Build RAG Chatbot with LangChain, OpenSearch, Google Vertex AI Gemini 1.5 Flash, and Ollama all-minilm

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 1.5 Flash: An advanced AI model designed for real-time applications, Gemini 1.5 Flash is optimized for speed and responsiveness in predictive analytics and NLP tasks. Its strengths lie in generating insights rapidly while ensuring accuracy, making it ideal for use cases in customer service automation and dynamic content generation.
Ollama all-minilm: Ollama all-minilm is a lightweight transformer-based model designed for efficient natural language understanding and generation tasks. Boasting a compact architecture, it excels in scenarios where computational resources are limited, making it ideal for mobile applications and real-time chatbots while maintaining competitive performance in language tasks.

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 1.5 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-1.5-flash", model_provider="google_vertexai")

Step 3: Install and Set Up Ollama all-minilm

pip install -qU langchain-ollama

from langchain_ollama import OllamaEmbeddings

embeddings = OllamaEmbeddings(model="all-minilm")

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 1.5 Flash optimization tips

Gemini 1.5 Flash is optimized for low-latency inference, making it ideal for real-time RAG applications. Improve efficiency by filtering out low-relevance documents before retrieval, ensuring optimal token usage. Use structured prompts with clear formatting to enhance response clarity. Keep temperature between 0.1 and 0.2 for accuracy, fine-tuning top-p as needed. Leverage Google’s AI infrastructure for dynamic scaling to handle fluctuating workloads. Implement caching for common queries to reduce redundant processing. In a multi-model deployment, use Gemini 1.5 Flash for fast responses while reserving Pro models for deeper reasoning.

Ollama all-minilm optimization tips

To optimize the Ollama all-minilm model in a Retrieval-Augmented Generation (RAG) setup, consider fine-tuning the model on domain-specific data to enhance its relevance and accuracy. Use efficient indexing techniques like FAISS for faster retrieval of embeddings from large datasets, ensuring smooth interaction between retrieval and generation phases. Adjust the temperature and top-k sampling parameters during generation to balance creativity and coherence based on your application needs. Monitor GPU utilization and adjust batch sizes to optimize throughput while maintaining responsiveness. Lastly, regularly evaluate and update the retrieval corpus to ensure the model generates the most pertinent information, improving overall performance.

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 functional and efficient RAG system! You now understand how LangChain acts as the glue that ties everything together, orchestrating workflows between your vector database, embedding model, and LLM. With OpenSearch as your vector database, you’ve seen how to store, index, and retrieve embeddings at scale, ensuring your system can quickly find the most relevant information for your queries. Google Vertex AI’s Gemini 1.5 Flash brought speed and affordability to the table, generating high-quality embeddings while keeping costs low, and Ollama’s all-minilm model demonstrated how lightweight, locally run LLMs can deliver impressive results without compromising on performance. Together, these tools create a seamless pipeline where data flows from storage to context enrichment and finally to intelligent, context-aware responses—all while staying adaptable to your specific needs.

But it doesn’t stop there! You’ve also picked up pro tips for optimizing your RAG system, like tuning chunk sizes for better retrieval or adjusting temperature settings in your LLM to balance creativity and accuracy. The free RAG cost calculator introduced in the tutorial empowers you to experiment fearlessly, letting you estimate expenses upfront so you can iterate without surprises. Now that you’ve seen how these pieces fit together, imagine the possibilities: custom chatbots, hyper-personalized search tools, or AI assistants that truly understand your domain. The tools are in your hands, the foundation is set—go ahead and build, tweak, and innovate. Whether you’re refining your first prototype or scaling up for production, every line of code you write brings you closer to creating something extraordinary. Let’s turn those ideas into reality—your next breakthrough is just a RAG pipeline away!

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! 💖