💡 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
Refactor check for uninitialized embeddings instance #212
davidmezzettif6b5c2f0fe4e
diff --git a/src/python/txtai/embeddings/search.py b/src/python/txtai/embeddings/search.pyindex 0f083b46..7be2587d 100644--- a/src/python/txtai/embeddings/search.py+++ b/src/python/txtai/embeddings/search.py@@ -39,6 +39,10 @@ class Search:list of (id, score) per query for ann search, list of dict per query for an ann+database search"""+ # Return empty results if ANN is not set+ if not self.ann:+ return []+if self.database:return self.dbsearch(queries, limit)@@ -61,7 +65,7 @@ class Search:embeddings = np.array([self.transform((None, query, None)) for query in queries])# Search approximate nearest neighbor index- results = self.ann.search(embeddings, limit) if self.ann else []+ results = self.ann.search(embeddings, limit)# Require scores to be greater than 0results = [[(i, score) for i, score in r if score > 0] for r in results]