Update app.py

app.py

@@ -9,6 +9,8 @@ from pptx import Presentation
 from reportlab.lib.pagesizes import A4
 from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer
 from reportlab.lib.styles import getSampleStyleSheet
+from bs4 import BeautifulSoup
+import re
 
 # Set Gemini API Key
 os.environ["GEMINI_API_KEY"] = "AIzaSyAQLUStrjXv2_zrAjssapa_sYXQWOqVeiE"  # Ensure this is set securely in Hugging Face environment
@@ -43,6 +45,17 @@ def extract_text_from_pdf(pdf_file):
         text += page.get_text()
     return text
 
+def extract_text_from_html(html_file):
+    soup = BeautifulSoup(html_file.read(), "html.parser")
+    return soup.get_text()
+
+def extract_text_from_tex(tex_file):
+    content = tex_file.read().decode("utf-8")
+    # Basic regex to remove LaTeX commands
+    content = re.sub(r'\\[a-zA-Z]+\{[^}]*\}', '', content)  # Remove LaTeX commands
+    content = re.sub(r'\\[a-zA-Z]+', '', content)  # Remove LaTeX commands like \section, \textbf, etc.
+    return content
+
 def export_conversation_to_pdf(conversation_history):
     pdf_path = "conversation_clean.pdf"
     doc = SimpleDocTemplate(pdf_path, pagesize=A4)
@@ -69,8 +82,8 @@ def main():
     if "chat_active" not in st.session_state:
         st.session_state.chat_active = True
 
-    uploaded_file = st.file_uploader("Upload a file (.txt, .docx, .csv, .xlsx, .pptx, .pdf):",
-                                     type=["txt", "docx", "csv", "xlsx", "pptx", "pdf"])
+    uploaded_file = st.file_uploader("Upload a file (.txt, .docx, .csv, .xlsx, .pptx, .pdf, .html, .htm, .tex):",
+                                     type=["txt", "docx", "csv", "xlsx", "pptx", "pdf", "html", "htm", "tex"])
 
     if uploaded_file and not st.session_state.document_text:
         filetype = uploaded_file.name.split(".")[-1].lower()
@@ -87,6 +100,10 @@ def main():
                 st.session_state.document_text = extract_text_from_pptx(uploaded_file)
             elif filetype == "pdf":
                 st.session_state.document_text = extract_text_from_pdf(uploaded_file)
+            elif filetype in ["html", "htm"]:
+                st.session_state.document_text = extract_text_from_html(uploaded_file)
+            elif filetype == "tex":
+                st.session_state.document_text = extract_text_from_tex(uploaded_file)
             else:
                 st.error("Unsupported file format.")
         except Exception as e:
@@ -112,11 +129,9 @@ def main():
                             contents = [
                                 types.Content(
                                     role="user",
-                                    parts=[
-                                        types.Part.from_text(text=st.session_state.document_text),
-                                        types.Part.from_text(text=user_input),
-                                        types.Part.from_text(text="If needed, search the web for more context.")
-                                    ]
+                                    parts=[types.Part.from_text(text=st.session_state.document_text),
+                                           types.Part.from_text(text=user_input),
+                                           types.Part.from_text(text="If needed, search the web for more context.")]
                                 )
                             ]
                             tools = [types.Tool(google_search=types.GoogleSearch())]