We have included the real LLM model that will extract the

main_service.py

@@ -2,7 +2,7 @@ import gradio as gr
 from utils_model import ModelFactory
 
 def retrieve_embeddings(input_text_query):
-    model_type = 'mock'
+    model_type = 'all-MiniLM-L6-v2'
     model_factory_obj = ModelFactory()
     model = model_factory_obj.create_model(model_type)
 

requirements.txt

@@ -1,3 +1,4 @@
+git+https://github.com/UKPLab/sentence-transformers.git@e2a0098b0fbe10bf9a140a9b1d4c2a3451f1571f
 gradio==5.37.0
 numpy==2.3.1
-pandas==2.3.1
+pandas==2.3.1

utils_model.py

@@ -1,6 +1,6 @@
 import numpy as np
 import pandas as pd
-# from sentence_transformers import SentenceTransformer
+from sentence_transformers import SentenceTransformer
 
 class ModelFactory():
 
@@ -13,8 +13,8 @@ class ModelFactory():
         if (model_type=='mock'):
             model = MockModel()
 
-        # if (model_type=='all-MiniLM-L6-v2'):
-        #     model = MiniLM_L6_v2_Model()
+        if (model_type=='all-MiniLM-L6-v2'):
+            model = MiniLM_L6_v2_Model()
 
         return model
 
@@ -36,14 +36,14 @@ class MockModel(BaseModel):
 
         return pd.DataFrame(random_embeddings)
 
-# class MiniLM_L6_v2_Model(BaseModel):
+class MiniLM_L6_v2_Model(BaseModel):
     
-#     def __init__(self):
-#         self.model = SentenceTransformer('all-MiniLM-L6-v2')
+    def __init__(self):
+        self.model = SentenceTransformer('all-MiniLM-L6-v2')
 
-#     def retrieve_embeddings(self, input_text):
-#         embeddings = self.model.encode(input_text, batch_size=32)
-#         embeddings *= 255
-#         embeddings = embeddings.astype(np.uint8).tolist()
+    def retrieve_embeddings(self, input_text):
+        embeddings = self.model.encode(input_text, batch_size=32)
+        embeddings *= 255
+        embeddings = embeddings.astype(np.uint8).tolist()
 
-#         return embeddings
+        return embeddings