Build RAG Chatbot with Llamaindex, HNSWlib, Amazon Titan Text G1, and voyage-3

Introduction to RAG

Retrieval-Augmented Generation (RAG) is a game-changer for GenAI applications, especially in conversational AI. It combines the power of pre-trained large language models (LLMs) like OpenAI’s GPT with external knowledge sources stored in vector databases such as Milvus and Zilliz Cloud, allowing for more accurate, contextually relevant, and up-to-date response generation. A RAG pipeline usually consists of four basic components: a vector database, an embedding model, an LLM, and a framework.

Key Components We'll Use for This RAG Chatbot

This tutorial shows you how to build a simple RAG chatbot in Python using the following components:

Llamaindex: a data framework that connects large language models (LLMs) with various data sources, enabling efficient retrieval-augmented generation (RAG). It helps structure, index, and query private or external data, optimizing LLM applications for search, chatbots, and analytics.
HNSWlib: a high-performance C++ and Python library for approximate nearest neighbor (ANN) search using the Hierarchical Navigable Small World (HNSW) algorithm. It provides fast, scalable, and efficient similarity search in high-dimensional spaces, making it ideal for vector databases and AI applications.
Amazon Titan Text G1: Amazon Titan Text G1 is a powerful language model designed for efficient text generation and understanding. It excels in handling large-scale text processing tasks with high accuracy and speed, making it ideal for content creation, summarization, and chatbots in enterprise applications.
Voyage-3: Designed for AI-powered navigation and journey planning, Voyage-3 optimizes route efficiency while providing real-time traffic updates and data insights. Its strengths lie in predictive analysis and adaptive learning, making it ideal for logistics, delivery services, and travel apps that demand reliable and intelligent navigation solutions.

By the end of this tutorial, you’ll have a functional chatbot capable of answering questions based on a custom knowledge base.

Note: Since we may use proprietary models in our tutorials, make sure you have the required API key beforehand.

Step 1: Install and Set Up Llamaindex

pip install llama-index

Step 2: Install and Set Up Amazon Titan Text G1

%pip install llama-index-llms-bedrock

from llama_index.llms.bedrock import Bedrock

llm = Bedrock(model="amazon.titan-text-express-v1", profile_name=profile_name)

Step 3: Install and Set Up voyage-3

%pip install llama-index-embeddings-voyageai

from llama_index.embeddings.voyageai import VoyageEmbedding

embed_model = VoyageEmbedding(
    voyage_api_key="",
    model_name="voyage-3",
)

Step 4: Install and Set Up HNSWlib

%pip install llama-index-vector-stores-hnswlib

from llama_index.vector_stores.hnswlib import HnswlibVectorStore
from llama_index.core import (
    VectorStoreIndex,
    StorageContext,
    SimpleDirectoryReader,
)

vector_store = HnswlibVectorStore.from_params(
    space="ip",
    dimension=embed_model._model.get_sentence_embedding_dimension(),
    max_elements=1000,
)

Step 5: Build a RAG Chatbot

Now that you’ve set up all components, let’s start to build a simple chatbot. We’ll use the Milvus introduction doc as a private knowledge base. You can replace it with your own dataset to customize your RAG chatbot.

import requests

from llama_index.core import SimpleDirectoryReader

# load documents
url = 'https://raw.githubusercontent.com/milvus-io/milvus-docs/refs/heads/v2.5.x/site/en/about/overview.md'
example_file = 'example_file.md'  # You can replace it with your own file paths.
response = requests.get(url)
with open(example_file, 'wb') as f:
    f.write(response.content)
documents = SimpleDirectoryReader(
    input_files=[example_file]
).load_data()

print("Document ID:", documents[0].doc_id)

storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(
    documents, storage_context=storage_context, embed_model=embed_model
)

query_engine = index.as_query_engine(llm=llm)
res = query_engine.query("What is Milvus?")  # You can replace it with your own question.
print(res)

Example output

Milvus is a high-performance, highly scalable vector database designed to operate efficiently across various environments, from personal laptops to large-scale distributed systems. It is available as both open-source software and a cloud service. Milvus excels in managing unstructured data by converting it into numerical vectors through embeddings, which facilitates fast and scalable searches and analytics. The database supports a wide range of data types and offers robust data modeling capabilities, allowing users to organize their data effectively. Additionally, Milvus provides multiple deployment options, including a lightweight version for quick prototyping and a distributed version for handling massive data scales.

Optimization Tips

As you build your RAG system, optimization is key to ensuring peak performance and efficiency. While setting up the components is an essential first step, fine-tuning each one will help you create a solution that works even better and scales seamlessly. In this section, we’ll share some practical tips for optimizing all these components, giving you the edge to build smarter, faster, and more responsive RAG applications.

LlamaIndex optimization tips

To optimize LlamaIndex for a Retrieval-Augmented Generation (RAG) setup, structure your data efficiently using hierarchical indices like tree-based or keyword-table indices for faster retrieval. Use embeddings that align with your use case to improve search relevance. Fine-tune chunk sizes to balance context length and retrieval precision. Enable caching for frequently accessed queries to enhance performance. Optimize metadata filtering to reduce unnecessary search space and improve speed. If using vector databases, ensure indexing strategies align with your query patterns. Implement async processing to handle large-scale document ingestion efficiently. Regularly monitor query performance and adjust indexing parameters as needed for optimal results.

