-
Notifications
You must be signed in to change notification settings - Fork 12
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
FIX: LLM sometimes returns string and the code handle it as list #186
Conversation
WalkthroughThe Changes
Sequence Diagram(s) (Beta)sequenceDiagram
participant User
participant extract_arguments
participant ChatOpenAI
User->>extract_arguments: Call with input, prompt, model
extract_arguments->>ChatOpenAI: Send prompt
ChatOpenAI-->>extract_arguments: Return response
alt Response is JSON array
extract_arguments->>extract_arguments: Parse JSON array
else Response is string
extract_arguments->>extract_arguments: Convert string to list
end
extract_arguments->>User: Return processed items
Poem
Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media? TipsChatThere are 3 ways to chat with CodeRabbit:
Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (invoked as PR comments)
Additionally, you can add CodeRabbit Configration File (
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Actionable comments posted: 0
Outside diff range and nitpick comments (1)
scatter/pipeline/steps/extraction.py (1)
Line range hint
1-1
: Remove unused import.- import os
Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Files selected for processing (1)
- scatter/pipeline/steps/extraction.py (1 hunks)
Additional context used
Ruff
scatter/pipeline/steps/extraction.py
1-1:
os
imported but unused
Additional comments not posted (1)
scatter/pipeline/steps/extraction.py (1)
50-56
: The changes correctly handle cases where the LLM returns a string instead of a list. However, consider converting the filter object to a list for Python 3 compatibility.[REFACTOR_SUGGESTion]
- items = filter(None, items) # omit empty strings + items = list(filter(None, items)) # omit empty strings
LLM sometimes returns a valid JSON string. In such cases, the original code mistakenly treats the string as a list and outputs it character by character.
This causes an error
TypeError: expected string or buffer
in the next embedding phase.Summary by CodeRabbit