Simplify to single-model chat app: llama3.1:8b only. Add /api/chat SSE streaming, chatbot UI, remove model selection/download UI, build-time model pull

Dockerfile

@@ -11,11 +11,18 @@ RUN pip install --no-cache-dir -r requirements.txt
 
 COPY . .
 
+RUN ollama serve > /tmp/ollama-build.log 2>&1 & \
+    sleep 5 && \
+    echo "Pulling llama3.1:8b..." && \
+    ollama pull llama3.1:8b 2>&1 || echo "WARNING: Build-time pull failed, will retry at runtime"
+
 EXPOSE 7860
 
 CMD ollama serve > /tmp/ollama.log 2>&1 & \
     sleep 3 && \
-    echo "Starting model pull in background..." && \
-    nohup ollama pull llama3.1:8b > /tmp/ollama-pull.log 2>&1 & \
-    echo "Model pull started, launching app..." && \
+    if ! ollama list 2>/dev/null | grep -q llama3.1; then \
+        echo "llama3.1:8b not found, pulling in background..." && \
+        nohup ollama pull llama3.1:8b > /tmp/ollama-pull.log 2>&1 & \
+    fi && \
+    echo "Starting app..." && \
     uvicorn app:app --host 0.0.0.0 --port 7860

app.py

@@ -1,15 +1,14 @@
 import json
 import asyncio
-import uuid
-import re
 import shutil
 from datetime import datetime, timedelta
 from typing import Optional
 
-from fastapi import FastAPI, HTTPException, Depends, status, WebSocket, WebSocketDisconnect, Request, Form
+import httpx
+from fastapi import FastAPI, HTTPException, Depends, Request
 from fastapi.security import HTTPBearer, HTTPAuthorizationCredentials
 from fastapi.staticfiles import StaticFiles
-from fastapi.responses import HTMLResponse, RedirectResponse, JSONResponse
+from fastapi.responses import HTMLResponse, StreamingResponse
 from fastapi.templating import Jinja2Templates
 from jose import JWTError, jwt
 from pydantic import BaseModel
@@ -17,8 +16,7 @@ from pydantic import BaseModel
 from config import settings
 from database import (
     init_db, create_user, get_user_by_username, verify_password,
-    get_user_by_api_key, create_download_session, update_download_progress,
-    get_download_session, get_user_sessions, create_api_key,
+    get_user_by_api_key, create_api_key,
     get_user_api_keys, revoke_api_key, generate_api_key
 )
 
@@ -30,6 +28,9 @@ app.mount("/static", StaticFiles(directory="static"), name="static")
 
 init_db()
 
+OLLAMA_MODEL = "llama3.1:8b"
+OLLAMA_BASE = "http://localhost:11434"
+
 
 # --- Models ---
 
@@ -45,8 +46,9 @@ class LoginRequest(BaseModel):
 class CreateApiKeyRequest(BaseModel):
     key_name: str
 
-class CreateSessionRequest(BaseModel):
-    model_name: str
+class ChatRequest(BaseModel):
+    message: str
+    stream: bool = True
 
 
 # --- Auth Helpers ---
@@ -71,34 +73,14 @@ async def get_current_user(credentials: HTTPAuthorizationCredentials = Depends(s
         raise HTTPException(status_code=401, detail="User not found")
     return user
 
-
-# --- WebSocket Progress Manager ---
-
-class ConnectionManager:
-    def __init__(self):
-        self.active_connections: dict[str, list[WebSocket]] = {}
-
-    async def connect(self, session_id: str, websocket: WebSocket):
-        await websocket.accept()
-        if session_id not in self.active_connections:
-            self.active_connections[session_id] = []
-        self.active_connections[session_id].append(websocket)
-
-    def disconnect(self, session_id: str, websocket: WebSocket):
-        if session_id in self.active_connections:
-            self.active_connections[session_id].remove(websocket)
-            if not self.active_connections[session_id]:
-                del self.active_connections[session_id]
-
-    async def broadcast(self, session_id: str, data: dict):
-        if session_id in self.active_connections:
-            for ws in self.active_connections[session_id]:
-                try:
-                    await ws.send_text(json.dumps(data))
-                except Exception:
-                    pass
-
-manager = ConnectionManager()
+async def get_user_or_none(request: Request):
+    auth = request.headers.get("Authorization", "")
+    if not auth.startswith("Bearer "):
+        return None
+    try:
+        return await get_current_user(HTTPAuthorizationCredentials(scheme="Bearer", credentials=auth[7:]))
+    except:
+        return None
 
 
 # --- Web Pages ---
@@ -115,9 +97,9 @@ async def login_page(request: Request):
 async def dashboard_page(request: Request):
     return templates.TemplateResponse("dashboard.html", {"request": request})
 
