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

# Knowledge base and RAG overview

> Learn how knowledge bases enhance agent responses with contextual information using RAG

## What is a knowledge base?

A knowledge base in Iqra AI is a structured collection of documents that enables your agents to access and retrieve relevant information during conversations. Using Retrieval-Augmented Generation (RAG), agents can ground their responses in your organization's specific knowledge, reducing hallucinations and providing accurate, contextual answers.

<Note>
  Knowledge bases are particularly powerful for customer support, technical documentation, and domain-specific assistance where accurate information retrieval is critical.
</Note>

## How RAG works in Iqra AI

The RAG pipeline in Iqra AI follows a sophisticated multi-stage process:

<Steps>
  <Step title="Document ingestion">
    Documents are uploaded and processed through extractors that support multiple formats (PDF, text, and more). The system uses the Unstructured API for complex document parsing.
  </Step>

  <Step title="Text chunking">
    Documents are split into manageable chunks using configurable strategies:

    * **General chunking**: Splits text by delimiter with configurable overlap
    * **Parent-child chunking**: Creates hierarchical chunks for better context preservation
  </Step>

  <Step title="Embedding generation">
    Each chunk is converted into a vector embedding using your configured embedding provider (currently supports Google Gemini). Embeddings are cached to improve performance and reduce API costs.
  </Step>

  <Step title="Vector storage">
    Embeddings are stored in Milvus, a high-performance vector database designed for similarity search at scale. Collections are dynamically loaded and unloaded based on usage.
  </Step>

  <Step title="Retrieval">
    When an agent receives a query, the system:

    1. Generates an embedding for the query
    2. Searches the vector database for similar chunks
    3. Optionally searches keyword indices for exact matches
    4. Combines results using hybrid search strategies
  </Step>

  <Step title="Post-processing">
    Retrieved chunks undergo reranking and reordering to optimize relevance. The system supports:

    * Rerank models for improved precision
    * Lost-in-the-middle reordering to combat position bias
    * Score thresholding to filter low-quality results
  </Step>

  <Step title="Context injection">
    The final curated context is injected into the agent's prompt, enabling it to generate responses grounded in your knowledge base.
  </Step>
</Steps>

## Key features

### Multiple retrieval strategies

Iqra AI supports three retrieval approaches:

* **Vector search**: Semantic similarity using embeddings
* **Full-text search**: Keyword-based matching for exact terms
* **Hybrid search**: Combines both approaches for maximum recall

### Intelligent chunking

Choose between chunking strategies based on your content:

<CardGroup cols={2}>
  <Card title="General chunking" icon="scissors">
    Simple recursive text splitting with configurable chunk size and overlap. Ideal for uniformly structured content.
  </Card>

  <Card title="Parent-child chunking" icon="diagram-nested">
    Hierarchical chunking that retrieves small chunks but provides larger parent context. Better for complex documents.
  </Card>
</CardGroup>

### Embedding cache

The system automatically caches embeddings to:

* Reduce API calls to embedding providers
* Improve query latency
* Lower operational costs

<Tip>
  Embedding cache is particularly effective for common queries and can significantly reduce costs in high-traffic scenarios.
</Tip>

### Dynamic collection management

Milvus collections are automatically loaded into memory when needed and released after a configurable expiry period. This ensures optimal memory usage while maintaining fast query performance.

## Benefits for agents

When you link a knowledge base to an agent, it gains several capabilities:

1. **Accurate responses**: Answers are grounded in verified information rather than model training data
2. **Source attribution**: Each response can cite specific documents and chunks
3. **Domain expertise**: Agents can handle specialized topics without fine-tuning
4. **Up-to-date information**: Knowledge bases can be updated without retraining models
5. **Reduced hallucinations**: Retrieval constrains the agent to factual information

## Architecture overview

The knowledge base system is built on several key components:

* **KnowledgeBaseRetrievalManager**: Orchestrates the entire retrieval pipeline
* **RAGRetrievalService**: Handles vector and keyword search operations
* **RAGDataPostProcessor**: Applies reranking and filtering to results
* **EmbeddingProviderManager**: Manages embedding model integrations
* **MilvusKnowledgeBaseClient**: Interfaces with the Milvus vector database
* **RAGKeywordStore**: Provides full-text search capabilities

<Warning>
  Knowledge bases require proper infrastructure setup including MongoDB for metadata, Milvus for vectors, and Redis for caching. See the [setup guide](/knowledge/setup) for deployment details.
</Warning>

## Next steps

<CardGroup cols={2}>
  <Card title="Setup guide" icon="wrench" href="/knowledge/setup">
    Learn how to create and configure your first knowledge base
  </Card>

  <Card title="Embedding providers" icon="brain" href="/knowledge/embedding-providers">
    Configure embedding model integrations
  </Card>

  <Card title="Retrieval strategies" icon="magnifying-glass" href="/knowledge/retrieval">
    Optimize retrieval configuration for your use case
  </Card>
</CardGroup>