Build RAG Chatbot with LangChain, LangChain vector store, NVIDA Llama 3 70B Instruct, and IBM slate-125m-english-rtrvr

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.)
NVIDIA Llama 3 70B Instruct: This powerful model is designed for instruction-following tasks, leveraging its 70 billion parameters to deliver high-quality responses. It excels in generating detailed answers and engaging in complex dialogues, making it ideal for educational tools, customer support, and interactive applications that require nuanced understanding and guidance.
IBM slate-125m-english-rtrvr: This model is designed for fine-tuning English text retrieval tasks, leveraging a slim and efficient architecture. Its strength lies in fast processing and high accuracy, making it ideal for applications that require quick and relevant information retrieval from large text datasets. Use cases include document search engines, chatbots, and content recommendation systems.

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 NVIDA Llama 3 70B 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("meta/llama3-70b-instruct", model_provider="nvidia")

Step 3: Install and Set Up IBM slate-125m-english-rtrvr

pip install -qU langchain-ibm

import getpass
import os

if not os.environ.get("WATSONX_APIKEY"):
  os.environ["WATSONX_APIKEY"] = getpass.getpass("Enter API key for IBM watsonx: ")

from langchain_ibm import WatsonxEmbeddings

embeddings = WatsonxEmbeddings(
    model_id="ibm/slate-125m-english-rtrvr",
    url="https://us-south.ml.cloud.ibm.com",
    project_id="<WATSONX PROJECT_ID>",
)

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.)

NVIDIA Llama 3 70B Instruct optimization tips

NVIDIA Llama 3 70B Instruct is a high-precision model ideal for RAG applications requiring in-depth reasoning and analysis. Optimize retrieval by using hierarchical document ranking to filter only the most relevant passages, reducing unnecessary token consumption. Structure prompts with a clear separation between user queries, retrieved context, and system instructions for optimal performance. Keep temperature between 0.1 and 0.3 for factual consistency while fine-tuning top-k and top-p for better control over response diversity. Leverage NVIDIA’s TensorRT-LLM and optimized inference stacks to accelerate model execution and reduce latency. Use batching strategies to improve throughput for high-volume workloads. If deploying multiple models, assign Llama 3 70B to handle complex queries requiring deep contextual understanding while reserving lighter models for faster, low-complexity tasks.

IBM slate-125m-english-rtrvr optimization tips

To optimize the IBM slate-125m-english-rtrvr for Retrieval-Augmented Generation (RAG), ensure that your document retrieval system is fine-tuned with domain-specific data to improve relevance. Utilize embeddings effectively by implementing cosine similarity for efficient nearest neighbor searches, and consider applying caching mechanisms to store frequently accessed documents. Additionally, experiment with various query augmentation techniques, like rephrasing or adding related keywords, to enhance retrieval performance. Monitor and analyze retrieval metrics (such as precision and recall) to iteratively refine your setup, and if possible, implement an ensemble approach by integrating multiple retrieval models to boost diversity in retrieved content. Finally, regularly update your corpus to reflect current knowledge and trends.

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?

You’ve just unlocked the magic of building a RAG system from the ground up! By diving into this tutorial, you’ve discovered how to weave together cutting-edge tools like LangChain’s flexible framework, the efficiency of its built-in vector store, the raw power of NVIDIA’s Llama 3 70B Instruct model for reasoning, and IBM’s lightweight yet mighty slate-125m-english-rtrvr embedding model to transform text into searchable vectors. Think about it: you’ve learned to orchestrate these components into a seamless pipeline where LangChain acts as the glue, the vector database turbocharges retrieval, embeddings make sense of unstructured data, and the LLM generates human-like answers. You’re not just stitching tools together—you’re creating intelligent systems that understand context, retrieve relevant information, and craft responses that feel almost human. And hey, those pro tips on optimizing chunk sizes or balancing speed and accuracy? Those are golden nuggets you can apply right away to fine-tune your RAG apps for real-world use!

But wait—there’s more! Remember that free RAG cost calculator we walked through? Now you can estimate expenses and plan resources like a pro, avoiding surprises down the road. This isn’t just about building; it’s about building smart. You’ve got the blueprint to innovate, experiment, and push boundaries. Imagine the applications: smarter chatbots, hyper-personalized search tools, or even AI-augmented research assistants. The tools are in your hands, and the possibilities are endless. So what’s next? Dive in, tweak those parameters, test new datasets, and watch your ideas come to life. The future of AI-driven solutions is yours to shape—go build something amazing, and don’t forget to have fun while you’re at it! 🚀

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! 💖