运行Azure认知服务OCR报错：KeyError: 'VISION_ENDPOINT'

你的代码当前是从系统环境变量中读取Azure Computer Vision的端点和密钥，但你通过命令行参数-k和-e传递的值并没有被代码处理，导致找不到对应环境变量触发KeyError。以下是三种可行的解决方式：

方式1：修改代码接收命令行参数 #

使用Python的argparse模块解析命令行传入的参数，替换原本从环境变量读取的逻辑：

import argparse
import json
import os
import azure.ai.vision as sdk

# 新增：解析命令行参数
parser = argparse.ArgumentParser()
parser.add_argument("-e", "--endpoint", required=True, help="Azure Vision Endpoint")
parser.add_argument("-k", "--key", required=True, help="Azure Vision Subscription Key")
args = parser.parse_args()

# 读取JSON文件（保留原有逻辑）
f = open("C:\\Users\\xxx\\xxx\\Documents\\ocr\\xxx.json")
data = json.load(f)
f.close()

# 使用命令行参数替换环境变量读取
service_options = sdk.VisionServiceOptions(args.endpoint, args.key)

# 以下保留原有代码逻辑
vision_source = sdk.VisionSource(
    url="https://learn.microsoft.com/azure/ai-services/computer-vision/media/quickstarts/presentation.png")

analysis_options = sdk.ImageAnalysisOptions()
analysis_options.features = (
    sdk.ImageAnalysisFeature.CAPTION |
    sdk.ImageAnalysisFeature.TEXT
)
analysis_options.language = "en"
analysis_options.gender_neutral_caption = True

image_analyzer = sdk.ImageAnalyzer(service_options, vision_source, analysis_options)
result = image_analyzer.analyze()

if result.reason == sdk.ImageAnalysisResultReason.ANALYZED:
    if result.caption is not None:
        print(" Caption:")
        print("   '{}', Confidence {:.4f}".format(result.caption.content, result.caption.confidence))
    if result.text is not None:
        print(" Text:")
        for line in result.text.lines:
            points_string = "{" + ", ".join([str(int(point)) for point in line.bounding_polygon]) + "}"
            print("   Line: '{}', Bounding polygon {}".format(line.content, points_string))
            for word in line.words:
                points_string = "{" + ", ".join([str(int(point)) for point in word.bounding_polygon]) + "}"
                print("     Word: '{}', Bounding polygon {}, Confidence {:.4f}"
                      .format(word.content, points_string, word.confidence))
else:
    error_details = sdk.ImageAnalysisErrorDetails.from_result(result)
    print(" Analysis failed.")
    print("   Error reason: {}".format(error_details.reason))
    print("   Error code: {}".format(error_details.error_code))
    print("   Error message: {}".format(error_details.message))

修改后，你可以继续用原来的命令行方式运行：

python sample.py -e "your_endpoint" -k "your_subscription_key"

方式2：设置系统环境变量后运行脚本 #

不需要修改代码，先在终端设置环境变量，再执行脚本：

Windows命令提示符（CMD） #

set VISION_ENDPOINT=your_endpoint
set VISION_KEY=your_subscription_key
python sample.py

Windows PowerShell #

$env:VISION_ENDPOINT="your_endpoint"
$env:VISION_KEY="your_subscription_key"
python sample.py

Linux/macOS终端 #

export VISION_ENDPOINT=your_endpoint
export VISION_KEY=your_subscription_key
python sample.py

方式3：临时硬编码参数（不推荐用于生产环境） #

如果只是临时测试，可以直接在代码中替换环境变量读取的部分，注意不要把密钥提交到版本控制系统：

# 替换原有service_options的代码
service_options = sdk.VisionServiceOptions("your_endpoint", "your_subscription_key")

内容的提问来源于stack exchange，提问作者Ananth Subramanian