From 3136b2e12064d9733e8be2f2df97f0f4bc9ccfe4 Mon Sep 17 00:00:00 2001
From: dhug <38571110+danielpatrickhug@users.noreply.github.com>
Date: Wed, 11 Jan 2023 14:53:53 -0500
Subject: [PATCH] added similarity functions and ran precommit (#633)

---
 .../oasst_backend/utils/similarity_functions.py | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)
 create mode 100644 backend/oasst_backend/utils/similarity_functions.py

diff --git a/backend/oasst_backend/utils/similarity_functions.py b/backend/oasst_backend/utils/similarity_functions.py
new file mode 100644
index 00000000..c166661f
--- /dev/null
+++ b/backend/oasst_backend/utils/similarity_functions.py
@@ -0,0 +1,17 @@
+from typing import List
+
+import numpy as np
+
+
+def cosine_similarity(a: List[float], b: List[float]):
+    """Compute cosine similarity (dot product of two vectors divided by the product of their norms.)"""
+    norm_a = np.linalg.norm(a)
+    norm_b = np.linalg.norm(b)
+    if norm_a == 0 or norm_b == 0:
+        raise ZeroDivisionError("One of the vectors has a norm of zero.")
+    return np.dot(a, b) / (norm_a * norm_b)
+
+
+def euclidean_distance(a: List[float], b: List[float]):
+    """Compute euclidean distance (norm of the difference of two vectors.)"""
+    return np.linalg.norm(np.subtract(a, b))