Build RAG Chatbot with LangChain, pgvector, Cohere Command R, and IBM all-minilm-l12-v2

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 R: This model is designed for high-performance retrieval tasks, offering advanced capabilities in understanding and generating natural language. Its strengths lie in semantic search and document summarization, making it ideal for applications such as customer support, content generation, and knowledge management, where accuracy and context relevance are paramount.
IBM all-minilm-l12-v2: This model is a compact yet powerful transformer-based architecture optimized for natural language understanding and processing tasks. It excels in scenarios requiring efficient computation without sacrificing performance, making it ideal for applications in chatbots, information retrieval, and sentiment analysis. Its lightweight design enables integration in resource-constrained environments while maintaining competitive 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 Cohere Command R

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-r", model_provider="cohere")

Step 3: Install and Set Up IBM all-minilm-l12-v2

pip install -qU langchain-ibm

import getpass
import os

if not os.environ.get("WATSONX_APIKEY"):
  os.environ["WATSONX_APIKEY"] = getpass.getpass("Enter API key for IBM watsonx: ")

from langchain_ibm import WatsonxEmbeddings

embeddings = WatsonxEmbeddings(
    model_id="sentence-transformers/all-minilm-l12-v2",
    url="https://us-south.ml.cloud.ibm.com",
    project_id="<WATSONX PROJECT_ID>",
)

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 R optimization tips

Cohere Command R is designed for retrieval-augmented generation, making efficient context retrieval and ranking critical for system performance. Optimize retrieval pipelines by using Cohere’s embedding-based search to identify and rank the most relevant documents, reducing unnecessary input context while maintaining accuracy. Improve response quality by fine-tuning temperature settings; lower values (0.1–0.2) work best for structured, fact-based queries, while higher values introduce more variability in generated responses. Utilize prompt templates to maintain consistent formatting, ensuring clarity in output. Implement batch processing where multiple queries need similar context, reducing redundant API calls. To enhance efficiency, cache top query results and leverage incremental context updates instead of repeatedly sending full document sets. If deploying at scale, monitor latency and response consistency with real-time metrics, adjusting retrieval thresholds dynamically for optimal balance between speed and completeness.

IBM all-minilm-l12-v2 optimization tips

To optimize the IBM all-minilm-l12-v2 model in a Retrieval-Augmented Generation (RAG) setup, consider fine-tuning it on domain-specific datasets to enhance relevance and accuracy for your particular use case. Implement model distillation techniques to reduce inference time while maintaining performance. Additionally, ensure efficient batch processing by adjusting the maximum sequence length based on your input data, and utilize mixed precision training to improve computational efficiency. Regularly evaluate the model's performance with various retrieval methods to identify the best combination and consider employing caching strategies for frequently accessed data to minimize latency. Finally, experiment with different hyperparameters, like learning rate and dropout rates, during fine-tuning 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 magic of building a powerful RAG system from scratch! You learned how LangChain acts as the glue that holds everything together, orchestrating workflows between components with ease. By integrating pgvector—a PostgreSQL extension for vector storage—you now know how to efficiently store and retrieve embeddings, turning unstructured data into searchable knowledge. Then came Cohere’s Command R, a state-of-the-art LLM that breathes life into your system, generating human-like responses by synthesizing retrieved context with your queries. And let’s not forget the IBM all-minilm-l12-v2 embedding model, which transformed raw text into meaningful vector representations, ensuring your system understands the nuances of language. Along the way, you picked up 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 for scalability without breaking the bank!

Now that you’ve seen how these pieces fit together—a framework, vector database, LLM, and embedding model—you’re ready to create your own intelligent applications! Whether it’s chatbots, research assistants, or custom knowledge bases, the possibilities are endless. Experiment with tweaking parameters, explore different LLMs, or layer in domain-specific data to make your RAG system truly unique. Remember, every iteration brings you closer to a faster, smarter, and more efficient solution. So go ahead—fire up your IDE, unleash your creativity, and start building. The future of AI-powered tools is in your hands, and this tutorial is just the beginning. Let’s make something amazing! 🚀

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! 💖