Create app.py

app.py

@@ -0,0 +1,43 @@
+import gradio as gr
+from transformers import pipeline
+import numpy as np
+import pandas as pd
+from sklearn.metrics.pairwise import cosine_similarity
+from InstructorEmbedding import INSTRUCTOR
+
+pipe = pipeline(model="facebook/bart-large-mnli")
+model = INSTRUCTOR('hkunlp/instructor-large')
+
+df = pd.read_csv('intent.csv', delimiter=';')
+
+data = [
+        [
+            f'Represent the document for retrieval of {x[desc]} information : ',
+            x[message]
+        ] for _,x in df.iterrows()
+    ]
+
+corpus_embeddings = embed_data(data)
+
+
+def predict(question, threshold, tags):
+  query  = [['Represent the question for retrieving supporting documents: ',question]]
+  query = model.encode(query)
+  similarities = cosine_similarity(query_embeddings,corpus_embeddings)
+  retrieved_doc_id = np.argmax(similarities)
+
+  if similarities[retrieved_doc_id]  < threshold:
+    ans = pipe(query, candidate_labels=[x.strip() for x in tags.split(",")])
+    ans['query_similarity_score'] = similarities[retrieved_doc_id]
+    return ans
+  return {"sequence" : data[retrieved_doc_id][-1], 'query_similarity_score : similarities[retrieved_doc_id]}
+
+
+
+
+
+gr.Interface(fn=predict,
+             inputs=["text", "number", "text"],
+             outputs="json").launch()
+
+