update the codebase poc ver1

workspace/sprint_1_2/CODEBASE/infra/implementation/ollama/medGemma_modal_ollama_deploy.py

@@ -0,0 +1,132 @@
+import subprocess
+import time
+import requests
+import modal
+
+OLLAMA_PORT = 11434
+MODEL_NAME = "medgemma:4b"
+
+# Persist downloaded models
+ollama_volume = modal.Volume.from_name(
+    "ollama-model-cache",
+    create_if_missing=True,
+)
+
+image = (
+    modal.Image.debian_slim()
+    .pip_install("requests")  # <--- THIS IS MISSING
+    .run_commands(
+        "apt-get update",
+        "apt-get install -y curl zstd ca-certificates",
+        "curl -fsSL https://ollama.com/install.sh | sh",
+
+    )
+    .env(
+        {
+            "OLLAMA_HOST": "0.0.0.0"
+        }
+       
+    )
+)
+
+app = modal.App("ollama-medgemma")
+
+
+@app.cls(
+    image=image,
+    gpu="l4",
+    min_containers=1,
+    max_containers=3,
+    scaledown_window=300,
+    volumes={"/root/.ollama": ollama_volume},
+)
+class OllamaServer:
+
+    @modal.enter()
+    def start_server(self):
+        print("Starting Ollama server...")
+
+        self.process = subprocess.Popen(
+            ["ollama", "serve"],
+            stdout=subprocess.PIPE,
+            stderr=subprocess.STDOUT,
+            text=True,
+        )
+
+        try:
+            self.wait_until_ready()
+
+            print(f"Checking model: {MODEL_NAME}")
+
+            installed = subprocess.run(
+                ["ollama", "list"],
+                capture_output=True,
+                text=True,
+                check=True,
+            )
+
+            if MODEL_NAME not in installed.stdout:
+                print(f"Downloading {MODEL_NAME}...")
+                subprocess.run(
+                    ["ollama", "pull", MODEL_NAME],
+                    check=True,
+                )
+            else:
+                print("Model already cached.")
+
+            print("Ollama ready.")
+
+            response = requests.post(
+                "http://0.0.0.0:11434/api/generate",
+                json={
+                    "model": MODEL_NAME,
+                    "prompt": "",
+                    "stream": False,
+                    "keep_alive": -1,
+                },
+                timeout=120,
+            )
+
+            response.raise_for_status()
+
+            print(response.json())
+        except Exception:
+            self.process.kill()
+            raise
+
+    def wait_until_ready(self):
+
+        deadline = time.time() + 180
+
+        while time.time() < deadline:
+            try:
+                r = requests.get(
+                    f"http://0.0.0.0:{OLLAMA_PORT}/api/tags",
+                    timeout=2,
+                )
+
+                if r.status_code == 200:
+                    return
+
+            except requests.RequestException:
+                pass
+
+            time.sleep(1)
+
+        raise RuntimeError("Ollama failed to start.")
+
+    @modal.web_server(port=OLLAMA_PORT)
+    def web(self):
+        pass
+
+    @modal.exit()
+    def shutdown(self):
+        print("Stopping Ollama...")
+
+        if self.process.poll() is None:
+            self.process.terminate()
+
+            try:
+                self.process.wait(timeout=10)
+            except subprocess.TimeoutExpired:
+                self.process.kill()

workspace/sprint_1_2/CODEBASE/infra/implementation/triton_run/modal_triton.py

@@ -188,6 +188,12 @@ async def proxy_all_triton_request(path: str, request: Request):
                 status_code=502
             )
 
+@web_app.get("/v2/models")
+async def forward_list_models():
+    async with httpx.AsyncClient() as client:
+        r = await client.get("http://127.0.0.1:8000/v2/models")
+        return Response(content=r.content, status_code=r.status_code, media_type=r.headers.get("content-type"))
+
 # -------------------------------------------------------------
 # THE UNIFIED SERVICE FUNCTION (1 Container, 1 GPU, 1 Triton Process)
 # -------------------------------------------------------------

workspace/sprint_1_2/CODEBASE/infra/implementation/triton_run/run.sh

@@ -1,2 +1,2 @@
 cd ../PILOT_PROJECT/workspace/sprint_1_2/CODEBASE/infra/implementation/triton_run
-modal deploy PILOT_PROJECT/workspace/sprint_1_2/codebase/infra/implementation/triton_run/modal_triton.py
+MODAL_PROFILE=dtj-tran modal deploy PILOT_PROJECT/workspace/sprint_1_2/codebase/infra/implementation/triton_run/modal_triton.py