search

konveyor / kai

Konveyor AI - static code analysis driven migration to new targets via Generative AI
Apache License 2.0
23 stars 28 forks source link

Google Gemini: "ResourceExhausted: 429 Resource has been exhausted" #314

Open jwmatthews opened 3 weeks ago

jwmatthews commented 3 weeks ago

While testing #307 I encountered the below.

Retrying langchain_google_genai.chat_models._chat_with_retry.<locals>._chat_with_retry in 2.0 seconds as it raised ResourceExhausted: 429 Resource has been exhausted (e.g. check quota)..

Running with config.toml containing:

# **Google Gemini Pro**
[models]
provider = "ChatGoogleGenerativeAI"

[models.args]
model = "gemini-pro"

I tested above with a free API key created via: https://aistudio.google.com/app/apikey

jwmatthews commented 3 weeks ago

I think this is simply an issue of use of free tier being rate limited and not sufficient for running run_example.py. I upgraded to paid tier on my account and that resolved the rate limit issue.

As of now I do not see us wanting to do any work to adapt and lower our request rate, so marking this as wontfix