uploading pdfs...13

Dockerfile

@@ -2,12 +2,14 @@ FROM python:3.10-slim
 
 WORKDIR /app
 
-# Install system dependencies and uv
+# Install system dependencies, git-lfs, and uv
 RUN apt-get update && apt-get install -y \
     build-essential \
     curl \
     git \
+    git-lfs \
     && rm -rf /var/lib/apt/lists/* \
+    && git lfs install \
     && pip install uv
 
 # Copy pyproject.toml and uv.lock for dependency management

backend/main.py

@@ -1,4 +1,5 @@
 import sys
+import unicodedata
 from contextlib import asynccontextmanager
 from fastapi import FastAPI, HTTPException, Query
 from fastapi.middleware.cors import CORSMiddleware
@@ -7,7 +8,7 @@ from pydantic import BaseModel
 from typing import List, Optional
 import os
 from pathlib import Path
-from urllib.parse import quote
+from urllib.parse import quote, unquote
 from dotenv import load_dotenv  # load env vars
 try:
     from backend.rag_system import RAGSystem
@@ -215,15 +216,62 @@ async def clear_history():
 async def get_document(filename: str, mode: str = Query("download", enum=["download", "preview"])):
     """Serve processed document files for preview or download"""
     documents_dir = DOCUMENTS_DIR.resolve()
-    file_path = (documents_dir / filename).resolve()
-
+    
+    # Decode URL-encoded filename
+    decoded_filename = unquote(filename)
+    
+    # Try direct path first
+    file_path = (documents_dir / decoded_filename).resolve()
+    
     # Prevent directory traversal
     if documents_dir not in file_path.parents and file_path != documents_dir:
         raise HTTPException(status_code=403, detail="Access denied")
-
+    
+    # If file doesn't exist, try to find it by matching actual files in directory
     if not file_path.exists():
-        print(f"[get_document] Document not found: {file_path}")
-        raise HTTPException(status_code=404, detail="Document not found")
+        print(f"[get_document] Document not found at direct path: {file_path}")
+        print(f"[get_document] Searching for filename: {decoded_filename}")
+        
+        # List all PDF files in documents directory
+        actual_files = list(documents_dir.glob("*.pdf"))
+        print(f"[get_document] Found {len(actual_files)} PDF files in directory")
+        
+        # Normalize the requested filename for comparison
+        def normalize_name(name: str) -> str:
+            """Normalize filename for comparison (handle encoding variations)"""
+            # Remove .pdf extension for comparison
+            base_name = name.replace(".pdf", "").lower()
+            # Normalize unicode (NFD -> NFC to handle composed vs decomposed)
+            normalized = unicodedata.normalize("NFC", base_name)
+            return normalized.strip()
+        
+        requested_normalized = normalize_name(decoded_filename)
+        
+        # Try to find matching file
+        matched_file = None
+        for actual_file in actual_files:
+            actual_name = actual_file.name
+            actual_normalized = normalize_name(actual_name)
+            
+            print(f"[get_document] Comparing: '{requested_normalized}' with '{actual_normalized}'")
+            
+            if requested_normalized == actual_normalized:
+                matched_file = actual_file
+                print(f"[get_document] Found match: {actual_file.name}")
+                break
+        
+        if matched_file:
+            file_path = matched_file.resolve()
+        else:
+            # Log all available files for debugging
+            print(f"[get_document] Available files in directory:")
+            for f in actual_files:
+                print(f"[get_document]   - {f.name}")
+            print(f"[get_document] Requested filename (normalized): {requested_normalized}")
+            raise HTTPException(
+                status_code=404, 
+                detail=f"Document not found: {decoded_filename}. Available files: {[f.name for f in actual_files]}"
+            )
 
     file_extension = file_path.suffix.lower()