connect to object storage (`s3`, `azure`, `gcs`) for syncing files in and out, and to LLM providers (`openai`, `anthropic`, `ollama`) for model-driven detection. Webhooks deliver events as runs and syncs progress.

    [View all integrations →](/features/integrations)
  </Accordion>

  <Accordion title="What programming languages do you support?">
    Official SDKs:

    * **TypeScript/JavaScript** — full API coverage
    * **Python** — HTTP client; typed service methods are in progress
    * **Rust** — HTTP client; typed service methods are in progress

    You can also use the REST API with any language.
  </Accordion>

  <Accordion title="Does Nvisy work with scanned documents?">
    Yes! Nvisy includes OCR (Optical Character Recognition) to extract and redact text from scanned documents and images.
  </Accordion>
</AccordionGroup>

## Security

<AccordionGroup>
  <Accordion title="What controls does Nvisy provide?">
    * Workspace isolation as the tenancy and access-control boundary
    * Per-workspace retention, overridable per pipeline
    * A reviewable detection phase — nothing is modified until redaction is applied
    * Verifiable audit trails with per-entity provenance
    * Self-hosting, so data and inference stay inside your own infrastructure
  </Accordion>

  <Accordion title="Where is data stored?">
    Self-hosting puts data location under your control. Nvisy is open-source, so the platform itself runs inside your own infrastructure.

    Where documents actually reside still depends on how you configure it. A workspace can sync files to `s3`, `azure`, or `gcs`, and detection can call a hosted LLM provider — either will send content outside your network. Documents stay entirely within your infrastructure only when every configured storage target and integration is local or private, for example local storage paired with an `ollama` connection so inference runs in-network too.

    [On-premise deployment →](/deployment/on-premise/requirements)
  </Accordion>

  <Accordion title="Do you have access to my documents?">
    With a self-hosted deployment, we have no access to your documents. They stay within the infrastructure you point Nvisy at — keep storage and model connections local or private if you need them to stay entirely in-network. Retention is yours to set per workspace and override per pipeline, including `zeroDays` to delete data as soon as processing finishes.
  </Accordion>

  <Accordion title="Can I audit what was redacted?">
    Yes! Every redaction includes a complete audit trail showing:

    * Who initiated the redaction
    * What was detected
    * What was redacted
    * When it occurred
    * Confidence scores

    [Learn about audit trails →](/features/audit-trails)
  </Accordion>
</AccordionGroup>

## Getting Started

<AccordionGroup>
  <Accordion title="How do I get started?">
    1. Sign up at [nvisy.com](https://nvisy.com), or self-host
    2. Create a workspace and issue an API token
    3. Install an SDK or call the REST API
    4. Upload a file, run detection, review, then redact

    [View quickstart guide →](/quickstart)
  </Accordion>

  <Accordion title="Do I need technical knowledge to use Nvisy?">
    For the API and SDKs, yes. A web interface is also available for reviewing detections and approving redactions without writing code.
  </Accordion>

  <Accordion title="Can I test Nvisy before committing?">
    Yes. Nvisy is open-source, so you can self-host and evaluate the full platform locally. For cloud access during private beta, [contact us](mailto:support@nvisy.com).
  </Accordion>

  <Accordion title="What if I need help?">
    We offer:

    * Documentation and guides
    * Email support ([support@nvisy.com](mailto:support@nvisy.com))
    * GitHub issues
  </Accordion>
</AccordionGroup>

## Features

<AccordionGroup>
  <Accordion title="Can I customize what gets redacted?">
    Yes. A policy targets labels from the deployment's taxonomy and names the operator to apply to each, per modality — for example `blackbox`, `blur`, or `pixelate` for images, and `mask`, `replace`, `pseudonymize`, or `encrypt` for text. Reviewers can override any individual detection before redaction is applied.

