Added fixes and improvements for multiple components #51
+281
−152
Conversation
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
Moorelatrice39
approved these changes
Jan 16, 2025
taddeusb90
changed the title
# or checking .is_running() / .status()
taddeusb90
changed the title
taddeusb90
changed the title
taddeusb90
changed the title
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Outdated suggestions cannot be applied.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.
Added .gitignore entries for
data/projects/provided new lines to ignore additional directories and scripts.Removed timeouts from
execute_code(...)calls in ai_lab_repo.py removing timeout=60 and timeout=120 so that the code no longer forcibly terminates after a short period.Updated logging to show if
self.verbosebefore printing certain debug statements** in literature_review**:New try-except block for FULL_TEXT retrieval in literature_review** if an
arxiv.Client().results(...)call fails, an [ERROR] Could not retrieve paper message is included instead of throwing an unhandled exception.Introduced a new --file-path argument if the user’s research topic string includes
{FILE}, the content of the file at--file-pathis read and substituted in the prompt. This avoids shell “argument list too long” issues.Changed default model from "gpt-4" to "o1-mini" and raised the default max_context_tokens to
128000for expanded context capacity.Added a new subprocess-based code execution method using
psutilto distinguish busy vs. idle states. Now, if the code is continuously active (CPU usage above a small threshold), it can run longer, but will be terminated early if idle for too long or if it exceeds a hard overall runtime.