# Document Intelligence Service

The **Document Intelligence Services** in Krutrim Cloud offer a comprehensive suite of AI-powered tools for **document processing, information extraction, and data privacy**. These services enable businesses and developers to automate the reading, understanding, and transformation of documents at scale.

With capabilities such as **text extraction, entity recognition, key-value pair detection, document summarization, and PII masking**, you can turn unstructured documents into structured, actionable insights while ensuring sensitive information is protected.

### **How It Works**

The **Document Processing API** operates asynchronously for efficiency and scalability:

1. **Submit a Document** – Upload the file via the Document API.
2. **Receive a fileId** – A unique `fileId` is generated to track your request.
3. **Check Processing Status** – Use the Status API to verify if processing is complete.
4. **Retrieve Results** – Once processing finishes, download the processed output from the provided link.

This approach allows you to submit documents without waiting for real-time processing, making it ideal for high-volume workloads.

### **Available Services**

* **Extract Text** – Pull raw text content from documents, scanned files, and images.
* **Extract Information** – Identify and extract structured details, including:
  * **PII** (Personally Identifiable Information)
  * **NER** (Named Entity Recognition)
  * **Key-Value Pairs**
* **Document Summarization** – Generate concise summaries that preserve the key points of the original content.
* **PII Masking** – Mask or obfuscate sensitive personal information to ensure compliance with privacy regulations.

### **Authentication & Rate Limits**

* **API Keys** – Required for all API requests. API keys can be generated and managed in the [**KMS (Key Management System)**](https://docs.cloud.olakrutrim.com/~/revisions/R3YmuRbo1BQTbXR88xJJ/basics/key-management-system/model-api-keys).
* **Rate Limits** – Default limit of **20 requests per minute (RPM)** to ensure fair usage.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.cloud.olakrutrim.com/basics/ai-solutions/document-intelligence-service.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.