Build RAG Chatbot with Llamaindex, HNSWlib, DeepSeek V3, and Ollama bge-m3

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.
DeepSeek-V3: DeepSeek-V3 is a cutting-edge, open-weight large language model (LLM) with 685 billion parameters, excelling in code generation, mathematical reasoning, and long-context understanding (up to 128K tokens). It adopts the MIT license, enabling free modification, distribution, and commercial use.
Ollama BGE-M3: A multilingual embedding model optimized for semantic understanding, retrieval, and clustering. Strengths include high accuracy across 100+ languages, robust performance in dense retrieval tasks, and scalability. Ideal for enterprise search systems, cross-lingual applications, and AI-driven knowledge management requiring precise semantic 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 DeepSeek V3

%pip install llama-index-llms-deepseek

from llama_index.llms.deepseek import DeepSeek

# you can also set DEEPSEEK_API_KEY in your environment variables
llm = DeepSeek(model="deepseek-chat", api_key="you_api_key")

# You might also want to set deepseek as your default llm
# from llama_index.core import Settings
# Settings.llm = llm

Step 3: Install and Set Up Ollama bge-m3

%pip install llama-index-embeddings-ollama

from llama_index.embeddings.ollama import OllamaEmbedding

embed_model = OllamaEmbedding(
    model_name="bge-m3",
)

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.

DeepSeek V3 optimization tips

DeepSeek V3 benefits from optimized retrieval and structured prompting to generate high-quality responses in RAG workflows. Improve retrieval accuracy by using domain-specific embeddings and reranking retrieved documents for relevance. Implement hierarchical chunking to structure long-form documents while keeping inputs within token limits. Use prompt tuning to guide the model’s reasoning and reduce hallucinations. Enable caching for frequently accessed knowledge to minimize latency and API costs. Experiment with retrieval augmentation techniques, such as query expansion, to improve recall. Monitor system performance and refine retrieval parameters continuously to maintain an efficient and cost-effective setup.

Ollama bge-m3 optimization tips

To optimize Ollama bge-m3 in a RAG setup, ensure input text is preprocessed (lowercasing, removing noise) and split into semantically coherent chunks (300-500 tokens) to balance retrieval accuracy and computational load. Use dynamic pooling to prioritize key phrases in embeddings. Fine-tune the model on domain-specific data with contrastive learning to enhance relevance. Adjust temperature and top-k sampling for controlled generation. Leverage batch inference for parallel processing and enable hardware acceleration (e.g., CUDA) for faster embeddings. Regularly validate retrieval performance with benchmark datasets to refine thresholds and ranking strategies.

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 it’s been! After diving into this tutorial, you’ve acquired some fantastic knowledge about the art of building a Retrieval-Augmented Generation (RAG) system by seamlessly integrating cutting-edge components like a framework, a vector database, a large language model (LLM), and an embedding model. You’ve learned how to harness the power of LlamaIndex for handling complex data structures and how HNSWlib allows for efficient similarity search across your embeddings. With DeepSeek V3, you can effortlessly find relevant context for your data, enhancing the way your LLM interacts with it. And let’s not forget the ease of utilizing the Ollama bge-m3 model to generate human-like responses that truly shine in your applications.

The tutorial didn't just stop at the basics either! You picked up some valuable optimization tips to ensure that your RAG pipeline runs smoothly and efficiently. Plus, you have access to a free RAG cost calculator that will help you assess and plan your resources wisely. This is just the beginning! Your newfound skills empower you to start building, optimizing, and innovating your own unique RAG applications. Remember, the world of AI is bursting with opportunities, and with what you’ve learned, you’re well-equipped to make your mark. So, roll up your sleeves, unleash your creativity, and dive into your own projects—you’ve got this!

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! 💖