Update app.py

app.py

@@ -7,6 +7,12 @@ from azure.storage.blob import BlobClient
 #import utils functions
 from preprocessing_images import preprocessing_function
 from extract_text import azure_ocr
+
+from sentence_transformers import SentenceTransformer
+from numpy.linalg import norm
+import numpy as np
+
+
 my_container = os.getenv("AZURE_CONTAINER")
 subscription_key = os.getenv("SUB_KEY")
 endpoint = os.getenv("AZURE_ENDPOINT")
@@ -58,7 +64,14 @@ def classify_class(incident_description):
     classification = response.choices[0].text.strip()
     return classification
 
-    
+def text_similarity(pdftext1,pdftext1):
+    sentences =["pdftext1","pdftext2"]
+    model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
+    embeddings = model.encode(sentences)
+    cosine = np.dot(embeddings[0],embeddings[1])/(norm(embeddings[0])*norm(embeddings[1]))
+    return cosine
+
+
 def avatiation(pdf_url1,pdf_url2):
     pdftext1 = ocr_pdf(pdf_url1)
     pdftext2 = ocr_pdf(pdf_url2)
@@ -68,7 +81,8 @@ def avatiation(pdf_url1,pdf_url2):
 
     defect_class2 = classify_class(pdftext2)
     main_issue2 =  classify_cause(pdftext2)
-    return main_issue1, defect_class1,main_issue2, defect_class2,
+    cosine = text_similarity(pdftext1,pdftext2)
+    return main_issue1, defect_class1,main_issue2, defect_class2,cosine
 
 
 
@@ -80,7 +94,9 @@ outputs = [gr.outputs.Textbox(label="Main Issue of the log report"),
            gr.outputs.Textbox(label="category of the log report"),
 
            gr.outputs.Textbox(label="Main Issue of the log report2"),
-           gr.outputs.Textbox(label="category of the log report2")
+           gr.outputs.Textbox(label="category of the log report2"),
+           gr.outputs.Textbox(label="log similarity)
+           
            ]