Merge branch 'master' into allow-timeout-customization-when-using-redis-cluster

Author: petyaslavova

.github/workflows/integration.yaml

@@ -74,7 +74,7 @@ jobs:
       max-parallel: 15
       fail-fast: false
       matrix:
-        redis-version: ['8.2-RC1-pre', '${{ needs.redis_version.outputs.CURRENT }}', '7.4.4', '7.2.9']
+        redis-version: ['8.2', '${{ needs.redis_version.outputs.CURRENT }}', '7.4.4', '7.2.9']
         python-version: ['3.9', '3.13']
         parser-backend: ['plain']
         event-loop: ['asyncio']
@@ -99,7 +99,7 @@ jobs:
       fail-fast: false
       matrix:
         redis-version: [ '${{ needs.redis_version.outputs.CURRENT }}' ]
-        python-version: ['3.9', '3.10', '3.11', '3.12', 'pypy-3.9', 'pypy-3.10']
+        python-version: ['3.10', '3.11', '3.12', 'pypy-3.9', 'pypy-3.10']
         parser-backend: [ 'plain' ]
         event-loop: [ 'asyncio' ]
     env:

redis/commands/vectorset/commands.py

@@ -129,6 +129,7 @@ def vsim(
         filter_ef: Optional[str] = None,
         truth: Optional[bool] = False,
         no_thread: Optional[bool] = False,
+        epsilon: Optional[Number] = None,
     ) -> Union[
         Awaitable[Optional[List[Union[List[EncodableT], Dict[EncodableT, Number]]]]],
         Optional[List[Union[List[EncodableT], Dict[EncodableT, Number]]]],
@@ -152,6 +153,9 @@ def vsim(
         ``no_thread`` when enabled forces the command to execute the search
                 on the data structure in the main thread.
 
+        ``epsilon`` floating point between 0 and 1, if specified will return
+                only elements with distance no further than the specified one.
+
         For more information see https://redis.io/commands/vsim
         """
 
@@ -176,6 +180,9 @@ def vsim(
         if count:
             pieces.extend(["COUNT", count])
 
+        if epsilon:
+            pieces.extend(["EPSILON", epsilon])
+
         if ef:
             pieces.extend(["EF", ef])
 

tests/test_asyncio/test_vsets.py

@@ -423,6 +423,21 @@ async def test_vsim_truth_no_thread_enabled(d_client):
     assert isinstance(sim_no_thread, dict)
 
 
+@skip_if_server_version_lt("8.2.0")
+async def test_vsim_epsilon(d_client):
+    await d_client.vset().vadd("myset", [2, 1, 1], "a")
+    await d_client.vset().vadd("myset", [2, 0, 1], "b")
+    await d_client.vset().vadd("myset", [2, 0, 0], "c")
+    await d_client.vset().vadd("myset", [2, 0, -1], "d")
+    await d_client.vset().vadd("myset", [2, -1, -1], "e")
+
+    res1 = await d_client.vset().vsim("myset", [2, 1, 1])
+    assert 5 == len(res1)
+
+    res2 = await d_client.vset().vsim("myset", [2, 1, 1], epsilon=0.5)
+    assert 4 == len(res2)
+
+
 @skip_if_server_version_lt("7.9.0")
 async def test_vdim(d_client):
     float_array = [1, 4.32, 0.11, 0.5, 0.9, 0.1, 0.2]

tests/test_search.py

@@ -3802,3 +3802,52 @@ def test_svs_vamana_vector_search_with_parameters(client):
     else:
         assert res["total_results"] == 3
         assert "doc0" == res["results"][0]["id"]
+
+
+@pytest.mark.redismod
+@skip_ifmodversion_lt("2.4.3", "search")
+@skip_if_server_version_lt("8.1.224")
+def test_svs_vamana_vector_search_with_parameters_leanvec(client):
+    client.ft().create_index(
+        (
+            VectorField(
+                "v",
+                "SVS-VAMANA",
+                {
+                    "TYPE": "FLOAT32",
+                    "DIM": 8,
+                    "DISTANCE_METRIC": "L2",
+                    "COMPRESSION": "LeanVec8x8",  # LeanVec compression required for REDUCE
+                    "CONSTRUCTION_WINDOW_SIZE": 200,
+                    "GRAPH_MAX_DEGREE": 32,
+                    "SEARCH_WINDOW_SIZE": 15,
+                    "EPSILON": 0.01,
+                    "TRAINING_THRESHOLD": 1024,
+                    "REDUCE": 4,  # Half of DIM (8/2 = 4)
+                },
+            ),
+        )
+    )
+
+    # Create test vectors (8-dimensional to match DIM)
+    vectors = [
+        [1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0],
+        [2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0],
+        [3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0],
+        [4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0],
+        [5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0],
+    ]
+
+    for i, vec in enumerate(vectors):
+        client.hset(f"doc{i}", "v", np.array(vec, dtype=np.float32).tobytes())
+
+    query = Query("*=>[KNN 3 @v $vec as score]").no_content()
+    query_params = {"vec": np.array(vectors[0], dtype=np.float32).tobytes()}
+
+    res = client.ft().search(query, query_params=query_params)
+    if is_resp2_connection(client):
+        assert res.total == 3
+        assert "doc0" == res.docs[0].id
+    else:
+        assert res["total_results"] == 3
+        assert "doc0" == res["results"][0]["id"]

tests/test_vsets.py

@@ -425,6 +425,21 @@ def test_vsim_truth_no_thread_enabled(d_client):
     assert isinstance(sim_no_thread, dict)
 
 
+@skip_if_server_version_lt("8.2.0")
+def test_vsim_epsilon(d_client):
+    d_client.vset().vadd("myset", [2, 1, 1], "a")
+    d_client.vset().vadd("myset", [2, 0, 1], "b")
+    d_client.vset().vadd("myset", [2, 0, 0], "c")
+    d_client.vset().vadd("myset", [2, 0, -1], "d")
+    d_client.vset().vadd("myset", [2, -1, -1], "e")
+
+    res1 = d_client.vset().vsim("myset", [2, 1, 1])
+    assert 5 == len(res1)
+
+    res2 = d_client.vset().vsim("myset", [2, 1, 1], epsilon=0.5)
+    assert 4 == len(res2)
+
+
 @skip_if_server_version_lt("7.9.0")
 def test_vdim(d_client):
     float_array = [1, 4.32, 0.11, 0.5, 0.9, 0.1, 0.2]