Add environment configuration, update README, and implement core functionality

- Create .env file for API keys and model configurations
- Update .gitignore to exclude .env file
- Revise README for clarity and add local run instructions
- Implement OpenAI and Ollama query functions in utils.py
- Establish response generation logic based on selected model

.env

@@ -0,0 +1,4 @@
+OPENAI_API_KEY=sk-xxxxx
+OPENAI_MODEL=gpt-4o
+USE_OLLAMA=false
+OLLAMA_MODEL=llama3

.gitignore

@@ -19,6 +19,7 @@ dist/
 downloads/
 eggs/
 .eggs/
+.env
 lib/
 lib64/
 parts/

README.md

@@ -1,22 +1,20 @@
 # 🤖 LLMates – Chat with Custom AI Personas
 
-LLMates is a minimalist, persona-driven chatbot interface built using **Gradio** and **OpenAI's GPT-3.5**.
-It lets you switch between assistant "personalities" like a **Python Tutor**, **Regex Helper**, or **Startup Coach**, all powered by curated prompt templates.
+LLMates is a minimal, modular chatbot app where you can switch between assistant personas powered by LLMs.
+It supports OpenAI (e.g. GPT-4o), or free alternatives like **Ollama** (LLaMA3, Mistral) or Hugging Face.
 
-## 🌟 Features
-- Predefined assistant personas (via prompt injection)
-- Seamless Gradio chat interface with session memory
-- Easy to extend with new roles or APIs
-- Clean and modular code
+## 💡 Personas
+- Python Tutor
+- Regex Helper
+- Motivational Coach
+- Startup Advisor
 
-## 🔧 Stack
+## ⚙️ Stack
 - Gradio UI
-- OpenAI Chat API (GPT-4.1)
-- Python + dotenv
+- OpenAI / Ollama / HF model backend
+- Modular Python
 
-## 📦 Coming Soon
-- Deploy on Hugging Face Spaces
-- Add real-time persona switching
-- Save/export chat sessions
-
----
+## 🧪 Run Locally
+```bash
+pip install -r requirements.txt
+python app.py

app.py

@@ -1,23 +1,2 @@
-# -*- coding: utf-8 -*-
+# This is the file for the gradio app
 
-"""
-llmates.py
-This module contains the main entry point for the llmates program.
-It initializes the application and displays a welcome message.
-"""
-
-
-def main():
-    """
-    The main entry point for the llmates program.
-    This function initializes the llmates application and displays a welcome message.
-    Returns:
-        None
-    """
-
-    print("Hello from llmates!")
-
-
-if __name__ == "__main__":
-    X = "Hello from the llama!"
-    main()

pyproject.toml

@@ -4,4 +4,9 @@ version = "0.1.0"
 description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.9"
-dependencies = []
+dependencies = [
+    "dotenv>=0.9.9",
+    "gradio>=4.44.1",
+    "openai>=1.82.0",
+    "requests>=2.32.3",
+]

utils.py

@@ -0,0 +1,44 @@
+from config import OPENAI_API_KEY, OPENAI_MODEL, USE_OLLAMA, OLLAMA_MODEL
+import requests
+import openai
+import os
+
+openai.api_key = OPENAI_API_KEY
+
+def query_openai(messages):
+    try:
+        response = openai.ChatCompletion.create(
+            model=OPENAI_MODEL,
+            messages=messages
+        )
+        return response["choices"][0]["message"]["content"]
+    except Exception as e:
+        return f"⚠️ OpenAI Error: {e}"
+
+def query_ollama(prompt):
+    try:
+        res = requests.post(
+            "http://localhost:11434/api/generate",
+            json={"model": OLLAMA_MODEL, "prompt": prompt}
+        )
+        return res.json()["response"]
+    except Exception as e:
+        return f"⚠️ Ollama Error: {e}"
+
+def generate_response(persona, user_input, history):
+    if USE_OLLAMA:
+        full_prompt = f"{persona}\n\n"
+        for u, b in history:
+            full_prompt += f"User: {u}\nBot: {b}\n"
+        full_prompt += f"User: {user_input}\nBot:"
+        reply = query_ollama(full_prompt)
+    else:
+        messages = [{"role": "system", "content": persona}]
+        for u, b in history:
+            messages.append({"role": "user", "content": u})
+            messages.append({"role": "assistant", "content": b})
+        messages.append({"role": "user", "content": user_input})
+        reply = query_openai(messages)
+
+    history.append((user_input, reply))
+    return history, history