Build RAG Chatbot with Llamaindex, HNSWlib, Mixtral 8x7B, and OpenAI text-embedding-3-small

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.
Mixtral 8x7B: A sparse mixture-of-experts (MoE) model with eight 7B parameter networks, designed for efficient, high-performance NLP tasks. Excels in text generation, reasoning, and multilingual support while minimizing computational costs. Ideal for scalable enterprise applications, real-time chatbots, and multi-task environments requiring optimized resource utilization and versatile AI capabilities.
OpenAI text-embedding-3-small: Designed to generate dense vector representations of text, this model excels in efficiency and cost-effectiveness, optimized for speed and low resource usage. It delivers competitive performance in semantic similarity, retrieval, and clustering tasks, making it ideal for large-scale applications like search engines, recommendation systems, and text classification where balancing accuracy with computational cost is crucial.

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 Mixtral 8x7B

%pip install llama-index-llms-mistralai

from llama_index.llms.mistralai import MistralAI

llm = MistralAI(model="open-mixtral-8x7b")

Step 3: Install and Set Up OpenAI text-embedding-3-small

%pip install llama-index-embeddings-openai

from llama_index.embeddings.openai import OpenAIEmbedding

embed_model = OpenAIEmbedding(
    model="text-embedding-3-small",
)

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.

Mixtral 8x7B optimization tips

To optimize Mixtral 8x7B in RAG, prioritize efficient context retrieval by fine-tuning chunk size and overlap for balanced relevance and latency. Use sparse attention configurations to reduce computational overhead, and enable tensor parallelism to leverage its mixture-of-experts architecture. Quantize the model to 4-bit precision (e.g., via GPTQ) for faster inference with minimal accuracy loss. Pre-filter retrieved documents to remove noise, and cache frequent query embeddings. Adjust temperature (0.2-0.5) and max tokens to balance creativity and focus. Profile expert routing to ensure balanced workload distribution across GPU resources.

OpenAI text-embedding-3-small optimization tips

Optimize input text by truncating or chunking to stay within the 8191-token limit while preserving semantic context. Normalize embeddings to unit vectors to improve cosine similarity accuracy. Batch embedding requests to reduce API calls and latency. Experiment with dimensionality reduction (e.g., 256-dim) to balance performance and storage costs. Preprocess text by removing redundant or noisy content and standardizing formats (lowercase, trimming whitespace). Cache frequent or static embeddings to avoid redundant computations. Monitor retrieval quality via metrics like recall@k and adjust chunking strategies or hybrid retrieval methods if needed. Fine-tune temperature and top-k parameters during generation to align with embedding outputs.

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?

Wow, what a journey you’ve been on in this tutorial! You’ve learned how to integrate a framework like LlamaIndex with a vector database such as HNSWlib, and how those work alongside a powerful LLM like Mixtral 8x7B and an embedding model like OpenAI's text-embedding-3-small. We’ve walked through the step-by-step process of building a Retrieval-Augmented Generation (RAG) system, where each component plays a crucial role in creating a pipeline that’s not only efficient but also capable of handling complex queries with clarity. From efficiently storing and retrieving data in the vector database to generating dynamic and contextually relevant responses using the LLM, every piece fits perfectly together. Along the way, we shared fantastic optimization tips to enhance your workflow, plus access to a free RAG cost calculator to keep your project on track!

Now that you’ve grasped the foundational concepts and practical applications, the world is your oyster! Imagine the innovative solutions you could build with this knowledge. Whether you want to create highly personalized chatbots, powerful search engines, or even sophisticated content generators, the possibilities are endless. Don’t hesitate to dive into your own projects, play with the configurations, and explore new features. With your newfound skills, you have the potential to transform ideas into reality. So jump in, start building, optimizing, and most importantly, have fun innovating your own RAG applications! The sky is the limit!

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! 💖