Build RAG Chatbot with LangChain, OpenSearch, Google Vertex AI Gemini 2.0 Flash, and Ollama mxbai-embed-large

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: This model is designed for rapid deployment and high-performance machine learning tasks. With enhanced capabilities for natural language processing and image recognition, it excels in real-time analytics and automated decision-making. Ideal for businesses seeking quick insights and efficient model training across various applications, including chatbots and data analysis.
Ollama mxbai-embed-large: This advanced AI model specializes in generating high-quality embeddings for natural language processing tasks. Its strength lies in capturing nuanced meanings and relationships within text data, making it ideal for semantic search, recommendation systems, and content clustering 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 Google Vertex AI Gemini 2.0 Flash

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-2.0-flash-001", model_provider="google_vertexai")

Step 3: Install and Set Up Ollama mxbai-embed-large

pip install -qU langchain-ollama

from langchain_ollama import OllamaEmbeddings

embeddings = OllamaEmbeddings(model="mxbai-embed-large")

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 optimization tips

Gemini 2.0 Flash is built for ultra-fast RAG applications, making it crucial to optimize efficiency and speed. Improve retrieval by minimizing the number of retrieved documents to avoid unnecessary token consumption. Structure prompts concisely, using bullet points or numbered lists for clarity. Set temperature to 0.1–0.2 for factual responses, fine-tuning top-p and top-k for variation control. Implement response caching for frequently queried topics to reduce latency. Take advantage of Google Cloud’s auto-scaling and GPU acceleration to maintain smooth performance under load. If using multiple models, leverage Flash for quick summarization and preliminary analysis before escalating queries to larger models.

Ollama mxbai-embed-large optimization tips

To optimize the Ollama mxbai-embed-large component in a Retrieval-Augmented Generation (RAG) setup, consider fine-tuning the embedding model on domain-specific data to enhance relevance in retrieval tasks. Utilize batching for input queries to improve throughput and efficiency, and implement caching mechanisms for frequently accessed embeddings to reduce latency. Monitor and analyze performance metrics to identify bottlenecks and iteratively adjust hyperparameters, such as learning rate and embedding size, while leveraging mixed-precision training to balance accuracy and resource utilization. Finally, regularly update your embedded database with fresh data to maintain the accuracy of retrieval results, ensuring your RAG system remains effective and responsive.

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 power of combining cutting-edge tools to build a robust RAG system! You learned how LangChain acts as the glue, orchestrating the entire pipeline by seamlessly connecting your data sources, vector databases, and language models. OpenSearch stepped in as your scalable, high-performance vector database, storing and retrieving dense embeddings efficiently—perfect for handling complex queries with speed and precision. Then came the magic of Google Vertex AI Gemini 2.0 Flash, a lightning-fast LLM that transforms retrieved context into human-like responses, balancing accuracy with cost-effectiveness. And let’s not forget Ollama’s mxbai-embed-large model, which turned your raw text into rich, meaningful embeddings, ensuring your RAG system understands context deeply. Together, these tools form a dynamic workflow: ingest data, embed it, store it, retrieve relevant snippets, and generate answers that feel natural and informed. You also picked up pro tips for optimizing performance, like tuning retrieval thresholds and chunking strategies, and even discovered a free RAG cost calculator to budget your AI experiments smartly.

Now that you’ve seen how these pieces fit together, the real fun begins! You’re equipped to experiment, tweak, and scale your RAG applications—whether you’re building chatbots, research assistants, or knowledge bases. Imagine customizing OpenSearch filters for domain-specific data, testing different embedding models for nuance, or fine-tuning Gemini’s outputs for your unique use case. The possibilities are endless, and you’ve got the toolkit to make it happen. So fire up your code editor, play with the parameters, and let your creativity run wild. The future of intelligent applications is in your hands, and there’s no better time to start shaping it. Go build something amazing—and remember, every line of code brings you closer to solving real-world problems with AI! 🚀

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! 💖