Build RAG Chatbot with LangChain, pgvector, NVIDA Llama 3 70B Instruct, and Ollama snowflake-arctic-embed

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.)
NVIDIA Llama 3 70B Instruct: This powerful model is designed for instruction-following tasks, leveraging its 70 billion parameters to deliver high-quality responses. It excels in generating detailed answers and engaging in complex dialogues, making it ideal for educational tools, customer support, and interactive applications that require nuanced understanding and guidance.
Ollama Snowflake-Arctic-Embed: This model specializes in generating high-dimensional embeddings for structured and unstructured data, leveraging advanced deep learning techniques. Its strengths include efficient handling of large datasets and producing contextual representations, making it ideal for applications in recommendation systems, semantic search, and personalized content delivery.

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 NVIDA Llama 3 70B Instruct

pip install -qU "langchain-nvidia-ai-endpoints"

import getpass
import os

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

from langchain.chat_models import init_chat_model

llm = init_chat_model("meta/llama3-70b-instruct", model_provider="nvidia")

Step 3: Install and Set Up Ollama snowflake-arctic-embed

pip install -qU langchain-ollama

from langchain_ollama import OllamaEmbeddings

embeddings = OllamaEmbeddings(model="snowflake-arctic-embed")

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.

NVIDIA Llama 3 70B Instruct optimization tips

NVIDIA Llama 3 70B Instruct is a high-precision model ideal for RAG applications requiring in-depth reasoning and analysis. Optimize retrieval by using hierarchical document ranking to filter only the most relevant passages, reducing unnecessary token consumption. Structure prompts with a clear separation between user queries, retrieved context, and system instructions for optimal performance. Keep temperature between 0.1 and 0.3 for factual consistency while fine-tuning top-k and top-p for better control over response diversity. Leverage NVIDIA’s TensorRT-LLM and optimized inference stacks to accelerate model execution and reduce latency. Use batching strategies to improve throughput for high-volume workloads. If deploying multiple models, assign Llama 3 70B to handle complex queries requiring deep contextual understanding while reserving lighter models for faster, low-complexity tasks.

Ollama snowflake-arctic-embed optimization tips

To optimize the Ollama snowflake-arctic-embed component in your Retrieval-Augmented Generation setup, ensure that you fine-tune the embedding model on domain-specific data to improve relevance and accuracy. Utilize a caching mechanism for frequently accessed embeddings to reduce computation time. Experiment with different embedding dimensions to balance performance and resource usage, and implement vector quantization techniques to save memory space without significantly impacting quality. Additionally, regularly monitor the performance metrics and adjust your hyperparameters accordingly to achieve the best outcomes in your retrieval tasks.

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 RAG (Retrieval-Augmented Generation) system from the ground up! You learned how LangChain acts as the glue, orchestrating workflows between components like a pro. With pgvector as your vector database, you saw how to store and query embeddings efficiently, turning unstructured data into searchable knowledge. Then came the magic of NVIDIA’s Llama 3 70B Instruct, a powerhouse LLM that generates human-like responses by leveraging retrieved context, and Ollama’s Snowflake-Arctic-Embed, which transformed text into rich embeddings with precision. Together, these tools form a seamless pipeline: ingest data, embed it, store it, retrieve relevant snippets, and generate answers that feel almost alive. You even explored optimization tricks—like tuning chunk sizes or adjusting similarity thresholds—to squeeze every drop of performance from your system. And let’s not forget the free RAG cost calculator, your secret weapon for balancing quality and budget!

Now that you’ve seen the pieces come together, it’s time to run wild with possibilities! Whether you’re building chatbots, research assistants, or custom AI tools, you’ve got the foundation to innovate. Experiment with different models, tweak your retrieval logic, or scale your database—every iteration brings you closer to something extraordinary. The future of AI-powered applications is yours to shape. So fire up your IDE, embrace the trial-and-error joy, and start creating. The world needs your ideas, and with RAG in your toolkit, there’s no limit to what you can build. Let’s go! 🚀

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! 💖