-@app.get("/progress/{session_id}", response_class=HTMLResponse)
-async def progress_page(request: Request, session_id: str):
-    return templates.TemplateResponse("progress.html", {"request": request, "session_id": session_id})
+@app.get("/chat", response_class=HTMLResponse)
+async def chat_page(request: Request):
+    return templates.TemplateResponse("chat.html", {"request": request})
 
 
 # --- Auth API ---
@@ -147,29 +129,26 @@ async def me(user: dict = Depends(get_current_user)):
     }
 
 
-# --- Model Recommendations ---
+# --- Model / Status ---
 
-@app.get("/api/models")
-async def get_models():
-    return {"models": settings.recommended_models}
-
-@app.get("/api/installed-models")
-async def installed_models():
+@app.get("/api/status")
+async def status():
     ollama_path = shutil.which("ollama")
     if not ollama_path:
-        return {"models": []}
+        return {"ollama": False, "model": False, "message": "Ollama not installed"}
     try:
         proc = await asyncio.create_subprocess_exec(ollama_path, "list", stdout=asyncio.subprocess.PIPE, stderr=asyncio.subprocess.PIPE)
         stdout, _ = await asyncio.wait_for(proc.communicate(), timeout=5)
-        models = []
-        for line in stdout.decode().strip().split("\n")[1:]:
-            if line.strip():
-                parts = line.split()
-                if len(parts) >= 1:
-                    models.append({"name": parts[0], "size": parts[2] if len(parts) > 2 else "?"})
-        return {"models": models}
-    except:
-        return {"models": []}
+        installed = [line.split()[0] for line in stdout.decode().strip().split("\n")[1:] if line.strip()]
+        model_ready = OLLAMA_MODEL in installed
+        return {
+            "ollama": True,
+            "model": model_ready,
+            "installed": installed,
+            "message": "Ready" if model_ready else f"Model {OLLAMA_MODEL} not yet installed (pulling in background)"
+        }
+    except Exception as e:
+        return {"ollama": False, "model": False, "message": str(e)}
 
 
 # --- API Key Management ---
@@ -189,168 +168,48 @@ async def delete_api_key(key_id: int, user: dict = Depends(get_current_user)):
     return {"message": "API key revoked"}
 
