From d01bad5169ae39aebee572e675a3792eb614a8f7 Mon Sep 17 00:00:00 2001
From: Ash Vardanian <1983160+ashvardanian@users.noreply.github.com>
Date: Mon, 25 Mar 2024 16:36:26 -0700
Subject: [PATCH] core[patch]: Convert SimSIMD back to NumPy (#19473)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch fixes the #18022 issue, converting the SimSIMD internal
zero-copy outputs to NumPy.

I've also noticed, that oftentimes `dtype=np.float32` conversion is used
before passing to SimSIMD. Which numeric types do LangChain users
generally care about? We support `float64`, `float32`, `float16`, and
`int8` for cosine distances and `float16` seems reasonable for
practically any kind of embeddings and any modern piece of hardware, so
we can change that part as well 🤗
---
 libs/community/langchain_community/utils/math.py                | 2 +-
 .../elasticsearch/langchain_elasticsearch/_utilities.py         | 2 +-
 libs/partners/mongodb/langchain_mongodb/utils.py                | 2 +-
 libs/partners/pinecone/langchain_pinecone/_utilities.py         | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/libs/community/langchain_community/utils/math.py b/libs/community/langchain_community/utils/math.py
index 99d47368197..2522c1255c6 100644
--- a/libs/community/langchain_community/utils/math.py
+++ b/libs/community/langchain_community/utils/math.py
@@ -29,7 +29,7 @@ def cosine_similarity(X: Matrix, Y: Matrix) -> np.ndarray:
         Z = 1 - simd.cdist(X, Y, metric="cosine")
         if isinstance(Z, float):
             return np.array([Z])
-        return Z
+        return np.array(Z)
     except ImportError:
         logger.info(
             "Unable to import simsimd, defaulting to NumPy implementation. If you want "
diff --git a/libs/partners/elasticsearch/langchain_elasticsearch/_utilities.py b/libs/partners/elasticsearch/langchain_elasticsearch/_utilities.py
index 0280708736f..33b302241ea 100644
--- a/libs/partners/elasticsearch/langchain_elasticsearch/_utilities.py
+++ b/libs/partners/elasticsearch/langchain_elasticsearch/_utilities.py
@@ -79,7 +79,7 @@ def cosine_similarity(X: Matrix, Y: Matrix) -> np.ndarray:
         Z = 1 - simd.cdist(X, Y, metric="cosine")
         if isinstance(Z, float):
             return np.array([Z])
-        return Z
+        return np.array(Z)
     except ImportError:
         X_norm = np.linalg.norm(X, axis=1)
         Y_norm = np.linalg.norm(Y, axis=1)
diff --git a/libs/partners/mongodb/langchain_mongodb/utils.py b/libs/partners/mongodb/langchain_mongodb/utils.py
index feb34ad1c23..854b2bc939a 100644
--- a/libs/partners/mongodb/langchain_mongodb/utils.py
+++ b/libs/partners/mongodb/langchain_mongodb/utils.py
@@ -38,7 +38,7 @@ def cosine_similarity(X: Matrix, Y: Matrix) -> np.ndarray:
         Z = 1 - simd.cdist(X, Y, metric="cosine")
         if isinstance(Z, float):
             return np.array([Z])
-        return Z
+        return np.array(Z)
     except ImportError:
         logger.info(
             "Unable to import simsimd, defaulting to NumPy implementation. If you want "
diff --git a/libs/partners/pinecone/langchain_pinecone/_utilities.py b/libs/partners/pinecone/langchain_pinecone/_utilities.py
index 37d61e9fb11..5ad9e407fcd 100644
--- a/libs/partners/pinecone/langchain_pinecone/_utilities.py
+++ b/libs/partners/pinecone/langchain_pinecone/_utilities.py
@@ -69,7 +69,7 @@ def cosine_similarity(X: Matrix, Y: Matrix) -> np.ndarray:
         Z = 1 - simd.cdist(X, Y, metric="cosine")
         if isinstance(Z, float):
             return np.array([Z])
-        return Z
+        return np.array(Z)
     except ImportError:
         X_norm = np.linalg.norm(X, axis=1)
         Y_norm = np.linalg.norm(Y, axis=1)