Retrieval-Augmented Generation

Overview

Retrieval-Augmented Generation (RAG) enables your agent to access and use large knowledge bases during conversations. Instead of loading entire documents into the context window, RAG retrieves only the most relevant information for each user query, allowing your agent to:

• Access much larger knowledge bases than would fit in a prompt
• Provide more accurate, knowledge-grounded responses
• Reduce hallucinations by referencing source material
• Scale knowledge without creating multiple specialized agents

RAG is ideal for agents that need to reference large documents, technical manuals, or extensive knowledge bases that would exceed the context window limits of traditional prompting. RAG adds on slight latency to the response time of your agent, around 250ms.

How RAG works

When RAG is enabled, your agent processes user queries through these steps:

1. Query processing: The user’s question is analyzed and reformulated for optimal retrieval.
2. Embedding generation: The processed query is converted into a vector embedding that represents the user’s question.
3. Retrieval: The system finds the most semantically similar content from your knowledge base.
4. Response generation: The agent generates a response using both the conversation context and the retrieved information.

This process ensures that relevant information to the user’s query is passed to the LLM to generate a factually correct answer.

Guide

Prerequisites

• An ElevenLabs account
• A configured ElevenLabs Conversational Agent
• At least one document added to your agent’s knowledge base

Enable RAG for your agent

Update via the dashboard

Update via the CLI

Update via the API

In your agent’s settings, navigate to the Knowledge Base section and toggle on the Use RAG option. Configure the embedding model, maximum document chunks, and maximum vector distance under the Advanced tab as needed.

Knowledge base indexing

Each document in your knowledge base needs to be indexed before it can be used with RAG. This process happens automatically when a document is added to an agent with RAG enabled.

Configure document usage modes (optional)

For each document in your knowledge base, you can choose how it’s used:

• Auto (default): The document is only retrieved when relevant to the query
• Prompt: The document is always included in the system prompt, regardless of relevance, but can also be retrieved by RAG

Test your RAG-enabled agent

After saving your configuration, test your agent by asking questions related to your knowledge base. The agent should now be able to retrieve and reference specific information from your documents.

Usage limits

To ensure fair resource allocation, ElevenLabs enforces limits on the total size of documents that can be indexed for RAG per workspace, based on subscription tier.

The limits are as follows:

Note:

• These limits apply to the total original file size of documents indexed for RAG, not the internal storage size of the RAG index itself (which can be significantly larger).
• Documents smaller than 500 bytes cannot be indexed for RAG and will automatically be used in the prompt instead.

API implementation

You can also implement RAG through the API:

1
from elevenlabs import ElevenLabs
2
import time
3
4
# Initialize the ElevenLabs client
5
elevenlabs = ElevenLabs(api_key="your-api-key")
6
7
# First, index a document for RAG
8
document_id = "your-document-id"
9
embedding_model = "e5_mistral_7b_instruct"
10
11
# Trigger RAG indexing
12
response = elevenlabs.conversational_ai.knowledge_base.document.compute_rag_index(
13
    documentation_id=document_id,
14
    model=embedding_model
15
)
16
17
# Check indexing status
18
while response.status not in ["SUCCEEDED", "FAILED"]:
19
    time.sleep(5)  # Wait 5 seconds before checking status again
20
    response = elevenlabs.conversational_ai.knowledge_base.document.compute_rag_index(
21
        documentation_id=document_id,
22
        model=embedding_model
23
    )
24
25
# Then update agent configuration to use RAG
26
agent_id = "agent_7101k5zvyjhmfg983brhmhkd98n6"
27
28
# Get the current agent configuration
29
agent_config = elevenlabs.conversational_ai.agents.get(agent_id=agent_id)
30
31
# Enable RAG in the agent configuration
32
agent_config.agent.prompt.rag = {
33
    "enabled": True,
34
    "embedding_model": "e5_mistral_7b_instruct",
35
    "max_documents_length": 10000
36
}
37
38
# Update document usage mode if needed
39
for i, doc in enumerate(agent_config.agent.prompt.knowledge_base):
40
    if doc.id == document_id:
41
        agent_config.agent.prompt.knowledge_base[i].usage_mode = "auto"
42
43
# Update the agent configuration
44
elevenlabs.conversational_ai.agents.update(
45
    agent_id=agent_id,
46
    conversation_config=agent_config.agent
47
)