 
-# --- Download Sessions ---
-
-@app.get("/api/ollama-status")
-async def ollama_status():
-    ollama_path = shutil.which("ollama")
-    if not ollama_path:
-        return {"available": False, "message": "Ollama not found on this server"}
-    try:
-        proc = await asyncio.create_subprocess_exec(ollama_path, "list", stdout=asyncio.subprocess.PIPE, stderr=asyncio.subprocess.PIPE)
-        stdout, _ = await asyncio.wait_for(proc.communicate(), timeout=5)
-        models = []
-        for line in stdout.decode().strip().split("\n")[1:]:
-            if line.strip():
-                parts = line.split()
-                if len(parts) >= 1:
-                    models.append(parts[0])
-        return {"available": True, "message": "Ollama is running", "models": models}
-    except Exception as e:
-        return {"available": False, "message": f"Ollama server not reachable: {str(e)}"}
-
-@app.post("/api/download-sessions")
-async def start_download_session(req: CreateSessionRequest, user: dict = Depends(get_current_user)):
-    ollama_path = shutil.which("ollama")
-    if not ollama_path:
-        raise HTTPException(status_code=400, detail="Ollama is not installed on this server. Run locally with Ollama installed.")
-    session_id = str(uuid.uuid4())
-    create_download_session(user["id"], session_id, req.model_name)
-    asyncio.create_task(ollama_download(session_id, req.model_name, ollama_path))
-    return {"session_id": session_id, "model_name": req.model_name, "status": "started"}
-
-@app.get("/api/download-sessions")
-async def list_sessions(user: dict = Depends(get_current_user)):
-    return {"sessions": get_user_sessions(user["id"])}
-
-@app.get("/api/download-sessions/{session_id}")
-async def get_session(session_id: str, user: dict = Depends(get_current_user)):
-    session = get_download_session(session_id)
-    if not session:
-        raise HTTPException(status_code=404, detail="Session not found")
-    if session["user_id"] != user["id"]:
-        raise HTTPException(status_code=403, detail="Not your session")
-    return session
-
-
-# --- WebSocket ---
-
-@app.websocket("/ws/{session_id}")
-async def websocket_endpoint(websocket: WebSocket, session_id: str):
-    await manager.connect(session_id, websocket)
-    try:
-        while True:
-            await websocket.receive_text()
-    except WebSocketDisconnect:
-        manager.disconnect(session_id, websocket)
-
-
-# --- Real Ollama Download ---
-
-def parse_ollama_progress(line: str) -> Optional[dict]:
-    m = re.search(r'pulling\s+\S+\s*:\s*(\d+)%\s*.*?(\d+\.?\d*)\s*(KB|MB|GB)\s*/\s*(\d+\.?\d*)\s*(KB|MB|GB)\s*(\d+\.?\d*)\s*(KB|MB)/s\s*(.+)?', line)
-    if m:
-        pct = int(m.group(1))
-        dl_val = float(m.group(2))
-        dl_unit = m.group(3)
-        total_val = float(m.group(4))
-        total_unit = m.group(5)
-        speed_val = float(m.group(6))
-        speed_unit = m.group(7)
-        eta_str = m.group(8).strip() if m.group(8) else ""
-
-        def to_mb(val, unit):
-            if unit == "GB": return int(val * 1024)
-            if unit == "KB": return int(val / 1024)
-            return int(val)
-
-        downloaded_mb = to_mb(dl_val, dl_unit)
-        total_mb = to_mb(total_val, total_unit)
-        speed_kbps = int(speed_val * 1024 if speed_unit == "MB" else speed_val)
-
-        eta_seconds = 0
-        if eta_str:
-            eta_parts = eta_str.split(":")
-            if len(eta_parts) == 2:
-                eta_seconds = int(eta_parts[0]) * 60 + int(eta_parts[1])
-            elif "m" in eta_str and "s" in eta_str:
-                parts = eta_str.replace("m", " ").replace("s", "").split()
-                eta_seconds = int(parts[0]) * 60 + (int(parts[1]) if len(parts) > 1 else 0)
-            elif "h" in eta_str:
-                parts = eta_str.replace("h", " ").replace("m", "").split()
-                eta_seconds = int(parts[0]) * 3600 + (int(parts[1]) * 60 if len(parts) > 1 else 0)
-
-        return {
-            "progress": pct,
-            "downloaded_mb": downloaded_mb,
-            "total_size_mb": total_mb,
-            "speed_kbps": speed_kbps,
-            "eta_seconds": eta_seconds,
-            "current_step": f"Downloading layer ({pct}%)"
-        }
-    if "pulling manifest" in line:
-        return {"current_step": "Pulling manifest...", "progress": 0}
-    if "verifying sha256" in line:
-        return {"current_step": "Verifying...", "progress": 95}
-    if "writing manifest" in line:
-        return {"current_step": "Writing manifest...", "progress": 98}
-    if "success" in line:
-        return {"current_step": "Done", "progress": 100, "status": "completed"}
-    return None
-
-async def ollama_download(session_id: str, model_name: str, ollama_path: str):
-    update_download_progress(session_id, status="starting", progress=0, current_step="Starting download...")
-    await manager.broadcast(session_id, {"status": "starting", "progress": 0, "current_step": "Starting download..."})
+# --- Chat API (streaming via SSE) ---
 
