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.
I'm not getting massively good performance from Gemini or Bison models
on a text generation task.For a bit of context, we have a Dialogflow CX
agent and we answer specific questions based on Text content which we
pass to a generator. An approach whic...
I'm trying to store the result from a Generator in a session param so I
can re-use without having to re-call the Generator e.g if a user asks to
repeat something and i need to access in further pages. For some reason
I can't access the Generator outp...
Hi All, we are close to using a generator in a production Dialogflow
project but unfortunately we've come across a usability problem due to
the length of time it takes for the Generator to return a response,
which can be a number of seconds which als...
Thanks for the response @xavidop . A quick follow up. I spent more time
prompt engineering and finally getting the responses I'm looking for, so
I'm happy. I need to test a lot more but at least now I'm getting better
results.A wise LLM once said "po...
There is a problem with using the Generators, they are not hugely
performant and also the way the Dialogflow responses are parsed i.e
waits for all responses to return before sending back a response means
that there is a lag. We've noticed this in ou...
