Update app.py

app.py

@@ -7,13 +7,6 @@ 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
-!pip install -U sentence-transformers
-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")
@@ -21,23 +14,23 @@ connection_string = os.getenv("AZURE_CON_STRING")
 openai.api_key = os.getenv("OPENAI_API_KEY")
 computervision_client = ComputerVisionClient(endpoint, CognitiveServicesCredentials(subscription_key))
 
-def ocr_pdf(pdf_url1):
-    preprocessing_function(pdf_url1)
-    my_blob = pdf_url1.split('/')[-1]
+def ocr_pdf(pdf_url):
+    preprocessing_function(pdf_url)
+    my_blob = pdf_url.split('/')[-1]
     blob = BlobClient.from_connection_string(conn_str=connection_string, container_name= my_container, blob_name=my_blob)
     with open("answer_paper.pdf", "rb") as data:
         blob.upload_blob(data,overwrite=True) 
     text = azure_ocr(blob.url,computervision_client)
     return text.strip()
 
-def ocr_pdf(pdf_url2):
-    preprocessing_function(pdf_url2)
-    my_blob = pdf_url2.split('/')[-1]
-    blob = BlobClient.from_connection_string(conn_str=connection_string, container_name= my_container, blob_name=my_blob)
-    with open("answer_paper.pdf", "rb") as data:
-        blob.upload_blob(data,overwrite=True) 
-    text = azure_ocr(blob.url,computervision_client)
-    return text.strip()
+# def ocr_pdf(pdf_url2):
+#     preprocessing_function(pdf_url2)
+#     my_blob = pdf_url2.split('/')[-1]
+#     blob = BlobClient.from_connection_string(conn_str=connection_string, container_name= my_container, blob_name=my_blob)
+#     with open("answer_paper.pdf", "rb") as data:
+#         blob.upload_blob(data,overwrite=True) 
+#     text = azure_ocr(blob.url,computervision_client)
+#     return text.strip()
 
 def classify_cause(incident_description):
     response = openai.Completion.create(
@@ -65,42 +58,26 @@ def classify_class(incident_description):
     classification = response.choices[0].text.strip()
     return classification
 
-def text_similarity(pdftext1,pdftext12):
-    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)
-
-    defect_class1 = classify_class(pdftext1)
-    main_issue1 =  classify_cause(pdftext1)
+    
+def avatiation(pdf_url):
+    pdftext = ocr_pdf(pdf_url)
 
-    defect_class2 = classify_class(pdftext2)
-    main_issue2 =  classify_cause(pdftext2)
-    cosine = text_similarity(pdftext1,pdftext2)
-    return main_issue1, defect_class1,main_issue2, defect_class2,cosine
+    
+    defect_class = classify_class(pdftext)
+    main_issue =  classify_cause(pdftext)
+    return main_issue, defect_class
 
 
 
 inputs1 = gr.inputs.Textbox(label="Link for aviation log reports")
-inputs2 = gr.inputs.Textbox(label="Link for aviation log reports 2")
+#inputs2 = gr.inputs.Textbox(label="Link for aviation log reports 2")
 
 
 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="log similarity")
-           
+           gr.outputs.Textbox(label="category of the log report")
            ]
            
 
-demo = gr.Interface(fn=avatiation,inputs= [inputs1,inputs2],outputs=outputs, title="ATA Auto classification using OCR and GPT3 ")
+demo = gr.Interface(fn=avatiation,inputs=inputs1,outputs=outputs, title="ATA Auto classification using OCR and GPT3 ")
 demo.launch()