Build RAG Chatbot with LangChain, Zilliz Cloud, Google Vertex AI Claude 3.5 Sonnet, and Ollama granite-embedding

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.
Zilliz Cloud: a fully managed vector database-as-a-service platform built on top of the open-source Milvus, designed to handle high-performance vector data processing at scale. It enables organizations to efficiently store, search, and analyze large volumes of unstructured data, such as text, images, or audio, by leveraging advanced vector search technology. It offers a free tier supporting up to 1 million vectors.
Google Vertex AI Claude 3.5 Sonnet: A refined model within the Claude family, designed for advanced natural language understanding and generation. It balances creativity and coherence, making it well-suited for generating high-quality content, engaging chatbots, and sophisticated text analysis. Its versatility and enhanced capabilities make it ideal for enterprises seeking rich interactive experiences.
Ollama Granite-Embedding: This AI model specializes in generating high-quality embeddings for various data types, enhancing search and recommendation systems. Its strength lies in its ability to capture complex relationships within data, making it ideal for applications like semantic search, natural language processing, or personalization in digital platforms.

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 Sonnet

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-sonnet-v2@20241022", model_provider="google_vertexai")

Step 3: Install and Set Up Ollama granite-embedding

pip install -qU langchain-ollama

from langchain_ollama import OllamaEmbeddings

embeddings = OllamaEmbeddings(model="granite-embedding")

Step 4: Install and Set Up Zilliz Cloud

pip install -qU langchain-milvus

from langchain_milvus import Zilliz

vector_store = Zilliz(
    embedding_function=embeddings,
    connection_args={
        "uri": ZILLIZ_CLOUD_URI,
        "token": ZILLIZ_CLOUD_TOKEN,
    },
)

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.

Zilliz Cloud optimization tips

Optimizing Zilliz Cloud for a RAG system involves efficient index selection, query tuning, and resource management. Use Hierarchical Navigable Small World (HNSW) indexing for high-speed, approximate nearest neighbor search while balancing recall and efficiency. Fine-tune ef_construction and M parameters based on your dataset size and query workload to optimize search accuracy and latency. Enable dynamic scaling to handle fluctuating workloads efficiently, ensuring smooth performance under varying query loads. Implement data partitioning to improve retrieval speed by grouping related data, reducing unnecessary comparisons. Regularly update and optimize embeddings to keep results relevant, particularly when dealing with evolving datasets. Use hybrid search techniques, such as combining vector and keyword search, to improve response quality. Monitor system metrics in Zilliz Cloud’s dashboard and adjust configurations accordingly to maintain low-latency, high-throughput performance.

Google Vertex AI Claude 3.5 Sonnet optimization tips

Claude 3.5 Sonnet on Google Vertex AI provides a strong balance between speed and depth. Improve retrieval by implementing intelligent reranking techniques that prioritize high-relevance documents. Structure prompts efficiently, with a logical flow to guide the model’s response. Keep temperature settings around 0.1–0.3, adjusting top-k and top-p to fine-tune diversity and precision. Leverage Google’s AI infrastructure for auto-scaling and load balancing to maintain optimal performance. Caching frequently used queries can reduce latency and API costs. In a multi-model deployment, assign Sonnet to handle general-purpose queries while reserving Opus for the most complex requests.

Ollama granite-embedding optimization tips

To optimize the Ollama granite-embedding component in your Retrieval-Augmented Generation (RAG) setup, ensure that you preprocess your text data to remove noise and irrelevant information, enhancing the quality of embeddings. Leverage batch processing to create embeddings in bulk, which can significantly improve throughput and reduce computational overhead. Experiment with different embedding dimensions to find the optimal trade-off between accuracy and performance for your specific use case. Additionally, consider fine-tuning your embeddings model on domain-specific data to enhance reactivity and relevance in your retrieval tasks. Finally, regularly monitor and evaluate performance metrics to identify bottlenecks and iteratively refine your approach.

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 power to build your own Retrieval-Augmented Generation (RAG) system from the ground up! By diving into this tutorial, you’ve learned how to seamlessly stitch together cutting-edge tools to create an AI pipeline that’s both smart and resourceful. You started with LangChain, the flexible framework that acts as your project’s backbone, orchestrating workflows and connecting components like a pro. Then, you integrated Zilliz Cloud, a blazing-fast vector database, to store and retrieve embeddings efficiently—ensuring your system can handle massive datasets without breaking a sweat. The magic of Google Vertex AI’s Claude 3.5 Sonnet brought your LLM into the mix, delivering nuanced, context-aware responses that feel almost human. And let’s not forget Ollama’s granite-embedding model, which transformed raw text into rich numerical representations, making your data searchable and meaningful. Together, these pieces form a RAG pipeline that’s greater than the sum of its parts: ingest data, embed it, store it, retrieve it, and generate answers—all in harmony.

But wait, there’s more! You also picked up pro tips for optimizing performance, like tweaking chunk sizes and fine-tuning retrieval parameters to balance speed and accuracy. The free RAG cost calculator you explored is a game-changer, helping you estimate expenses and scale wisely. Now that you’ve seen how these tools collaborate, imagine the possibilities—custom chatbots, dynamic Q&A systems, or even domain-specific knowledge hubs. The skills you’ve gained aren’t just theoretical; they’re a launchpad for real-world innovation. So what’s next? Start experimenting! Tinker with different models, refine your pipelines, and push the boundaries of what RAG can do. The future of intelligent applications is yours to build. Let’s get coding—your next breakthrough is just a prototype away! 🚀

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! 💖