Changes default cache embedding model (#326)

Changes the default semantic cache embedding model to our fine tuned
model.

Author: justin-cechmanek

docs/user_guide/03_llmcache.ipynb

@@ -271,7 +271,7 @@
    "outputs": [],
    "source": [
     "# Widen the semantic distance threshold\n",
-    "llmcache.set_threshold(0.3)"
+    "llmcache.set_threshold(0.5)"
    ]
   },
   {

redisvl/extensions/cache/llm/semantic.py

@@ -111,8 +111,19 @@ def __init__(
             if dtype:
                 vectorizer_kwargs.update(dtype=dtype)
 
+            # raise a warning to inform users we changed the default model
+            # remove this warning in future releases
+            logger.warning(
+                "The default vectorizer has changed from `sentence-transformers/all-mpnet-base-v2` "
+                "to `redis/langcache-embed-v1` in version 0.6.0 of RedisVL. "
+                "For more information about this model, please refer to https://arxiv.org/abs/2504.02268 "
+                "or visit https://huggingface.co/redis/langcache-embed-v1. "
+                "To continue using the old vectorizer, please specify it explicitly in the constructor as: "
+                "vectorizer=HFTextVectorizer(model='sentence-transformers/all-mpnet-base-v2')"
+            )
+
             self._vectorizer = HFTextVectorizer(
-                model="sentence-transformers/all-mpnet-base-v2",
+                model="redis/langcache-embed-v1",
                 **vectorizer_kwargs,
             )
 
@@ -147,6 +158,20 @@ def __init__(
         # Check for existing cache index and handle schema mismatch
         self.overwrite = overwrite
         if not self.overwrite and self._index.exists():
+
+            if not vectorizer:
+                # user hasn't specified a vectorizer and an index already exists they're not overwriting
+                # raise a warning to inform users we changed the default embedding model
+                # remove this warning in future releases
+                logger.warning(
+                    "The default vectorizer has changed from `sentence-transformers/all-mpnet-base-v2` "
+                    "to `redis/langcache-embed-v1` in version 0.6.0 of RedisVL. "
+                    "For more information about this model, please refer to https://arxiv.org/abs/2504.02268 "
+                    "or visit https://huggingface.co/redis/langcache-embed-v1. "
+                    "To continue using the old vectorizer, please specify it explicitly in the constructor as: "
+                    "vectorizer=HFTextVectorizer(model='sentence-transformers/all-mpnet-base-v2')"
+                )
+
             existing_index = SearchIndex.from_existing(
                 name, redis_client=self._index.client
             )

tests/integration/test_llmcache.py

@@ -17,7 +17,7 @@
 
 @pytest.fixture
 def vectorizer():
-    return HFTextVectorizer("sentence-transformers/all-mpnet-base-v2")
+    return HFTextVectorizer("redis/langcache-embed-v1")
 
 
 @pytest.fixture
@@ -720,12 +720,17 @@ def test_cache_filtering(cache_with_filters):
     # test we can pass a list of tags
     combined_filter = filter_1 | filter_2 | filter_3
     results = cache_with_filters.check(
-        "test prompt 1", filter_expression=combined_filter, num_results=5
+        "test prompt 1",
+        filter_expression=combined_filter,
+        num_results=5,
+        distance_threshold=0.5,
     )
     assert len(results) == 3
 
     # test that default tag param searches full cache
-    results = cache_with_filters.check("test prompt 1", num_results=5)
+    results = cache_with_filters.check(
+        "test prompt 1", num_results=5, distance_threshold=0.6
+    )
     assert len(results) == 4
 
     # test no results are returned if we pass a nonexistant tag
@@ -784,7 +789,10 @@ def test_complex_filters(cache_with_filters):
     # test we can do range filters on inserted_at and updated_at fields
     range_filter = Num("inserted_at") < current_timestamp
     results = cache_with_filters.check(
-        "prompt 1", filter_expression=range_filter, num_results=5
+        "prompt 1",
+        filter_expression=range_filter,
+        num_results=5,
+        distance_threshold=0.5,
     )
     assert len(results) == 2