Build RAG Chatbot with Llamaindex, HNSWlib, DeepSeek V3, and Ollama snowflake-arctic-embed

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 Snowflake-Arctic-Embed: A high-performance embedding model optimized for semantic understanding and retrieval tasks. It excels in generating dense vector representations for text, offering robust accuracy and scalability. Ideal for enterprise applications like semantic search, recommendation systems, and data clustering, particularly in environments leveraging Snowflake’s data ecosystem for seamless integration and large-scale analytics.

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 snowflake-arctic-embed

%pip install llama-index-embeddings-ollama

from llama_index.embeddings.ollama import OllamaEmbedding

embed_model = OllamaEmbedding(
    model_name="snowflake-arctic-embed",
)

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 Snowflake-Arctic-Embed optimization tips

To optimize Ollama Snowflake-Arctic-Embed in a RAG setup, ensure input text is cleanly chunked (e.g., 256-512 tokens) to align with its context window. Use batch processing for embeddings to reduce latency, and leverage hardware acceleration (e.g., CUDA for GPUs). Fine-tune with domain-specific data to improve retrieval relevance. Quantize the model for faster inference with minimal accuracy loss. Cache frequently accessed embeddings, and experiment with dimensionality reduction techniques like PCA if storage or speed constraints exist. Regularly validate embedding quality using similarity benchmarks.

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 we've taken together in this tutorial! By diving into the world of RAG (Retrieval-Augmented Generation) systems, you've learned how to seamlessly integrate a robust framework with a powerful vector database, leveraging the capabilities of a cutting-edge Large Language Model (LLM) and an efficient embedding model. Not only did we explore how LlamaIndex organizes and retrieves information, bolstered by HNSWlib for fast similarity searches, but you also discovered how DeepSeek V3 enhances your data retrieval accuracy. With the Ollama snowflake-arctic-embed, your embeddings will be optimally tuned for fantastic performance. Each of these components brings unique capabilities to the table, allowing you to craft a sophisticated system that intelligently combines retrieval and generation.

But we didn’t stop there! You also picked up some handy optimization tips to fine-tune your RAG pipeline and even a free RAG cost calculator to help manage your deployment expenses. Isn’t it exciting to see how effortlessly all these pieces come together? Now it's time for you to harness the knowledge you've gained and let your creativity shine! Start building, optimizing, and innovating your own RAG applications today. The possibilities are endless, and with your newfound skills, you can create solutions that truly make an impact. Get out there and transform your ideas into reality—your journey in crafting innovative technology starts now!

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! 💖