stuff

src/utils/__init__.py

@@ -1,4 +1,5 @@
 from .system_monitor import SystemMonitor
 from .gpu_monitor import GPUMonitor
+from .ollama_monitor import OllamaMonitor
 
-__all__ = ['SystemMonitor', 'GPUMonitor']
+__all__ = ['SystemMonitor', 'GPUMonitor', 'OllamaMonitor']

src/utils/ollama.py

@@ -1,6 +1,6 @@
 import httpx
 from nicegui import ui
-from typing import Tuple
+from typing import Tuple, Dict
 
 
 async def status(url='http://127.0.0.1:11434') -> Tuple[bool, str]:
@@ -24,27 +24,30 @@ async def available_models(url='http://127.0.0.1:11434'):
         return response.json()["models"]
 
 
-async def loaded_models(url='http://127.0.0.1:11434'):
+async def active_models(url='http://127.0.0.1:11434'):
     async with httpx.AsyncClient() as client:
         response = await client.get(f"{url}/api/ps")
         response.raise_for_status()
 
-        return response.json()
+        return response.json()["models"]
 
 
-async def create_ollama_model(name, modelfile_content, url='http://127.0.0.1:11434'):
+async def create_ollama_model(model_name, model_from, parameters=None, quantizie=None, url='http://127.0.0.1:11434'):
     data = {
-        "name": name,
-        "from": "qwen2.5-coder:7b",
-        "modelfile": modelfile_content,
-        "stream": False
+        "model": model_name,
+        "from": model_from,
+        "stream": True
     }
 
+    if parameters:
+        data['parameters'] = parameters
+    if quantizie:
+        data['quantizie'] = quantizie
+
     async with httpx.AsyncClient() as client:
-        response = await client.post(f"{url}/api/create", json=data)
-        response.raise_for_status()
-        print(response.text)
-        return response.json()
+        async with client.stream('POST', f"{url}/api/create", json=data) as response:
+            async for chunk in response.aiter_text():
+                yield chunk
 
 
 async def delete_model(name, url='http://127.0.0.1:11434') -> bool:
@@ -79,3 +82,11 @@ async def stream_chat(data, url='http://127.0.0.1:11434'):
         async with client.stream('POST', f"{url}/api/chat", json=data) as response:
             async for chunk in response.aiter_text():
                 yield chunk
+
+
+async def download_model(model, url='http://127.0.0.1:11434'):
+    data = {'name': model, 'stream': True}
+    async with httpx.AsyncClient() as client:
+        async with client.stream('POST', f"{url}/api/pull", json=data) as response:
+            async for chunk in response.aiter_text():
+                yield chunk

src/utils/ollama_monitor.py

@@ -0,0 +1,21 @@
+import psutil
+import platform
+import time
+import logging
+from dataclasses import dataclass, field
+from datetime import datetime, timedelta
+from typing import Dict, Any, List, Optional, Literal
+from nicegui import binding
+from utils import ollama
+logger = logging.getLogger(__name__)
+
+
+@binding.bindable_dataclass
+class OllamaMonitor:
+    status: bool = False
+    version: str = 'Unknown'
+    active_models: Dict = field(default_factory=dict)
+
+    async def update(self):
+        self.status, self.version = await ollama.status()
+        self.active_models = await ollama.active_models() if self.status else {}