+@app.post("/api/chat")
+async def chat(req: ChatRequest, user: Optional[dict] = Depends(get_current_user)):
+    if not user:
+        raise HTTPException(status_code=401, detail="Authentication required")
+    model_ready = await check_model_ready()
+    if not model_ready:
+        raise HTTPException(status_code=503, detail=f"{OLLAMA_MODEL} is still downloading. Please wait and try again.")
+
+    async def generate():
+        async with httpx.AsyncClient(timeout=None) as client:
+            async with client.stream(
+                "POST",
+                f"{OLLAMA_BASE}/api/chat",
+                json={"model": OLLAMA_MODEL, "messages": [{"role": "user", "content": req.message}], "stream": True},
+            ) as resp:
+                async for line in resp.aiter_lines():
+                    if not line.strip():
+                        continue
+                    try:
+                        chunk = json.loads(line)
+                        content = chunk.get("message", {}).get("content", "")
+                        if content:
+                            yield f"data: {json.dumps({'content': content})}\n\n"
+                        if chunk.get("done"):
+                            yield f"data: {json.dumps({'done': True})}\n\n"
+                    except json.JSONDecodeError:
+                        continue
+
+    return StreamingResponse(generate(), media_type="text/event-stream")
+
+async def check_model_ready() -> bool:
     try:
         proc = await asyncio.create_subprocess_exec(
-            ollama_path, "pull", model_name,
-            stdout=asyncio.subprocess.PIPE,
-            stderr=asyncio.subprocess.PIPE
+            shutil.which("ollama"), "list",
+            stdout=asyncio.subprocess.PIPE, stderr=asyncio.subprocess.PIPE
         )
-
-        last_progress = {}
-
-        async def read_stderr():
-            nonlocal last_progress
-            while True:
-                line = await proc.stderr.readline()
-                if not line:
-                    break
-                decoded = line.decode(errors="replace").strip()
-                if not decoded:
-                    continue
-                parsed = parse_ollama_progress(decoded)
-                if parsed:
-                    last_progress.update({k: v for k, v in parsed.items() if v is not None})
-                    data = dict(last_progress)
-                    data["status"] = "downloading"
-                    update_download_progress(session_id, **data)
-                    await manager.broadcast(session_id, data)
-
-        async def read_stdout():
-            async for line in proc.stdout:
-                decoded = line.decode(errors="replace").strip()
-                if decoded:
-                    last_progress["current_step"] = decoded
-                    data = dict(last_progress)
-                    data["status"] = "downloading"
-                    update_download_progress(session_id, **data)
-                    await manager.broadcast(session_id, data)
-
-        await asyncio.gather(read_stderr(), read_stdout())
-        await proc.wait()
-
-        if proc.returncode == 0:
-            update_download_progress(session_id, status="completed", progress=100, current_step="Done", speed_kbps=0, eta_seconds=0, completed_at=datetime.utcnow().isoformat())
-            await manager.broadcast(session_id, {"status": "completed", "progress": 100, "current_step": "Done"})
-        else:
-            update_download_progress(session_id, status="error", current_step="Download failed", error_message=f"Process exited with code {proc.returncode}")
-            await manager.broadcast(session_id, {"status": "error", "current_step": "Download failed"})
-
-    except Exception as e:
-        update_download_progress(session_id, status="error", current_step="Error", error_message=str(e))
-        await manager.broadcast(session_id, {"status": "error", "current_step": f"Error: {str(e)}"})
+        stdout, _ = await asyncio.wait_for(proc.communicate(), timeout=5)
+        return any(OLLAMA_MODEL in line for line in stdout.decode().strip().split("\n")[1:])
+    except:
+        return False
 
