Build RAG Chatbot with LangChain, pgvector, Google Vertex AI Claude 3.5 Haiku, and NVIDIA embed-qa-4

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 Claude 3.5 Haiku: This advanced AI model leverages Google's Vertex AI platform, offering robust capabilities for natural language processing and data analysis. Notable for its versatility and scalability, it excels in complex tasks like content generation and sentiment analysis, making it ideal for enterprises aiming to enhance decision-making with AI-driven insights.
NVIDIA embed-qa-4: This model specializes in question answering tasks, leveraging cutting-edge embedding techniques to enhance accuracy and comprehension. Its strengths lie in understanding context and retrieving precise information effectively. Ideal for applications in customer support, educational platforms, and any domain needing rapid, context-aware responses to user inquiries.

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 Claude 3.5 Haiku

pip install -qU "langchain[google-vertexai]"

# Ensure your VertexAI credentials are configured

from langchain.chat_models import init_chat_model

llm = init_chat_model("claude-3-5-haiku@20241022", model_provider="google_vertexai")

Step 3: Install and Set Up NVIDIA embed-qa-4

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="NV-Embed-QA")

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 Claude 3.5 Haiku optimization tips

Claude 3.5 Haiku on Google Vertex AI is optimized for both efficiency and improved response quality. Enhance retrieval by applying relevance filtering before passing documents to the model. Keep prompts structured with clear separators between user queries and retrieved context. Adjust temperature (0.1–0.3) for optimal factual accuracy while tuning top-p for output control. Use Google Cloud’s serverless scaling to handle large query loads without performance degradation. Implement caching strategies for frequently requested information to reduce redundant API calls. If used alongside larger models, deploy Haiku for rapid responses in latency-sensitive scenarios, reserving complex reasoning for higher-tier models.

NVIDIA embed-qa-4 optimization tips

NVIDIA embed-qa-4 is a high-performance embedding model optimized for question-answering tasks in RAG systems. Improve retrieval efficiency by generating embeddings at both the document and sentence levels, allowing for granular matching. Use similarity threshold tuning to balance precision and recall when retrieving documents. For large-scale applications, employ GPU-accelerated ANN search frameworks such as FAISS with optimized indexing parameters. Cache frequently used embeddings to reduce API overhead and speed up query processing. When handling dynamic knowledge bases, implement scheduled re-embedding of updated documents to maintain search relevance. Consider fine-tuning retrieval pipelines by integrating metadata-based filters alongside vector search for improved contextual accuracy.

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 discovered how to harness the power of cutting-edge tools to create a robust RAG system from scratch! You learned to use LangChain as the glue that binds everything together, orchestrating workflows and simplifying complex interactions between components. With pgvector as your vector database, you saw how to store and efficiently retrieve embeddings, turning unstructured data into searchable knowledge. The Google Vertex AI Claude 3.5 Haiku model became your creative powerhouse, generating human-like responses by leveraging retrieved context, while NVIDIA’s embed-qa-4 embedding model transformed text into rich numerical representations, ensuring your system understands semantic relationships deeply. Together, these tools formed a seamless pipeline: ingesting data, encoding it into vectors, retrieving relevant information, and synthesizing answers that feel both accurate and natural.

But wait—there’s more! You also picked up pro tips for optimizing performance, like tweaking chunking strategies and indexing methods in pgvector to balance speed and accuracy. And let’s not forget the free RAG cost calculator introduced in the tutorial, a game-changer for estimating expenses and scaling your projects wisely. Now that you’ve seen how these pieces fit together, imagine the possibilities: chatbots that feel eerily helpful, research assistants that dig through mountains of data, or custom solutions tailored to your unique needs. The tools are in your hands, and the momentum is yours—so go ahead, experiment fearlessly, refine relentlessly, and build something that blows minds. The future of intelligent applications starts with you pushing “run” on that next idea. Let’s make it happen! 🚀

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! 💖