client
client copied to clipboard
⚡️ Gemini PHP is a community-maintained PHP API client that allows you to interact with the Gemini AI API.
See https://ai.google.dev/gemini-api/docs/api-overview#json Seems currently there is no way for me to pass arbitrary/custom data for `GenerationConfig`
   here is code  Api key 
How can I access my tuned models?
Getting error message: ``` "message": "Gemini 1.0 Pro Vision has been deprecated on July 12, 2024. Consider switching to different model, for example gemini-1.5-flash.", ``` Please update model as previous...
Support for gemini-1.0-pro, gemini-1.0-pro-latest, gemini-1.5-pro, gemini-1.5-flash #25
There is no method for chat to stream a reply
# Context Google's `GenerateContentResponse` includes a "[usageMetadata](https://ai.google.dev/api/generate-content#usagemetadata)". The above has reference to 4 attributes of the usageMetadata, however the actual returned response currently only includes the 3 listed [here in...
Resolve google-gemini-php/client#8 Use v1beta as default base URL to support the feature
Using the examples fails with the following error: Error! Gemini API operation failed: operation=models/gemini-pro-vision:generateContent, status_code=404, response={ "error": { "code": 404, "message": "Gemini 1.0 Pro Vision has been deprecated on July...
In the readme is **batchEmbedContents** mentioned: `Use the embedding-001 model with either embedContents or batchEmbedContents:` But there seems to be no way to use batchEmbedContents (only embedContents as a string...