Prompt generation step is so slow, take 4 minutes #1192
ssling0817
started this conversation in
General
Replies: 0 comments
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.
Uh oh!
There was an error while loading. Please reload this page.
-
I am using DatabricksConnector for input dataframe. Its size is 2017x41, but it always took around 4 minutes to generate prompt.
I guess its because databricks_connector.to_json() needs around 3 minutes to complete.
Is there any way to speed up the process?
`2024-06-02 13:47:20 [INFO] Executing Pipeline: GenerateChatPipeline
2024-06-02 13:49:43 [INFO] Executing Step 0: ValidatePipelineInput
2024-06-02 13:49:43 [INFO] Executing Step 1: CacheLookup
2024-06-02 13:49:43 [INFO] Executing Step 2: PromptGeneration
2024-06-02 13:53:21 [INFO] Using prompt:
dfs[0]:2017x41`
Beta Was this translation helpful? Give feedback.
All reactions