C
I
Y
JJJC
C
"type": "text"
A
TCCCCCCconst query = messages.map(({ content, role }) => ${role}: ${content}).join("\n\n"); helper for the AutoRAG prompt system. also this is repeated itself twice and deserve a function on its own. will fix the PR for the base64 images and add it all there
F
CC
C
CB
Stream OK” : “
No stream body”, { No stream bodyCCBPP
PP
like most stuffPPPP
B
B
prompt_tokens and completion_tokens were replaced with input_tokens and output_tokens).instructions parameter stopped working when the input was in an OpenAI-like format (like [{role: "assistant", content: "foobar" }, ...]).
B
K
S
C
LL
ZPZPPP
Q
VV
"type": "text"const query = messages.map(({ content, role }) => ).join("\n\n");prompt_tokenscompletion_tokensinput_tokensoutput_tokensinstructions[{role: "assistant", content: "foobar" }, ...]