fix: resolve windows encoding and harden FAISS indexing logic#283
Open
srinivasan-ai-dev wants to merge 3 commits intojenkinsci:mainfrom
Open
fix: resolve windows encoding and harden FAISS indexing logic#283srinivasan-ai-dev wants to merge 3 commits intojenkinsci:mainfrom
srinivasan-ai-dev wants to merge 3 commits intojenkinsci:mainfrom
Conversation
Author
|
All feedback has been addressed and verified. CI checks are passing, and I've resolved the individual conversation threads. Ready for further review! |
srinivasan-ai-dev
force-pushed
the
fix/windows-compatibility-and-robustness
branch
from
30506c2 to
159e663
Compare
Author
|
Hi @berviantoleo, I have addressed the Pylint style violations and fixed the AttributeError in the backend unit tests by implementing type-checking for the chunking input. The PR should now be ready for a final review. Thank you! |
srinivasan-ai-dev
force-pushed
the
fix/windows-compatibility-and-robustness
branch
from
159e663 to
8a7973f
Compare
Author
|
Hi @berviantoleo, just checking in to see if there’s anything I can clarify regarding the FAISS indexing changes or if you’d like me to resolve any specific blockers! Thanks. |
berviantoleo
added
the
bug
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR addresses critical environment and pipeline bottlenecks identified during Windows setup and testing with smaller datasets.
Key Fixes:
Windows Compatibility: Enforced UTF-8 encoding in JSON reading to prevent UnicodeDecodeError.
Schema Resiliency: Updated extract_chunk_docs.py to handle nested dictionary structures, preventing KeyError.
FAISS Fallback: Implemented dynamic switching to IndexFlatL2 when the dataset is smaller than the cluster count (nlist), preventing training crashes.
Dependency Hardening: Updated requirements-cpu.txt to ensure a smoother local setup.
This ensures the project is more accessible for new contributors on diverse operating systems.