Gemini Model Unable to Extract Text from Uploaded Image, Requests Direct Text Input Instead

Gemini API
1

GenerateContentResponse(
done=True,
iterator=None,
result=protos.GenerateContentResponse({
“candidates”: [
{
“content”: {
“parts”: [
{
“text”: “I am sorry, I do not have access to the internet to fetch content from the provided URL. Therefore, I cannot extract text from the image. \n\nIf you would like me to analyze text, please provide the text directly. \n”
}
],
“role”: “model”
},
“finish_reason”: “STOP”,
“index”: 0,
“safety_ratings”: [
{
“category”: “HARM_CATEGORY_SEXUALLY_EXPLICIT”,
“probability”: “NEGLIGIBLE”
},
{
“category”: “HARM_CATEGORY_HATE_SPEECH”,
“probability”: “NEGLIGIBLE”
},
{
“category”: “HARM_CATEGORY_HARASSMENT”,
“probability”: “NEGLIGIBLE”
},
{
“category”: “HARM_CATEGORY_DANGEROUS_CONTENT”,
“probability”: “NEGLIGIBLE”
}
]
}
],
“usage_metadata”: {
“prompt_token_count”: 44,
“candidates_token_count”: 47,
“total_token_count”: 91
}
}),

3

Hi @KSaudit

The feature of giving url is not available for Gemini API as it doesn’t have access to Internet. You can download the image and provide the image to Model.

Thanks