generative-ai-python
generative-ai-python copied to clipboard
The Gemini API Python SDK enables developers to use Google's state-of-the-art generative AI models to build AI-powered features and applications.
### Description of the bug: SDK should fix or error faster. ### Actual vs expected behavior: _No response_ ### Any other information you'd like to share? _No response_
### Description of the bug: """ Mark Daoust Yeah, sometimes the api returns __nothing__ one way or another. response.text Isn't meant to be robust to that. Are there candidates or...
Intermittent grpc._channel._InactiveRPCError / google.api_core.exceptions.InternalServerError: 500
### Description of the bug: When making several sequential requests to `generate_content`, every 5-10 requests seems to result in a `grpc._channel._InactiveRpcError / google.api_core.exceptions.InternalServerError: 500`. These requests are well within the...
### Description of the feature request: With Vertex API when you catch a function call you can deal with that and then return the information back to the AI in...
### Description of the feature request: There shuld be a RequestOptions TypedDict to explain what attributesd are allowed. ### What problem are you trying to solve with this feature? _No...
### Description of the bug: when i am trying to ask a question to the model by adding the image ,sometimes i am getting below error grpc._channel._MultiThreadedRendezvous:
### Description of the bug: The error occurs when "res = geminiClient.generate_content(conversation).text" is reached again in a recursive function call. I expected it to work the same way it did...
### Description of the feature request: Indic Languages which are supported via web-interface is not supported via API. Gemini web interface currently supports major Indic languages like Hindi, Bangla, Marathi,...
### Description of the bug: When a generation fails due to safety settings, it does a silent fail and just returns a response with zero candidate count. ### Actual vs...
Hi there, I tried to count the token number of a text using `google.generativeai.count_message_tokens` according to the following code. I got 12 for the input "a". Does `google.generativeai.count_message_tokens` include something...