Build RAG Chatbot with Llamaindex, HNSWlib, Anthropic Claude 3.5 Sonnet, and voyage-3-large

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.
Anthropic Claude 3.5 Sonnet: An advanced AI model optimized for complex reasoning, multilingual generation, and data analysis. Combines high accuracy with efficiency, ideal for enterprise automation, technical workflows, and customer support requiring deep contextual understanding and scalable deployment across diverse applications.
Voyage-3-Large: This model is designed for generative tasks, offering enhanced creativity and contextual understanding. With robust training on diverse datasets, it excels in producing coherent narratives and dialogue, making it ideal for applications in storytelling, content creation, and interactive experiences where imaginative output is essential.

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 Anthropic Claude 3.5 Sonnet

%pip install llama-index-llms-anthropic

from llama_index.llms.anthropic import Anthropic

# To customize your API key, do this
# otherwise it will lookup ANTHROPIC_API_KEY from your env variable
# llm = Anthropic(api_key="")
llm = Anthropic(model="claude-3-5-sonnet-latest")

Step 3: Install and Set Up voyage-3-large

%pip install llama-index-embeddings-voyageai

from llama_index.embeddings.voyageai import VoyageEmbedding

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

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.

Anthropic Claude 3.5 Sonnet optimization tips

Optimize Claude 3.5 Sonnet in RAG systems by refining retrieval quality through semantic chunking (300-500 tokens) with 15% overlap for context continuity. Use structured prompts with clear instructions and document separators (e.g., ``` markers) to distinguish context from queries. Set temperature=0.3 for factual consistency and max_tokens=512 to balance depth/brevity. Implement query-aware context filtering to remove irrelevant passages before generation. Leverage system prompts to enforce output formats and safety guardrails. Monitor latency using streaming mode for real-time applications, and cache frequent query-answer pairs to reduce repeat computations.

voyage-3-large optimization tips

voyage-3-large provides enhanced reasoning capabilities, making it ideal for complex RAG tasks requiring deep contextual understanding. Optimize retrieval by implementing a multi-step ranking system that prioritizes highly relevant documents while filtering out lower-quality information. Use structured prompts with clearly delineated context and user queries to improve comprehension. Adjust temperature (0.1–0.3) and fine-tune top-k and top-p settings to maintain accuracy and prevent excessive variability. Take advantage of parallelized inference and request batching to improve processing efficiency. Leverage caching for high-frequency queries to reduce costs and latency. In multi-model setups, deploy voyage-3-large for intricate reasoning tasks while using smaller models for less complex queries to balance cost and performance effectively.

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 the tutorial! You’ve just taken an exciting leap into the world of Retrieval-Augmented Generation (RAG) systems by integrating a framework, vector database, LLM, and embedding model. Throughout this journey, you've learned how to synergize LlamaIndex with HNSWlib to create a powerful indexing system that enhances your data retrieval process. By leveraging Anthropic's Claude 3.5 Sonnet as your LLM, you can generate high-quality outputs that are contextually relevant thanks to the underlying semantic embeddings from the voyage-3-large model. Isn’t it thrilling to see how these components work together seamlessly to enhance both the precision and creativity of your applications?

But wait, there’s more! You’ve also picked up some invaluable optimization tips that will help you refine your RAG pipeline for maximum performance. The included free RAG cost calculator will not only assist you in budgeting your projects but also empower you to innovate without breaking the bank. Now it’s time to put your new skills into action. Imagine the possibilities as you start building, tweaking, and enhancing your own RAG applications! Dive into your projects with enthusiasm, explore new ideas, and don’t hesitate to push the boundaries of what you can achieve. Your journey into the realm of RAG has only just begun, and I can’t wait to see what amazing solutions you will create!

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! 💖