gpt-4-1106-vision-preview
POST
https://api.gaiasc.com/v1/chat/completions
最后修改时间：2024-03-04 05:02:44
责任人：未设置
介绍
目前，GPT-4 Turbo with vision 不支持 message.name 参数、functions/tools response_format 参数，目前必须设置了一个 max_tokens默认值。
快速入门
from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
model="gpt-4-vision-preview",
messages=[
{
"role": "user",
"content": [
{"type": "text", "text": "What’s in this image?"},
{
"type": "image_url",
"image_url": {
"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
},
},
],
}
],
max_tokens=300,
)
print(response.choices[0])上传 base 64 编码图像(不推荐)
import base64
import requests
# OpenAI API Key
api_key = "YOUR_OPENAI_API_KEY"
# Function to encode the image
def encode_image(image_path):
with open(image_path, "rb") as image_file:
return base64.b64encode(image_file.read()).decode('utf-8')
# Path to your image
image_path = "path_to_your_image.jpg"
# Getting the base64 string
base64_image = encode_image(image_path)
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {api_key}"
}
payload = {
"model": "gpt-4-vision-preview",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "What’s in this image?"
},
{
"type": "image_url",
"image_url": {
"url": f"data:image/jpeg;base64,{base64_image}"
}
}
]
}
],
"max_tokens": 300
}
response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload)
print(response.json())多个图像输入
from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
model="gpt-4-vision-preview",
messages=[
{
"role": "user",
"content": [
{
"type": "text",
"text": "What are in these images? Is there any difference between them?",
},
{
"type": "image_url",
"image_url": {
"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
},
},
{
"type": "image_url",
"image_url": {
"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
},
},
],
}
],
max_tokens=300,
)
print(response.choices[0])低保真或高保真图像理解
detail low``highlow将禁用“高分辨率”模型。该模型将收到低分辨率 512px x 512px 版本的图像，并以 65 个代币的预算表示图像。这允许 API 返回更快的响应，并为不需要高细节的用例使用更少的输入令牌。high将启用“高分辨率”模式，该模式首先允许模型查看低分辨率图像，然后根据输入图像大小将输入图像的详细裁剪创建为 512px 正方形。每个详细的作物都使用两倍的代币预算（65 个代币），总共 129 个代币。from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
model="gpt-4-vision-preview",
messages=[
{
"role": "user",
"content": [
{"type": "text", "text": "What’s in this image?"},
{
"type": "image_url",
"image_url": {
"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
"detail": "high"
},
},
],
}
],
max_tokens=300,
)
print(response.choices[0].message.content)管理映像
局限性
计算成本
detail detail: low detail: high常见问题
我可以微调图像功能吗？gpt-4
我可以用来生成图像吗？gpt-4
dall-e-3 gpt-4-vision-preview我可以上传什么类型的文件？
我可以上传的图片大小有限制吗？
我可以删除我上传的图片吗？
在哪里可以了解有关 GPT-4 with Vision 注意事项的更多信息？
GPT-4 with Vision 的速率限制如何工作？
GPT-4 with Vision 能理解图像元数据吗？
如果我的图像不清晰会怎样？
请求参数
Header 参数
Content-Type
string
必需
示例值:
application/json
Accept
string
必需
示例值:
application/json
Authorization
string
必需
示例值:
Bearer {{YOUR_API_KEY}}
Body 参数application/json