generative-ai-python

generative-ai-python copied to clipboard

Frequent 500 errors: error counting image token, media index[0] err: failed to decode base64 string: illegal base64 data at input byte 0 (request id: 2025101012300457216932209497692)', 'type': 'shell_api_error', 'param': '', 'code': 'count_token_failed'}

1

### Description of the bug: This problem frequently occurs when using Python 3.10 to call google-genai version 1.38.0. The image file encoding uses the following method with open(image_path, 'rb') as...

dzqjk

### Description of the feature request: Currently, the gemini-embedding-001 endpoint returns a single, aggregated vector representing the entire text input. This request is to add a feature, likely through an...

Dyson96

## Description of the change Relax the version requirement of google-ai-generativelanguage, this is to improve the interoperability with other libraries such as `langchain-google-genai` ## Motivation Spotted in https://github.com/langchain-ai/langchain-google/issues/956, the hard...

windkit

TypeError: object GenerateContentResponse can't be used in 'await' expression with model.generate_content_async() in Google Colab (Python 3.11)

2

### Description of the bug: When using the google-generativeai library in a Google Colab environment (Python 3.11), calling model.generate_content_async() consistently results in a TypeError: object GenerateContentResponse can't be used in...

bheindorf

### Description of the feature request: I used the env-var "XDG_CONFIG_HOME" and "GEMINI_USER_HOME" to specify the saved path of check-points, but failed. Does cli has the features to redirect the...

RealityTracer

### Description of the bug: In some of my use cases, I have very frequent 500 errors. I'm retrying them, but some are persistent. Here's an example `GenerateContentParameters` https://gist.github.com/uriva/ec104cbf926ad142036490460ce8c2ad ###...

uriva

### Description of the bug: Hello, I am experiencing a persistent 404 Not Found error when trying to use the generateContent method with both gemini-1.0-pro and gemini-pro models. My region...

atharvrana77811

### Description of the bug: **Summary:** The Gemini API (accessed via Google AI Studio paid tier) is exhibiting non-deterministic behavior for the `gemini-2.5-pro` model. It is producing different outputs for...

shuknk8s

### Description of the bug: Hello, I'm occasionally experiencing empty responses by the Gemini model. The task is to chunk a man page into blocks, so the content is of...

sebastianrath

AttributeError: module 'google.generativeai' has no attribute 'Tool' on a fresh environment

4

### Description of the bug: Body: Hello, I am encountering a persistent AttributeError: module 'google.generativeai' has no attribute 'Tool' even after extensive debugging, including a full virtual environment rebuild. The...

ericchen913900