Build RAG Chatbot with LangChain, pgvector, OpenAI GPT-4o mini, and NVIDIA nv-embedqa-e5-v5

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.)
OpenAI GPT-4o mini: This model is a compact version of the advanced GPT-4 architecture, designed for efficiency and lower resource consumption. It delivers strong performance in natural language understanding and generation tasks, making it ideal for chatbot implementations, content creation, and interactive applications where responsiveness and cost-effectiveness are crucial.
NVIDIA nv-embedqa-e5-v5: This model combines advanced natural language processing with deep learning to perform efficient question answering. It excels in understanding context and providing accurate responses from embedded knowledge sources. Ideal for applications in customer support, chatbots, and interactive learning environments, it enhances user engagement through intuitive interactions.

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 OpenAI GPT-4o mini

pip install -qU "langchain[openai]"

import getpass
import os

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

from langchain.chat_models import init_chat_model

llm = init_chat_model("gpt-4o-mini", model_provider="openai")

Step 3: Install and Set Up NVIDIA nv-embedqa-e5-v5

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="nvidia/nv-embedqa-e5-v5")

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.

OpenAI GPT-4o mini optimization tips

GPT-4o mini is a smaller and more cost-effective variant of GPT-4o, making it ideal for low-latency RAG applications. Optimize retrieval by limiting the number of retrieved documents to only the most relevant, ensuring the model does not get overloaded with unnecessary context. Structure prompts effectively by using bullet points or numbered lists to enhance clarity and focus. Keep temperature at 0.1–0.2 for factual responses, adjusting top-p and top-k values to refine output precision. Implement caching for frequently accessed queries to minimize API calls and reduce costs. For high-throughput applications, batch process multiple queries to optimize API efficiency. Stream responses to improve interactivity in real-time applications. If using GPT-4o mini in a multi-model pipeline, consider using it for simpler tasks while reserving larger models for complex reasoning.

NVIDIA nv-embedqa-e5-v5 optimization tips

To optimize the NVIDIA nv-embedqa-e5-v5 in a Retrieval-Augmented Generation (RAG) setup, first ensure that your model is correctly fine-tuned with a diverse training dataset to enhance retrieval accuracy. Utilize mixed precision training to boost computational efficiency and reduce memory usage. Implement batching for queries and responses to leverage parallel processing capabilities. Regularly monitor and adjust the learning rate and other hyperparameters for optimal training performance. Finally, incorporate caching mechanisms for frequently accessed embeddings and results to significantly speed up retrieval times.

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 now understand how LangChain acts as the glue that ties everything together, orchestrating workflows to seamlessly connect your vector database (pgvector) with powerful language models like OpenAI’s GPT-4o mini. You’ve seen how NVIDIA’s nv-embed-qa-e5-v5 embedding model transforms raw text into rich numerical representations, enabling pgvector to store and retrieve context with lightning-fast efficiency. Together, these tools form a dynamic pipeline where data is indexed, retrieved, and synthesized into accurate, context-aware responses—perfect for chatbots, research tools, or any application that needs to “understand” information. Plus, you’ve learned practical tips for optimizing performance, like tuning chunk sizes and refining retrieval strategies, to make your system faster and more cost-effective.

But wait—there’s more! The tutorial also equipped you with tools like the free RAG cost calculator to estimate expenses and experiment with trade-offs between speed, accuracy, and budget. Imagine the possibilities now: you can customize this pipeline for niche domains, scale it to handle massive datasets, or even integrate multimedia inputs. The future of intelligent applications is in your hands, and you’ve got the skills to shape it. So what’s next? Start building! Tinker with different models, experiment with hybrid retrieval methods, or push the boundaries of what RAG can do. Every line of code you write brings us closer to smarter, more responsive AI. Let’s go—your next breakthrough is just a prototype 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! 💖