diff --git a/examples/notebooks/Multimodal.ipynb b/examples/notebooks/Multimodal.ipynb index 11b14df..f1b8e9d 100644 --- a/examples/notebooks/Multimodal.ipynb +++ b/examples/notebooks/Multimodal.ipynb @@ -1,5 +1,14 @@ { "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "
\n", + " \n", + "
" + ] + }, { "cell_type": "code", "execution_count": 1, @@ -9,19 +18,13 @@ "name": "stdout", "output_type": "stream", "text": [ - "ChatCompletion(id='chatcmpl-65a710ba-41d1-4d0a-a124-a44b2b4a0189', choices=[Choice(finish_reason='stop', index=0, message=ChatCompletionMessage(content=' The image reads \"LlamaC++.\"', role='assistant', function_call=None, tool_calls=None))], created=1699413274, model='gpt-4-vision-preview', object='chat.completion', system_fingerprint=None, usage=CompletionUsage(completion_tokens=10, prompt_tokens=624, total_tokens=634))\n" + "{'text': 'Llama C++'}\n" ] } ], "source": [ "from openai import OpenAI\n", "\n", - "import urllib.request\n", - "import base64\n", - "\n", - "def get_data_url(url):\n", - " return \"data:image/png;base64,\" + base64.b64encode(urllib.request.urlopen(url).read()).decode(\"utf-8\")\n", - "\n", "client = OpenAI(base_url=\"http://100.64.159.73:8000/v1\", api_key=\"sk-1234\")\n", "response = client.chat.completions.create(\n", " model=\"gpt-4-vision-preview\",\n", @@ -32,23 +35,17 @@ " {\n", " \"type\": \"image_url\",\n", " \"image_url\": {\n", - " \"url\": get_data_url(\"https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png\"),\n", - " # \"url\": \"https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png\",\n", + " \"url\": \"https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png\",\n", " },\n", " },\n", - " {\"type\": \"text\", \"text\": \"What does the image say\"},\n", + " {\"type\": \"text\", \"text\": \"What does the image say. Format your response as a json object with a single 'text' key.\"},\n", " ],\n", " }\n", " ],\n", + " response_format={ \"type\": \"json_object\" }\n", ")\n", - "print(response)" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "![](https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png)" + "import json\n", + "print(json.loads(response.choices[0].message.content))" ] }, {