 
 # --- Startup ---

templates/chat.html

@@ -0,0 +1,199 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Chat - Ollama</title>
+    <link rel="stylesheet" href="/static/style.css">
+    <style>
+        .chat-layout { display: flex; gap: 20px; min-height: 70vh; }
+        .chat-sidebar { width: 260px; flex-shrink: 0; }
+        .chat-main { flex: 1; display: flex; flex-direction: column; }
+        .chat-box { flex: 1; overflow-y: auto; padding: 16px; background: #f8f9fa; border-radius: 12px; margin-bottom: 12px; max-height: 60vh; }
+        .message { margin-bottom: 16px; display: flex; }
+        .message.user { justify-content: flex-end; }
+        .message.assistant { justify-content: flex-start; }
+        .message .bubble { max-width: 80%; padding: 10px 16px; border-radius: 16px; line-height: 1.5; white-space: pre-wrap; }
+        .message.user .bubble { background: #4361ee; color: white; border-bottom-right-radius: 4px; }
+        .message.assistant .bubble { background: white; color: #333; border: 1px solid #e0e0e0; border-bottom-left-radius: 4px; }
+        .chat-input-row { display: flex; gap: 8px; }
+        .chat-input-row input { flex: 1; padding: 12px 16px; border: 1px solid #ddd; border-radius: 24px; font-size: 1rem; }
+        .chat-input-row button { padding: 12px 24px; border-radius: 24px; }
+        .model-badge { display: inline-block; padding: 4px 12px; border-radius: 12px; font-size: 0.8rem; font-weight: 600; margin-bottom: 12px; }
+        .model-badge.ready { background: #d4edda; color: #155724; }
+        .model-badge.loading { background: #fff3cd; color: #856404; }
+        .model-badge.error { background: #f8d7da; color: #721c24; }
+        #status-msg { font-size: 0.9rem; color: #666; margin-top: 8px; }
+        .typing-indicator { display: none; padding: 10px 16px; background: white; border: 1px solid #e0e0e0; border-radius: 16px; border-bottom-left-radius: 4px; max-width: 80px; }
+        .typing-indicator.active { display: flex; gap: 4px; }
+        .typing-indicator span { width: 8px; height: 8px; background: #999; border-radius: 50%; animation: bounce 1.4s infinite; }
+        .typing-indicator span:nth-child(2) { animation-delay: 0.2s; }
+        .typing-indicator span:nth-child(3) { animation-delay: 0.4s; }
+        @keyframes bounce { 0%, 80%, 100% { transform: translateY(0); } 40% { transform: translateY(-8px); } }
+        @media (max-width: 768px) { .chat-layout { flex-direction: column; } .chat-sidebar { width: 100%; } }
+    </style>
+</head>
+<body>
+    <div class="container">
+        <header>
+            <h1>Llama 3.1 Chat</h1>
+            <div>
+                <span id="model-status" class="model-badge loading">Checking...</span>
+                <a href="/dashboard" class="btn btn-secondary">Dashboard</a>
+                <button class="btn btn-secondary" onclick="logout()">Logout</button>
+            </div>
+        </header>
+
+        <div class="chat-layout">
+            <div class="chat-sidebar">
+                <div class="card">
+                    <h2>Info</h2>
+                    <p><strong>Model:</strong> llama3.1:8b</p>
+                    <p id="status-msg">Checking model status...</p>
+                    <button class="btn btn-primary" style="width:100%;margin-top:12px" onclick="newChat()">New Chat</button>
+                </div>
+            </div>
+
+            <div class="chat-main">
+                <div class="chat-box" id="chat-box">
+                    <div class="message assistant">
+                        <div class="bubble">Hello! I'm Llama 3.1 (8B). Ask me anything.</div>
+                    </div>
+                    <div class="typing-indicator" id="typing"><span></span><span></span><span></span></div>
+                </div>
+
+                <form class="chat-input-row" onsubmit="sendMessage(event)">
+                    <input type="text" id="message-input" placeholder="Type your message..." required autofocus>
+                    <button type="submit" class="btn btn-primary">Send</button>
+                </form>
+            </div>
+        </div>
+    </div>
+
+    <script>
+        const token = localStorage.getItem('token');
+        if (!token) window.location.href = '/login';
+
+        let reading = false;
+
+        function logout() { localStorage.removeItem('token'); window.location.href = '/login'; }
+
+        function newChat() {
+            document.getElementById('chat-box').innerHTML = `
+                <div class="message assistant">
+                    <div class="bubble">Hello! I'm Llama 3.1 (8B). Ask me anything.</div>
+                </div>
+                <div class="typing-indicator" id="typing"><span></span><span></span><span></span></div>
+            `;
+        }
+
+        function addMessage(role, content) {
+            const box = document.getElementById('chat-box');
+            const typing = document.getElementById('typing');
+            const div = document.createElement('div');
+            div.className = `message ${role}`;
+            div.innerHTML = `<div class="bubble">${content}</div>`;
+            box.insertBefore(div, typing);
+            box.scrollTop = box.scrollHeight;
+        }
+
+        // Check model status
+        async function checkStatus() {
+            const res = await fetch('/api/status', {headers: {'Authorization': `Bearer ${token}`}});
+            const data = await res.json();
+            const badge = document.getElementById('model-status');
+            const msg = document.getElementById('status-msg');
+            if (data.model) {
+                badge.className = 'model-badge ready';
+                badge.textContent = 'Model Ready';
+                msg.textContent = 'llama3.1:8b is ready to use';
+            } else if (data.ollama) {
+                badge.className = 'model-badge loading';
+                badge.textContent = 'Downloading...';
+                msg.textContent = data.message || 'Model is being downloaded in background. Please wait...';
+                setTimeout(checkStatus, 10000);
+            } else {
+                badge.className = 'model-badge error';
+                badge.textContent = 'Unavailable';
+                msg.textContent = data.message || 'Ollama not available';
+            }
+        }
+        checkStatus();
+
+        async function sendMessage(e) {
+            e.preventDefault();
+            if (reading) return;
+
+            const input = document.getElementById('message-input');
+            const text = input.value.trim();
+            if (!text) return;
+            input.value = '';
+
+            addMessage('user', text);
+            reading = true;
+
+            const typing = document.getElementById('typing');
+            typing.classList.add('active');
+
+            let assistantContent = '';
+            const bubbleDiv = document.createElement('div');
+            bubbleDiv.className = 'message assistant';
+            const bubble = document.createElement('div');
+            bubble.className = 'bubble';
+            bubbleDiv.appendChild(bubble);
+            const box = document.getElementById('chat-box');
+            box.insertBefore(bubbleDiv, typing);
+
+            try {
+                const res = await fetch('/api/chat', {
+                    method: 'POST',
+                    headers: {'Authorization': `Bearer ${token}`, 'Content-Type': 'application/json'},
+                    body: JSON.stringify({message: text, stream: true})
+                });
+
+                if (!res.ok) {
+                    const err = await res.json();
+                    bubble.textContent = err.detail || 'Error: Model not ready yet';
+                    reading = false;
+                    typing.classList.remove('active');
+                    return;
+                }
+
+                const reader = res.body.getReader();
+                const decoder = new TextDecoder();
+                let buffer = '';
+
+                while (true) {
+                    const {done, value} = await reader.read();
+                    if (done) break;
+
+                    buffer += decoder.decode(value, {stream: true});
+                    const lines = buffer.split('\n');
+                    buffer = lines.pop() || '';
+
+                    for (const line of lines) {
+                        if (!line.startsWith('data: ')) continue;
+                        try {
+                            const data = JSON.parse(line.slice(6));
+                            if (data.done) {
+                                reading = false;
+                                typing.classList.remove('active');
+                                break;
+                            }
+                            if (data.content) {
+                                assistantContent += data.content;
+                                bubble.textContent = assistantContent;
+                                box.scrollTop = box.scrollHeight;
+                            }
+                        } catch(e) {}
+                    }
+                }
+            } catch(e) {
+                bubble.textContent = 'Error: Connection failed';
+                reading = false;
+                typing.classList.remove('active');
+            }
+        }
+    </script>
+</body>
+</html>

