Build RAG Chatbot with LangChain, pgvector, NVIDIA Qwen2.5-7B-Instruct, and Azure text-embedding-3-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.
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.)
NVIDIA Qwen2.5-7B-Instruct: This advanced language model is designed for instruction-following tasks, leveraging the capabilities of 7 billion parameters to comprehend and generate diverse text responses. Its strengths lie in natural language understanding and contextual adaptability, making it ideal for applications in tutoring, conversational agents, and automated content generation across various domains.
Azure text-embedding-3-large: This powerful AI model specializes in generating high-quality text embeddings for natural language processing tasks. With its advanced understanding of context, it excels in applications like semantic search, recommendation systems, and clustering. Ideal for developers seeking to enhance text analysis and retrieval in complex datasets while ensuring robust accuracy and performance.

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 NVIDIA Qwen2.5-7B-Instruct

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.chat_models import init_chat_model

llm = init_chat_model("qwen/qwen2.5-7b-instruct", model_provider="nvidia")

Step 3: Install and Set Up Azure text-embedding-3-large

pip install -qU langchain-openai

import getpass
import os

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

from langchain_openai import AzureOpenAIEmbeddings

embeddings = AzureOpenAIEmbeddings(
    azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
    azure_deployment=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],
    openai_api_version=os.environ["AZURE_OPENAI_API_VERSION"],
)

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.

NVIDIA Qwen2.5-7B-Instruct Optimization Tips

To optimize the NVIDIA Qwen2.5-7B-Instruct model in a Retrieval-Augmented Generation (RAG) setup, consider implementing mixed precision training to reduce memory footprint and accelerate training times. Fine-tune the model on domain-specific data to enhance relevancy in generated responses while adjusting the retrieval component's cosine similarity threshold to balance precision and recall. Utilize an efficient caching mechanism to store frequently accessed data, ensuring low-latency responses. Experiment with varying the number of retrievals based on query complexity, and leverage batch processing during inference to maximize throughput. Finally, keep an eye on hardware utilization metrics to adjust configurations and achieve optimal performance.

Azure text-embedding-3-large optimization tips

Azure text-embedding-3-large is a powerful model for generating high-quality text embeddings. Optimize efficiency by preprocessing input text to remove redundant content and ensure the embeddings focus on the most important concepts. Leverage approximate nearest neighbor (ANN) search algorithms like FAISS or HNSW for fast retrieval across large datasets. When dealing with high-throughput applications, implement caching strategies to store frequently accessed embeddings, reducing API call overhead. Use multi-threading or parallel processing to handle batch requests and reduce latency in large-scale systems. Consider dimensionality reduction techniques, such as PCA or quantization, to reduce storage requirements and improve retrieval speed. Regularly update embeddings to reflect new data and ensure your system’s search results are accurate.

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 now, you’ve unlocked something incredible—the power to build a RAG system from scratch using cutting-edge tools! You’ve seen how LangChain acts as the glue, elegantly connecting every piece of the puzzle. It orchestrates the flow of data, letting you retrieve context from pgvector, a vector database that’s both flexible and lightning-fast for similarity searches. You learned how Azure’s text-embedding-3-large transforms text into rich, meaningful embeddings, giving your system the ability to “understand” queries at a deeper level. And when it’s time to generate answers, NVIDIA’s Qwen2.5-7B-Instruct steps in as your creative powerhouse, crafting responses that feel human and insightful. Together, these tools form a seamless pipeline that retrieves relevant information and generates answers dynamically—no more static, outdated responses! Plus, you picked up pro tips like optimizing chunk sizes for pgvector and balancing cost-performance tradeoffs with the free RAG cost calculator, ensuring your projects stay efficient and budget-friendly.

This isn’t just about building a tool—it’s about opening doors to innovation. You’ve got the skills to create AI applications that learn, adapt, and deliver real value. Imagine enhancing customer support, powering research tools, or building personalized assistants—all within your reach. The tutorial gave you the blueprint, but the magic happens when you experiment, tweak, and make it your own. So fire up your IDE, play with different embedding models, fine-tune prompts for Qwen2.5, or explore hybrid search strategies in pgvector. The future of intelligent systems is yours to shape. Start building, stay curious, and let your creativity run wild. The next breakthrough RAG app? It could be yours! 🚀

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! 💖