Build RAG Chatbot with LangChain, pgvector, Cohere Command R, and Azure text-embedding-3-small

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.
Pgvector: an open-source extension for PostgreSQL that enables efficient storage and querying of high-dimensional vector data, essential for machine learning and AI applications. Designed to handle embeddings, it supports fast approximate nearest neighbor (ANN) searches using algorithms like HNSW and IVFFlat. Since it is just a vector search add-on to traditional search 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.)
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.
Azure text-embedding-3-small: This AI model specializes in generating dense vector representations of text inputs, facilitating semantic understanding and comparison. Its strengths lie in efficiency and scalability, making it ideal for applications such as text classification, information retrieval, and natural language processing tasks where rapid semantic similarity assessments 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 Azure text-embedding-3-small

pip install -qU langchain-openai

import getpass
import os

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

from langchain_openai import AzureOpenAIEmbeddings

embeddings = AzureOpenAIEmbeddings(
    azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
    azure_deployment=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],
    openai_api_version=os.environ["AZURE_OPENAI_API_VERSION"],
)

Step 4: Install and Set Up pgvector

pip install -qU langchain-postgres

from langchain_postgres import PGVector

vector_store = PGVector(
    embeddings=embeddings,
    collection_name="my_docs",
    connection="postgresql+psycopg://...",
)

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.

pgvector optimization tips

To optimize pgvector in a Retrieval-Augmented Generation (RAG) setup, consider indexing your vectors using GiST or IVFFlat to significantly speed up search queries and improve retrieval performance. Make sure to leverage parallelization for query execution, allowing multiple queries to be processed simultaneously, especially for large datasets. Optimize memory usage by tuning the vector storage size and using compressed embeddings where possible. To further enhance query speed, implement pre-filtering techniques to narrow down search space before querying. Regularly rebuild indexes to ensure they are up to date with any new data. Fine-tune vectorization models to reduce dimensionality without sacrificing accuracy, thus improving both storage efficiency and retrieval times. Finally, manage resource allocation carefully, utilizing horizontal scaling for larger datasets and offloading intensive operations to dedicated processing units to maintain responsiveness during high-traffic periods.

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.

Azure text-embedding-3-small optimization tips

To optimize the Azure text-embedding-3-small model for your Retrieval-Augmented Generation (RAG) setup, consider batching your input text to process multiple requests simultaneously, which can significantly enhance throughput. Use relevant keywords for fine-tuning the embeddings and ensure your text is preprocessed to remove noise, such as unnecessary punctuation or stop words. Experiment with different similarity metrics during retrieval, like cosine similarity, to improve result relevance. Leverage caching mechanisms to store frequently accessed embeddings, reducing response times. Finally, monitor and analyze performance metrics regularly for iterative improvements and adapt your approach based on user feedback to align the model more closely with your specific use case.

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 magic of building a RAG system from the ground up! You learned how LangChain acts as the glue, seamlessly orchestrating the flow between components. With its modular design, LangChain simplified connecting pgvector—a powerful vector database that stores and retrieves embeddings efficiently—to your pipeline. Speaking of embeddings, you saw how Azure’s text-embedding-3-small transformed raw text into rich numerical representations, enabling semantic search that understands context, not just keywords. Then came Cohere’s Command R, the LLM powerhouse that synthesized retrieved data into coherent, human-like responses, turning your system from a simple search tool into an intelligent conversation partner. Together, these pieces formed a robust RAG pipeline that answers questions with precision and depth, whether you’re building a chatbot, research assistant, or knowledge hub!

But wait—there’s more! You also picked up pro tips for optimizing performance, like tweaking chunk sizes for embeddings and balancing speed with accuracy in retrieval. And let’s not forget the free RAG cost calculator, a game-changer for estimating expenses and scaling wisely. Now that you’ve seen how these tools work in harmony, imagine the possibilities! You’re equipped to create custom solutions, experiment with different models, and refine your system for specific use cases. The world of AI-driven applications is yours to explore. So, what are you waiting for? Fire up your IDE, tweak those parameters, and start building. Your next breakthrough RAG project is just a few lines of code away—go make it happen! 🚀

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! 💖