openai.internal.ChatParams
The per-request knobs a caller configured on the wrapper client. Typed parameters lower into the typed request only when non-null; `request_body` is the deep-merge escape hatch applied last (PLAN P0.3).
Reference version
Signature
class openai.internal.ChatParamsThe per-request knobs a caller configured on the wrapper client. Typed
parameters lower into the typed request only when non-null; request_body is
the deep-merge escape hatch applied last (PLAN P0.3).
Source:<builtin>/openai/ns_internal/chat.bamlbytes 7254–8475
Fields
model
stringapi_key
string | nulltemperature
float | nullmax_tokens
int | nullmax_completion_tokens
int | nulltop_p
float | nullstop
string[] | nullseed
int | nullheaders
map<string, string> | nullquery_params
map<string, string> | nullrequest_body
baml.json.json | nullStatic methods
function
new
(model: string,
api_key: string | null = …,
temperature: float | null = …,
max_tokens: int | null = …,
max_completion_tokens: int | null = …,
top_p: float | null = …,
stop: string[] | null = …,
seed: int | null = …,
headers: map<string, string> | null = …,
query_params: map<string, string> | null = …,
request_body: baml.json.json | null = …
) -> openai.internal.ChatParams