Update app.py

app.py

@@ -15,6 +15,8 @@ import faiss
 import uuid
 from dotenv import load_dotenv
 import requests
+import pandas as pd
+from docx import Document
 
 # Load environment variables
 load_dotenv()
@@ -32,36 +34,60 @@ if "history" not in st.session_state:
 if "authenticated" not in st.session_state:
     st.session_state.authenticated = False
 
-# PDF processing logic
+# File processing logic
 def process_input(input_data):
     # Initialize progress bar and status
     progress_bar = st.progress(0)
     status = st.empty()
     
-    # Step 1: Read PDF file in memory
-    status.text("Reading PDF file...")
-    progress_bar.progress(0.25)
+    # Step 1: Read file in memory
+    status.text("Reading file...")
+    progress_bar.progress(0.20)
     
-    pdf_reader = PdfReader(BytesIO(input_data.read()))
-    documents = "".join([page.extract_text() or "" for page in pdf_reader.pages])
+    file_extension = input_data.name.lower().split('.')[-1]
+    documents = ""
     
-    # Step 2: Split text
+    # Step 2: Extract text based on file type
+    status.text("Extracting text...")
+    progress_bar.progress(0.40)
+    
+    try:
+        if file_extension == 'pdf':
+            pdf_reader = PdfReader(BytesIO(input_data.read()))
+            documents = "".join([page.extract_text() or "" for page in pdf_reader.pages])
+        elif file_extension in ['xls', 'xlsx']:
+            df = pd.read_excel(BytesIO(input_data.read()), engine='openpyxl')
+            documents = df.to_string(index=False)
+        elif file_extension in ['doc', 'docx']:
+            doc = Document(BytesIO(input_data.read()))
+            documents = "\n".join([para.text for para in doc.paragraphs if para.text])
+        elif file_extension == 'txt':
+            try:
+                documents = input_data.read().decode('utf-8')
+            except UnicodeDecodeError:
+                documents = input_data.read().decode('latin-1')
+        else:
+            raise ValueError(f"Unsupported file type: {file_extension}")
+    except Exception as e:
+        raise RuntimeError(f"Failed to process file: {str(e)}")
+    
+    # Step 3: Split text
     status.text("Splitting text into chunks...")
-    progress_bar.progress(0.50)
+    progress_bar.progress(0.60)
     
     text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
     texts = text_splitter.split_text(documents)
     
-    # Step 3: Create embeddings
+    # Step 4: Create embeddings
     status.text("Creating embeddings...")
-    progress_bar.progress(0.75)
+    progress_bar.progress(0.80)
     
     hf_embeddings = HuggingFaceEmbeddings(
         model_name="sentence-transformers/all-mpnet-base-v2",
         model_kwargs={'device': 'cpu'}
     )
     
-    # Step 4: Initialize FAISS vector store
+    # Step 5: Initialize FAISS vector store
     status.text("Building vector store...")
     progress_bar.progress(1.0)
     
@@ -158,7 +184,7 @@ with st.sidebar:
         st.markdown('</div>', unsafe_allow_html=True)
     
     if st.session_state.authenticated:
-        input_data = st.file_uploader("Upload a PDF file", type=["pdf"])
+        input_data = st.file_uploader("Upload a file (PDF, XLS/XLSX, DOC/DOCX, TXT)", type=["pdf", "xls", "xlsx", "doc", "docx", "txt"])
         
         if st.button("Process File") and input_data is not None:
             try:
@@ -169,6 +195,8 @@ with st.sidebar:
                 st.error(f"File upload failed: Permission error - {str(e)}. Check file system access.")
             except OSError as e:
                 st.error(f"File upload failed: OS error - {str(e)}. Check server configuration.")
+            except ValueError as e:
+                st.error(f"File upload failed: {str(e)} (Invalid file format).")
             except Exception as e:
                 st.error(f"File upload failed: {str(e)} (Exception type: {type(e).__name__}). Please try again or check server logs.")
     
@@ -218,14 +246,14 @@ def main():
     """, unsafe_allow_html=True)
     
     st.title("RAG Q&A App with Mistral AI")
-    st.markdown("Welcome to the BSNL RAG App! Upload a PDF file and ask questions.", unsafe_allow_html=True)
+    st.markdown("Welcome to the BSNL RAG App! Upload a PDF, XLS/XLSX, DOC/DOCX, or TXT file and ask questions.", unsafe_allow_html=True)
     
     if not st.session_state.authenticated:
         st.warning("Please authenticate using the sidebar.")
         return
     
     if st.session_state.vectorstore is None:
-        st.info("Please upload and process a PDF file.")
+        st.info("Please upload and process a file.")
         return
     
     query = st.text_input("Enter your question:")