templates/dashboard.html

@@ -3,7 +3,7 @@
 <head>
     <meta charset="UTF-8">
     <meta name="viewport" content="width=device-width, initial-scale=1.0">
-    <title>Dashboard - Ollama Manager</title>
+    <title>Dashboard - Ollama</title>
     <link rel="stylesheet" href="/static/style.css">
 </head>
 <body>
@@ -11,17 +11,12 @@
         <header>
             <h1>Dashboard</h1>
             <div>
-                <span id="ollama-badge" class="status status-pending">Checking Ollama...</span>
+                <span id="ollama-badge" class="status status-pending">Checking...</span>
+                <a href="/chat" class="btn btn-primary">Chat</a>
                 <button class="btn btn-secondary" onclick="logout()">Logout</button>
             </div>
         </header>
 
-        <div id="ollama-warning" class="card hidden" style="border: 2px solid #e63946;">
-            <h2>Ollama Not Available</h2>
-            <p id="ollama-msg">Ollama is not installed or not running on this server.</p>
-            <p>To use this app locally: <code>ollama serve</code> then <code>python app.py</code></p>
-        </div>
-
         <div class="dashboard-grid">
             <div class="card">
                 <h2>Your Profile</h2>
@@ -38,22 +33,23 @@
             </div>
 
             <div class="card">
-                <h2>Installed Models</h2>
-                <ul id="installed-models" class="model-list"><li>Loading...</li></ul>
-            </div>
-
-            <div class="card full-width">
-                <h2>Start Download</h2>
-                <form onsubmit="startDownload(event)">
-                    <select id="model-select" required></select>
-                    <button type="submit" class="btn btn-primary">Download</button>
-                </form>
-                <p id="download-error" class="error"></p>
+                <h2>Model Status</h2>
+                <p><strong>Model:</strong> llama3.1:8b</p>
+                <p><strong>Status:</strong> <span id="model-status-text">Checking...</span></p>
+                <div id="installed-section">
+                    <p><strong>Installed Models:</strong></p>
+                    <ul id="installed-models" class="model-list"><li>Loading...</li></ul>
+                </div>
+                <a href="/chat" class="btn btn-primary" style="width:100%;margin-top:12px;text-align:center">Open Chat</a>
             </div>
 
             <div class="card full-width">
-                <h2>Download Sessions</h2>
-                <div id="sessions-list"></div>
+                <h2>Quick Start</h2>
+                <p>Use the chat interface to interact with <strong>llama3.1:8b</strong>.</p>
+                <p>Generate API keys above to access the model programmatically via <code>POST /api/chat</code>.</p>
+                <p style="margin-top:8px;font-size:0.9rem;color:#666;">
+                    Model status: <span id="status-sub">checking...</span>
+                </p>
             </div>
         </div>
     </div>
@@ -73,10 +69,7 @@
             return res;
         }
 
-        function logout() {
-            localStorage.removeItem('token');
-            window.location.href = '/login';
-        }
+        function logout() { localStorage.removeItem('token'); window.location.href = '/login'; }
 
         // Load profile
         api('/api/me').then(r => r.json()).then(data => {
@@ -87,40 +80,41 @@
             `;
         });
 
