Build RAG Chatbot with LangChain, pgvector, OpenAI GPT-o1, and IBM granite-embedding-107m-multilingual

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.)
OpenAI GPT-01: This foundational model marks the beginning of OpenAI’s generative pre-trained transformers. With its broad training on diverse text, GPT-01 is proficient in various NLP tasks including text generation, translation, and conversation. Its versatility makes it ideal for prototyping applications and enhancing interactive user experiences in early AI deployments.
IBM granite-embedding-107m-multilingual: This AI model specializes in generating multilingual embeddings, allowing for semantic understanding across various languages. With 107 million parameters, it excels in tasks such as cross-lingual retrieval, translation, and sentiment analysis, making it ideal for global applications that require nuanced understanding of diverse linguistic contexts.

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 OpenAI GPT-o1

pip install -qU "langchain[openai]"

import getpass
import os

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

from langchain.chat_models import init_chat_model

llm = init_chat_model("o1", model_provider="openai")

Step 3: Install and Set Up IBM granite-embedding-107m-multilingual

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="ibm/granite-embedding-107m-multilingual",
    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.

OpenAI GPT-o1 optimization tips

GPT-o1 is designed for optimized efficiency and cost-effectiveness, making it well-suited for scalable RAG systems. Improve retrieval performance by implementing dynamic retrieval depth—fetching broader context for complex queries and narrower focus for straightforward ones. Use prompt compression techniques to remove unnecessary metadata while maintaining core information. Adjust temperature settings (0.1–0.3) based on the required response specificity, ensuring balanced output quality. Deploy caching strategies for repeated queries to enhance response speed and lower operational costs. Utilize function calling to structure responses and avoid ambiguous or overly verbose answers. When handling large-scale workloads, distribute requests across multiple instances to balance resource allocation and reduce bottlenecks. Monitor API usage and optimize retrieval strategies continuously to maintain efficiency.

IBM granite-embedding-107m-multilingual optimization tips

To optimize the IBM granite-embedding-107m-multilingual model in a Retrieval-Augmented Generation (RAG) setup, start by fine-tuning the model on domain-specific data to improve its relevance and contextual understanding. Use batch processing for embedding generation to enhance throughput, and implement caching mechanisms for frequently queried embeddings to reduce latency. Regularly evaluate and update your retrieval strategies using various metrics, such as precision and recall, to ensure you're consistently retrieving the most pertinent data. Additionally, consider augmenting your dataset with diverse multilingual inputs to develop a more robust understanding of different languages, and experiment with different hyperparameter settings, such as learning rates and embedding dimensions, to find the optimal configuration for 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 power of combining cutting-edge tools to build a fully functional RAG system from scratch! You learned how LangChain acts as the glue, orchestrating the flow of data between components while simplifying complex workflows like document loading, chunking, and chaining prompts. You saw how pgvector, a PostgreSQL extension, transforms into a high-performance vector database, storing embeddings generated by IBM’s efficient granite-embedding-107m-multilingual model. This embedding model’s multilingual capabilities let you handle diverse text inputs, while OpenAI’s GPT-4o (assuming “GPT-o1” was a typo) delivered sharp, context-aware responses by leveraging retrieved data. Together, these pieces form a seamless pipeline: documents are embedded, stored as vectors for lightning-fast similarity searches, and fed to the LLM to generate answers that feel both informed and natural. You also picked up pro tips—like optimizing pgvector indexes for speed or tweaking chunk sizes for accuracy—and maybe even explored the free RAG cost calculator to estimate expenses as you scale!

Now that you’ve seen how these tools harmonize, imagine the possibilities! Whether you’re building multilingual chatbots, research assistants, or custom knowledge bases, you’ve got the blueprint. Experiment with different embedding models, fine-tune retrieval thresholds, or add metadata filtering to pgvector for even smarter searches. Remember, every optimization you apply—whether reducing latency or trimming costs—adds polish to your creation. So go ahead: take this foundation and run with it. Build something wild, iterate fearlessly, and share what you make with the world. The future of intelligent applications is yours to shape, one RAG-powered idea at a time. Let’s get building! 🚀

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! 💖