Update app.py

app.py

@@ -23,9 +23,49 @@ logger = logging.getLogger(__name__)
 # تنظیم API Key
 gemini_api_key = os.environ.get('GEMINI_API_KEY')
 if not gemini_api_key:
-    raise ValueError("GOOGLE_API_KEY پیدا نشد. لطفاً آن را در تنظیمات Space تنظیم کنید.")
+    raise ValueError("GOOGLE_API_KEY not found. Please set it in the Space settings.")
 genai.configure(api_key=gemini_api_key)
 
+# متون برای زبان‌های مختلف
+TEXTS = {
+    "English": {
+        "title": "Professional Thesis Analyzer with Gemini",
+        "description": "Upload your <span class='english'>PDF</span> file and use the analysis, summary, plagiarism check, or quality evaluation features.",
+        "upload_label": "Upload <span class='english'>PDF</span> File",
+        "mode_label": "Processing Mode",
+        "modes": ["Academic Analysis (RAG)", "Auto Summary", "Plagiarism Check", "Quality Evaluation", "Standard Response"],
+        "query_label": "Question or Request",
+        "query_placeholder": "Enter your question or request here...",
+        "section_label": "Target Section",
+        "sections": ["Entire Document", "Introduction", "Methodology", "Results", "Discussion", "References"],
+        "language_label": "Response Language",
+        "languages": ["English", "Farsi"],
+        "detail_label": "Detail Level",
+        "details": ["Brief", "Detailed"],
+        "submit": "Submit",
+        "output_label": "Processing Result",
+        "output_placeholder": "Results will be displayed here..."
+    },
+    "Farsi": {
+        "title": "تحلیلگر حرفه‌ای پایان‌نامه با Gemini",
+        "description": "فایل <span class='english'>PDF</span> خود را آپلود کنید و از قابلیت‌های تحلیل، خلاصه، چک سرقت ادبی یا ارزیابی کیفیت استفاده کنید.",
+        "upload_label": "آپلود فایل <span class='english'>PDF</span>",
+        "mode_label": "حالت پردازش",
+        "modes": ["تحلیل آکادمیک (RAG)", "خلاصه خودکار", "چک سرقت ادبی", "ارزیابی کیفیت", "پاسخ استاندارد"],
+        "query_label": "سوال یا درخواست",
+        "query_placeholder": "سوال یا درخواست خود را اینجا بنویسید...",
+        "section_label": "بخش موردنظر",
+        "sections": ["کل سند", "مقدمه", "روش‌شناسی", "نتایج", "بحث", "منابع"],
+        "language_label": "زبان پاسخ",
+        "languages": ["انگلیسی", "فارسی"],
+        "detail_label": "سطح جزئیات",
+        "details": ["خلاصه", "جامع"],
+        "submit": "ارسال",
+        "output_label": "نتیجه پردازش",
+        "output_placeholder": "نتایج اینجا نمایش داده می‌شود..."
+    }
+}
+
 def process_single_pdf(pdf_file):
     pdf_path = pdf_file.name if hasattr(pdf_file, 'name') else pdf_file
     logger.info(f"Starting to process file: {pdf_path}")
@@ -299,6 +339,77 @@ def evaluate_quality(docs, sections):
 
 llm_gemini = ChatGoogleGenerativeAI(model="gemini-pro", google_api_key=gemini_api_key, convert_system_message_to_human=True, temperature=0.5)
 
