Update app.py

app.py

@@ -1,65 +1,8 @@
 model = "gemma2:27b"
-
-import os 
-
-os.system("curl https://ollama.ai/install.sh | sh")
-
-import nest_asyncio
-nest_asyncio.apply()
-
-import asyncio
-
-# Run Async Ollama
-# Taken from: https://stackoverflow.com/questions/77697302/how-to-run-ollama-in-google-colab
-# NB: You may need to set these depending and get cuda working depending which backend you are running.
-# Set environment variable for NVIDIA library
-# Set environment variables for CUDA
-os.environ['PATH'] += ':/usr/local/cuda/bin'
-# Set LD_LIBRARY_PATH to include both /usr/lib64-nvidia and CUDA lib directories
-os.environ['LD_LIBRARY_PATH'] = '/usr/lib64-nvidia:/usr/local/cuda/lib64'
-
-async def run_process(cmd):
-    print('>>> starting', *cmd)
-    process = await asyncio.create_subprocess_exec(
-        *cmd,
-        stdout=asyncio.subprocess.PIPE,
-        stderr=asyncio.subprocess.PIPE
-    )
-
-    # define an async pipe function
-    async def pipe(lines):
-        async for line in lines:
-            print(line.decode().strip())
-
-        await asyncio.gather(
-            pipe(process.stdout),
-            pipe(process.stderr),
-        )
-
-    # call it
-    await asyncio.gather(pipe(process.stdout), pipe(process.stderr))
-
-import threading
-
-async def start_ollama_serve():
-    await run_process(['ollama', 'serve'])
-
-def run_async_in_thread(loop, coro):
-    asyncio.set_event_loop(loop)
-    loop.run_until_complete(coro)
-    loop.close()
-
-# Create a new event loop that will run in a new thread
-new_loop = asyncio.new_event_loop()
-
-# Start ollama serve in a separate thread so the cell won't block execution
-thread = threading.Thread(target=run_async_in_thread, args=(new_loop, start_ollama_serve()))
-thread.start()
-
-# Load up model
-
-os.system(f"ollama pull {model}")
-
+import ollama
+import os
+ollama_path="/usr/local/lib/python3.10/site-packages/ollama"
+os.system(f"{ollama_path} ollama pull {model}")
 
 import copy
 import gradio as gr