-        // Check Ollama status
-        fetch('/api/ollama-status').then(r => r.json()).then(data => {
+        // Check status
+        async function loadStatus() {
+            const res = await fetch('/api/status', {headers: {'Authorization': `Bearer ${token}`}});
+            const data = await res.json();
             const badge = document.getElementById('ollama-badge');
-            if (data.available) {
+            const statusText = document.getElementById('model-status-text');
+            const subText = document.getElementById('status-sub');
+
+            if (data.model) {
                 badge.className = 'status status-completed';
-                badge.textContent = 'Ollama Ready';
+                badge.textContent = 'Ready';
+                statusText.textContent = 'Ready';
+                subText.textContent = 'llama3.1:8b is ready';
+            } else if (data.ollama) {
+                badge.className = 'status status-downloading';
+                badge.textContent = 'Downloading...';
+                statusText.textContent = 'Downloading model...';
+                subText.textContent = data.message || 'Model is being downloaded';
+                setTimeout(loadStatus, 10000);
             } else {
                 badge.className = 'status status-error';
-                badge.textContent = 'Ollama Unavailable';
-                document.getElementById('ollama-warning').classList.remove('hidden');
-                document.getElementById('ollama-msg').textContent = data.message;
+                badge.textContent = 'Unavailable';
+                statusText.textContent = 'Unavailable';
+                subText.textContent = data.message || 'Ollama not reachable';
             }
-        });
 
-        // Load installed models
-        fetch('/api/installed-models').then(r => r.json()).then(data => {
+            // Installed models
             const ul = document.getElementById('installed-models');
-            if (data.models.length === 0) {
-                ul.innerHTML = '<li>No models installed yet. Download one below.</li>';
+            if (data.installed && data.installed.length > 0) {
+                ul.innerHTML = data.installed.map(m => `<li>${m}</li>`).join('');
             } else {
-                ul.innerHTML = data.models.map(m => `<li><strong>${m.name}</strong> (${m.size})</li>`).join('');
+                ul.innerHTML = '<li>None yet</li>';
             }
-        });
-
-        // Load recommended models
-        fetch('/api/models').then(r => r.json()).then(data => {
-            const select = document.getElementById('model-select');
-            data.models.filter(m => !m.name.includes('70b')).forEach(m => {
-                const opt = document.createElement('option');
-                opt.value = m.name;
-                opt.textContent = `${m.name} (${m.size})`;
-                select.appendChild(opt);
-            });
-        });
+        }
+        loadStatus();
 
         // Load API keys
         async function loadApiKeys() {
@@ -150,39 +144,6 @@
                 loadApiKeys();
             }
         }
-
-        // Start download
-        async function startDownload(e) {
-            e.preventDefault();
-            const model = document.getElementById('model-select').value;
-            const res = await api('/api/download-sessions', {method: 'POST', body: {model_name: model}});
-            const data = await res.json();
-            if (!res.ok) {
-                document.getElementById('download-error').textContent = data.detail || 'Download failed';
-                return;
-            }
-            window.location.href = `/progress/${data.session_id}`;
-        }
-
-        // Load sessions
-        async function loadSessions() {
-            const res = await api('/api/download-sessions');
-            const data = await res.json();
-            const div = document.getElementById('sessions-list');
-            if (data.sessions.length === 0) {
-                div.innerHTML = '<p>No download sessions yet.</p>';
-                return;
-            }
-            div.innerHTML = data.sessions.map(s => `
-                <div class="session-item">
-                    <a href="/progress/${s.session_id}"><strong>${s.model_name}</strong></a>
-                    <span class="status status-${s.status}">${s.status}</span>
-                    <span>${s.progress}%</span>
-                    <small>${s.started_at}</small>
-                </div>
-            `).join('');
-        }
-        loadSessions();
     </script>
 </body>
 </html>

templates/index.html

@@ -3,40 +3,33 @@
 <head>
     <meta charset="UTF-8">
     <meta name="viewport" content="width=device-width, initial-scale=1.0">
-    <title>Ollama Model Manager</title>
+    <title>FreeAPI - Llama 3.1</title>
     <link rel="stylesheet" href="/static/style.css">
 </head>
 <body>
     <div class="container">
         <header>
-            <h1>Ollama Model Manager</h1>
-            <p>Manage Ollama model downloads for 16GB systems</p>
+            <h1>FreeAPI</h1>
+            <p>Llama 3.1 8B API & Chat</p>
         </header>
         <div class="hero">
             <div class="card">
                 <h2>Get Started</h2>
-                <p>Register to generate API keys and track model download progress.</p>
+                <p>Register to get API keys and chat with Llama 3.1 8B.</p>
                 <div class="buttons">
                     <a href="/login" class="btn btn-primary">Login / Register</a>
+                    <a href="/chat" class="btn btn-secondary">Try Chat</a>
                 </div>
             </div>
             <div class="card">
-                <h2>Recommended Models</h2>
-                <ul id="model-list" class="model-list"></ul>
+                <h2>API Access</h2>
+                <p><code>POST /api/chat</code> with your API key</p>
+                <p>Model: <strong>llama3.1:8b</strong></p>
+                <p style="font-size:0.85rem;color:#666;margin-top:8px">
+                    Register → Generate API key → Chat via UI or API
+                </p>
             </div>
         </div>
     </div>
-    <script>
-        fetch('/api/models')
-            .then(r => r.json())
-            .then(data => {
-                const ul = document.getElementById('model-list');
-                data.models.filter(m => !m.name.includes('70b')).forEach(m => {
-                    const li = document.createElement('li');
-                    li.innerHTML = `<strong>${m.name}</strong> (${m.size}, ${m.ram} RAM) - ${m.description}`;
-                    ul.appendChild(li);
-                });
-            });
-    </script>
 </body>
 </html>

