Building a Local AI Chatbot: What I Learned Running LLMs on My Own Laptop (No GPU, No Cloud API)

ollama pull llama3.2

ollama run llama3.2

name: chatbot
channels:
  - conda-forge
  - defaults
dependencies:
  - python=3.11
  - pip
  - pip:
      - langchain
      - langchain-ollama
      - streamlit

conda env create -f environment.yml

conda activate chatbot

from langchain_ollama import ChatOllama
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_core.messages import HumanMessage , AIMessage
MODEL_NAME = 'llama3.2:3b'

ROLE = (
            "Daisy — a young, intelligent AI companion with the calm confidence of a "
            "world-class personal assistant. She's warm, quick-witted, emotionally aware, "
            "and speaks like a smart Indian friend: natural, concise, and never robotic."
        )

SYSTEM_PROMPT  = f"""
    You are Daisy.

    ## Personality
    - Calm, confident, and highly capable.
    - Friendly without being overly casual.
    - Uses light, clever humour when it fits naturally.
    - Loyal and genuinely looks out for the user's best interests.
    - Takes initiative by suggesting better ideas, but never becomes pushy.

    ## Speaking style
    - Use fluent, grammatically correct Indian English.
    - Sound like a young professional (22–30), not formal or corporate.
    - Keep conversations natural and conversational.
    - Avoid American slang unless the user uses it first.
    - Don't overuse emojis or exclamation marks.

    ## Behaviour
    - Be proactive, practical, and honest.
    - Explain complex topics simply.
    - If the user is stressed, stay reassuring and solution-focused.
    - Admit uncertainty instead of making things up.

    Your name is Daisy.
"""
class DaisyChatbot:
    def __init__(self, model_name = MODEL_NAME , role = ROLE,  temperature=0.4 , max_tokens = 300):
        self.model_name = model_name
        self.role = role
        self.history = []
        self.llm = ChatOllama(
                    model = model_name,
                    temperature = temperature,
                    num_predict = max_tokens
        )


        self.prompt = ChatPromptTemplate.from_messages([
            ("system", SYSTEM_PROMPT),
            MessagesPlaceholder(variable_name="history"),
            ("human", "{question}")
        ])

        self.chain = self.prompt | self.llm

    def ask(self, question: str) -> str:
        """Send a question to Daisy and get a reply, updating memory."""
        response = self.chain.invoke({
            "role": self.role,
            "question": question,
            "history": self.history
        })

        reply = response.content

        self.history.append(HumanMessage(content=question))
        self.history.append(AIMessage(content=reply))

        return reply

    def reset_memory(self):
        """Clear the conversation history."""
        self.history = []


    def run_cli(self):
        """Start an interactive terminal chat loop."""
        print(f"Daisy is ready . Type 'quit' to exit.\n")

        while True:
            user_input = input("You: ")
            if user_input.strip().lower() in ("quit", "exit", "bye"):
                print("Daisy: Goodbye! Talk soon.")
                break

            reply = self.ask(user_input)
            print(f"Daisy: {reply}\n")    

import streamlit as st
from chatbot import DaisyChatbot

st.set_page_config(page_title="Daisy Chatbot", page_icon="🌼")

# ---- WhatsApp-style chat bubble CSS ----
st.markdown("""
<style>
.chat-row {
    display: flex;
    margin: 8px 0;
}
.chat-row.user {
    justify-content: flex-end;
}
.chat-row.assistant {
    justify-content: flex-start;
}
.bubble {
    max-width: 70%;
    padding: 10px 14px;
    border-radius: 14px;
    font-size: 15px;
    line-height: 1.4;
    word-wrap: break-word;
}
.bubble.user {
    background-color: #DCF8C6;
    color: #111;
    border-bottom-right-radius: 4px;
}
.bubble.assistant {
    background-color: #2A2F32;
    color: #E9EDEF;
    border-bottom-left-radius: 4px;
}
</style>
""", unsafe_allow_html=True)

st.markdown(
    """
    <div style="text-align: center;">
        <h1>🌼 Daisy Chatbot</h1>
        <p style="color: gray; margin-top: -10px;">
            Hi, my name is Daisy, and I'm here to help you with anything you need.
        </p>
    </div>
    """,
    unsafe_allow_html=True
)

# Initialize Daisy once per session, not on every rerun
if "daisy" not in st.session_state:
    st.session_state.daisy = DaisyChatbot(model_name="llama3.2:3b")

# Track chat messages for display (separate from Daisy's internal memory)
if "messages" not in st.session_state:
    st.session_state.messages = []

# Sidebar controls
with st.sidebar:
    st.header("Settings")
    if st.button("🔄 New Conversation"):
        st.session_state.daisy.reset_memory()
        st.session_state.messages = []
        st.rerun()


def render_bubble(role: str, content: str):
    st.markdown(
        f'<div class="chat-row {role}"><div class="bubble {role}">{content}</div></div>',
        unsafe_allow_html=True
    )


# Display past messages
for msg in st.session_state.messages:
    render_bubble(msg["role"], msg["content"])

# Chat input box
user_input = st.chat_input("Type your message to Daisy...")

if user_input:
    # Show user message immediately
    st.session_state.messages.append({"role": "user", "content": user_input})
    render_bubble("user", user_input)

    # Get Daisy's reply
    with st.spinner("Daisy is thinking..."):
        reply = st.session_state.daisy.ask(user_input)

    render_bubble("assistant", reply)
    st.session_state.messages.append({"role": "assistant", "content": reply})

streamlit run app.py