Shorter tracebacks (bad solution maybe?) #295
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
ProducerMatt
commented
Jun 21, 2023
| """Search for relevant items for the query. | ||
|
|
||
| First we load all items from the Alignment Newsletter database. | ||
| Then we sort the items by relevance to the query. | ||
| Finally we return the most relevant items, if any. | ||
| """ | ||
| query = prompt |
There was a problem hiding this comment.
I'll factor out these redundant lines once I know whether I'm on the right track at all.
|
Rob made a good suggestion, make the traceback generator have a duplicate object detector and only print the first occurrence. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I'm trying to change the way that tracebacks work so that callbacks don't reprint the original prompt. This involves giving arguments to the callbacks in such a way that the traceback collector will know to remove them (I decided to try to leave the message ID if there is one, otherwise just leaving
<prompt>).This is my attempted solution, which makes the keyword argument
promptsomething that the traceback module removes. However it doesn't work. Every module gets asked the question but no responses are ever returned, not even the initial once's inviting a traceback. (I notice that the Sentience module prints "Confused response sent") I'd love it if someone could point out what I'm doing wrong, because I even tried redoing this from scratch and got the same result. Also if anyone knows how to make Python print a stack trace for all threads on demand I'd like to know.would help #294