Build RAG Chatbot with LangChain, pgvector, Azure GPT-4o mini, and IBM all-minilm-l6-v2

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.)
Azure GPT-4o Mini: A compact version of the powerful GPT-4 architecture, designed for efficient processing in resource-constrained environments. It delivers robust performance in natural language understanding and generation, making it suitable for chatbots, customer support, and content creation. Ideal for applications where speed and scalability are essential without compromising on quality.
IBM all-minilm-l6-v2: This model is a compact, efficient transformer-based language representation model optimized for tasks requiring fast inferencing. It excels in natural language understanding tasks such as sentiment analysis and information retrieval, making it ideal for applications in chatbots, search engines, and data annotation.

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 Azure GPT-4o mini

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 AzureChatOpenAI

llm = AzureChatOpenAI(
    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 3: Install and Set Up IBM all-minilm-l6-v2

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="sentence-transformers/all-minilm-l6-v2",
    url="https://us-south.ml.cloud.ibm.com",
    project_id="<WATSONX PROJECT_ID>",
)

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.

Azure GPT-4o mini optimization tips

Azure GPT-4o mini is a cost-efficient, low-latency model optimized for fast RAG applications. Improve retrieval by ensuring only the top-ranked, most relevant documents are included in the context to minimize unnecessary token consumption. Structure prompts with bullet points or numbered lists for clarity. Adjust temperature settings between 0.1 and 0.2 for precision, modifying top-p as needed for response diversity. To enhance performance, batch multiple API requests and implement caching for frequently queried information. Azure’s infrastructure allows for auto-scaling, so configure dynamic scaling to handle varying workloads efficiently. Stream responses for improved real-time performance, ensuring fast and interactive user experiences. If used in a pipeline, assign GPT-4o mini to preliminary filtering or summarization while reserving larger models for complex tasks.

IBM all-minilm-l6-v2 optimization tips

To optimize the performance of IBM all-minilm-l6-v2 in a Retrieval-Augmented Generation (RAG) setup, consider implementing streamlined query preprocessing to remove stop words and normalize text, ensuring that input queries are concise and relevant. Layering caching strategies on frequently retrieved results can significantly reduce latency, while fine-tuning the model with domain-specific data enhances relevance and accuracy. Additionally, experiment with batch processing during inference to leverage parallelization, and monitor and adjust hyperparameters like learning rates and maximum token counts to refine model responses. Lastly, ensure that your retrieval system is seamlessly integrated with the generation process to maintain context and coherence in generated outputs.

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 fully functional RAG system! You learned how LangChain acts as the glue, seamlessly orchestrating interactions between your vector database (pgvector), your embedding model (IBM’s all-minilm-l6-v2), and your large language model (Azure GPT-4o mini). The magic happens when LangChain retrieves context from pgvector—which stores your data as semantic vectors—and feeds it to Azure GPT-4o mini, enabling it to generate accurate, context-aware responses. Along the way, you saw how IBM’s lightweight embedding model transforms text into meaningful vectors efficiently, making retrieval fast and scalable. But it’s not just about integration; you also picked up pro tips for optimizing performance, like tuning chunk sizes and balancing latency with accuracy, ensuring your RAG pipeline runs smoothly in real-world scenarios. Plus, the free RAG cost calculator introduced here helps you estimate expenses upfront, empowering you to make smart, budget-friendly decisions as you scale.

Now that you’ve seen the pieces come together, imagine the possibilities! Whether you’re enhancing chatbots, building intelligent search engines, or crafting personalized recommendation systems, you’ve got the toolkit to innovate. The best part? You’re not just following steps—you’re understanding how these technologies collaborate to solve complex problems. So go ahead—experiment with different datasets, tweak parameters, and push the boundaries of what your RAG system can do. The future of AI-powered applications is in your hands, and this tutorial is just the beginning. Start building, keep optimizing, and let your creativity run wild. The next breakthrough could be yours! 🚀✨

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! 💖