AutoRag Agent - PraisonAI

Automatically retrieve relevant context based on query analysis with AutoRagAgent.

Quick Start

Create AutoRagAgent

import { AutoRagAgent, RetrievalPolicy } from 'praisonai';

const autoRag = new AutoRagAgent({
  retrievalPolicy: RetrievalPolicy.AUTO,
  topK: 5,
  rerank: true
});

Check if Retrieval Needed

// Queries that trigger retrieval
autoRag.shouldRetrieve("What is machine learning?");  // true
autoRag.shouldRetrieve("Explain the document");       // true
autoRag.shouldRetrieve("Find information about AI");  // true

// Queries that don't trigger retrieval
autoRag.shouldRetrieve("Hi");                         // false
autoRag.shouldRetrieve("Thanks");                     // false

Retrieval Policies

import { RetrievalPolicy } from 'praisonai';

RetrievalPolicy.AUTO    // Smart detection based on query
RetrievalPolicy.ALWAYS  // Always retrieve context
RetrievalPolicy.NEVER   // Never retrieve context

Configuration

import { AutoRagAgent, AutoRagAgentConfig, RetrievalPolicy } from 'praisonai';

const config: AutoRagAgentConfig = {
  retrievalPolicy: RetrievalPolicy.AUTO,
  topK: 5,                    // Number of results to retrieve
  hybrid: false,              // Use hybrid search
  rerank: true,               // Rerank results
  includeCitations: true,     // Include citations in response
  citationsMode: 'append',    // 'append' | 'hidden' | 'none'
  maxContextTokens: 4000,     // Max tokens for context
  autoMinLength: 10           // Min query length for auto mode
};

const autoRag = new AutoRagAgent(config);

Configuration Options

Option	Type	Default	Description
`retrievalPolicy`	`RetrievalPolicy`	`AUTO`	When to retrieve context
`topK`	`number`	`5`	Number of results to retrieve
`hybrid`	`boolean`	`false`	Use hybrid (keyword + semantic) search
`rerank`	`boolean`	`false`	Rerank results for relevance
`includeCitations`	`boolean`	`true`	Include source citations
`citationsMode`	`string`	`'append'`	How to show citations
`maxContextTokens`	`number`	`4000`	Max context window
`autoMinLength`	`number`	`10`	Min query length for AUTO

Auto Keywords

Queries containing these keywords trigger retrieval in AUTO mode:

import { DEFAULT_AUTO_KEYWORDS } from 'praisonai';

// Default keywords that trigger retrieval
const keywords = [
  'what', 'how', 'why', 'when', 'where', 'who', 'which',
  'explain', 'describe', 'summarize', 'find', 'search',
  'tell me', 'show me', 'according to', 'based on',
  'cite', 'source', 'reference', 'document', 'paper'
];

Custom Keywords

const autoRag = new AutoRagAgent({
  retrievalPolicy: RetrievalPolicy.AUTO,
  autoKeywords: new Set([
    'what', 'how', 'explain',
    'my custom keyword',
    'another trigger'
  ])
});

Methods

shouldRetrieve

Check if a query should trigger retrieval:

const autoRag = new AutoRagAgent();

// Returns true for questions
autoRag.shouldRetrieve("What is the capital of France?");  // true

// Returns true for search queries
autoRag.shouldRetrieve("Find documents about AI");         // true

// Returns false for short queries
autoRag.shouldRetrieve("Hi");                              // false

// Returns false for non-question statements
autoRag.shouldRetrieve("Thanks for your help");            // false

getConfig

Get the current configuration:

const config = autoRag.getConfig();
console.log(config.topK);           // 5
console.log(config.retrievalPolicy); // 'auto'

Common Patterns

With Knowledge Base
With Agent

import { AutoRagAgent, RetrievalPolicy, Knowledge } from 'praisonai';

const knowledge = new Knowledge({
  sources: ['./docs'],
  embeddings: 'text-embedding-3-small'
});

const autoRag = new AutoRagAgent({
  retrievalPolicy: RetrievalPolicy.AUTO,
  topK: 5,
  rerank: true
});

async function answer(query: string) {
  if (autoRag.shouldRetrieve(query)) {
    const context = await knowledge.search(query, { topK: 5 });
    return generateWithContext(query, context);
  }
  return generateDirect(query);
}

import { Agent, AutoRagAgent, RetrievalPolicy } from 'praisonai';

const autoRag = new AutoRagAgent({
  retrievalPolicy: RetrievalPolicy.AUTO
});

const agent = new Agent({
  name: "RAG Assistant",
  instructions: "Answer questions using retrieved context"
});

async function chat(query: string) {
  const needsContext = autoRag.shouldRetrieve(query);
  
  if (needsContext) {
    // Add context to the query
    const context = await retrieveContext(query);
    return agent.start(`Context: ${context}\n\nQuestion: ${query}`);
  }
  
  return agent.start(query);
}

API Reference

AutoRagAgent

AutoRagAgent class reference

AutoRagAgentConfig

Configuration options

Best Practices

Use AUTO for general chatbots

AUTO mode balances retrieval costs with response quality for most use cases.

Use ALWAYS for document Q&A

When every query relates to documents, use ALWAYS to ensure context is included.

Enable reranking for accuracy

Reranking improves result relevance at a small latency cost.

Tune autoMinLength

Increase autoMinLength to avoid retrieval for very short queries.

RAG Agent

Full RAG implementation

Knowledge Base

Build knowledge bases

​Quick Start

​Retrieval Policies

​Configuration

​Configuration Options

​Auto Keywords

​Custom Keywords

​Methods

​shouldRetrieve

​getConfig

​Common Patterns

​API Reference