Skip to content

armgit / txtai

Public Imported from GitHub
0

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

Move quantize config param to Faiss, closes #311

davidmezzetti4db72769c085
diff --git a/src/python/txtai/ann/faiss.py b/src/python/txtai/ann/faiss.py
index 6c871326..e64cbb5e 100644
--- a/src/python/txtai/ann/faiss.py
+++ b/src/python/txtai/ann/faiss.py
@@ -86,7 +86,7 @@ class Faiss(ANN):
return components
# Get storage setting
- storage = "SQ8" if self.config.get("quantize") else "Flat"
+ storage = "SQ8" if self.setting("quantize", self.config.get("quantize")) else "Flat"
# Small index, use storage directly with IDMap
if count <= 5000: