LlamaIndex Integration

Overview

LlamaIndex (formerly GPT Index) is a powerful data framework designed for building LLM applications with custom data sources. It provides the tools necessary to connect large language models to external data and build knowledge-enhanced applications.

Key Features

Data Connectors: Connect to various data sources including files, databases, and APIs
Indexing Strategies: Multiple indexing methods optimized for different retrieval patterns
Query Engines: Run natural language queries against your data
Agent Frameworks: Build sophisticated agents that can reason over your data
Multi-Modal Support: Process text, images, and other data types

Use Case

Building RAG (Retrieval-Augmented Generation) applications
Creating knowledge bases with natural language querying
Developing document Q&A systems with private data
Building semantic search applications

Setup Instructions

1. Set up a Python Environment:

Open your terminal or command prompt.
Create a new directory for your project and navigate to it
Create and activate a virtual environment

# Create virtual environment
python -m venv llamaindex-env

# Activate on macOS/Linux
source llamaindex-env/bin/activate

# Activate on Windows
llamaindex-env\Scripts\activate

2. Install Required Packages:

With your virtual environment activated, install the necessary packages

# Install the core LlamaIndex package
pip install llama-index

# Install the OpenAI-compatible integration
pip install llama-index-llms-openai-like

# Install additional dependencies for document processing
pip install llama-index-readers-file python-dotenv

3. Set up Environment Variables:

Create a new file named .env in your project directory
Open it in your text editor
Add your relaxAI API credentials:

API_KEY=<RELAX_API_KEY>
API_BASE=https://api.relax.ai/v1/

4. Create Configuration Module:

Create a new file named config.py in your project directory.
Add the following sample code to configure LlamaIndex with relaxAI:

import os
from llama_index.llms.openai_like import OpenAILike
from dotenv import load_dotenv

# Load environment variables
load_dotenv()

# Configure the LLM
def get_llm():
    return OpenAILike(
      model="Llama-4-Maverick-17B-128E",
      api_key=os.getenv("API_KEY"),
      api_base=os.getenv("API_BASE"),
      is_chat_model=True,
      temperature=0.7,
      max_tokens=500,
      api_version='v1'
    )

5. Create a Basic Query Script:

Create a new file named query_example.py
Add the following code to test your relaxAI integration:

from config import get_llm

# Get configured LLM
llm = get_llm()

# Test with a simple query
response = llm.complete("What is the capital of France?")
print(str(response))

6. Run the Test Script:

In your terminal, run the test script:

python query_example.py

Expected output:

The capital of France is Paris.

Code Example

from llama_index.llms.openai_like import OpenAILike

# Configure with relaxAI API
llm = OpenAILike(
    model="Llama-4-Maverick-17B-128E",
    api_key="RELAX_API_KEY",
    api_base="https://api.relax.ai/v1/"
)

# Use in your application
response = llm.complete("Hello World!")
print(str(response))

Advanced Usage

Here’s an example of using LlamaIndex with relaxAI for document retrieval:

from llama_index import VectorStoreIndex, SimpleDirectoryReader
from llama_index.llms.openai_like import OpenAILike

# Load documents
documents = SimpleDirectoryReader("./data").load_data()

# Configure LLM
llm = OpenAILike(
      model="Llama-4-Maverick-17B-128E",
      api_key="RELAX_API_KEY",
      api_base="https://api.relax.ai/v1/"
)

# Create index
index = VectorStoreIndex.from_documents(documents, llm=llm)

# Create query engine
query_engine = index.as_query_engine()

# Query your data
response = query_engine.query("What information is in these documents?")
print(str(response))