Conversation
This branch has not been deployed
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
processing_phrases, e.g.30cm/s→30cm s). Addedprocessing_phrases_preserve_punctand use it for stored entityname/idin the three SPG extractors; keptprocessing_phrasesfor matching/dedup keys.BatchVectorizercrashed withTypeError: 'NoneType' object is not iterablewhen a vectorize model returnedNonefor a batch. Added_coalesce_vectorsto flatten safely and raise an actionable error; also fixed the async path feeding the unfilteredtexts[start:end]instead ofsub_texts.table_retrieverthrewKeyError: 'beforeText'because builder storesbefore_text/after_text(snake_case). Reads now tolerate both naming conventions.medical_nerprompt used Chinese schema display names (extract_types→name_zh); now uses English type identifiers fromload()(matchingdefault_ner), so the LLM NERcategoryaligns to SPG type identifiers.McpExecutor.schema()method that was accidentally defined at module level (referenced undefinedself).Files changed
kag/common/utils.pykag/builder/component/extractor/schema_constraint_extractor.pykag/builder/component/extractor/schema_free_extractor.pykag/builder/component/extractor/knowledge_unit_extractor.pykag/builder/component/vectorizer/batch_vectorizer.pykag/builder/prompt/medical/ner.pykag/common/tools/algorithm_tool/chunk_retriever/table_retriever.pykag/solver/executor/mcp/mcp_executor.pyTest plan
py_compile.pytestshould be run in a configured env (import kagrequires env setup).Closes #737 #718 #747 #685 #704