Log in
Log into community
Find answers from the community
s
F
Y
a
P
3,278
View all posts
Related posts
Did this answer your question?
😞
😐
😃
Powered by
Hall
Inactive
Updated 2 years ago
0
Follow
ChatGPT API
ChatGPT API
0
Follow
G
Glenn
2 years ago
·
OpenAI just released their ChatGPT models/API. Thoughts on integration with gpt-index?
G
H
T
10 comments
Share
Open in Discord
G
Glenn
2 years ago
https://platform.openai.com/docs/guides/chat/faq
H
HAL 9000
2 years ago
shouldn't it be as easy as just changing the model in
LLMPredictor
?
H
HAL 9000
2 years ago
oh I see it is not same as completions endpoint.
G
Glenn
2 years ago
There’s an additional parameter “messages”. not sure how easy/difficult that would be to implement
T
Teemu
2 years ago
I tried, it didnt work
H
HAL 9000
2 years ago
is the messages your entire conversation with the assistant?
G
Glenn
2 years ago
I think so…which is kinda meh to me. Like what if you have many messages lol, I guess it’s up to us to determine how many messages we want to be in context
G
Glenn
2 years ago
But Now that I think about it, each chat thread probably won’t be more than a small number of messages anyways…in theory
H
HAL 9000
2 years ago
does it persist the conversation after you send a request to
chat/completions
endpoint or you can only create a conversation once and then that's it?
H
HAL 9000
2 years ago
What I mean is that they don't return
conversation-id
unlike how they do it on browser.
Add a reply
Sign up and join the conversation on Discord
Join on Discord