From 2ef9c38b8b82be5289bd4cef3ec73a1553e07e2d Mon Sep 17 00:00:00 2001
From: Hossam Hagag <90828745+hh-space-invader@users.noreply.github.com>
Date: Wed, 4 Dec 2024 09:25:35 +0200
Subject: [PATCH] Tsk 409 support gte models (#415)

* new: Added support for gte base model

* tests: Added test cannonical vectors for gte model
---
 fastembed/text/pooled_normalized_embedding.py | 9 +++++++++
 tests/test_text_onnx_embeddings.py            | 1 +
 2 files changed, 10 insertions(+)

diff --git a/fastembed/text/pooled_normalized_embedding.py b/fastembed/text/pooled_normalized_embedding.py
index 70660420..47ec91a1 100644
--- a/fastembed/text/pooled_normalized_embedding.py
+++ b/fastembed/text/pooled_normalized_embedding.py
@@ -75,6 +75,15 @@
         "sources": {"hf": "jinaai/jina-embeddings-v2-base-es"},
         "model_file": "onnx/model.onnx",
     },
+    {
+        "model": "thenlper/gte-base",
+        "dim": 768,
+        "description": "General text embeddings, Unimodal (text), supports English only input text, 512 input tokens truncation, Prefixes for queries/documents: not necessary, 2024 year.",
+        "license": "mit",
+        "size_in_GB": 0.44,
+        "sources": {"hf": "thenlper/gte-base"},
+        "model_file": "onnx/model.onnx",
+    },
 ]
 
 
diff --git a/tests/test_text_onnx_embeddings.py b/tests/test_text_onnx_embeddings.py
index f576330c..a40794be 100644
--- a/tests/test_text_onnx_embeddings.py
+++ b/tests/test_text_onnx_embeddings.py
@@ -64,6 +64,7 @@
     ),
     "snowflake/snowflake-arctic-embed-l": np.array([0.0189, -0.0673, 0.0183, 0.0124, 0.0146]),
     "Qdrant/clip-ViT-B-32-text": np.array([0.0083, 0.0103, -0.0138, 0.0199, -0.0069]),
+    "thenlper/gte-base": np.array([0.0038, 0.0355, 0.0181, 0.0092, 0.0654]),
 }