HNSWlib optimization tips

To optimize HNSWlib for a Retrieval-Augmented Generation (RAG) setup, fine-tune the M parameter (number of connections per node) to balance accuracy and memory usage—higher values improve recall but increase indexing time. Adjust ef_construction (search depth during indexing) to enhance retrieval quality. During queries, set ef_search dynamically based on latency vs. accuracy trade-offs. Use multi-threading for faster indexing and querying. Ensure vectors are properly normalized for consistent similarity comparisons. If working with large datasets, periodically rebuild the index to maintain efficiency. Store the index on disk and load it efficiently for persistence in production environments. Monitor query performance and tweak parameters to achieve optimal speed-recall balance.

Amazon Titan Text G1 optimization tips

To optimize Amazon Titan Text G1 in a RAG setup, ensure your retrieval pipeline delivers precise and well-structured context to leverage its advanced text generation capabilities. Use embedding models optimized for semantic search to retrieve the most relevant documents efficiently. Fine-tune document chunking to provide enough context without exceeding token limits. Experiment with prompt engineering techniques to guide the model toward accurate and relevant responses. Utilize caching for frequently asked queries to reduce API calls and improve latency. Adjust temperature and top-k sampling settings to balance response creativity and consistency. Monitor inference times and optimize query batching to enhance throughput while maintaining cost efficiency.

voyage-3 optimization tips

voyage-3 is a versatile model suitable for balanced performance in RAG systems, making efficient retrieval strategies crucial for maintaining low latency and high accuracy. Improve retrieval by leveraging embedding-based similarity search with reranking to ensure relevant context is included. Structure prompts with clear context separation and concise instructions to maximize response accuracy. Set temperature between 0.1 and 0.3 for controlled output while tuning top-k and top-p for flexibility. Implement response caching for frequently queried data to minimize redundant processing and API calls. Utilize parallel processing and request batching to optimize resource efficiency. For multi-model deployments, assign voyage-3 to mid-tier complexity tasks while using larger models for deeper analysis and smaller models for real-time, low-latency queries.

By implementing these tips across your components, you'll be able to enhance the performance and functionality of your RAG system, ensuring it’s optimized for both speed and accuracy. Keep testing, iterating, and refining your setup to stay ahead in the ever-evolving world of AI development.

RAG Cost Calculator: A Free Tool to Calculate Your Cost in Seconds

Estimating the cost of a Retrieval-Augmented Generation (RAG) pipeline involves analyzing expenses across vector storage, compute resources, and API usage. Key cost drivers include vector database queries, embedding generation, and LLM inference.

RAG Cost Calculator is a free tool that quickly estimates the cost of building a RAG pipeline, including chunking, embedding, vector storage/search, and LLM generation. It also helps you identify cost-saving opportunities and achieve up to 10x cost reduction on vector databases with the serverless option.

Calculate your RAG cost now.

Calculate your RAG cost

What Have You Learned?

Congratulations on making it through this tutorial! You’ve just unlocked the exciting potential of building a sophisticated RAG (Retrieval-Augmented Generation) system by integrating four powerful components: the LlamaIndex framework, HNSWlib for efficient vector storage and retrieval, Amazon Titan Text G1 as your capable language model, and a keenly crafted embedding model. Throughout this journey, you’ve learned not only how to assemble these components, but also how to leverage their individual capabilities to orchestrate an intelligent, responsive pipeline that enhances information retrieval and generation. From using LlamaIndex to seamlessly manage and query your data to mastering the intricacies of HNSWlib for lightning-fast searches, you’ve equipped yourself with tools to tackle real-world challenges with confidence!

But wait—there’s more! This tutorial also shared practical optimization tips to streamline your RAG system and included a free cost calculator to help you estimate and manage expenses efficiently. Talk about starting on the right foot! By combining these insights, you're now empowered to create a dynamic RAG application that not only meets your needs but also opens the door to endless possibilities. So, what are you waiting for? Dive in, start building, optimizing, and innovating your very own RAG applications. Your journey towards creating cutting-edge solutions has just begun—let your imagination guide you!

Further Resources

🌟 In addition to this RAG tutorial, unleash your full potential with these incredible resources to level up your RAG skills.

How to Build a Multimodal RAG | Documentation
How to Enhance the Performance of Your RAG Pipeline
Graph RAG with Milvus | Documentation
How to Evaluate RAG Applications - Zilliz Learn
Generative AI Resource Hub | Zilliz

We'd Love to Hear What You Think!

We’d love to hear your thoughts! 🌟 Leave your questions or comments below or join our vibrant Milvus Discord community to share your experiences, ask questions, or connect with thousands of AI enthusiasts. Your journey matters to us!

If you like this tutorial, show your support by giving our Milvus GitHub repo a star ⭐—it means the world to us and inspires us to keep creating! 💖