Build RAG Chatbot with Llamaindex, HNSWlib, OpenAI GPT-4o mini, and Cohere embed-multilingual-v3.0

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.
OpenAI GPT-4o mini: A streamlined, cost-efficient variant of GPT-4, optimized for scalable AI applications. It balances high performance with reduced computational demands, offering fast response times and lower costs. Ideal for real-time chatbots, content generation, and integration into resource-constrained environments like mobile apps or high-volume transactional systems.
Cohere embed-multilingual-v3.0: A multilingual text embedding model designed to convert text in over 100 languages into high-dimensional vectors (1024 dimensions), excelling in semantic understanding and cross-lingual tasks. Its strengths include robust multilingual alignment and nuanced context capture, ideal for cross-language semantic search, multilingual document clustering, and enhancing NLP applications like recommendation systems in diverse linguistic environments.

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 OpenAI GPT-4o mini

%pip install llama-index llama-index-llms-openai

from llama_index.llms.openai import OpenAI

llm = OpenAI(
    model="gpt-4o-mini",
    # api_key="some key",  # uses OPENAI_API_KEY env var by default
)

Step 3: Install and Set Up Cohere embed-multilingual-v3.0

%pip install llama-index-embeddings-cohere

from llama_index.embeddings.cohere import CohereEmbedding

embed_model = CohereEmbedding(
    api_key=cohere_api_key,
    model_name="embed-multilingual-v3.0",
)

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.

OpenAI GPT-4o Mini optimization tips

To optimize the OpenAI GPT-4o Mini in a RAG setup, ensure concise input formatting by truncating or summarizing retrieved documents to stay within token limits. Use precise query phrasing to improve retrieval relevance, and filter redundant context to reduce noise. Leverage temperature and max_tokens parameters to balance creativity and focus. Cache frequent queries to minimize API calls and latency. Regularly validate outputs against ground truth to refine prompts and retrieval logic. Prioritize structured templates for consistent responses and implement error handling for rate limits or timeouts.

Cohere embed-multilingual-v3.0 optimization tips

To optimize Cohere embed-multilingual-v3.0 in RAG, preprocess text by normalizing casing, removing redundant whitespace, and filtering low-relevance content. Use appropriate chunk sizes (200–500 tokens) to balance context retention and embedding quality. Batch embedding requests to reduce latency. Leverage its multilingual strength by aligning input language with supported locales and applying language-specific stopword filtering. Fine-tune retrieval with hybrid search (semantic + keyword) and metadata filters. Regularly update embeddings to reflect new data and test retrieval accuracy using diverse multilingual queries to ensure robust cross-lingual performance.

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 an incredible journey we’ve just shared through the intricacies of building your very own Retrieval-Augmented Generation (RAG) system! You’ve unlocked the powerful synergy between a robust framework, a vector database, a cutting-edge large language model, and an innovative embedding model. By integrating LlamaIndex for easy data management, HNSWlib for swift and efficient nearest neighbor searches, OpenAI's GPT-4o mini for remarkable language generation, and Cohere’s embed-multilingual-v3.0 for seamless text embeddings, you now have the foundational knowledge to create dynamic, responsive applications that can truly transform the way we access and process information. It’s all about harnessing the unique capabilities of these tools to bolster your RAG pipeline and deliver smart, contextually aware responses.

As you delve deeper into this exciting domain, remember to explore the optimization tips shared in the tutorial; they’re gold nuggets that can enhance your applications even further! And don’t forget about the handy free RAG cost calculator we discussed; it’s a fantastic tool to help pinpoint your resource usage and keep your projects efficient. Now it’s your turn to roll up your sleeves: start building, optimizing, and innovating those RAG applications! The world is waiting for your creativity and solutions, so let your ideas take flight and bring your vision to life! You’ve got this—let the possibilities ahead energize 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! 💖