Build RAG Chatbot with LangChain, pgvector, Google Vertex AI Gemini 2.0 Flash, and nomic-embed-text-v1.5

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: 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.
nomic-embed-text-v1.5: This model specializes in generating high-quality text embeddings that capture semantic meaning and contextual nuances. Its strength lies in facilitating efficient similarity search and information retrieval tasks. Ideal for applications in recommendation systems, semantic search, and natural language understanding, it enhances performance in various NLP 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

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 nomic-embed-text-v1.5

pip install -qU langchain-nomic

import getpass
import os

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

from langchain_nomic import NomicEmbeddings

embeddings = NomicEmbeddings(model="nomic-embed-text-v1.5")

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 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.

nomic-embed-text-v1.5 optimization tips

nomic-embed-text-v1.5 is a well-rounded embedding model that performs effectively in diverse text retrieval scenarios. Optimize text preprocessing by removing stop words and redundant information before embedding to improve storage efficiency. Use hierarchical indexing structures to manage embeddings in large-scale datasets, improving retrieval speed. Leverage cosine similarity filtering to refine search results post-query. For cost-effective scaling, batch embed multiple documents at once and store embeddings in a distributed vector database like Milvus or FAISS. If dealing with rapidly changing data, implement incremental indexing rather than full reprocessing to save computation time. Regularly monitor embedding quality by validating against a benchmarked dataset to ensure relevance.

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 building a RAG system from the ground up using cutting-edge tools! You’ve seen how LangChain acts as the glue, seamlessly connecting every component of the pipeline. With its flexible framework, you orchestrated workflows to retrieve and generate answers like a pro. Then came pgvector, your trusty vector database, which transformed PostgreSQL into a high-performance engine for storing and querying embeddings at scale. You learned how to index and search through dense vectors efficiently, making lightning-fast semantic searches possible. The magic of Google Vertex AI Gemini 2.0 Flash brought your system to life—this lightweight yet powerful LLM delivered quick, accurate responses while keeping costs in check, proving you don’t need massive models to achieve great results. And let’s not forget nomic-embed-text-v1.5, the embedding model that converted text into rich, multidimensional vectors, capturing nuances in your data so your RAG system understands context like never before.

But wait—there’s more! You also picked up pro tips for optimizing your pipeline, like balancing chunk sizes for embeddings and tweaking retrieval thresholds to boost accuracy. And that free RAG cost calculator? It’s your secret weapon for planning budgets and scaling projects without surprises. Now that you’ve seen how these pieces fit together—the framework, the database, the LLM, and the embeddings—you’re ready to create smarter, faster, and more intuitive applications. Imagine the chatbots, search tools, and AI assistants you can build! So go ahead—experiment, iterate, and innovate. Tweak those parameters, explore new datasets, and watch your ideas come to life. The future of AI-powered solutions is in your hands, and this tutorial is just the beginning. Let’s build something amazing! 🚀

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! 💖