Build RAG Chatbot with Llamaindex, HNSWlib, DeepSeek R1, and jina-embeddings-v3

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 R1: DeepSeek R1 is an open-weight large language model (LLM) designed for high-performance natural language processing, featuring a 128K context window for long-document understanding. It excels in reasoning, coding, and text generation, making it ideal for research, commercial applications, and AI-driven workflows requiring extended context retention and adaptability.
Jina-Embeddings-v3: A state-of-the-art embedding model designed for high-dimensional vector representations of text, excelling in multilingual understanding and long-context retention. Its scalable architecture ensures robust performance in semantic search, clustering, and retrieval-augmented generation (RAG) systems. Ideal for applications requiring precise semantic analysis across diverse languages and lengthy documents, combining accuracy with efficiency.

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 R1

%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-reasoner", 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 jina-embeddings-v3

%pip install llama-index-embeddings-jinaai

You may also need other packages that do not come direcly with llama-index.

!pip install Pillow

from llama_index.embeddings.jinaai import JinaEmbedding

embed_model = JinaEmbedding(
    api_key=jinaai_api_key,
    model="jina-embeddings-v3",
    # choose `retrieval.passage` to get passage embeddings
    task="retrieval.passage",
)

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 R1 optimization tips

To optimize DeepSeek R1 in a RAG setup, ensure that retrieval delivers high-quality, semantically relevant documents by fine-tuning your embedding model and search strategies. Use hybrid retrieval (vector + keyword search) to improve accuracy, especially for complex queries. Keep document chunks concise but rich in context to avoid exceeding token limits. Leverage caching to reduce redundant queries and enhance response speed. Experiment with prompt templates to maximize the model’s reasoning and comprehension capabilities. Monitor API latency and adjust query batching to improve efficiency. Fine-tune temperature settings to maintain consistency in generated responses.

Jina-embeddings-v3 optimization tips

To optimize Jina-embeddings-v3 in a RAG setup, preprocess input text by normalizing casing, removing redundant whitespace, and truncating to the model’s maximum sequence length (e.g., 8,192 tokens). Batch embedding generation for parallel processing, balancing GPU/CPU memory constraints. Use FP16 precision for faster inference if hardware supports it. Cache frequently accessed document embeddings to reduce recomputation. Experiment with dimensionality reduction (e.g., PCA) if downstream tasks tolerate lower-dimensional vectors. Regularly update to the latest model version for performance improvements. Monitor latency and adjust batch sizes dynamically for throughput-latency trade-offs.

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 making it through this enlightening tutorial! You’ve just uncovered the exciting world of integrating a powerful framework with a vector database, a language model, and an embedding model to construct your very own Retrieval-Augmented Generation (RAG) system. By diving into LlamaIndex, HNSWlib, DeepSeek R1, and jina-embeddings-v3, you’ve learned not just how to assemble these components, but how they interplay to enhance the performance and accuracy of your applications. Each piece of this puzzle plays a crucial role: the framework organizes and manages your data, the vector database efficiently stores and retrieves information, the LLM generates coherent and contextually relevant responses, and the embedding model transforms your text into a dense vector space for optimal search capabilities.

As you explored the nuances of each component, you also picked up valuable optimization tips that can help you refine your RAG pipeline for better efficiency and performance. The inclusion of a free RAG cost calculator is a fantastic bonus that empowers you to assess the economic feasibility of your projects effortlessly. Keep this momentum going! You have the tools and knowledge to innovate and create transformative applications with RAG. So, roll up your sleeves, start building, and let your imagination run wild. The future of your RAG applications is bright—get out there and make your mark!

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! 💖