Build RAG Chatbot with LangChain, Faiss, NVIDIA Deepseek R1, and Ollama paraphrase-multilingual

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:

LangChain: An open-source framework that helps you orchestrate the interaction between LLMs, vector stores, embedding models, etc, making it easier to integrate a RAG pipeline.
Faiss: also known as Facebook AI Similarity Search, is an open-source vector search library that allows developers to quickly search for semantically similar multimedia data within a massive dataset of unstructured data. (If you want a much more scalable solution or hate to manage your own infrastructure, we recommend using Zilliz Cloud, which is a fully managed vector database service built on the open-source Milvus and offers a free tier supporting up to 1 million vectors.)
NVIDIA Deepseek R1: This advanced AI model is designed for high-fidelity image synthesis and enhancement, leveraging NVIDIA’s cutting-edge graphics technology. With its ability to generate realistic visuals and improve image quality, Deepseek R1 is ideal for applications in gaming, film production, and virtual reality, where lifelike graphics are paramount.
Ollama Paraphrase-Multilingual: This AI model specializes in generating paraphrases across multiple languages, enhancing content diversity and accessibility. Its strength lies in understanding context while altering sentence structure, making it ideal for translation services, content creation, and multilingual learning applications.

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 LangChain

%pip install --quiet --upgrade langchain-text-splitters langchain-community langgraph

Step 2: Install and Set Up NVIDIA Deepseek R1

pip install -qU "langchain-nvidia-ai-endpoints"

import getpass
import os

if not os.environ.get("NVIDIA_API_KEY"):
  os.environ["NVIDIA_API_KEY"] = getpass.getpass("Enter API key for NVIDIA: ")

from langchain.chat_models import init_chat_model

llm = init_chat_model("deepseek-ai/deepseek-r1", model_provider="nvidia")

Step 3: Install and Set Up Ollama paraphrase-multilingual

pip install -qU langchain-ollama

from langchain_ollama import OllamaEmbeddings

embeddings = OllamaEmbeddings(model="paraphrase-multilingual")

Step 4: Install and Set Up Faiss

pip install -qU langchain-community

from langchain_community.vectorstores import FAISS

vector_store = FAISS(embedding_function=embeddings)

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 bs4
from langchain import hub
from langchain_community.document_loaders import WebBaseLoader
from langchain_core.documents import Document
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langgraph.graph import START, StateGraph
from typing_extensions import List, TypedDict

# Load and chunk contents of the blog
loader = WebBaseLoader(
    web_paths=("https://milvus.io/docs/overview.md",),
    bs_kwargs=dict(
        parse_only=bs4.SoupStrainer(
            class_=("doc-style doc-post-content")
        )
    ),
)

docs = loader.load()

text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
all_splits = text_splitter.split_documents(docs)

# Index chunks
_ = vector_store.add_documents(documents=all_splits)

# Define prompt for question-answering
prompt = hub.pull("rlm/rag-prompt")


# Define state for application
class State(TypedDict):
    question: str
    context: List[Document]
    answer: str


# Define application steps
def retrieve(state: State):
    retrieved_docs = vector_store.similarity_search(state["question"])
    return {"context": retrieved_docs}


def generate(state: State):
    docs_content = "\n\n".join(doc.page_content for doc in state["context"])
    messages = prompt.invoke({"question": state["question"], "context": docs_content})
    response = llm.invoke(messages)
    return {"answer": response.content}


# Compile application and test
graph_builder = StateGraph(State).add_sequence([retrieve, generate])
graph_builder.add_edge(START, "retrieve")
graph = graph_builder.compile()

Test the Chatbot

Yeah! You've built your own chatbot. Let's ask the chatbot a question.

response = graph.invoke({"question": "What data types does Milvus support?"})
print(response["answer"])

Example Output

Milvus supports various data types including sparse vectors, binary vectors, JSON, and arrays. Additionally, it handles common numerical and character types, making it versatile for different data modeling needs. This allows users to manage unstructured or multi-modal data efficiently.

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.