    [Redaction workflow →](/features/redaction-workflow)
  </Accordion>

  <Accordion title="Can I process documents in bulk?">
    Yes! Nvisy supports batch processing with parallel execution for faster processing of multiple documents.
  </Accordion>

  <Accordion title="Does redaction preserve document formatting?">
    Yes, Nvisy preserves the original document structure, fonts, images, and layout while redacting sensitive information.
  </Accordion>

  <Accordion title="Can I get notifications when redaction is complete?">
    Yes. Register a webhook to receive events as runs and syncs progress, or subscribe to a run's server-sent events stream for live status.

    [Learn about webhooks →](/api-reference/introduction#webhooks)
  </Accordion>

  <Accordion title="What happens if detection misses something?">
    You can:

    1. Adjust the confidence threshold
    2. Add custom patterns for organization-specific data
    3. Review detections before finalizing
    4. Manually mark additional items for redaction
  </Accordion>

  <Accordion title="Can I redact specific types of information only?">
    Yes. A policy targets specific labels from the deployment's taxonomy and names the operator to apply to each. Query `GET /catalog/labels/` to see what a deployment supports, then reference those labels from your policy.

    Because `keep` is an operator, a policy can also record that something was recognized and deliberately left intact.
  </Accordion>
</AccordionGroup>

## Deployment

<AccordionGroup>
  <Accordion title="What are my deployment options?">
    * **Cloud**: Fully managed, auto-scaling
    * **On-premises**: Complete control in your infrastructure
    * **Hybrid**: Combine cloud and on-premises

    [Compare deployment options →](/deployment/cloud/getting-started)
  </Accordion>

  <Accordion title="What are the system requirements for on-premises?">
    Illustrative production starting point:

    * 16+ CPU cores
    * 32 GB+ RAM
    * 500 GB+ NVMe SSD
    * 10 Gbps network
    * Docker or Kubernetes

    These are preliminary guidance rather than benchmarked minimums — size from a trial run with your own documents.

    [View complete requirements →](/deployment/on-premise/requirements)
  </Accordion>

  <Accordion title="Can I deploy Nvisy in my private cloud?">
    Yes! Nvisy can be deployed on AWS, Azure, Google Cloud, or any Kubernetes-compatible environment.
  </Accordion>

  <Accordion title="Do you offer professional services for deployment?">
    Yes, enterprise customers can request professional services for deployment, training, and custom integrations.
  </Accordion>
</AccordionGroup>

## Troubleshooting

<AccordionGroup>
  <Accordion title="Why is my API key not working?">
    Common causes:

    * API key not set in environment variables
    * Using test key in production (or vice versa)
    * API key expired or revoked
    * Extra spaces or characters in the key

    [Troubleshoot authentication →](/deployment/cloud/authentication)
  </Accordion>

  <Accordion title="Why is redaction taking so long?">
    Processing time depends on:

    * Document size (pages)
    * File format (PDFs are fastest)
    * Detection types enabled
    * Current system load

    Typical documents finish in under 10 seconds, though this is not a committed figure — large documents, OCR-heavy scans, and busy instances take longer.
  </Accordion>

  <Accordion title="Why am I getting rate limited?">
    Retry with exponential backoff. In the TypeScript SDK, `NvisyApiError.isRetryable()` tells you whether an error is worth retrying.
  </Accordion>

  <Accordion title="My file upload is failing">
    Check:

    * File size (max 100 MB by default)
    * File format is supported
    * File is not corrupted
    * API key has upload permissions
  </Accordion>
</AccordionGroup>

## Still Have Questions?

<CardGroup cols={2}>
  <Card title="Documentation" icon="book" href="/quickstart">
    Read our comprehensive guides
  </Card>

  <Card title="GitHub" icon="github" href="https://github.com/nvisycom">
    Report issues or contribute
  </Card>

  <Card title="Email Support" icon="envelope" href="mailto:support@nvisy.com">
    Contact our support team
  </Card>

  <Card title="Sales" icon="phone" href="mailto:sales@nvisy.com">
    Talk to sales about enterprise needs
  </Card>
</CardGroup>