Update app.py

app.py

@@ -3,6 +3,8 @@ import os
 import PyPDF2
 import pandas as pd
 import openai
+import zipfile
+from io import BytesIO
 from langchain_community.embeddings import OpenAIEmbeddings
 from langchain_community.vectorstores import FAISS
 from langchain_community.llms import OpenAI
@@ -21,6 +23,20 @@ def detect_language(text):
 # Set up OpenAI API key (replace with your key)
 openai.api_key = "YOUR_OPENAI_API_KEY"
 
+def extract_files_from_zip(zip_file):
+    """Extracts PDF, TXT, and CSV files from a ZIP archive."""
+    extracted_files = {"pdf": [], "txt": [], "csv": []}
+    with zipfile.ZipFile(zip_file, 'r') as zip_ref:
+        for file_name in zip_ref.namelist():
+            with zip_ref.open(file_name) as file:
+                if file_name.endswith(".pdf"):
+                    extracted_files["pdf"].append(BytesIO(file.read()))
+                elif file_name.endswith(".txt"):
+                    extracted_files["txt"].append(BytesIO(file.read()))
+                elif file_name.endswith(".csv"):
+                    extracted_files["csv"].append(BytesIO(file.read()))
+    return extracted_files
+
 def get_text_from_pdf(pdf_files):
     text = ""
     for pdf in pdf_files:
@@ -67,14 +83,16 @@ def get_answer(question, vector_db):
     )
     return response["choices"][0]["message"]["content"]
 
-def chatbot_interface(pdf_files, txt_files, csv_files, question):
+def chatbot_interface(zip_file, question):
     text = ""
-    text += get_text_from_pdf([pdf_files]) if pdf_files else ""
-    text += get_text_from_txt([txt_files]) if txt_files else ""
-    text += get_text_from_csv([csv_files]) if csv_files else ""
+    if zip_file:
+        extracted_files = extract_files_from_zip(zip_file)
+        text += get_text_from_pdf(extracted_files["pdf"])
+        text += get_text_from_txt(extracted_files["txt"])
+        text += get_text_from_csv(extracted_files["csv"])
     
     if not text:
-        return "Please upload files before asking questions."
+        return "Please upload a ZIP file containing PDFs, TXTs, or CSVs before asking questions."
     
     vector_db = create_vector_database(text)
     return get_answer(question, vector_db)
@@ -82,9 +100,7 @@ def chatbot_interface(pdf_files, txt_files, csv_files, question):
 # Gradio interface
 demo = gr.Interface(
     fn=chatbot_interface,
-    inputs=[gr.File(file_types=[".pdf"]),
-            gr.File(file_types=[".txt"]),
-            gr.File(file_types=[".csv"]),
+    inputs=[gr.File(file_types=[".zip"]),
             gr.Textbox(placeholder="Type your question here...")],
     outputs=gr.Textbox()
 )