Build RAG Chatbot with LangChain, OpenSearch, Google Vertex AI Gemini 2.0 Flash-Lite, and NVIDIA arctic-embed-l

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.
OpenSearch: An open-source search and analytics suite derived from Elasticsearch. It offers robust full-text search and real-time analytics, with vector search available as an add-on for similarity-based queries, extending its capabilities to handle high-dimensional data. Since it is just a vector search add-on rather than a purpose-built vector database, it lacks scalability and availability and many other advanced features required by enterprise-level applications. Therefore, if you prefer 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.)
Google Vertex AI Gemini 2.0 Flash-Lite: This model streamlines AI deployment with an emphasis on low-latency and cost-efficient solutions. It excels in real-time applications like chatbots and interactive tools, combining high performance with seamless integration across various frameworks. Ideal for businesses looking to enhance user engagement without compromising efficiency.
NVIDIA arctic-embed-l: This AI model is designed for optimizing embedded systems with a focus on low-latency processing and energy efficiency. It excels in real-time applications, making it ideal for edge computing in smart devices, IoT applications, and automated systems, enabling advanced analytics and decision-making on-site.

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 Google Vertex AI Gemini 2.0 Flash-Lite

pip install -qU "langchain[google-vertexai]"

# Ensure your VertexAI credentials are configured

from langchain.chat_models import init_chat_model

llm = init_chat_model("gemini-1.5-flash", model_provider="google_vertexai")

Step 3: Install and Set Up NVIDIA arctic-embed-l

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_nvidia_ai_endpoints import NVIDIAEmbeddings

embeddings = NVIDIAEmbeddings(model="snowflake/arctic-embed-l")

Step 4: Install and Set Up OpenSearch

pip install --upgrade --quiet  opensearch-py langchain-community

from langchain_community.vectorstores import OpenSearchVectorSearch
opensearch_vector_search = OpenSearchVectorSearch(
    "http://localhost:9200",
    "embeddings",
    embedding_function
)

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.

OpenSearch optimization tips

To optimize OpenSearch in a Retrieval-Augmented Generation (RAG) setup, fine-tune indexing by enabling efficient mappings and reducing unnecessary stored fields. Use HNSW for vector search to speed up similarity queries while balancing recall and latency with appropriate ef_search and ef_construction values. Leverage shard and replica settings to distribute load effectively, and enable caching for frequent queries. Optimize text-based retrieval with BM25 tuning and custom analyzers for better relevance. Regularly monitor cluster health, index size, and query performance using OpenSearch Dashboards and adjust configurations accordingly.

Google Vertex AI Gemini 2.0 Flash-Lite optimization tips

Gemini 2.0 Flash-Lite is a lightweight, fast-response model suited for cost-efficient RAG applications. Improve retrieval by using high-precision embeddings to minimize irrelevant context. Structure prompts efficiently, keeping them short and well-organized. Adjust temperature (0.1–0.2) for accuracy, tuning top-p for output variety when needed. Cache frequent queries to reduce API usage and improve performance. Use Google’s auto-scaling infrastructure to handle demand spikes seamlessly. If deploying multiple models, utilize Flash-Lite for initial filtering and summarization while reserving larger models for in-depth reasoning.

NVIDIA arctic-embed-l optimization tips

To optimize the NVIDIA arctic-embed-l component in your Retrieval-Augmented Generation (RAG) setup, consider implementing a multi-threading approach to parallelize data processing, which can significantly enhance throughput. Make use of mixed precision training to speed up the model's computations while minimizing memory usage. Regularly fine-tune your embeddings with domain-specific data to improve their relevance and accuracy. Additionally, leverage batch processing techniques to reduce latency and ensure efficient GPU utilization. Monitor your inference times and adjust the cache size dynamically based on workload patterns to balance speed and resource consumption effectively.

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 RAG system from the ground up! You learned how LangChain acts as the glue that elegantly orchestrates the entire pipeline, seamlessly connecting your data, models, and workflows. OpenSearch steps in as your powerhouse vector database, storing and retrieving embeddings with lightning speed while offering hybrid search capabilities to balance keyword and semantic matching. The NVIDIA arctic-embed-l model transforms raw text into rich, meaningful embeddings, giving your system the superpower to understand context and relationships in your data. Then, Google Vertex AI’s Gemini 2.0 Flash-Lite takes center stage as the LLM, generating human-like responses by synthesizing retrieved information with its deep language understanding. Together, these tools form a robust RAG pipeline that’s both scalable and cost-effective, especially with the tutorial’s optimization tips—like smart chunking strategies and query routing—to keep your system fast and efficient. And don’t forget that handy free RAG cost calculator to help you budget like a pro!

Now that you’ve seen how these pieces fit together, it’s time to unleash your creativity! You’re not just building a tool—you’re crafting intelligent systems that can answer questions, analyze data, and even spark new ideas. Experiment with different embedding models, tweak retrieval parameters, or explore OpenSearch’s advanced features like custom scoring. The sky’s the limit when you combine these technologies with your unique vision. Whether you’re optimizing for speed, accuracy, or cost, you’ve got the toolkit to make it happen. So go out there, build something amazing, and watch as your RAG-powered applications transform raw data into actionable insights. The future of AI is yours to shape—start coding, keep iterating, and let your innovations shine! 🚀

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! 💖