Build RAG Chatbot with LangChain, pgvector, Google Vertex AI Gemini 2.0 Flash Thinking, and Ollama nomic-embed-text

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.
Pgvector: an open-source extension for PostgreSQL that enables efficient storage and querying of high-dimensional vector data, essential for machine learning and AI applications. Designed to handle embeddings, it supports fast approximate nearest neighbor (ANN) searches using algorithms like HNSW and IVFFlat. Since it is just a vector search add-on to traditional search 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 Thinking: This advanced AI model is designed for rapid, high-quality cognitive analysis and decision-making. It leverages enhanced natural language understanding and generation, enabling seamless interactions. Ideal for real-time applications in customer service, content creation, and intelligent automation, it excels in scenarios that demand quick, insightful responses.
Ollama nomic-embed-text: This model specializes in generating high-quality text embeddings, designed to enhance semantic understanding in various NLP tasks. Its strengths lie in contextual representation and scalability, making it suitable for applications like semantic search, recommendation systems, and clustering. Ideal for developers looking to integrate profound text analysis into their projects.

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 Thinking

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-thinking-exp-01-21", model_provider="google_vertexai")

Step 3: Install and Set Up Ollama nomic-embed-text

pip install -qU langchain-ollama

from langchain_ollama import OllamaEmbeddings

embeddings = OllamaEmbeddings(model="nomic-embed-text")

Step 4: Install and Set Up pgvector

pip install -qU langchain-postgres

from langchain_postgres import PGVector

vector_store = PGVector(
    embeddings=embeddings,
    collection_name="my_docs",
    connection="postgresql+psycopg://...",
)

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.

pgvector optimization tips

To optimize pgvector in a Retrieval-Augmented Generation (RAG) setup, consider indexing your vectors using GiST or IVFFlat to significantly speed up search queries and improve retrieval performance. Make sure to leverage parallelization for query execution, allowing multiple queries to be processed simultaneously, especially for large datasets. Optimize memory usage by tuning the vector storage size and using compressed embeddings where possible. To further enhance query speed, implement pre-filtering techniques to narrow down search space before querying. Regularly rebuild indexes to ensure they are up to date with any new data. Fine-tune vectorization models to reduce dimensionality without sacrificing accuracy, thus improving both storage efficiency and retrieval times. Finally, manage resource allocation carefully, utilizing horizontal scaling for larger datasets and offloading intensive operations to dedicated processing units to maintain responsiveness during high-traffic periods.

Google Vertex AI Gemini 2.0 Flash Thinking optimization tips

Gemini 2.0 Flash Thinking is designed for rapid yet thoughtful responses in RAG systems. Optimize retrieval by focusing on high-confidence document matching, reducing unnecessary data processing. Keep prompts structured, providing key details upfront while avoiding excessive context. Adjust temperature settings (0.1–0.3) to fine-tune response diversity. Use caching to reduce API overhead for repeated queries. Take advantage of Google Cloud’s GPU-accelerated processing to improve throughput. If using Flash Thinking alongside larger models, assign it to medium-complexity reasoning tasks that require faster turnaround than Pro models but more depth than standard Flash.

Ollama nomic-embed-text optimization tips

Ollama nomic-embed-text is designed for robust text embedding generation, making it essential to optimize how embeddings are stored and queried in a RAG pipeline. Preprocess input text by stripping unnecessary metadata and normalizing case to maintain consistency. Choose an optimized vector indexing strategy, such as IVF-PQ for balanced speed and accuracy, depending on dataset size. Use approximate nearest neighbor search to accelerate retrieval while maintaining a high recall rate. Cache commonly accessed embeddings to avoid redundant computations. If embeddings are used for long-term retrieval tasks, periodically refresh and retrain on new data to prevent model drift. Optimize database queries to quickly retrieve relevant embeddings and minimize I/O bottlenecks.

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 RAG system from the ground up! You learned how LangChain acts as the glue, orchestrating the entire pipeline—connecting your data, models, and workflows seamlessly. With pgvector as your vector database, you can store and retrieve embeddings efficiently, leveraging PostgreSQL’s reliability while tapping into advanced similarity search capabilities. Google Vertex AI Gemini 2.0 Flash Thinking brought speed and intelligence to the table, generating crisp, context-aware responses, while Ollama’s nomic-embed-text model transformed raw text into rich embeddings, ensuring your system understands nuance and meaning. Together, these tools create a dynamic loop: ingest data, embed it, store it for quick access, and generate answers that feel human and precise. Plus, you picked up pro tips for optimizing performance, like balancing latency and accuracy, and even discovered a free RAG cost calculator to keep your projects budget-friendly without sacrificing power.

Now that you’ve seen how these pieces fit together, imagine what’s next! You’re equipped to build smarter chatbots, personalized recommendation engines, or even AI-powered research assistants. The magic of RAG is in its flexibility—swap models, tweak databases, or scale to new use cases with confidence. Remember, every iteration makes your system sharper. So go ahead, experiment fearlessly, optimize relentlessly, and let your creativity run wild. The tools are in your hands, and the possibilities are endless. Start building, share what you create, and watch how your RAG applications transform ideas into impact. The future of AI-driven solutions is yours to shape—let’s make it incredible! 🚀

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! 💖