From d3e6cfa1f71c9693bc5094e194a4ec59fa87b26f Mon Sep 17 00:00:00 2001
From: aakash <aakashsuresh@berkeley.edu>
Date: Mon, 6 Oct 2025 14:40:04 -0700
Subject: [PATCH] fix: Resolve SentenceTransformer model_kwargs parameter
 conflict

- Fix local_files_only parameter conflict in embedding_compute.py
- Create separate copies of model_kwargs and tokenizer_kwargs for local vs network loading
- Prevents parameter conflicts when falling back from local to network loading
- Resolves TypeError in test_readme_examples.py tests

This addresses the SentenceTransformer initialization issues in CI tests.
---
 .../leann-core/src/leann/embedding_compute.py | 20 +++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/packages/leann-core/src/leann/embedding_compute.py b/packages/leann-core/src/leann/embedding_compute.py
index a01bd3b..fafa1a0 100644
--- a/packages/leann-core/src/leann/embedding_compute.py
+++ b/packages/leann-core/src/leann/embedding_compute.py
@@ -184,28 +184,32 @@ def compute_embeddings_sentence_transformers(
 
         try:
             # Try local loading first
-            model_kwargs["local_files_only"] = True
-            tokenizer_kwargs["local_files_only"] = True
+            local_model_kwargs = model_kwargs.copy()
+            local_tokenizer_kwargs = tokenizer_kwargs.copy()
+            local_model_kwargs["local_files_only"] = True
+            local_tokenizer_kwargs["local_files_only"] = True
 
             model = SentenceTransformer(
                 model_name,
                 device=device,
-                model_kwargs=model_kwargs,
-                tokenizer_kwargs=tokenizer_kwargs,
+                model_kwargs=local_model_kwargs,
+                tokenizer_kwargs=local_tokenizer_kwargs,
                 local_files_only=True,
             )
             logger.info("Model loaded successfully! (local + optimized)")
         except Exception as e:
             logger.warning(f"Local loading failed ({e}), trying network download...")
             # Fallback to network loading
-            model_kwargs["local_files_only"] = False
-            tokenizer_kwargs["local_files_only"] = False
+            network_model_kwargs = model_kwargs.copy()
+            network_tokenizer_kwargs = tokenizer_kwargs.copy()
+            network_model_kwargs["local_files_only"] = False
+            network_tokenizer_kwargs["local_files_only"] = False
 
             model = SentenceTransformer(
                 model_name,
                 device=device,
-                model_kwargs=model_kwargs,
-                tokenizer_kwargs=tokenizer_kwargs,
+                model_kwargs=network_model_kwargs,
+                tokenizer_kwargs=network_tokenizer_kwargs,
                 local_files_only=False,
             )
             logger.info("Model loaded successfully! (network + optimized)")