Improved query, print & exception handling in REPL Tool #3215
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
The following improvements are made to the Python REPL Tool: 1) Improved the sanitization of query (using regex), by removing python command (since gpt-3.5-turbo sometimes assumes python console as a terminal, and runs python command first which causes error). Also sometimes 1 line python codes contain single backticks. (i) Eg of python in query: > Entering new LLMMathChain chain... 1291.25 * 6 ```python print(1291.25 * 6) ``` (ii) Eg of 1 line query with single backtick: Thought:I have the number of unique Account IDs, but I need to count the number of active accounts Action: python_repl_ast Action Input: `len(df[df['Status'] == 'Active'])` 2) Improved the capturing of print by redirecting stdout to output of Python REPL Tool (without cluttering the actual stdout). 3) Made sure the exception format type is returned in all cases, when the exec() function throws an exception.
Updated formatting by running the "poetry run black ." command.
|
I corrected the lint formatting by running the "poetry run black ." command and created a new commit. |
hwchase17
reviewed
Apr 25, 2023
|
@hwchase17 I have added 7 new test cases as you asked. I have also rerun the lining commands one by one and fixed the formatting issues. This is my first time adding test cases, so it took a while. If any linting issues persist (none were detected when run locally by me), I request you to fix it if possible. |
|
@hwchase17, is there anything blocking this merge? |
vowelparrot
pushed a commit
that referenced
this pull request
May 22, 2023
Update to pull request #3215 Summary: 1) Improved the sanitization of query (using regex), by removing python command (since gpt-3.5-turbo sometimes assumes python console as a terminal, and runs python command first which causes error). Also sometimes 1 line python codes contain single backticks. 2) Added 7 new test cases. For more details, view the previous pull request. --------- Co-authored-by: Deepak S V <svdeepak99@users.noreply.github.com>
|
Reopened this PR & merged in #4997 |
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.
The following improvements are made to the Python REPL Tool:
(i) Eg of python in query:
(ii) Eg of 1 line query with single backtick:
Thought: I have the number of unique Account IDs, but I need to count the number of active accounts Action: python_repl_ast
Action Input:
`len(df[df['Status'] == 'Active'])`Improved the capturing of print by redirecting stdout to output of Python REPL Tool (without cluttering the actual stdout). Also when the return of eval() function is None, then returning stdout (in case code contains a print or info statement).
Made sure the exception format type is returned in all cases, when the exec() function throws an exception.