support department selection

app.py

@@ -10,17 +10,41 @@ with open("dep_course_title_to_content_embed.pickle", "rb") as handle:
     loaded_map = pickle.load(handle)
 
 dep_name_course_name = list(loaded_map.keys())
-dep_name = [x for (x,y) in dep_name_course_name]
-course_titles = [y for (x,y) in dep_name_course_name]
-course_content_embeddings = np.array(list(loaded_map.values()), dtype=np.float32)
+deps = list(set([x for (x,y) in dep_name_course_name]))
+dep_to_course_name = {}
+dep_to_course_embedding = {}
+
+for dep in deps:
+    dep_to_course_name[dep] = []
+    dep_to_course_embedding[dep] = []
+
+for (dep_name, course_name), embedding in loaded_map.items():
+    # print(embedding.shape)
+    dep_to_course_name[dep_name].append(course_name)
+    dep_to_course_embedding[dep_name].append(np.array(embedding, dtype = np.float32))
 
 cos = torch.nn.CosineSimilarity(dim=1, eps=1e-6)
-def give_best_match(query):
+
+def give_best_match(query, Department):
+    if not Department:
+        Department = deps
+    course_titles = []
+    course_content_embeddings = []
+    for dep in Department:
+        course_titles +=  dep_to_course_name[dep]
+        course_content_embeddings += dep_to_course_embedding[dep]
+    course_content_embeddings =  np.stack(course_content_embeddings)
     embed = model.encode(query)
     result = cos(torch.from_numpy(course_content_embeddings),torch.from_numpy(embed))
     indices = reversed(np.argsort(result))
     predictions = {course_titles[i] : float(result[i]) for i in indices}
     return predictions
 
-demo = gr.Interface(fn = give_best_match, inputs=gr.Textbox(label="Describe the course",lines = 5, placeholder = "Type anything related to course/s\n\nTitle, Topics/Sub Topics, Refernce books, Questions asked in exams or some random fun stuff.") ,outputs=gr.Label(label = "Most Relevant Courses", num_top_classes=5))
+demo = gr.Interface(fn = give_best_match,
+                    inputs=[ 
+                        gr.Textbox(label="Describe the course",lines = 5, placeholder = "Type anything related to course/s\n\nTitle, Topics/Sub Topics, Refernce books, Questions asked in exams or some random fun stuff."),
+                         gr.CheckboxGroup(deps),
+                        ],
+                    outputs=gr.Label(label = "Most Relevant Courses", num_top_classes=5)
+                    )
 demo.launch()