Build RAG Chatbot with LangChain, pgvector, Cohere Command, and NVIDIA arctic-embed-l

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.)
Cohere Command: Cohere Command is a powerful language model designed for task-oriented applications, emphasizing efficiency and scalability. It excels in generating contextual responses, deploying natural language processing tasks like text generation, summarization, and query answering. Ideal for businesses looking to enhance customer interactions and automate workflows with accurate and relevant outputs.
NVIDIA arctic-embed-l: This AI model is designed for optimizing embedded systems with a focus on low-latency processing and energy efficiency. It excels in real-time applications, making it ideal for edge computing in smart devices, IoT applications, and automated systems, enabling advanced analytics and decision-making on-site.

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 Cohere Command

pip install -qU "langchain[cohere]"

import getpass
import os

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

from langchain.chat_models import init_chat_model

llm = init_chat_model("command", model_provider="cohere")

Step 3: Install and Set Up NVIDIA arctic-embed-l

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_nvidia_ai_endpoints import NVIDIAEmbeddings

embeddings = NVIDIAEmbeddings(model="snowflake/arctic-embed-l")

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.

Cohere Command optimization tips

Cohere Command is a general-purpose language model that can be optimized for RAG workflows through prompt engineering, efficient retrieval, and structured response control. To improve accuracy, use Cohere’s reranking capabilities to filter and prioritize retrieved documents before passing them into the model. Keep input prompts concise and structured, reducing token overhead while ensuring clear context for the model. Optimize response quality by adjusting parameters such as temperature (0.1–0.3 for factual accuracy) and top-p sampling to control creativity levels. Implement hybrid search techniques by combining dense and sparse retrieval methods to improve recall and precision. For cost-efficient scaling, cache frequently queried responses and precompute embeddings for common knowledge areas. Stream responses where real-time generation is required, minimizing latency while ensuring user engagement. Monitor API usage and latency through Cohere’s analytics tools to fine-tune retrieval strategies based on performance trends.

NVIDIA arctic-embed-l optimization tips

To optimize the NVIDIA arctic-embed-l component in your Retrieval-Augmented Generation (RAG) setup, consider implementing a multi-threading approach to parallelize data processing, which can significantly enhance throughput. Make use of mixed precision training to speed up the model's computations while minimizing memory usage. Regularly fine-tune your embeddings with domain-specific data to improve their relevance and accuracy. Additionally, leverage batch processing techniques to reduce latency and ensure efficient GPU utilization. Monitor your inference times and adjust the cache size dynamically based on workload patterns to balance speed and resource consumption 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 now, you’ve unlocked the magic of building a RAG system from the ground up! You learned how LangChain acts as the glue, orchestrating the entire pipeline with its flexible framework—connecting data sources, managing workflows, and seamlessly integrating components. With pgvector as your vector database, you saw how to store and retrieve embeddings efficiently, leveraging PostgreSQL’s power to handle similarity searches at scale. Cohere Command stepped in as the LLM powerhouse, turning retrieved context into coherent, human-like responses, while NVIDIA’s arctic-embed-l model transformed raw text into rich embeddings, ensuring your system understands the nuances of your data. Together, these tools form a robust RAG pipeline that’s both dynamic and responsive, capable of tackling everything from customer support bots to research assistants.

But it doesn’t stop there! You also picked up pro tips for optimizing performance, like fine-tuning chunking strategies or indexing metadata in pgvector to speed up queries. And let’s not forget the cherry on top—the free RAG cost calculator you explored, which helps you balance accuracy and budget as you scale. Imagine what’s next: tweaking parameters, experimenting with hybrid search, or even training custom embeddings. The possibilities are endless, and you’ve got all the tools to make it happen. So go ahead—dive into your own projects, play with these building blocks, and watch your ideas come to life. The future of intelligent applications is in your hands, and you’re already crushing it. Time to build, innovate, and wow the world with what you’ve learned! 🚀

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! 💖