Update app.py

app.py

@@ -1,4 +1,4 @@
-import streamlit as st
+import gradio as gr
 import fitz
 from transformers import pipeline, MBart50TokenizerFast, MBartForConditionalGeneration
 from multiprocessing import Pool, cpu_count
@@ -63,20 +63,16 @@ def translate_summary(summary, lang):
 
     return " ".join(translated_chunks)
 
-
-
 # Function to read PDF and summarize and translate chunk by chunk
-def summarize_and_translate_pdf(uploaded_file, lang):
-    # Save uploaded PDF to a temporary file
-    with tempfile.NamedTemporaryFile(delete=False) as temp_file:
-        temp_file.write(uploaded_file.read())
-        temp_file_path = temp_file.name
+def summarize_and_translate_pdf(pdf_content, lang):
+    # Save PDF content to a temporary file
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as temp_file:
+        temp_file.write(pdf_content)
 
     try:
-        doc = fitz.open(temp_file_path)
+        doc = fitz.open(temp_file.name)
     except FileNotFoundError:
-        st.error("File not found. Please make sure the file path is correct.")
-        return []
+        return "File not found. Please make sure the file path is correct."
 
     total_chunks = len(doc)
     chunks = []
@@ -91,42 +87,26 @@ def summarize_and_translate_pdf(uploaded_file, lang):
         translated_chunks = pool.starmap(summarize_and_translate_chunk, [(chunk, lang) for chunk in chunks])
 
     # Delete temporary file
-    os.unlink(temp_file_path)
+    temp_file.close()
 
     return translated_chunks
 
-
-# Streamlit UI
-st.title("PDF Summarization and Translation")
-
-# File upload
-uploaded_file = st.file_uploader("Upload a PDF file", type="pdf")
-if uploaded_file:
-    # Display uploaded file
-    st.write("Uploaded PDF file:", uploaded_file.name)
-
-    # Language selection
-    languages = {
-        "Arabic": "ar_AR", "Czech": "cs_CZ", "German": "de_DE", "English": "en_XX", "Spanish": "es_XX",
-        "Estonian": "et_EE", "Finnish": "fi_FI", "French": "fr_XX", "Gujarati": "gu_IN", "Hindi": "hi_IN",
-        "Italian": "it_IT", "Japanese": "ja_XX", "Kazakh": "kk_KZ", "Korean": "ko_KR", "Lithuanian": "lt_LT",
-        "Latvian": "lv_LV", "Burmese": "my_MM", "Nepali": "ne_NP", "Dutch": "nl_XX", "Romanian": "ro_RO",
-        "Russian": "ru_RU", "Sinhala": "si_LK", "Turkish": "tr_TR", "Vietnamese": "vi_VN", "Chinese": "zh_CN",
-        "Afrikaans": "af_ZA", "Azerbaijani": "az_AZ", "Bengali": "bn_IN", "Persian": "fa_IR", "Hebrew": "he_IL",
-        "Croatian": "hr_HR", "Indonesian": "id_ID", "Georgian": "ka_GE", "Khmer": "km_KH", "Macedonian": "mk_MK",
-        "Malayalam": "ml_IN", "Mongolian": "mn_MN", "Marathi": "mr_IN", "Polish": "pl_PL", "Pashto": "ps_AF",
-        "Portuguese": "pt_XX", "Swedish": "sv_SE", "Swahili": "sw_KE", "Tamil": "ta_IN", "Telugu": "te_IN",
-        "Thai": "th_TH", "Tagalog": "tl_XX", "Ukrainian": "uk_UA", "Urdu": "ur_PK", "Xhosa": "xh_ZA",
-        "Galician": "gl_ES", "Slovene": "sl_SI"
-    }
-
-    lang = st.selectbox("Select language for translation", list(languages.keys()))
-
-    # Translate PDF
-    if st.button("Summarize and Translate"):
-        translated_chunks = summarize_and_translate_pdf(uploaded_file, languages[lang])
-        
-        # Display translated text
-        st.header("Translated Summary")
-        for chunk in translated_chunks:
-            st.write(chunk)
+# Gradio Interface
+def summarize_and_translate_interface(pdf_content, lang):
+    translated_chunks = summarize_and_translate_pdf(pdf_content, lang)
+    return "\n".join(translated_chunks)
+
+# Gradio UI
+input_pdf = gr.inputs.File(label="Upload a PDF file", type="file")
+language = gr.inputs.Dropdown(choices=["Arabic", "Czech", "German", "English", "Spanish", "Estonian", "Finnish",
+                                       "French", "Gujarati", "Hindi", "Italian", "Japanese", "Kazakh", "Korean",
+                                       "Lithuanian", "Latvian", "Burmese", "Nepali", "Dutch", "Romanian", "Russian",
+                                       "Sinhala", "Turkish", "Vietnamese", "Chinese", "Afrikaans", "Azerbaijani",
+                                       "Bengali", "Persian", "Hebrew", "Croatian", "Indonesian", "Georgian", "Khmer",
+                                       "Macedonian", "Malayalam", "Mongolian", "Marathi", "Polish", "Pashto",
+                                       "Portuguese", "Swedish", "Swahili", "Tamil", "Telugu", "Thai", "Tagalog",
+                                       "Ukrainian", "Urdu", "Xhosa", "Galician", "Slovene"],
+                             label="Select language for translation")
+output_text = gr.outputs.Textbox(label="Translated Summary")
+
+gr.Interface(summarize_and_translate_interface, inputs=[input_pdf, language], outputs=output_text).launch()