Local Chatbot (Streamlit + Ollama)

A simple, privacy‑friendly chatbot UI built with Streamlit and powered by Ollama for local LLM inference.

---

✨ Features

• Multi‑chat sessions: create, switch, rename, and delete conversations.
• Per‑chat system prompt: customize the assistant’s behavior for each chat.
• Streaming responses: see answers appear in real time.
• Temperature & Max tokens controls: fine‑tune generation.
• Local storage: chats are saved as JSON files in ./chats/.

---

🧩 Requirements

• Python 3.9+
• https://ollama.ai installed and running locally
• Streamlit and Requests libraries

---

🚀 Quick Start

1. Install dependencies

   pip install streamlit requests

2. Start Ollama and pull a model

   ollama serve
   ollama pull llama3.2

3. Run the app

   streamlit run app.py

---

💾 Data Persistence

Chats are stored in ./chats/<chat_id>.json with this structure:

{
  "name": "Chat 1",
  "created_at": "2025-11-07T15:42:10",
  "model": "llama3.2",
  "system_prompt": "You are a helpful AI assistant.",
  "messages": [
    { "role": "user", "content": "Hello" },
    { "role": "assistant", "content": "Hi! How can I help?" }
  ]
}

---

⚙️ Configuration

Edit app.py to change:

• OLLAMA_CHAT_API: Ollama API endpoint (default: http://localhost:11434/api/chat)
• MODEL_NAME: default model name
• SAVE_DIR: folder for chat files
• Logo path and size

---

📚 Tech Stack

• Frontend: Streamlit
• Backend: Ollama local LLM
• Storage: JSON files

---