Build RAG Chatbot with LangChain, pgvector, Mistral AI Codestral Mamba, and voyage-3

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 Codestral Mamba: A high-performance coding assistant designed to enhance software development efficiency, Codestral Mamba excels in generating and debugging code across multiple programming languages. With its advanced understanding of programming contexts and common libraries, it is ideal for developers seeking rapid prototyping, code optimization, and refactoring support.
Voyage-3: Designed for AI-powered navigation and journey planning, Voyage-3 optimizes route efficiency while providing real-time traffic updates and data insights. Its strengths lie in predictive analysis and adaptive learning, making it ideal for logistics, delivery services, and travel apps that demand reliable and intelligent navigation solutions.

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 Codestral Mamba

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("open-codestral-mamba", model_provider="mistralai")

Step 3: Install and Set Up voyage-3

pip install -qU langchain-voyageai

import getpass
import os

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

from langchain-voyageai import VoyageAIEmbeddings

embeddings = VoyageAIEmbeddings(model="voyage-3")

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 Codestral Mamba optimization tips

Codestral Mamba is optimized for code generation and completion, making it ideal for RAG applications that involve structured programming queries. Improve retrieval quality by using embeddings trained on code datasets to ensure retrieved context aligns well with the programming language and task. To enhance response accuracy, ensure input prompts are formatted with clear specifications, including function definitions, docstrings, and comments. Adjust temperature values dynamically—lower values (0.1–0.2) for deterministic code generation, higher values (0.3–0.5) for exploratory suggestions. Use caching for common programming patterns and frequently queried snippets to reduce latency. If deploying in an IDE or interactive coding environment, enable streaming to provide real-time feedback and suggestions. Leverage parallel inference techniques when handling multiple simultaneous code queries to optimize performance.

voyage-3 optimization tips

voyage-3 is a versatile model suitable for balanced performance in RAG systems, making efficient retrieval strategies crucial for maintaining low latency and high accuracy. Improve retrieval by leveraging embedding-based similarity search with reranking to ensure relevant context is included. Structure prompts with clear context separation and concise instructions to maximize response accuracy. Set temperature between 0.1 and 0.3 for controlled output while tuning top-k and top-p for flexibility. Implement response caching for frequently queried data to minimize redundant processing and API calls. Utilize parallel processing and request batching to optimize resource efficiency. For multi-model deployments, assign voyage-3 to mid-tier complexity tasks while using larger models for deeper analysis and smaller models for real-time, low-latency queries.

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 the ground up! You learned how LangChain acts as the glue that orchestrates the entire pipeline, seamlessly connecting your data sources, language models, and vector databases. With pgvector, you now have a scalable, PostgreSQL-powered vector database to store and retrieve embeddings efficiently, ensuring your system can handle real-world data demands. The integration of Mistral AI’s Codestral Mamba as your LLM brought lightning-fast, high-quality text generation to the table, turning retrieved information into coherent, context-aware responses. And by leveraging voyage-3 as your embedding model, you mastered the art of transforming raw text into rich numerical representations, capturing semantic meaning for precise similarity searches. Along the way, you discovered optimization tricks like chunking strategies for better retrieval and indexing best practices in pgvector to speed up queries—plus, the free RAG cost calculator gave you a practical tool to estimate expenses and fine-tune your setup without breaking the bank.

Now, armed with this toolkit, you’re ready to revolutionize how information is accessed and utilized. Imagine building chatbots that answer with razor-sharp accuracy, creating research assistants that synthesize knowledge in seconds, or crafting personalized recommendation engines that feel almost magical. The tutorial didn’t just teach you steps—it handed you the keys to innovate. So go ahead! Experiment with different LLMs, tweak your embedding models, or layer in domain-specific data to make your RAG system uniquely yours. The best part? Every improvement you make ripples outward, solving real problems and delighting users. The future of intelligent applications is yours to shape—start building, keep iterating, and watch your ideas come to life. You’ve got this! 🚀

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! 💖