Build RAG Chatbot with LangChain, OpenSearch, NVIDIA BGE-M3, and HuggingFace all-MiniLM-L12-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.
OpenSearch: An open-source search and analytics suite derived from Elasticsearch. It offers robust full-text search and real-time analytics, with vector search available as an add-on for similarity-based queries, extending its capabilities to handle high-dimensional data. Since it is just a vector search add-on 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 BGE-M3: The NVIDIA BGE-M3 is a state-of-the-art language model designed to generate human-like text, making it suitable for a variety of natural language processing tasks. Its strength lies in its ability to produce coherent and contextually relevant responses, making it ideal for applications in chatbots, content creation, and virtual assistants. BGE-M3 excels in understanding nuanced input, providing users with highly accurate and engaging interactions, thereby enhancing automated communication systems across multiple industries.
HuggingFace all-MiniLM-L12-v1: This model is a lightweight transformer designed for efficient natural language understanding and generation tasks. It excels in providing high-quality embeddings for various applications, including search, clustering, and conversational AI, while maintaining a small footprint for faster inference and deployment. Ideal for resource-constrained environments or mobile applications, it offers a balance between performance and efficiency.

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 BGE-M3

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("baai/bge-m3", model_provider="nvidia")

Step 3: Install and Set Up HuggingFace all-MiniLM-L12-v1

pip install -qU langchain-huggingface

from langchain_huggingface import HuggingFaceEmbeddings

embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L12-v1")

Step 4: Install and Set Up OpenSearch

pip install --upgrade --quiet  opensearch-py langchain-community

from langchain_community.vectorstores import OpenSearchVectorSearch
opensearch_vector_search = OpenSearchVectorSearch(
    "http://localhost:9200",
    "embeddings",
    embedding_function
)

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.

OpenSearch optimization tips

To optimize OpenSearch in a Retrieval-Augmented Generation (RAG) setup, fine-tune indexing by enabling efficient mappings and reducing unnecessary stored fields. Use HNSW for vector search to speed up similarity queries while balancing recall and latency with appropriate ef_search and ef_construction values. Leverage shard and replica settings to distribute load effectively, and enable caching for frequent queries. Optimize text-based retrieval with BM25 tuning and custom analyzers for better relevance. Regularly monitor cluster health, index size, and query performance using OpenSearch Dashboards and adjust configurations accordingly.

NVIDIA BGE-M3 optimization tips

To optimize the NVIDIA BGE-M3 in a Retrieval-Augmented Generation (RAG) setup, ensure that your data retrieval system is finely tuned for reusability and relevance—consider implementing a caching mechanism to store frequently accessed documents. Additionally, experimenting with the retrieval parameters, such as k-value in nearest neighbor searches, can yield better results for your specific tasks. Utilize mixed-precision training to enhance throughput and reduce memory usage without compromising model performance. Regularly monitor and fine-tune hyperparameters through validation tests to achieve the best balance between speed and accuracy. Lastly, leverage NVIDIA's TensorRT or ONNX optimization tools for model deployment to maximize inference efficiency.

HuggingFace all-MiniLM-L12-v1 optimization tips

To optimize the HuggingFace all-MiniLM-L12-v1 model for your Retrieval-Augmented Generation (RAG) setup, consider implementing mixed precision training to speed up computations and reduce memory usage, enabling you to handle larger batch sizes. Experiment with layer freezing during fine-tuning to preserve certain parameters while optimizing others, ensuring faster convergence. Use an efficient data preprocessing pipeline to reduce input bottlenecks, and implement caching mechanisms for frequently accessed data. Furthermore, leverage model distillation techniques to create smaller, faster versions of the model that maintain comparable performance, and experiment with different pooling strategies to find the most effective way to condense retrieved documents for better context input. Lastly, regularly monitor and fine-tune hyperparameters such as learning rate and batch size based on validation performance to achieve optimal results.

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 learned how to stitch together cutting-edge tools to build a powerful RAG system from the ground up! You now understand how LangChain acts as the glue, orchestrating the entire workflow by seamlessly connecting your data pipeline, retrieval logic, and generative AI. OpenSearch steps in as your trusty vector database, handling the heavy lifting of storing and retrieving embeddings at scale while offering flexibility with hybrid search capabilities. You explored the magic of embedding models like NVIDIA’s BGE-M3, which supercharges multilingual text understanding, and Hugging Face’s all-MiniLM-L12-v1, a lightweight yet robust option for balancing speed and accuracy. Together, these tools transform raw data into context-aware responses, letting your LLM generate answers that feel insightful and precise. Plus, you picked up pro tips for optimizing performance—like tuning chunk sizes, experimenting with reranking strategies, or using the free RAG cost calculator to estimate expenses before scaling up.

What’s next? You’ve unlocked the power to create AI applications that don’t just answer questions but understand context and nuance. Whether you’re building a multilingual support bot, a research assistant, or a creative content generator, you now have the toolkit to make it happen. Remember, every tweak and experiment brings you closer to a smoother, faster, and more cost-effective system. So go ahead—clone that repo, tweak those parameters, and let your ideas take flight. The RAG ecosystem is evolving fast, and you’re already riding the wave. Start building, keep iterating, and who knows? Your project might just be the next big thing in AI. The sky’s the limit—now go get your hands dirty and make something awesome! 🚀

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! 💖