generative-ai-for-beginners/19-slm/python/Phi-3-Vision-Nividia-NIM.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    },
    "polyglot_notebook": {
     "kernelName": "csharp"
    },
    "vscode": {
     "languageId": "polyglot-notebook"
    }
   },
   "outputs": [],
   "source": [
    "import requests, base64"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    },
    "polyglot_notebook": {
     "kernelName": "csharp"
    },
    "vscode": {
     "languageId": "polyglot-notebook"
    }
   },
   "outputs": [],
   "source": [
    "invoke_url = \"https://ai.api.nvidia.com/v1/vlm/microsoft/phi-3-vision-128k-instruct\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    },
    "polyglot_notebook": {
     "kernelName": "csharp"
    },
    "vscode": {
     "languageId": "polyglot-notebook"
    }
   },
   "outputs": [],
   "source": [
    "with open(\"./img/demo.png\", \"rb\") as f:\n",
    "  image_b64 = base64.b64encode(f.read()).decode()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    },
    "polyglot_notebook": {
     "kernelName": "csharp"
    },
    "vscode": {
     "languageId": "polyglot-notebook"
    }
   },
   "outputs": [],
   "source": [
    "len(image_b64)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    },
    "polyglot_notebook": {
     "kernelName": "csharp"
    },
    "vscode": {
     "languageId": "polyglot-notebook"
    }
   },
   "outputs": [],
   "source": [
    "assert len(image_b64) < 180_000, \\\n",
    "  \"To upload larger images, use the assets API (see docs)\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    },
    "polyglot_notebook": {
     "kernelName": "csharp"
    },
    "vscode": {
     "languageId": "polyglot-notebook"
    }
   },
   "outputs": [],
   "source": [
    "stream = False"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    },
    "polyglot_notebook": {
     "kernelName": "csharp"
    },
    "vscode": {
     "languageId": "polyglot-notebook"
    }
   },
   "outputs": [],
   "source": [
    "headers = {\n",
    "  \"Authorization\": \"Bearer Your Nvidia NIM API Key\",\n",
    "  \"Accept\": \"text/event-stream\" if stream else \"application/json\"\n",
    "}\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    },
    "polyglot_notebook": {
     "kernelName": "csharp"
    },
    "vscode": {
     "languageId": "polyglot-notebook"
    }
   },
   "outputs": [],
   "source": [
    "# payload = {\n",
    "#   \"messages\": [\n",
    "#     {\n",
    "#       \"role\": \"user\",\n",
    "#       \"content\": f'Tell me what is in the picture <img src=\"data:image/png;base64,{image_b64}\" />'\n",
    "#     }\n",
    "#   ],\n",
    "#   \"max_tokens\": 1024,\n",
    "#   \"temperature\": 0.6,\n",
    "#   \"top_p\": 1.0,\n",
    "#   \"stream\": stream\n",
    "# }\n",
    "\n",
    "payload = {\n",
    "  \"messages\": [\n",
    "    {\n",
    "      \"role\": \"user\",\n",
    "      \"content\": f'Please create Python code for image, and use plt to save the new picture under imgs/ and name it phi-3-vision.jpg. <img src=\"data:image/png;base64,{image_b64}\" />'\n",
    "    }\n",
    "  ],\n",
    "  \"max_tokens\": 1024,\n",
    "  \"temperature\": 0.6,\n",
    "  \"top_p\": 1.0,\n",
    "  \"stream\": stream\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    },
    "polyglot_notebook": {
     "kernelName": "csharp"
    },
    "vscode": {
     "languageId": "polyglot-notebook"
    }
   },
   "outputs": [],
   "source": [
    "response = requests.post(invoke_url, headers=headers, json=payload)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    },
    "polyglot_notebook": {
     "kernelName": "csharp"
    },
    "vscode": {
     "languageId": "polyglot-notebook"
    }
   },
   "outputs": [],
   "source": [
    "if stream:\n",
    "    for line in response.iter_lines():\n",
    "        if line:\n",
    "            print(line.decode(\"utf-8\"))\n",
    "else:\n",
    "    print(response.json())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    },
    "polyglot_notebook": {
     "kernelName": "csharp"
    },
    "vscode": {
     "languageId": "polyglot-notebook"
    }
   },
   "outputs": [],
   "source": [
    "code = response.json()[\"choices\"][0][\"message\"][\"content\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    },
    "polyglot_notebook": {
     "kernelName": "csharp"
    },
    "vscode": {
     "languageId": "polyglot-notebook"
    }
   },
   "outputs": [],
   "source": [
    "code"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    },
    "polyglot_notebook": {
     "kernelName": "csharp"
    },
    "vscode": {
     "languageId": "polyglot-notebook"
    }
   },
   "outputs": [],
   "source": [
    "# Find the starting index of the Python code block within the generated code\n",
    "# The index function locates the substring '```python' and adds 9 to skip past it\n",
    "begin = code.index('```python') + 9\n",
    "\n",
    "# Slice the code string from the calculated starting index to the end\n",
    "# This removes the initial part of the string up to and including '```python'\n",
    "code = code[begin:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    },
    "polyglot_notebook": {
     "kernelName": "csharp"
    },
    "vscode": {
     "languageId": "polyglot-notebook"
    }
   },
   "outputs": [],
   "source": [
    "end = code.index('```')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    },
    "polyglot_notebook": {
     "kernelName": "csharp"
    },
    "vscode": {
     "languageId": "polyglot-notebook"
    }
   },
   "outputs": [],
   "source": [
    "code = code[:end]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    },
    "polyglot_notebook": {
     "kernelName": "csharp"
    },
    "vscode": {
     "languageId": "polyglot-notebook"
    }
   },
   "outputs": [],
   "source": [
    "code"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "dotnet_interactive": {
     "language": "csharp"
    },
    "polyglot_notebook": {
     "kernelName": "csharp"
    },
    "vscode": {
     "languageId": "polyglot-notebook"
    }
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".NET (C#)",
   "language": "C#",
   "name": ".net-csharp"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.8"
  },
  "polyglot_notebook": {
   "kernelInfo": {
    "defaultKernelName": "csharp",
    "items": [
     {
      "aliases": [],
      "name": "csharp"
     }
    ]
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}