💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
Python agentsaiai-agentsembeddingsinformation-retrievallanguage-modellarge-language-modelsllmnlppythonragretrieval-augmented-generationsearchsearch-enginesemantic-searchsentence-embeddingstransformerstxtaivector-databasevector-search
Update comment
davidmezzettic15090a30390
diff --git a/src/python/txtai/data/questions.py b/src/python/txtai/data/questions.pyindex 045fb659..e629fde7 100644--- a/src/python/txtai/data/questions.py+++ b/src/python/txtai/data/questions.py@@ -53,7 +53,7 @@ class Questions(Data):# Get and format answeranswers = self.answers(data, samples[x])- # If no answers are given, set the cls_index as answer.+ # If no answers are given, set cls token as answer.if len(answers["answer_start"]) == 0:tokenized["start_positions"].append(clstoken)tokenized["end_positions"].append(clstoken)