[Add] Logging for each message of GPTAssistant #2677
Conversation
|
Added Fix to resolve #2697 |
|
@ekzhu @WaelKarkoub this check is failing "ContribTests / RetrieveChatTest-Ubuntu (3.9) (pull_request)" any idea why ? and how do we fix it ? |
| @@ -213,6 +217,12 @@ def _invoke_assistant( | |||
| role=message["role"], | |||
| ) | |||
|
|
|||
| self.client.create( | |||
There was a problem hiding this comment.
I don't really understand the log related implement, but I would like to know if it will call openai completion function?
There was a problem hiding this comment.
.create() calls the log_chat_completion() which is responsible only for logging data into sqlite DB.
its the self._get_run_response() which makes openai chat completions call
There was a problem hiding this comment.
for the GPTAssistantAgent we use the run to get the responses from the assistant. i think calling the openai completion doesn't add up to the actual assistant logs.
See if adding |
|
@sonichi @ekzhu @WaelKarkoub i ran the |
|
These are the error messages found from failed checks, how do we fix them during workflow runs ? |
This comment was marked as outdated.
This comment was marked as outdated.
Sorry, something went wrong.
| @@ -213,6 +217,12 @@ def _invoke_assistant( | |||
| role=message["role"], | |||
| ) | |||
|
|
|||
| self.client.create( | |||
There was a problem hiding this comment.
for the GPTAssistantAgent we use the run to get the responses from the assistant. i think calling the openai completion doesn't add up to the actual assistant logs.
@IANTHEREAL @ekzhu
Why are these changes needed?
It solves the logging issue with GPTAssistant Sequential chats, where only the last message of a sequential step was being logged, rather than logging each GPTAssistant Agent interaction.
Related issue number
Closes #2644
Checks