Log in
Log into community
Find answers from the community
View all posts
Related posts
Did this answer your question?
π
π
π
Powered by
Hall
Inactive
Updated 3 months ago
0
Follow
Max tokens
Max tokens
Inactive
0
Follow
D
Daslav
2 years ago
Β·
nop, gpt-3.5-turbo
L
D
6 comments
Share
Open in Discord
L
Logan M
2 years ago
That might by why the output changes so much. Gpt-3.5 can be... difficult to work with, compared to text-davinci-003
L
Logan M
2 years ago
I honestly think openai has dumbed it down in the last month lol
D
Daslav
2 years ago
With davinci-003 + max_token 1024 + chunk_size_limit=1024 + top_n=10 (Cohere) + k=10 (Weaviate),
I receive good responses, but they are very, very slow. LOL
L
Logan M
2 years ago
Lol could enable streaming maybe, to help the responses feel faster
When you say top_n with cohere, you mean llm reranking or?
D
Daslav
2 years ago
reranking, right!
L
Logan M
2 years ago
Nice! Yea that's probably going to be the main bottleneck, llm calls are costly in terms of time
Add a reply
Sign up and join the conversation on Discord
Join on Discord