add initial implementation

.gitignore

@@ -0,0 +1,3 @@
+venv/
+flagged/
+**/__pycache__/**

app.py

@@ -0,0 +1,26 @@
+from sentence_transformers import SentenceTransformer
+import pickle
+import numpy as np
+import torch
+import gradio as gr
+
+model = SentenceTransformer('paraphrase-MiniLM-L6-v2')
+
+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)
+
+cos = torch.nn.CosineSimilarity(dim=1, eps=1e-6)
+def give_best_match(query):
+    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="text",outputs=gr.Label(num_top_classes=5))
+demo.launch()

dep_course_title_to_content_embed.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c7d2991aa7d9ddc6cfeb6ebb7e0d37edec497f94a533ad74d8297a9c387cc89
+size 1220492

requirements.txt

@@ -0,0 +1,4 @@
+gradio==3.4.1
+numpy==1.23.3
+sentence-transformers==2.2.2
+torch==1.12.1