LangChain optimization tips

To optimize LangChain, focus on minimizing redundant operations in your workflow by structuring your chains and agents efficiently. Use caching to avoid repeated computations, speeding up your system, and experiment with modular design to ensure that components like models or databases can be easily swapped out. This will provide both flexibility and efficiency, allowing you to quickly scale your system without unnecessary delays or complications.

Faiss Optimization Tips

To enhance the performance of the Faiss library in a Retrieval-Augmented Generation (RAG) system, begin by selecting the appropriate index type based on your data volume and query speed requirements; for example, using an IVF (Inverted File) index can significantly speed up queries on large datasets by reducing the search space. Optimize your indexing process by using the nlist parameter to partition data into smaller clusters and set an appropriate number of probes (nprobe) during retrieval to balance between speed and accuracy. Ensure the vectors are properly normalized and consider using 16-bit or 8-bit quantization during indexing to reduce memory footprints for large datasets while maintaining reasonable retrieval accuracy. Additionally, consider leveraging GPU acceleration if available, as Faiss highly benefits from parallel processing, leading to faster nearest neighbor searches. Continuous fine-tuning and benchmarking with varying parameters and configurations can guide you in finding the most efficient setup specific to your data characteristics and retrieval requirements.

NVIDIA Deepseek R1 optimization tips

To optimize the NVIDIA Deepseek R1 for Retrieval-Augmented Generation (RAG), ensure that your input data is well-prepared and indexed for fast access, leveraging its caching capabilities. Utilize mixed-precision training to enhance performance while reducing memory usage, and experiment with different batch sizes to find the most efficient processing speed. Additionally, regularly monitor and fine-tune hyperparameters such as learning rate and dropout rates based on validation results to avoid overfitting. Implement asynchronous data loading to keep the GPU actively processing while managing I/O operations. Finally, streamline the architecture by pruning non-essential layers and optimizing the model's inference pipeline to enhance real-time retrieval performance.

Ollama Paraphrase-Multilingual Optimization Tips

To optimize the Ollama paraphrase-multilingual component in your Retrieval-Augmented Generation (RAG) setup, ensure that your training dataset is diverse and representative of the languages and dialects you intend to support, as this enhances paraphrasing accuracy across contexts. Use transfer learning with domain-specific data to improve performance on niche topics. Adjust hyperparameters such as learning rate and batch size based on validation results to enhance convergence. Implement a caching mechanism for frequently accessed paraphrases to reduce response time during retrieval. Monitor and analyze performance metrics regularly to identify bottlenecks, and consider fine-tuning the model periodically based on user feedback and new datasets to adapt to evolving language use.

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?

By diving into this tutorial, you’ve unlocked the magic of building a powerful RAG system from scratch! You learned how LangChain acts as the glue, seamlessly connecting your pipeline’s components. With its modular design, LangChain simplified orchestrating workflows—like fetching documents, splitting text, and routing queries—while keeping your code clean and scalable. Then came Faiss, the vector database superhero, which turbocharged your semantic search capabilities. By indexing embeddings generated by Ollama’s paraphrase-multilingual model, you transformed unstructured text into searchable knowledge, enabling lightning-fast retrieval of relevant context. And let’s not forget the star of the show: NVIDIA’s Deepseek R1 LLM, which took that retrieved context and crafted coherent, human-like responses, proving how cutting-edge models can elevate your application’s intelligence. Together, these tools formed a dynamic RAG pipeline that’s both efficient and adaptable, ready to tackle real-world queries with precision!

But wait—there’s more! You also discovered pro tips for optimizing performance, like fine-tuning chunk sizes for embeddings and balancing speed with accuracy in retrieval. The tutorial even threw in a free RAG cost calculator to help you budget deployments wisely, ensuring your projects stay scalable and cost-effective. Now that you’ve seen how these pieces fit together—frameworks, databases, models, and embeddings—it’s your turn to experiment! Tweak parameters, explore multilingual capabilities with Ollama, or swap components to suit your needs. The world of RAG is your playground, and you’re equipped with the tools to innovate. So go ahead—build something bold, optimize fearlessly, and let your creativity shape the future of AI-powered applications. The next breakthrough? It starts with you hitting “run”! 🚀

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! 💖