Build RAG Chatbot with LangChain, pgvector, Mistral AI Ministral 8B, and Google Vertex AI textembedding-gecko@001

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.)
Mistral AI Ministral 8B: This model is designed for high-performance generative tasks with 8 billion parameters, offering a balance of efficiency and capability. It excels in document generation, conversational AI, and creative content production. Ideal for developers seeking a powerful yet manageable model for sophisticated language applications without the resource demands of larger architectures.
Google Vertex AI textembedding-gecko@001: This AI model specializes in generating high-quality text embeddings, facilitating superior semantic understanding and context capturing. Its strengths lie in efficient processing and scalability, making it ideal for applications like search, recommendation systems, and natural language understanding tasks that demand precise insights from textual data.

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 Mistral AI Ministral 8B

pip install -qU "langchain[mistralai]"

import getpass
import os

if not os.environ.get("MISTRAL_API_KEY"):
  os.environ["MISTRAL_API_KEY"] = getpass.getpass("Enter API key for Mistral AI: ")

from langchain.chat_models import init_chat_model

llm = init_chat_model("ministral-8b-latest", model_provider="mistralai")

Step 3: Install and Set Up Google Vertex AI textembedding-gecko@001

pip install -qU langchain-google-vertexai

from langchain_google_vertexai import VertexAIEmbeddings

embeddings = VertexAIEmbeddings(model="textembedding-gecko@001")

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.

Mistral AI Ministral 8B optimization tips

Ministral 8B provides a balance between efficiency and reasoning power, making it a good mid-range choice for RAG applications. Optimize retrieval by leveraging hybrid search (combining vector and keyword search) to improve accuracy. Use prompt engineering techniques, such as structured input formatting and logical ordering of context, to enhance response quality. Adjust temperature (0.1–0.3) and top-k values to balance factual accuracy with creative flexibility. Implement response caching for commonly accessed queries to improve latency. If deploying at scale, use model parallelism to distribute workloads efficiently across multiple GPUs or nodes. Optimize memory management by using half-precision (FP16) or quantized models to improve throughput. Fine-tune retrieval granularity, ensuring that only the most relevant and concise context is included in each query.

Google Vertex AI textembedding-gecko@001 optimization tips

Google Vertex AI textembedding-gecko@001 provides strong semantic understanding suitable for a variety of RAG workflows. To optimize retrieval, preprocess text to remove non-essential words and structure content to highlight key information. Use nearest neighbor search with techniques like HNSW or FAISS to enhance retrieval speed without sacrificing accuracy. Optimize batch processing by grouping multiple text queries together, reducing API call overhead and increasing throughput. Fine-tune temperature settings to ensure consistent responses, and adjust top-k or top-p parameters based on the desired level of output diversity. Cache embeddings for frequently used text and set up periodic updates to ensure embedding freshness. Use dimensionality reduction to manage memory usage and storage costs effectively.

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 powerful RAG system from the ground up! You’ve seen how LangChain acts as the glue, seamlessly orchestrating the flow of data between components while handling tasks like document splitting and prompt templating. Paired with pgvector, a vector database that stores and retrieves embeddings with speed and precision, you’ve learned to turn unstructured text into searchable knowledge. Speaking of embeddings, Google Vertex AI’s textembedding-gecko@001 transformed your documents into rich numerical representations, capturing meaning in ways that let pgvector work its similarity-search wizardry. And at the heart of it all, Mistral AI’s Mixtral 8B brought the brains, generating human-like responses grounded in the context you retrieved—proving that open-source models can pack serious punch! Along the way, you picked up pro tips like optimizing chunk sizes for better retrieval and balancing cost-performance tradeoffs, maybe even experimenting with the free RAG cost calculator to budget your AI projects wisely.

Now you’re equipped to build systems that don’t just answer questions but understand context—a superpower in today’s AI-driven world. Imagine the applications: smarter chatbots, research assistants that dig through mountains of data, or tools that democratize access to niche knowledge. The tutorial didn’t just hand you code; it gave you a blueprint for innovation. So what’s next? Tweak those parameters, experiment with new datasets, or swap in different models—every iteration is a step toward mastery. The future of intelligent apps is yours to shape. Go break things, optimize relentlessly, and build something that blows minds. The RAG revolution is here, and you’re already leading the charge! 🚀

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! 💖