Build RAG Chatbot with LangChain, Zilliz Cloud, Cohere Command R, and Ollama bge-m3

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.
Cohere Command R: This model is designed for high-performance retrieval tasks, offering advanced capabilities in understanding and generating natural language. Its strengths lie in semantic search and document summarization, making it ideal for applications such as customer support, content generation, and knowledge management, where accuracy and context relevance are paramount.
Ollama bge-m3: Ollama bge-m3 is a powerful language model designed for sophisticated natural language understanding and generation tasks. It excels in providing contextual responses, making it suitable for applications such as chatbots, content creation, and digital assistants, where conversational fluency and coherence are crucial.

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 Cohere Command R

pip install -qU "langchain[cohere]"

import getpass
import os

if not os.environ.get("COHERE_API_KEY"):
  os.environ["COHERE_API_KEY"] = getpass.getpass("Enter API key for Cohere: ")

from langchain.chat_models import init_chat_model

llm = init_chat_model("command-r", model_provider="cohere")

Step 3: Install and Set Up Ollama bge-m3

pip install -qU langchain-ollama

from langchain_ollama import OllamaEmbeddings

embeddings = OllamaEmbeddings(model="bge-m3")

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.

Cohere Command R optimization tips

Cohere Command R is designed for retrieval-augmented generation, making efficient context retrieval and ranking critical for system performance. Optimize retrieval pipelines by using Cohere’s embedding-based search to identify and rank the most relevant documents, reducing unnecessary input context while maintaining accuracy. Improve response quality by fine-tuning temperature settings; lower values (0.1–0.2) work best for structured, fact-based queries, while higher values introduce more variability in generated responses. Utilize prompt templates to maintain consistent formatting, ensuring clarity in output. Implement batch processing where multiple queries need similar context, reducing redundant API calls. To enhance efficiency, cache top query results and leverage incremental context updates instead of repeatedly sending full document sets. If deploying at scale, monitor latency and response consistency with real-time metrics, adjusting retrieval thresholds dynamically for optimal balance between speed and completeness.

Ollama bge-m3 optimization tips

To optimize the Ollama bge-m3 component in a Retrieval-Augmented Generation setup, consider implementing a well-defined caching strategy for frequently accessed data, which will significantly reduce response times and improve overall latency. Additionally, fine-tune your query relevance by adjusting the parameters for the retrieval model to maximize quality, leveraging embeddings for context enrichment. Batch processing of queries can further improve throughput. Lastly, monitor performance metrics continuously to identify bottlenecks and make data-driven adjustments, ensuring robust scalability and responsiveness in production environments.

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 unlocked the power of combining cutting-edge tools to build a robust RAG system from scratch! You learned how LangChain acts as the glue, seamlessly orchestrating workflows between components like Zilliz Cloud—a high-performance vector database that stores and retrieves embeddings at scale—and Cohere Command R, an LLM that transforms retrieved data into human-like responses. The magic starts with Ollama’s bge-m3 embedding model, which converts text into rich numerical representations, enabling Zilliz Cloud to find contextually relevant chunks in milliseconds. Together, these tools form a dynamic pipeline where data flows intelligently: embeddings capture meaning, vector search pinpoints knowledge, and the LLM synthesizes answers that feel natural and informed. You’ve seen firsthand how flexibility and speed come alive when modern frameworks, databases, and models collaborate—and how tweaks like chunk sizing or metadata filtering can supercharge accuracy and efficiency.

But this is just the beginning! With the optimization tips and free RAG cost calculator from the tutorial, you’re equipped to experiment, iterate, and tailor solutions to your needs. Whether you’re building chatbots, research assistants, or enterprise search tools, you now have the blueprint to innovate. Imagine enhancing your pipeline with hybrid search, real-time updates, or custom fine-tuning—your creativity is the limit. So fire up your IDE, plug in these tools, and start crafting RAG applications that amaze. The future of intelligent systems is yours to shape, one query at a time. Let’s build something extraordinary! 🚀

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! 💖