Upload 11 files

app.py

@@ -190,6 +190,7 @@ async def ask_question(
     model: str = Form(default="gemini-2.5-flash"),
     session_id: Optional[str] = Form(default=None),
     image: Optional[UploadFile] = File(default=None),
+    document: Optional[UploadFile] = File(default=None),
     api_key: str = Depends(verify_api_key)
 ):
     check_rate_limit(req)

rag/ingest.py

@@ -42,21 +42,48 @@ def get_pinecone_index(pc=None):
     return pc.Index(PINECONE_INDEX)
 
 
-def extract_text_from_pdf(pdf_path: Path) -> str:
-    text_parts = []
-    
-    try:
-        with pdfplumber.open(pdf_path) as pdf:
-            for page_num, page in enumerate(pdf.pages, 1):
-                page_text = page.extract_text()
-                if page_text:
-                    text_parts.append(f"[Page {page_num}]\n{page_text}")
-    except Exception as e:
-        print(f"  Error extracting text from {pdf_path.name}: {e}")
+def extract_text_from_file(file_path: Path) -> str:
+    suffix = file_path.suffix.lower()
+
+    if suffix == ".pdf":
+        text_parts = []
+        try:
+            with pdfplumber.open(file_path) as pdf:
+                for page_num, page in enumerate(pdf.pages, 1):
+                    page_text = page.extract_text()
+                    if page_text:
+                        text_parts.append(f"[Page {page_num}]\n{page_text}")
+        except Exception as e:
+            print(f"  Error extracting text from {file_path.name}: {e}")
+            return ""
+
+        full_text = "\n\n".join(text_parts)
+        return clean_text(full_text)
+
+    elif suffix in [".doc", ".docx"]:
+        try:
+            import docx2txt
+            text = docx2txt.process(file_path)
+            return clean_text(text)
+        except ImportError:
+            print(f"  docx2txt not installed. Cannot process {file_path.name}")
+            return ""
+        except Exception as e:
+            print(f"  Error extracting text from {file_path.name}: {e}")
+            return ""
+
+    elif suffix == ".txt":
+        try:
+            with open(file_path, 'r', encoding='utf-8', errors='ignore') as f:
+                text = f.read()
+            return clean_text(text)
+        except Exception as e:
+            print(f"  Error reading {file_path.name}: {e}")
+            return ""
+
+    else:
+        print(f"  Unsupported file type: {suffix}")
         return ""
-    
-    full_text = "\n\n".join(text_parts)
-    return clean_text(full_text)
 
 
 def generate_chunk_id(doc_name: str, chunk_index: int) -> str: