Update app.py

app.py

@@ -33,6 +33,7 @@ import line_cor
 import altair as alt
 #pytesseract.pytesseract.tesseract_cmd = r"./Tesseract-OCR/tesseract.exe"
 from PIL import Image
+st.title("Bangla and English Summarizer: Upload Images/Pdf or input texts to summarize!")
 API_URL0 = "https://api-inference.huggingface.co/models/csebuetnlp/mT5_multilingual_XLSum"
 headers0 = {"Authorization": "Bearer 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"}
 API_URL1 = "https://api-inference.huggingface.co/models/Michael-Vptn/text-summarization-t5-base"
@@ -82,7 +83,6 @@ def bansum(text):
        text_output = out[0]["summary_text"]
        st.success(text_output) 
 
-st.title("Bangla and English Summarizer: Upload Images/Pdf or input texts to summarize!")
 @st.cache
 def load(x):
     return x
@@ -94,79 +94,78 @@ def change_photo_state():
     st.session_state["photo"]="done"
 message = st.text_input("Type your text here!")
 c2, c3 = st.columns([2,1])
-uploaded_photo = load(c2.file_uploader("Upload your Images/PDF",type=['jpg','png','jpeg','pdf'], on_change=change_photo_state))
-camera_photo = load(c3.camera_input("Capture a photo to summarize: ", on_change=change_photo_state))
-if st.checkbox("Summarization"):
-    if st.session_state["photo"]=="done" or message:
-        if uploaded_photo and uploaded_photo.type=='application/pdf':
-            tet = read_pdf(uploaded_photo)
-            # with tempfile.NamedTemporaryFile(delete=False) as temp_file:
-            #     temp_file.write(uploaded_photo.read())
-            #     temp_file_path = temp_file.name
-                
-            # loader = PyPDFLoader(temp_file_path)
-            # if loader:
-            #     text.extend(loader.load())
-            #     os.remove(temp_file_path)
-            # text_splitter = CharacterTextSplitter(separator="\n", chunk_size=1000, chunk_overlap=100, length_function=len)
-            # text_chunks = text_splitter.split_documents(text)
-            values = st.slider('Select a approximate number of lines to see and summarize',value=[0, len(tet)//(7*100)])
-            text = tet[values[0]*7*10:values[1]*10*100] if values[0]!=len(tet)//(10*100) else tet[len(tet)//(10*100):]
-            #st.success(type(text_chunks))
-            if st.button("English Pdf Summarize"):
-                st.subheader("Selected text for summarize: ")
-                st.success(text)
-                st.subheader("Summarized Text: ")
-                engsum(text)
-        
-        elif uploaded_photo and uploaded_photo.type !='application/pdf':
-            text=None
-            img = Image.open(uploaded_photo)
-            img = img.save("img.png")
-            img = cv2.imread("img.png")
-            st.text("Select the summarization type:")
-            if st.button("BENGALI"):
-                text =  pytesseract.image_to_string(img, lang="ben")
-                st.subheader("সারাংশ/সারমর্ম")
-                bansum(text)
-            if st.button("ENGLISH"): 
-                text=pytesseract.image_to_string(img)
-                st.subheader("Summarized Text")
-                engsum(text)
-            #st.success(text)
-        elif camera_photo:
-            text=None
-            img = Image.open(camera_photo)
-            img = img.save("img.png")
-            img = cv2.imread("img.png")
-            #text = pytesseract.image_to_string(img) if st.checkbox("Bangla") else pytesseract.image_to_string(img, lang="ben")
-            st.text("Select the summarization type:")
-            if st.button("Bangla"):
-                text =  pytesseract.image_to_string(img, lang="ben")
-                st.subheader("সারাংশ/সারমর্ম")
-                bansum(text)
-            if st.button("English"): 
-                text=pytesseract.image_to_string(img)
-                st.subheader("Summarized Text")
-                engsum(text)
-        else:
-            text=None
-            text = message
