Build RAG Chatbot with Llamaindex, HNSWlib, OpenAI GPT-o1, and Cohere embed-multilingual-light-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-1: A foundational transformer-based language model designed for natural language understanding and generation. Strengths include coherent text generation, contextual comprehension, and adaptability to diverse NLP tasks. Ideal for text completion, basic conversational agents, and early-stage language research, serving as a precursor to more advanced models like GPT-3 and GPT-4.
Cohere embed-multilingual-light-v3.0: A compact multilingual embedding model designed to generate high-quality text representations across 100+ languages. It excels in efficient semantic understanding and retrieval, optimized for low-resource environments. Ideal for multilingual search, content moderation, and customer support applications requiring fast, accurate cross-lingual text analysis.

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-o1

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

from llama_index.llms.openai import OpenAI

llm = OpenAI(
    model="o1",
    # api_key="some key",  # uses OPENAI_API_KEY env var by default
)

Step 3: Install and Set Up Cohere embed-multilingual-light-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-light-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-01 optimization tips

To optimize OpenAI GPT-01 in a RAG setup, fine-tune prompts to include explicit instructions and structured context (e.g., “Answer using: [retrieved text]”). Limit response length with max_tokens to reduce verbosity and cost. Use a lower temperature (0.2–0.5) for factual accuracy. Preprocess retrieved documents to remove irrelevant content, ensuring inputs fit token limits. Cache frequent queries to minimize API calls. Experiment with chunking strategies for context injection and prioritize critical information at the prompt’s start or end. Monitor latency and adjust batch sizes for throughput efficiency.

Cohere embed-multilingual-light-v3.0 optimization tips

To optimize Cohere’s embed-multilingual-light-v3.0 in RAG, preprocess text by truncating or chunking inputs to 512 tokens for efficiency. Use batch inference to parallelize embedding generation, balancing batch size with latency and memory constraints. Normalize embeddings post-generation to improve cosine similarity accuracy. Leverage multilingual capabilities by ensuring consistent language tagging and avoiding mixed-language batches. Cache frequently accessed embeddings to reduce redundant computations. Fine-tune retrieval thresholds to balance precision and recall. Monitor model performance using metrics like retrieval hit rate and latency, and update document embeddings periodically to reflect data changes.

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 completing this tutorial! You’ve just embarked on an exciting journey into the world of Retrieval-Augmented Generation (RAG) systems. By integrating a powerful framework like LlamaIndex with a robust vector database such as HNSWlib, alongside the capabilities of the OpenAI GPT-01 model and the Cohere multilingual embedding model, you’ve unlocked a treasure trove of possibilities for building dynamic and intelligent applications. Throughout this tutorial, you learned how each component contributes uniquely—LlamaIndex for seamless data management, HNSWlib for efficient information retrieval, GPT-01 for human-like text generation, and the Cohere model for understanding multiple languages—ensuring that your RAG pipeline is not only effective but also versatile.

You were also provided with valuable optimization tips to enhance the performance of your system and could even explore a handy free RAG cost calculator to help you manage your project's budget effectively. Imagine the innovations you can create by harnessing these technologies! This knowledge positions you at the forefront of a transformative field, and there’s no limit to what you can achieve. So, roll up your sleeves and start creating, optimizing, and personalizing your RAG applications! Your journey toward innovation has just begun, and we can’t wait to see what amazing projects you’ll bring to life!

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! 💖