Replies: 1 comment
-
Please see this thread: https://github.com/orgs/langfuse/discussions/3429 Prompts are available immediately as they are served from the prompt cache: https://langfuse.com/docs/prompt-management/features/caching |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Describe the feature or potential improvement
Right now, you can supply a
httpx_client
to theLangfuse
module on instantiation. This is great, but it means that I can't call async forget_prompt
under the high-level API.It's already supported by the
AsyncFernLangfuse
object, but just needs to be passed through down the chain of instantiation from theLangfuse
object. Right now I have to overwrite theasync_api
with a customAsyncFernLangfuse
instance to bypass this behavior.Assuming that eventually, the the python SDK will support dynamically choosing sync/async calls, the idea here is to allow:
async_httpx_client
to be a variable passed through from theLangfuse
object__init__
method all the way through theLangfuseResourceManager
and intoAsyncFernLangfuse
Additional information
No response
Beta Was this translation helpful? Give feedback.
All reactions