-            if st.button("Bangla"):
-                bansum(text)
-            if st.button("English"): 
-                engsum(text)  
-        # if st.button("English Text Generation"): 
-        #     def query(payload):
-        #     	response = requests.post(API_URL2, headers=headers2, json=payload)
-        #     	return response.json()
-                
-        #     out = query({
-        #     	"inputs": text,
-        #     })
-        #     if isinstance(out, list) and out[0].get("generated_text"):
-        #         text_output = out[0]["generated_text"]
-        #         st.success(text_output)
-        #         #text=text_output
+uploaded_photo = load(c3.file_uploader("Upload your Images/PDF",type=['jpg','png','jpeg','pdf'], on_change=change_photo_state))
+camera_photo = load(c2.camera_input("Capture a photo to summarize: ", on_change=change_photo_state))
+if st.session_state["photo"]=="done" or message:
+    if uploaded_photo and uploaded_photo.type=='application/pdf':
+        tet = read_pdf(uploaded_photo)
+        # with tempfile.NamedTemporaryFile(delete=False) as temp_file:
+        #     temp_file.write(uploaded_photo.read())
+        #     temp_file_path = temp_file.name
+            
+        # loader = PyPDFLoader(temp_file_path)
+        # if loader:
+        #     text.extend(loader.load())
+        #     os.remove(temp_file_path)
+        # text_splitter = CharacterTextSplitter(separator="\n", chunk_size=1000, chunk_overlap=100, length_function=len)
+        # text_chunks = text_splitter.split_documents(text)
+        values = st.slider('Select a approximate number of lines to see and summarize',value=[0, len(tet)//(7*100)])
+        text = tet[values[0]*7*10:values[1]*10*100] if values[0]!=len(tet)//(10*100) else tet[len(tet)//(10*100):]
+        #st.success(type(text_chunks))
+        if st.button("English Pdf Summarize"):
+            st.subheader("Selected text for summarize: ")
+            st.success(text)
+            st.subheader("Summarized Text: ")
+            engsum(text)
+    
+    elif uploaded_photo and uploaded_photo.type !='application/pdf':
+        text=None
+        img = Image.open(uploaded_photo)
+        img = img.save("img.png")
+        img = cv2.imread("img.png")
+        st.text("Select the summarization type:")
+        if st.button("BENGALI"):
+            text =  pytesseract.image_to_string(img, lang="ben")
+            st.subheader("সারাংশ/সারমর্ম")
+            bansum(text)
+        if st.button("ENGLISH"): 
+            text=pytesseract.image_to_string(img)
+            st.subheader("Summarized Text")
+            engsum(text)
+        #st.success(text)
+    elif camera_photo:
+        text=None
+        img = Image.open(camera_photo)
+        img = img.save("img.png")
+        img = cv2.imread("img.png")
+        #text = pytesseract.image_to_string(img) if st.checkbox("Bangla") else pytesseract.image_to_string(img, lang="ben")
+        st.text("Select the summarization type:")
+        if st.button("Bangla"):
+            text =  pytesseract.image_to_string(img, lang="ben")
+            st.subheader("সারাংশ/সারমর্ম")
+            bansum(text)
+        if st.button("English"): 
+            text=pytesseract.image_to_string(img)
+            st.subheader("Summarized Text")
+            engsum(text)
+    else:
+        text=None
+        text = message
+        if st.button("Bangla"):
+            bansum(text)
+        if st.button("English"): 
+            engsum(text)  
+    # if st.button("English Text Generation"): 
+    #     def query(payload):
+    #     	response = requests.post(API_URL2, headers=headers2, json=payload)
+    #     	return response.json()
+            
+    #     out = query({
+    #     	"inputs": text,
+    #     })
+    #     if isinstance(out, list) and out[0].get("generated_text"):
+    #         text_output = out[0]["generated_text"]
+    #         st.success(text_output)
+    #         #text=text_output