This website uses Cookies. Click Accept to agree to our website's cookie use as described in our Privacy Policy. Click Preferences to customize your cookie settings.
Background:I am testing Langchain + VertexAI to read different annual
reports.Observations:I found different models provide different response
behaviours.chat-bison@001: I gave instruction to model and tell model
not to provide answer if answer canno...
Dear all,I would like to set safety filter in Vertex AI API
call.However, I cannot find information talking about how to do it.I
asked Bard to give me sample code. However, it does not work.Can anyone
suggest me how can I add Safety filter to control...
Dear all,I would like to the Vertex AI response in html format instead
of text format.Does anyone know if the native Vertex AI response output
support HTML format?Many Thanks,Victor
Hi Robert, which model you are using? I found out that after moving to
Gemini Flash 2.0. This issue improved. I seldom seeing this issue
again.I gave up 1.5. No way to fix.
You have pointed out a good point to fallback to 001. I didn't think
about this approach. Anything, I stopped using Gemini for production
until it becomes stable.
Same problem here. So annoying. I have to switch to use another AI
service provider to keep my services up and running.I checked no quota
warning in console. And I requested quota to 30,000 already.Error: 429
Online prediction request quota exceeded ...
