Build RAG Chatbot with LangChain, LangChain vector store, AWS Bedrock Claude 3 Haiku, and NVIDIA nv-embed-v1

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.
LangChain in-memory vector store: an in-memory, ephemeral vector store that stores embeddings in-memory and does an exact, linear search for the most similar embeddings. The default similarity metric is cosine similarity, but can be changed to any of the similarity metrics supported by ml-distance. It is intended for demos and does not yet support ids or deletion. (If you want a much more scalable solution for your apps or even enterprise projects, we recommend using Zilliz Cloud, which is a fully managed vector database service built on the open-source Milvusand offers a free tier supporting up to 1 million vectors.)
AWS Bedrock Claude 3 Haiku: This model harnesses the power of Claude 3 within AWS's Bedrock service, facilitating scalable AI solutions. It excels in natural language understanding and generation tasks, making it ideal for customer support, content creation, and conversational agents. Its integration with cloud infrastructure ensures flexibility and ease of deployment for enterprises.
NVIDIA nv-embed-v1: This model specializes in generating high-quality embeddings for various applications, such as image and text processing. Its strength lies in efficiently capturing semantic similarities and contextual information. Ideal for tasks like semantic search, recommendation systems, and natural language understanding, it facilitates advanced AI solutions across diverse industries.

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 AWS Bedrock Claude 3 Haiku

pip install -qU "langchain[aws]"

# Ensure your AWS credentials are configured

from langchain.chat_models import init_chat_model

llm = init_chat_model("anthropic.claude-3-haiku-20240307-v1:0", model_provider="bedrock_converse")

Step 3: Install and Set Up NVIDIA nv-embed-v1

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-embed-v1")

Step 4: Install and Set Up LangChain vector store

pip install -qU langchain-core

from langchain_core.vectorstores import InMemoryVectorStore

vector_store = InMemoryVectorStore(embeddings)

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.

LangChain in-memory vector store optimization tips

LangChain in-memory vector store is just an ephemeral vector store that stores embeddings in-memory and does an exact, linear search for the most similar embeddings. It has very limited features and is only intended for demos. If you plan to build a functional or even production-level solution, 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.)

AWS Bedrock Claude 3 Haiku optimization tips

Claude 3 Haiku on AWS Bedrock is designed for speed and efficiency, making it ideal for real-time RAG applications. Optimize retrieval by prioritizing high-precision embeddings and filtering out low-relevance documents before passing them to the model. Keep prompts structured with clear formatting to help the model focus on the most critical context. Use temperature settings between 0.1 and 0.3 for factual accuracy and adjust top-p to balance diversity. For latency-sensitive applications, leverage AWS Bedrock’s scaling capabilities to ensure smooth performance under heavy loads. Implement caching for frequently accessed queries to reduce API calls and improve response times. If used in a multi-model setup, reserve Haiku for fast preliminary filtering or summarization before escalating complex queries to larger models.

NVIDIA nv-embed-v1 Optimization Tips

To optimize the NVIDIA nv-embed-v1 within a Retrieval-Augmented Generation (RAG) setup, ensure you fine-tune your models with domain-specific data to improve relevance and accuracy. Utilize mixed precision training to speed up training times and reduce memory usage. Implement efficient batching techniques to handle larger datasets, maximizing throughput. Leverage NVIDIA’s TensorRT for inference optimization, enabling faster response times during retrieval. Lastly, monitor GPU utilization and experiment with various hyperparameters, such as learning rates and dropout rates, for optimal performance tailored to your application needs.

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 just unlocked the power of building a RAG system from the ground up using cutting-edge tools! You learned how LangChain acts as the glue, seamlessly orchestrating interactions between your data, AI models, and workflows. By integrating the LangChain Vector Store as your vector database, you discovered how to store and retrieve contextual information efficiently, turning raw data into actionable insights. Then came the magic of AWS Bedrock’s Claude 3 Haiku—a lightning-fast LLM that transforms retrieved context into human-like responses, blending speed with creativity. Pairing this with NVIDIA’s nv-embed-v1 embedding model, you saw how high-quality embeddings turn text into rich numerical representations, ensuring your system understands nuances and delivers accurate answers. Together, these components form a dynamic pipeline that breathes life into your applications, making them smarter and more responsive.

But wait—there’s more! You also picked up pro tips for optimizing performance, like tweaking chunk sizes and refining retrieval strategies to balance speed and accuracy. And let’s not forget the free RAG cost calculator, a handy tool to estimate expenses and scale wisely without surprises. Now, armed with this knowledge, you’re ready to innovate. Imagine the chatbots, research assistants, or personalized tools you can build! The future of AI-driven applications is in your hands. So go ahead—experiment, iterate, and push boundaries. Your journey with RAG is just beginning, and the possibilities are endless. Start creating, keep learning, and watch your ideas come to life! 🚀

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! 💖