Build RAG Chatbot with LangChain, pgvector, Anthropic Claude 3.5 Haiku, and HuggingFace all-MiniLM-L12-v1

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 3.5 Haiku: This model builds upon Claude 3's capabilities with enhanced understanding and generation of nuanced language. It excels in creative writing, conversational AI, and complex query handling. Best suited for tasks where clarity and depth of response are paramount, Claude 3.5 balances efficiency with sophisticated insights.
HuggingFace all-MiniLM-L12-v1: This model is a lightweight transformer designed for efficient natural language understanding and generation tasks. It excels in providing high-quality embeddings for various applications, including search, clustering, and conversational AI, while maintaining a small footprint for faster inference and deployment. Ideal for resource-constrained environments or mobile applications, it offers a balance between performance and efficiency.

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 3.5 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-3-5-haiku-latest", model_provider="anthropic")

Step 3: Install and Set Up HuggingFace all-MiniLM-L12-v1

pip install -qU langchain-huggingface

from langchain_huggingface import HuggingFaceEmbeddings

embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L12-v1")

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 3.5 Haiku optimization tips

Claude 3.5 Haiku offers improved efficiency and accuracy over its predecessor, making it ideal for latency-sensitive RAG workflows. Optimize by leveraging structured prompts that minimize token waste while maintaining clarity. Use adaptive retrieval strategies where simpler queries receive fewer context documents, preventing excessive computation. Implement embeddings-based reranking to ensure only the most relevant information is passed to the model, improving both speed and response quality. Reduce API calls by caching high-traffic queries and employing response summarization techniques to streamline outputs. Tune temperature and nucleus sampling to ensure responses remain factual and well-structured, typically keeping temperature around 0.1-0.2 for strict accuracy. Optimize batch processing for large-scale retrieval tasks, reducing the overhead of multiple individual queries. Use Claude 3.5 Haiku in combination with higher-end models strategically, allowing for cost-effective scaling in production RAG systems.

HuggingFace all-MiniLM-L12-v1 optimization tips

To optimize the HuggingFace all-MiniLM-L12-v1 model for your Retrieval-Augmented Generation (RAG) setup, consider implementing mixed precision training to speed up computations and reduce memory usage, enabling you to handle larger batch sizes. Experiment with layer freezing during fine-tuning to preserve certain parameters while optimizing others, ensuring faster convergence. Use an efficient data preprocessing pipeline to reduce input bottlenecks, and implement caching mechanisms for frequently accessed data. Furthermore, leverage model distillation techniques to create smaller, faster versions of the model that maintain comparable performance, and experiment with different pooling strategies to find the most effective way to condense retrieved documents for better context input. Lastly, regularly monitor and fine-tune hyperparameters such as learning rate and batch size based on validation performance to achieve optimal results.

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 modern AI tooling to build a fully functional RAG pipeline from the ground up! You learned how LangChain acts as the glue, orchestrating workflows between components with ease. By integrating pgvector as your vector database, you saw how to store and retrieve dense embeddings efficiently—turning unstructured data into searchable knowledge. Anthropic Claude 3.5 Haiku stepped in as your LLM powerhouse, generating human-like responses that feel natural and context-aware, while HuggingFace’s all-MiniLM-L12-v1 model transformed text into meaningful embeddings, bridging the gap between raw data and semantic understanding. Together, these tools created a seamless pipeline where retrieval meets generation, enabling smarter, faster, and more accurate AI applications. You even picked up pro tips for optimizing performance, like tuning chunk sizes and balancing speed-accuracy trade-offs—plus, that free RAG cost calculator you explored ensures you can build cost-efficient systems without surprises!

Now, imagine what’s next. You’ve got the blueprint to build RAG systems that answer questions, summarize content, or power chatbots with domain-specific expertise. The tools are yours to wield, and the possibilities are endless. Whether you’re enhancing customer support, analyzing research papers, or creating personalized experiences, you’re equipped to innovate. Remember, every line of code you write brings AI closer to real-world impact. So fire up your IDE, experiment with new datasets, tweak those parameters, and watch your ideas come alive. The future of intelligent applications is yours to shape—start building, keep iterating, and let your creativity run wild! 🚀

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! 💖