Open plopezamaya opened 3 weeks ago
Also note that when deploying models into azure the model name will not always be gpt-4-turbo-2024-04-09
or one of the litellm model names. Meaning that for azure providers or custom providers there should be a case Model Base Name
Making a deployment with the nameprd-myprojectapi-gpt35-turbo-eu-west-3
on azure have the following properties :
prd-myprojectapi-gpt35-turbo-eu-west-3
gpt-35-turbo-1106
This will allow to use the azure deployments/endpoints while using the dynamic maximum number of tokens for the base model and not having a single maximum number of tokens to be set in GEN_AI_MAX_TOKENS
Image generation is supported only for
openai
providers and model names equal togpt-4-turbo
.Some examples of this can be seen in the
v3.0.79
:-
backend/danswer/chat/process_message.py
:web/src/app/admin/assistants/AssistantEditor.tsx
:Azure deployments e.i
model
is not alwaysgpt-4-turbo
as it can follow some deployment conventions. Therefore it will not be recognized neither for the Image Generation nor for the maximum number of tokens usinglitellm.model_cost
function :On idea could be to have model type set in the UI (gpt-4-turbo) and leave the model name for the deployment. Using this model type you can now check for the image generation and also for the cost and use the name to query the endpoint.