+def update_interface(language):
+    texts = TEXTS[language]
+    return (
+        gr.Markdown.update(value=f"#{texts['title']}"),
+        gr.Markdown.update(value=texts['description']),
+        gr.File.update(label=texts['upload_label']),
+        gr.Radio.update(label=texts['mode_label'], choices=texts['modes']),
+        gr.Textbox.update(label=texts['query_label'], placeholder=texts['query_placeholder']),
+        gr.Dropdown.update(label=texts['section_label'], choices=texts['sections']),
+        gr.Dropdown.update(label=texts['language_label'], choices=texts['languages']),
+        gr.Dropdown.update(label=texts['detail_label'], choices=texts['details']),
+        gr.Button.update(value=texts['submit']),
+        gr.Textbox.update(label=texts['output_label'], placeholder=texts['output_placeholder'])
+    )
+
+def academic_chatbot(pdf_file, mode, query, language, detail_level, section_dropdown):
+    start_time = time.time()
+    logger.info(f"Starting processing - Mode: {mode}, Question: {query}, Language: {language}, Detail: {detail_level}, Section: {section_dropdown}")
+    
+    if mode != "Standard Response" and not pdf_file:
+        return "Please upload at least one PDF file."
+    
+    if mode == "Standard Response":
+        chain = create_conversation_chain(None, None, mode, language, detail_level)
+        try:
+            result = chain.invoke({"question": query})["text"]
+            return f"{result}\n\n⏱ Processing time: {time.time() - start_time:.2f} seconds"
+        except Exception as e:
+            logger.error(f"Error in standard processing: {str(e)}")
+            return f"Error: {str(e)}"
+    
+    pdf_files = pdf_file if isinstance(pdf_file, list) else [pdf_file]
+    _, docs, sections, error = upload_and_process_pdf(pdf_files)
+    if error:
+        return error
+    
+    target_docs = docs if section_dropdown == "Entire Document" else sections.get(section_dropdown, docs)
+    context = " ".join([doc.page_content for doc in target_docs])
+    
+    vector_store = None
+    if mode in ["Academic Analysis (RAG)", "Plagiarism Check", "Quality Evaluation"]:
+        vector_store, vectordb_error = create_vector_db(target_docs)
+        if vectordb_error:
+            return vectordb_error
+    
+    chain = create_conversation_chain(vector_store, target_docs, mode, language, detail_level, section_dropdown)
+    try:
+        if mode == "Auto Summary":
+            time.sleep(2)
+            result = chain.invoke({"context": context[:5000]})["text"]
+        elif mode == "Plagiarism Check":
+            plagiarism_result = check_plagiarism(context)
+            result = plagiarism_result
+        elif mode == "Quality Evaluation":
+            score, explanation, suggestions, auto_fix = evaluate_quality(target_docs, sections)
+            time.sleep(2)
+            result = chain.invoke({"context": context[:5000], "score": score, "explanation": explanation, "suggestions": suggestions})["text"] + auto_fix
+        else:
+            result = chain.invoke({"question": query, "chat_history": []})["answer"]
+        
+        if mode not in ["Plagiarism Check", "Quality Evaluation"]:
+            resources = suggest_resources(context)
+            result += "\n\n**Suggested Resources:**\n" + "\n".join(resources)
+        
+        return f"{result}\n\n⏱ Processing time: {time.time() - start_time:.2f} seconds"
+    except Exception as e:
+        logger.error(f"Error in processing: {str(e)}")
+        if "429" in str(e):
+            return "Error: Rate limit exceeded for Gemini API. Please wait a few minutes and try again."
+        return f"Error: {str(e)}"
+
 academic_analysis_prompt = PromptTemplate(
     template="""You are a professional academic analyst. Provide a deep and structured analysis of {section}:
 1. Based solely on the provided text.
@@ -368,81 +479,14 @@ def create_conversation_chain(vector_store, docs, mode, language, detail_level,
         chain = LLMChain(llm=llm_gemini, prompt=general_qa_prompt.partial(language=language))
     return chain
 
