💡 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 #704 to not require a path parameter in Embeddings as not all vector models need a path. Update test.
davidmezzettif3b7cb9569eb
diff --git a/src/python/txtai/embeddings/base.py b/src/python/txtai/embeddings/base.pyindex 3104437b..bc430a2d 100644--- a/src/python/txtai/embeddings/base.py+++ b/src/python/txtai/embeddings/base.py@@ -744,7 +744,7 @@ class Embeddings:self.scoring = self.createscoring() if scoring and (not isinstance(scoring, dict) or not scoring.get("terms")) else None# Dense vectors - transforms data to embeddings vectors- self.model = self.loadvectors() if self.config and self.config.get("path") else None+ self.model = self.loadvectors() if self.config else None# Query modelself.query = self.loadquery() if self.config else Nonediff --git a/test/python/testoptional.py b/test/python/testoptional.pyindex cac20266..e1d81563 100644--- a/test/python/testoptional.py+++ b/test/python/testoptional.py@@ -253,7 +253,7 @@ class TestOptional(unittest.TestCase):VectorsFactory.create({"method": "words"}, None)with self.assertRaises(ImportError):- VectorsFactory.create({"method": "sentence-transformers", "path": ""}, None)+ VectorsFactory.create({"method": "sentence-transformers", "path": "sentence-transformers/nli-mpnet-base-v2"}, None)def testWorkflow(self):"""