Build RAG Chatbot with LangChain, pgvector, Anthropic Claude 3 Haiku, and Cohere embed-english-light-v2.0

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.)
Anthropic Claude 3: This advanced AI language model from Anthropic focuses on safety and alignment, capable of generating coherent and context-aware text. It excels in creative writing, conversational AI, and insightful summarization. Ideal for creating engaging content while ensuring adherence to ethical standards and user intent.
Cohere embed-english-light-v2.0: This lightweight embedding model is designed for efficient English text encoding, providing high-quality representations for various natural language processing tasks. It excels in scenarios requiring embedding generation with minimal computational resources, such as document similarity, clustering, and recommendation systems, ensuring fast performance without compromising accuracy.

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 Anthropic Claude 3 Haiku

pip install -qU "langchain[anthropic]"

import getpass
import os

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

from langchain.chat_models import init_chat_model

llm = init_chat_model("claude-3-haiku-20240307", model_provider="anthropic")

Step 3: Install and Set Up Cohere embed-english-light-v2.0

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_cohere import CohereEmbeddings

embeddings = CohereEmbeddings(model="embed-english-light-v2.0")

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.

Anthropic Claude 3 Haiku optimization tips

Claude 3 Haiku is designed for efficiency, making it a great choice for low-latency RAG applications. Optimize token usage by structuring prompts concisely, removing redundant text, and leveraging system messages effectively to guide responses. Use function calling when applicable to offload structured processing tasks and improve response reliability. Batch process queries where possible to reduce API overhead and enhance throughput. If latency is critical, consider caching frequent queries and pre-generating responses for common questions. Fine-tune response control with temperature and top-p sampling; lower temperature values (e.g., 0.2-0.3) help maintain consistency in factual retrieval tasks. Use streaming mode for real-time applications to get faster partial responses while processing large prompts. Regularly evaluate and adjust model parameters based on performance benchmarks to balance speed and accuracy in your RAG pipeline.

Cohere embed-english-light-v2.0 optimization tips

Cohere embed-english-light-v2.0 is designed for faster, more resource-efficient embedding generation in English-language tasks. To optimize processing, preprocess text by removing stopwords, punctuation, and unnecessary formatting to minimize the complexity of the input. Leverage vector compression techniques, such as quantization or PCA, to reduce storage requirements without sacrificing significant accuracy. For retrieval, implement hybrid search strategies that combine keyword search with dense vector search to achieve faster and more relevant results. Use multi-threading or parallel processing to handle large batches of embeddings efficiently. Apply caching for frequently queried embeddings to minimize re-processing and reduce query latency, especially for high-traffic RAG systems.

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 system that’s both intelligent and efficient! You’ve seen how LangChain acts as the glue, seamlessly orchestrating the flow of data between components while simplifying complex workflows. With pgvector, you’ve harnessed the magic of vector databases to store and retrieve embeddings at scale, turning unstructured text into searchable knowledge. The Cohere embed-english-light-v2.0 model stepped in to transform raw text into rich, contextual embeddings, ensuring your system understands nuances and relationships in the data. And let’s not forget Anthropic Claude 3 Haiku, the LLM that brings it all to life—generating human-like responses grounded in the retrieved context, balancing speed, accuracy, and cost-effectiveness like a pro. Along the way, you picked up optimization tricks like chunking strategies for better embeddings and indexing best practices in pgvector to turbocharge performance. Plus, that free RAG cost calculator? It’s your new secret weapon for balancing budgets without sacrificing quality.

Now you’re equipped to build RAG systems that don’t just answer questions—they understand them. Whether you’re tackling customer support bots, research assistants, or creative content generators, you’ve got the tools to make it happen. The best part? This is just the beginning. Experiment with different models, tweak retrieval thresholds, or layer in domain-specific data to make your application uniquely powerful. Remember, every iteration makes your system smarter and more adaptable. So go ahead—fire up your IDE, plug in these components, and watch your ideas transform into AI-driven solutions. The future of intelligent applications is in your hands, and it’s time to build something amazing. Let’s RAG on! 🚀

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! 💖