templates/progress.html

@@ -1,94 +0,0 @@
-<!DOCTYPE html>
-<html lang="en">
-<head>
-    <meta charset="UTF-8">
-    <meta name="viewport" content="width=device-width, initial-scale=1.0">
-    <title>Download Progress - Ollama Manager</title>
-    <link rel="stylesheet" href="/static/style.css">
-</head>
-<body>
-    <div class="container">
-        <header>
-            <h1>Download Progress</h1>
-            <a href="/dashboard" class="btn btn-secondary">Back to Dashboard</a>
-        </header>
-
-        <div class="progress-container">
-            <div class="card">
-                <h2 id="model-name">Model: <span id="model-label"></span></h2>
-                <div class="progress-bar-wrapper">
-                    <div class="progress-bar" id="progress-bar"></div>
-                </div>
-                <p id="progress-percent" class="progress-text">0%</p>
-                <div class="progress-details">
-                    <p><strong>Status:</strong> <span id="status-text">Pending</span></p>
-                    <p><strong>Step:</strong> <span id="step-text">Waiting...</span></p>
-                    <p><strong>Downloaded:</strong> <span id="downloaded-text">0 MB</span> / <span id="total-text">0 MB</span></p>
-                    <p><strong>Speed:</strong> <span id="speed-text">0</span> KB/s</p>
-                    <p><strong>ETA:</strong> <span id="eta-text">--</span></p>
-                </div>
-            </div>
-        </div>
-    </div>
-
-    <script>
-        const sessionId = '{{ session_id }}';
-        const token = localStorage.getItem('token');
-        if (!token) window.location.href = '/login';
-
-        // Load session info
-        fetch(`/api/download-sessions/${sessionId}`, {
-            headers: {'Authorization': `Bearer ${token}`}
-        }).then(r => r.json()).then(data => {
-            document.getElementById('model-label').textContent = data.model_name || 'Unknown';
-        });
-
-        // WebSocket
-        const protocol = window.location.protocol === 'https:' ? 'wss:' : 'ws:';
-        const ws = new WebSocket(`${protocol}//${window.location.host}/ws/${sessionId}`);
-
-        ws.onmessage = function(event) {
-            const data = JSON.parse(event.data);
-
-            const progress = data.progress || 0;
-            document.getElementById('progress-bar').style.width = progress + '%';
-            document.getElementById('progress-percent').textContent = progress + '%';
-
-            if (data.status) document.getElementById('status-text').textContent = data.status;
-            if (data.current_step) document.getElementById('step-text').textContent = data.current_step;
-            if (data.downloaded_mb !== undefined) document.getElementById('downloaded-text').textContent = data.downloaded_mb + ' MB';
-            if (data.total_size_mb !== undefined) document.getElementById('total-text').textContent = data.total_size_mb + ' MB';
-            if (data.speed_kbps !== undefined) document.getElementById('speed-text').textContent = data.speed_kbps;
-            if (data.eta_seconds !== undefined) {
-                const eta = data.eta_seconds;
-                if (eta <= 0) document.getElementById('eta-text').textContent = 'Done';
-                else if (eta < 60) document.getElementById('eta-text').textContent = eta + 's';
-                else document.getElementById('eta-text').textContent = Math.floor(eta / 60) + 'm ' + (eta % 60) + 's';
-            }
-
-            if (data.status === 'completed') {
-                document.getElementById('status-text').textContent = 'Completed';
-                document.getElementById('step-text').textContent = 'Done';
-                document.getElementById('progress-bar').style.width = '100%';
-                document.getElementById('progress-percent').textContent = '100%';
-            }
-
-            if (data.status === 'error') {
-                document.getElementById('status-text').textContent = 'Error';
-                document.getElementById('progress-bar').style.background = 'linear-gradient(90deg, #e63946, #c1121f)';
-            }
-        };
-
-        ws.onerror = function() {
-            document.getElementById('status-text').textContent = 'Connecting...';
-        };
-
-        ws.onclose = function() {
-            if (document.getElementById('status-text').textContent !== 'Completed' &&
-                document.getElementById('status-text').textContent !== 'Error') {
-                document.getElementById('status-text').textContent = 'Disconnected';
-            }
-        };
-    </script>
-</body>
-</html>