💡 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 reducer to be consistent with embeddings patterns
davidmezzetti4ac7aa26ea27
diff --git a/src/python/txtai/embeddings/reducer.py b/src/python/txtai/embeddings/reducer.pyindex 8b5fa000..ac7c3d57 100644--- a/src/python/txtai/embeddings/reducer.py+++ b/src/python/txtai/embeddings/reducer.py@@ -83,7 +83,7 @@ class Reducer:"""# Dimensionality reduction- with open(f"{path}/lsa", "rb") as handle:+ with open(path, "rb") as handle:self.model = pickle.load(handle)def save(self, path):@@ -94,5 +94,5 @@ class Reducer:path: directory path to save model"""- with open(f"{path}/lsa", "wb") as handle:+ with open(path, "wb") as handle:pickle.dump(self.model, handle, protocol=pickle.HIGHEST_PROTOCOL)