-def academic_chatbot(pdf_file, mode, query, language, detail_level, section_dropdown):
-    start_time = time.time()
-    logger.info(f"Starting processing - Mode: {mode}, Question: {query}, Language: {language}, Detail: {detail_level}, Section: {section_dropdown}")
-    
-    if mode != "Standard Response" and not pdf_file:
-        return "Please upload at least one PDF file."
-    
-    if mode == "Standard Response":
-        chain = create_conversation_chain(None, None, mode, language, detail_level)
-        try:
-            result = chain.invoke({"question": query})["text"]
-            return f"{result}\n\n⏱ Processing time: {time.time() - start_time:.2f} seconds"
-        except Exception as e:
-            logger.error(f"Error in standard processing: {str(e)}")
-            return f"Error: {str(e)}"
-    
-    pdf_files = pdf_file if isinstance(pdf_file, list) else [pdf_file]
-    _, docs, sections, error = upload_and_process_pdf(pdf_files)
-    if error:
-        return error
-    
-    target_docs = docs if section_dropdown == "Entire Document" else sections.get(section_dropdown, docs)
-    context = " ".join([doc.page_content for doc in target_docs])
-    
-    vector_store = None
-    if mode in ["Academic Analysis (RAG)", "Plagiarism Check", "Quality Evaluation"]:
-        vector_store, vectordb_error = create_vector_db(target_docs)
-        if vectordb_error:
-            return vectordb_error
-    
-    chain = create_conversation_chain(vector_store, target_docs, mode, language, detail_level, section_dropdown)
-    try:
-        if mode == "Auto Summary":
-            time.sleep(2)
-            result = chain.invoke({"context": context[:5000]})["text"]
-        elif mode == "Plagiarism Check":
-            plagiarism_result = check_plagiarism(context)
-            result = plagiarism_result
-        elif mode == "Quality Evaluation":
-            score, explanation, suggestions, auto_fix = evaluate_quality(target_docs, sections)
-            time.sleep(2)
-            result = chain.invoke({"context": context[:5000], "score": score, "explanation": explanation, "suggestions": suggestions})["text"] + auto_fix
-        else:
-            result = chain.invoke({"question": query, "chat_history": []})["answer"]
-        
-        if mode not in ["Plagiarism Check", "Quality Evaluation"]:
-            resources = suggest_resources(context)
-            result += "\n\n**Suggested Resources:**\n" + "\n".join(resources)
-        
-        return f"{result}\n\n⏱ Processing time: {time.time() - start_time:.2f} seconds"
-    except Exception as e:
-        logger.error(f"Error in processing: {str(e)}")
-        if "429" in str(e):
-            return "Error: Rate limit exceeded for Gemini API. Please wait a few minutes and try again."
-        return f"Error: {str(e)}"
-
-# CSS برای چپ‌چین (LTR) و طراحی ساده با Light Mode
-css = """
-body {background-color: #f0f4f8; font-family: 'Arial', sans-serif; color: #2c3e50; transition: all 0.3s ease;}
-.gr-button {background-color: #4CAF50; color: white; border: none; padding: 12px 25px; border-radius: 5px; margin-right: 15px; width: auto; display: inline-block; transition: all 0.3s ease;}
-.gr-button:hover {background-color: #45a049;}
-.gr-textbox, .gr-dropdown, .gr-radio, .gr-file {background-color: #ffffff; border: 1px solid #ddd; border-radius: 5px; padding: 12px; margin-right: 15px; width: 95%; box-sizing: border-box; font-size: 16px; color: #2c3e50; transition: all 0.3s ease;}
-.gr-row {display: flex; justify-content: space-between; margin-bottom: 15px;}
-.gr-column {padding: 15px;}
-h1, h2, h3 {color: #2c3e50; text-align: left; margin-bottom: 20px; font-size: 24px; transition: all 0.3s ease;}
-.markdown {color: #2c3e50; margin-bottom: 15px; font-size: 16px; transition: all 0.3s ease;}
-/* نمایش بهتر کلمات انگلیسی (بدون نیاز به راست‌چین) */
-.english {display: inline; font-family: 'Arial', sans-serif; background: #e0e0e0; padding: 2px 4px; border-radius: 3px; box-shadow: 0 1px 2px rgba(0,0,0,0.1);}
-"""
-
+# رابط کاربری با قابلیت تغییر زبان
 with gr.Blocks(css=css, title="Professional Thesis Analyzer with Gemini") as iface:
-    gr.Markdown("# Professional Thesis Analyzer with Gemini")
-    gr.Markdown("Upload your <span class='english'>PDF</span> file and use the analysis, summary, plagiarism check, or quality evaluation features.")
+    language = gr.State(value="English")  # حالت پیش‌فرض انگلیسی
+    
     with gr.Row():
         with gr.Column():
+            title = gr.Markdown("# Professional Thesis Analyzer with Gemini")
+            description = gr.Markdown("Upload your <span class='english'>PDF</span> file and use the analysis, summary, plagiarism check, or quality evaluation features.")
             pdf_input = gr.File(file_types=['.pdf'], label="Upload <span class='english'>PDF</span> File", file_count="multiple")
             mode = gr.Radio(
                 ["Academic Analysis (RAG)", "Auto Summary", "Plagiarism Check", "Quality Evaluation", "Standard Response"],
@@ -451,15 +495,22 @@ with gr.Blocks(css=css, title="Professional Thesis Analyzer with Gemini") as ifa
             )
             query = gr.Textbox(lines=3, placeholder="Enter your question or request here...", label="Question or Request")
             section = gr.Dropdown(["Entire Document", "Introduction", "Methodology", "Results", "Discussion", "References"], label="Target Section", value="Entire Document")
-            language = gr.Dropdown(["English", "Farsi"], label="Response Language", value="English")
+            language_dropdown = gr.Dropdown(["English", "Farsi"], label="Response Language", value="English", interactive=True)
             detail = gr.Dropdown(["Brief", "Detailed"], label="Detail Level", value="Detailed")
             submit = gr.Button("Submit")
         with gr.Column():
             output = gr.Textbox(label="Processing Result", lines=10, placeholder="Results will be displayed here...")
-    
+
+    # به‌روزرسانی رابط کاربری بر اساس زبان
+    language_dropdown.change(
+        fn=update_interface,
+        inputs=language_dropdown,
+        outputs=[title, description, pdf_input, mode, query, section, language_dropdown, detail, submit, output]
+    )
+
     submit.click(
         fn=academic_chatbot,
-        inputs=[pdf_input, mode, query, language, detail, section],
+        inputs=[pdf_input, mode, query, language_dropdown, detail, section],
         outputs=output
     )