> ## Documentation Index
> Fetch the complete documentation index at: https://io-migration.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

> The  API on R2R enables developers to build powerful AI systems that . It integrates the strengths of semantic search, knowledge graphs, and prompt-based generation for advanced question answering and intelligent assistants.

## What Is RAG on R2R?

* **Retrieval + Generation Workflow:** RAG operates in two phases:

  * **Retrieve** relevant document chunks via semantic search or knowledge graph lookup.
  * **Generate** coherent and contextually accurate responses using those retrieved chunks and your customized prompts.

* **Why It Matters:** By tapping into real, structured, or unstructured content, RAG systems produce answers grounded in facts, avoiding hallucinations and improving trustworthiness.

## Core Components

| Component | Description |
| - | - |
| **Documents & Chunks** | Ingested files or text are segmented into **Chunks**—the basis for retrieval. |
| **Indices** | Vector indices enable fast similarity search over chunk embeddings. |
| **Graphs** | Knowledge graph extracts relationships and entities, enabling intelligent navigation of concepts. |
| **Prompts** | Prompt templates shape the generation step, with type-safe inputs and version control. |
| **System Endpoints** | Provide health checks, diagnostics, and monitoring for your RAG pipeline. |

## Getting Started

To get started with the R2R API, you’ll need to:

* [Install R2R](https://github.com/SciPhi-AI/R2R) in your environment
* Run the server with `python -m r2r.serve`, or customize your FastAPI for production settings.

For detailed installation and setup instructions, please refer to R2R [Installation Guide](https://r2r-docs.sciphi.ai/self-hosting/installation/overview).

## Authentication

### API keys

IO Intelligence APIs authenticate requests using API keys. You can [generate API keys from your user](https://ai.io.net/ai/api-keys) account:

> [!WARNING]
>
> Always treat your API key as a secret! Do not share it or expose it in client-side code (e.g., browsers or mobile apps). Instead, store it securely in an environment variable or a key management service on your backend server.

Include the API key in an `Authorization` HTTP header for all API requests:

```
Authorization: Bearer \$IOINTELLIGENCE_API_KEY
```

## Examples for RAG Workflows

### Step 1: Search for relevant chunks (Retrieval)

```curl curl theme={null}
curl -X POST https://api.intelligence.io.solutions/api/r2r/v3/retrieval/search /
  -H "Authorization: Bearer \$IOINTELLIGENCE_API_KEY" /
  -H "Content-Type: application/json" /
  -d '{
    "query": "What is Retrieval-Augmented Generation?",
    "top_k": 5
}'
```

### Step 2: Generate a response using RAG

Assuming you’ve retrieved relevant chunks and want to pass them as context:

```curl curl theme={null}
curl -X POST https://api.intelligence.io.solutions/api/r2r/v3/rag/generate /
  -H "Authorization: Bearer \$IOINTELLIGENCE_API_KEY" /
  -H "Content-Type: application/json" /
  -d '{
    "prompt_name": "default_rag",
    "inputs": {
      "query": "What is Retrieval-Augmented Generation?",
      "context": "Chunk 1 text/nChunk 2 text/nChunk 3 text" //it's just example chunk text
    }
}'
```

## Token Quotas & Usage

Each account has daily usage limits based on model and request volume. Check the [IO Intelligence API Quotas](https://io-migration.mintlify.site/reference/get-started-with-io-intelligence-api.md#quotas) for up-to-date information.

## Next Steps

Explore the API reference for detailed guides:

* **[Retrieval](https://io-migration.mintlify.site/reference/retrieval.md)** – perform semantic and hybrid search across ingested data
* **[Documents](https://io-migration.mintlify.site/reference/documents.md)** – management and metadata
* **[Graphs](https://io-migration.mintlify.site/reference/graphs.md)** – entity extraction and knowledge graphs
* **[Indices](https://io-migration.mintlify.site/reference/indices.md)** – create and configure embeddings
* **[Chunks](https://io-migration.mintlify.site/reference/chunks.md)** – ingest, list, search
* **[Users](https://io-migration.mintlify.site/reference/users.md)** – manage API users, authentication, and access control
* **[Collections](https://io-migration.mintlify.site/reference/collections.md)** – group related documents and control indexing scope
* **[Conversations](https://io-migration.mintlify.site/reference/conversations.md)** – manage chat sessions, history, and context retention
* **[Prompts](https://io-migration.mintlify.site/reference/prompts.md)** – template definition and versioning
* **[System](https://io-migration.mintlify.site/reference/system.md)** – health and diagnostics


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.