介绍 gpt-4o

%pip install --upgrade openai --quiet

from openai import OpenAI 
import os

## Set the API key and model name
MODEL="gpt-4o"
client = OpenAI(api_key=os.environ.get("OPENAI_API_KEY", "<your OpenAI API key if not set as an env var>"))

completion = client.chat.completions.create(
  model=MODEL,
  messages=[
    {"role": "system", "content": "You are a helpful assistant. Help me with my math homework!"},
    {"role": "user", "content": "Hello! Could you solve 2+2?"}
  ]
)

print("Assistant: " + completion.choices[0].message.content)

Assistant: Of course! 

\[ 2 + 2 = 4 \]

If you have any other questions, feel free to ask!

from IPython.display import Image, display, Audio, Markdown
import base64

IMAGE_PATH = "data/triangle.png"

# Preview image for context
display(Image(IMAGE_PATH))

# Open the image file and encode it as a base64 string
def encode_image(image_path):
    with open(image_path, "rb") as image_file:
        return base64.b64encode(image_file.read()).decode("utf-8")

base64_image = encode_image(IMAGE_PATH)

response = client.chat.completions.create(
    model=MODEL,
    messages=[
        {"role": "system", "content": "You are a helpful assistant that responds in Markdown. Help me with my math homework!"},
        {"role": "user", "content": [
            {"type": "text", "text": "What's the area of the triangle?"},
            {"type": "image_url", "image_url": {
                "url": f"data:image/png;base64,{base64_image}"
            }}
        ]}
    ],
    temperature=0.0,
)

print(response.choices[0].message.content)

To find the area of the triangle, we can use Heron's formula. First, we need to find the semi-perimeter of the triangle.

The sides of the triangle are 6, 5, and 9.

1. Calculate the semi-perimeter \( s \):
\[ s = \frac{a + b + c}{2} = \frac{6 + 5 + 9}{2} = 10 \]

2. Use Heron's formula to find the area \( A \):
\[ A = \sqrt{s(s-a)(s-b)(s-c)} \]

Substitute the values:
\[ A = \sqrt{10(10-6)(10-5)(10-9)} \]
\[ A = \sqrt{10 \cdot 4 \cdot 5 \cdot 1} \]
\[ A = \sqrt{200} \]
\[ A = 10\sqrt{2} \]

So, the area of the triangle is \( 10\sqrt{2} \) square units.

response = client.chat.completions.create(
    model=MODEL,
    messages=[
        {"role": "system", "content": "You are a helpful assistant that responds in Markdown. Help me with my math homework!"},
        {"role": "user", "content": [
            {"type": "text", "text": "What's the area of the triangle?"},
            {"type": "image_url", "image_url": {
                "url": "https://upload.wikimedia.org/wikipedia/commons/e/e2/The_Algebra_of_Mohammed_Ben_Musa_-_page_82b.png"
            }}
        ]}
    ],
    temperature=0.0,
)

print(response.choices[0].message.content)

To find the area of the triangle, we can use Heron's formula. Heron's formula states that the area of a triangle with sides of length \(a\), \(b\), and \(c\) is:

\[ \text{Area} = \sqrt{s(s-a)(s-b)(s-c)} \]

where \(s\) is the semi-perimeter of the triangle:

\[ s = \frac{a + b + c}{2} \]

For the given triangle, the side lengths are \(a = 5\), \(b = 6\), and \(c = 9\). 

First, calculate the semi-perimeter \(s\):

\[ s = \frac{5 + 6 + 9}{2} = \frac{20}{2} = 10 \]

Now, apply Heron's formula:

\[ \text{Area} = \sqrt{10(10-5)(10-6)(10-9)} \]
\[ \text{Area} = \sqrt{10 \cdot 5 \cdot 4 \cdot 1} \]
\[ \text{Area} = \sqrt{200} \]
\[ \text{Area} = 10\sqrt{2} \]

So, the area of the triangle is \(10\sqrt{2}\) square units.

%pip install opencv-python --quiet
%pip install moviepy --quiet

import cv2
from moviepy.editor import VideoFileClip
import time
import base64

# We'll be using the OpenAI DevDay Keynote Recap video. You can review the video here: https://www.youtube.com/watch?v=h02ti0Bl6zk
VIDEO_PATH = "data/keynote_recap.mp4"

def process_video(video_path, seconds_per_frame=2):
    base64Frames = []
    base_video_path, _ = os.path.splitext(video_path)

    video = cv2.VideoCapture(video_path)
    total_frames = int(video.get(cv2.CAP_PROP_FRAME_COUNT))
    fps = video.get(cv2.CAP_PROP_FPS)
    frames_to_skip = int(fps * seconds_per_frame)
    curr_frame=0

    # Loop through the video and extract frames at specified sampling rate
    while curr_frame < total_frames - 1:
        video.set(cv2.CAP_PROP_POS_FRAMES, curr_frame)
        success, frame = video.read()
        if not success:
            break
        _, buffer = cv2.imencode(".jpg", frame)
        base64Frames.append(base64.b64encode(buffer).decode("utf-8"))
        curr_frame += frames_to_skip
    video.release()

    # Extract audio from video
    audio_path = f"{base_video_path}.mp3"
    clip = VideoFileClip(video_path)
    clip.audio.write_audiofile(audio_path, bitrate="32k")
    clip.audio.close()
    clip.close()

    print(f"Extracted {len(base64Frames)} frames")
    print(f"Extracted audio to {audio_path}")
    return base64Frames, audio_path

# Extract 1 frame per second. You can adjust the `seconds_per_frame` parameter to change the sampling rate
base64Frames, audio_path = process_video(VIDEO_PATH, seconds_per_frame=1)

MoviePy - Writing audio in data/keynote_recap.mp3
MoviePy - Done.
Extracted 218 frames
Extracted audio to data/keynote_recap.mp3

## Display the frames and audio for context
display_handle = display(None, display_id=True)
for img in base64Frames:
    display_handle.update(Image(data=base64.b64decode(img.encode("utf-8")), width=600))
    time.sleep(0.025)

Audio(audio_path)