StructSense Pipeline Upgrade: Specialized Tools, Robust Chunking, and BioPortal Integration#62
Merged
Conversation
… manager in case of parallel agent sometimes deepcopy was failing
llm_ner means that the ner is performed via API call using llm
- Add ConceptMappingTool to alignment_agent (task_tools.py) - Run concept mapping by default when pipeline has alignment_task; use max_workers (app.py) - apply_concept_mapping_to_result: parallel mapping, add ontology_id/ontology_label/ontology + concept_mapping_provenance (postprocessing.py) - Provenance: 'tool' when from Concept Mapping Tool, 'llm_knowledge' when from LLM (config + postprocessing) - Simplify ner_config_old.yaml: clear pipeline vars, simple task roles - Remove enable_concept_mapping/concept_mapping_max_workers flags; concept mapping driven by alignment_task presence Co-authored-by: Cursor <cursoragent@cursor.com>
…nse into evaluation_result_paper
Evaluation result paper
Fix poetry issue githubworkflow
Removed 'keyphrase_extraction' from task_type parameterization in tests.
Update test parameterization for task_type.
Added additional paths to the codespell skip list.
Performance cost optimization
Update codespell skip list in pre-commit config
Corrected comments and formatting in the YAML configuration.
…ython api; updating config file to use gpt-4o-mini to be more consistent
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
updating tests
Merging this PR as it fixed the issue--extracting less entity and not saving the result. Additionally, this PR contains many other updates merged from other PRs.
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
5 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 pull request introduces major improvements to StructSense, including the addition of specialized tools, fixes to the chunking mechanism, and integration with BioPortal as the ontology database.
What’s Included
Issues this PR addresses