Applying fixes for all multi agent notebooks

Author: alex-akv

ai/ai-starter-kit/helm-chart/ai-starter-kit/files/multi-agent-ollama.ipynb

@@ -224,7 +224,7 @@
     "        return JSONResponse(status_code=500, content={\"error\": str(e)})\n",
     "\n",
     "if __name__ == \"__main__\":\n",
-    "    uvicorn.run(app, host=\"0.0.0.0\", port=8000)\n",
+    "    uvicorn.run(app, host=\"0.0.0.0\", port=8001)\n",
     "'''\n",
     "\n",
     "with open('/tmp/ollama_wrapper.py', 'w') as f:\n",
@@ -292,12 +292,12 @@
     "for i in range(30):\n",
     "    time.sleep(1)\n",
     "    try:\n",
-    "        r = requests.get(\"http://localhost:8000/v1/healthz\", timeout=1)\n",
+    "        r = requests.get(\"http://localhost:8001/v1/healthz\", timeout=1)\n",
     "        if r.status_code == 200:\n",
     "            print(f\"\\n API is ready! Response: {r.json()}\")\n",
-    "            print(f\"\\nOpenAI-compatible API running at: http://localhost:8000/v1\")\n",
-    "            print(f\"Health: http://localhost:8000/v1/healthz\")\n",
-    "            print(f\"Chat:   http://localhost:8000/v1/chat/completions\")\n",
+    "            print(f\"\\nOpenAI-compatible API running at: http://localhost:8001/v1\")\n",
+    "            print(f\"Health: http://localhost:8001/v1/healthz\")\n",
+    "            print(f\"Chat:   http://localhost:8001/v1/chat/completions\")\n",
     "            api_ready = True\n",
     "            break\n",
     "    except requests.exceptions.ConnectionError:\n",
@@ -317,8 +317,8 @@
     "    print(\"\\nLast 50 lines of logs:\")\n",
     "    !tail -50 /tmp/wrapper.log\n",
     "    \n",
-    "    print(\"\\nChecking if port 8000 is in use:\")\n",
-    "    !netstat -tlnp 2>/dev/null | grep 8000 || echo \"No process on port 8000\"\n",
+    "    print(\"\\nChecking if port 8001 is in use:\")\n",
+    "    !netstat -tlnp 2>/dev/null | grep 8001 || echo \"No process on port 8001\"\n",
     "    \n",
     "    print(\"\\nChecking Python processes:\")\n",
     "    !ps aux | grep python | grep -v grep"
@@ -343,7 +343,7 @@
    "source": [
     "import os, time, requests, json\n",
     "\n",
-    "BASE_URL = \"http://localhost:8000/v1\"\n",
+    "BASE_URL = \"http://localhost:8001/v1\"\n",
     "OLLAMA_DIRECT = os.getenv(\"OLLAMA_HOST\", \"http://ai-starter-kit-ollama:11434\")\n",
     "\n",
     "try:\n",
@@ -430,7 +430,7 @@
    "source": [
     "import os, requests, json, time\n",
     "\n",
-    "BASE_URL = \"http://localhost:8000/v1\"  \n",
+    "BASE_URL = \"http://localhost:8001/v1\"  \n",
     "OLLAMA_DIRECT = os.getenv(\"OLLAMA_HOST\", \"http://ai-starter-kit-ollama:11434\")\n",
     "\n",
     "def call_llm(role_prompt, user_message, temperature=0.4, max_tokens=150, use_wrapper=True):\n",

ai/ai-starter-kit/helm-chart/ai-starter-kit/files/multi-agent-ramalama.ipynb

@@ -225,7 +225,7 @@
     "        return JSONResponse(status_code=500, content={\"error\": str(e)})\n",
     "\n",
     "if __name__ == \"__main__\":\n",
-    "    uvicorn.run(app, host=\"0.0.0.0\", port=8000)\n",
+    "    uvicorn.run(app, host=\"0.0.0.0\", port=8002)\n",
     "'''\n",
     "\n",
     "with open('/tmp/ramalama_wrapper.py', 'w') as f:\n",
@@ -284,7 +284,7 @@
     "print(\"Process is running\")\n",
     "\n",
     "print(\"\\nWaiting for API to respond...\")\n",
-    "API_URL = \"http://localhost:8000\"\n",
+    "API_URL = \"http://localhost:8002\"\n",
     "api_ready = False\n",
     "\n",
     "for i in range(30):\n",
@@ -316,8 +316,8 @@
     "    print(\"\\nLast 50 lines of logs:\")\n",
     "    !tail -50 /tmp/ramalama_wrapper.log\n",
     "    \n",
-    "    print(\"\\nChecking if port 8000 is in use:\")\n",
-    "    !netstat -tlnp 2>/dev/null | grep 8000 || echo \"No process on port 8000\"\n",
+    "    print(\"\\nChecking if port 8002 is in use:\")\n",
+    "    !netstat -tlnp 2>/dev/null | grep 8002 || echo \"No process on port 8002\"\n",
     "    \n",
     "    print(\"\\nNote: You can re-run this cell - the API might just need more time to start\")"
    ]
@@ -342,7 +342,7 @@
     "import os, time, requests, json\n",
     "\n",
     "USE_WRAPPER = True\n",
-    "BASE_URL = \"http://localhost:8000/v1\" if USE_WRAPPER else os.getenv(\"RAMALAMA_HOST\", \"http://127.0.0.1:8080\")\n",
+    "BASE_URL = \"http://localhost:8002/v1\" if USE_WRAPPER else os.getenv(\"RAMALAMA_HOST\", \"http://127.0.0.1:8080\")\n",
     "\n",
     "def health():\n",
     "    if USE_WRAPPER:\n",
@@ -401,7 +401,7 @@
    "source": [
     "import os, requests, json, time\n",
     "\n",
-    "BASE_URL = \"http://localhost:8000/v1\"  \n",
+    "BASE_URL = \"http://localhost:8002/v1\"  \n",
     "RAMALAMA_DIRECT = os.getenv(\"RAMALAMA_HOST\", \"http://127.0.0.1:8080\")\n",
     "\n",
     "def call_llm(role_prompt, user_message, temperature=0.4, max_tokens=150, use_wrapper=True):\n",

ai/ai-starter-kit/helm-chart/ai-starter-kit/files/multi-agent.ipynb

@@ -584,7 +584,7 @@
     "mlflow.set_tracking_uri(tracking_uri)\n",
     "print(f\"MLflow Tracking URI: {tracking_uri}\")\n",
     "\n",
-    "exp_name = os.getenv(\"MLFLOW_EXPERIMENT_NAME\", \"ray-llama-cpp\")\n",
+    "exp_name = os.getenv(\"MLFLOW_EXPERIMENT_NAME\", \"ray-transformers\")\n",
     "exp = mlflow.set_experiment(exp_name)\n",
     "print(f\"Experiment: {exp.name} (ID: {exp.experiment_id})\")\n",
     "print(\"-\" * 60)\n",