Cognitive Services docstrings state that uploads can be used, but library doesn't actually support it

[yuhui]

Expected result

The Cognitive Services docstrings state that uploads can be sent to the endpoint.

E.g.

azure-sdk-for-python/sdk/cognitiveservices/azure-cognitiveservices-vision-computervision/azure/cognitiveservices/vision/computervision/operations/_computer_vision_client_operations.py

Lines 19 to 26 in decd1a4

	def analyze_image(
	self, url, visual_features=None, details=None, language="en", custom_headers=None, raw=False, **operation_config):
	"""This operation extracts a rich set of visual features based on the
	image content.
	Two input methods are supported -- (1) Uploading an image or (2)
	specifying an image URL. Within your request, there is an optional
	parameter to allow you to choose which features to return. By default,
	image categories are returned in the response.

Note this line:

Two input methods are supported -- (1) Uploading an image or (2) specifying an image URL.

Actual result

In reality, the code doesn't actually support uploads. E.g. for the analyze_image() function, only a publicly reachable url of an image can be used.

Next steps

Update the docstrings to reflect how the library's functions should be used in reality.

Thanks for the feedback! We are routing this to the appropriate team for follow-up. cc @dfulcer

[suside]

Worth noting that this still works:

image = open('./test.jpg', 'rb')
results = computervision_client.analyze_image_in_stream(image)

so this is indeed only docstrings issue.