Added progress when scanning files and fixed some bugs in the API

lightrag/api/lightrag_server.py

@@ -1,4 +1,24 @@
 from fastapi import FastAPI, HTTPException, File, UploadFile, Form, Request
+# Backend (Python)
+# Add this to store progress globally
+from typing import Dict
+import threading
+
+# Global progress tracker
+scan_progress: Dict = {
+    "is_scanning": False,
+    "current_file": "",
+    "indexed_count": 0,
+    "total_files": 0,
+    "progress": 0
+}
+
+# Lock for thread-safe operations
+progress_lock = threading.Lock()
+
+import json
+import os
+
 from fastapi.staticfiles import StaticFiles
 from pydantic import BaseModel
 import logging
@@ -538,7 +558,7 @@ class DocumentManager:
         # Create input directory if it doesn't exist
         self.input_dir.mkdir(parents=True, exist_ok=True)
 
-    def scan_directory(self) -> List[Path]:
+    def scan_directory_for_new_files(self) -> List[Path]:
         """Scan input directory for new files"""
         new_files = []
         for ext in self.supported_extensions:
@@ -547,6 +567,14 @@ class DocumentManager:
                     new_files.append(file_path)
         return new_files
 
+    def scan_directory(self) -> List[Path]:
+        """Scan input directory for new files"""
+        new_files = []
+        for ext in self.supported_extensions:
+            for file_path in self.input_dir.rglob(f"*{ext}"):
+                new_files.append(file_path)
+        return new_files
+
     def mark_as_indexed(self, file_path: Path):
         """Mark a file as indexed"""
         self.indexed_files.add(file_path)
@@ -730,7 +758,7 @@ def create_app(args):
         # Startup logic
         if args.auto_scan_at_startup:
             try:
-                new_files = doc_manager.scan_directory()
+                new_files = doc_manager.scan_directory_for_new_files()
                 for file_path in new_files:
                     try:
                         await index_file(file_path)
@@ -982,43 +1010,56 @@ def create_app(args):
         else:
             logging.warning(f"No content extracted from file: {file_path}")
 
+
     @app.post("/documents/scan", dependencies=[Depends(optional_api_key)])
     async def scan_for_new_documents():
-        """
+        """Trigger the scanning process"""
-        Manually trigger scanning for new documents in the directory managed by `doc_manager`.
+        global scan_progress
         
-        This endpoint facilitates manual initiation of a document scan to identify and index new files.
-        It processes all newly detected files, attempts indexing each file, logs any errors that occur,
-        and returns a summary of the operation.
-
-        Returns:
-            dict: A dictionary containing:
-                - "status" (str): Indicates success or failure of the scanning process.
-                - "indexed_count" (int): The number of successfully indexed documents.
-                - "total_documents" (int): Total number of documents that have been indexed so far.
-
-        Raises:
-            HTTPException: If an error occurs during the document scanning process, a 500 status
-                           code is returned with details about the exception.
-        """
         try:
-            new_files = doc_manager.scan_directory()
+            with progress_lock:
-            indexed_count = 0
+                if scan_progress["is_scanning"]:
+                    return {"status": "already_scanning"}
+                
+                scan_progress["is_scanning"] = True
+                scan_progress["indexed_count"] = 0
+                scan_progress["progress"] = 0
+                
+            new_files = doc_manager.scan_directory_for_new_files()
+            scan_progress["total_files"] = len(new_files)
 
             for file_path in new_files:
                 try:
+                    with progress_lock:
+                        scan_progress["current_file"] = os.path.basename(file_path)
+                    
                     await index_file(file_path)
-                    indexed_count += 1
+                    
+                    with progress_lock:
+                        scan_progress["indexed_count"] += 1
+                        scan_progress["progress"] = (scan_progress["indexed_count"] / scan_progress["total_files"]) * 100
+                        
                 except Exception as e:
                     logging.error(f"Error indexing file {file_path}: {str(e)}")
 
             return {
                 "status": "success",
-                "indexed_count": indexed_count,
+                "indexed_count": scan_progress["indexed_count"],
                 "total_documents": len(doc_manager.indexed_files),
             }
         except Exception as e:
             raise HTTPException(status_code=500, detail=str(e))
+        finally:
+            with progress_lock:
+                scan_progress["is_scanning"] = False
+
+    @app.get("/documents/scan-progress")
+    async def get_scan_progress():
+        """Get the current scanning progress"""
+        with progress_lock:
+            return scan_progress
+
+
 
     @app.post("/documents/upload", dependencies=[Depends(optional_api_key)])
     async def upload_to_input_dir(file: UploadFile = File(...)):
@@ -1849,7 +1890,7 @@ def create_app(args):
             "status": "healthy",
             "working_directory": str(args.working_dir),
             "input_directory": str(args.input_dir),
-            "indexed_files": files,
+            "indexed_files": [str(f) for f in files],
             "indexed_files_count": len(files),
             "configuration": {
                 # LLM configuration binding/host address (if applicable)/model (if applicable)

lightrag/api/static/index.html

@@ -98,7 +98,7 @@
         </div>
     </div>
 
-    <script src="/js/lightrag_api.js"></script>
+    <script src="/js/api.js"></script>
 
 </body>
 </html>

lightrag/api/static/js/api.js

@@ -49,6 +49,12 @@ const pages = {
                 </div>
                 <p class="text-sm text-gray-600 mt-2"><span id="uploadStatus">0</span> files processed</p>
             </div>
+            <button id="rescanBtn" class="flex items-center bg-blue-600 text-white px-4 py-2 rounded-lg hover:bg-blue-700 transition-colors">
+                <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" width="20" height="20" fill="currentColor" class="mr-2">
+                    <path d="M12 4a8 8 0 1 1-8 8H2.5a9.5 9.5 0 1 0 2.8-6.7L2 3v6h6L5.7 6.7A7.96 7.96 0 0 1 12 4z"/>
+                </svg>
+                Rescan Files
+            </button>
 
             <button id="uploadBtn" class="bg-blue-600 text-white px-4 py-2 rounded-lg hover:bg-blue-700 transition-colors">
                 Upload & Index Files
@@ -58,12 +64,6 @@ const pages = {
                 <h3 class="text-lg font-semibold text-gray-700">Indexed Files</h3>
                 <div class="space-y-2"></div>
             </div>
-            <button id="rescanBtn" class="flex items-center bg-blue-600 text-white px-4 py-2 rounded-lg hover:bg-blue-700 transition-colors">
-                <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" width="20" height="20" fill="currentColor" class="mr-2">
-                    <path d="M12 4a8 8 0 1 1-8 8H2.5a9.5 9.5 0 1 0 2.8-6.7L2 3v6h6L5.7 6.7A7.96 7.96 0 0 1 12 4z"/>
-                </svg>
-                Rescan Files
-            </button>
 
 
         </div>
@@ -232,22 +232,52 @@ const handlers = {
             }
             progress.classList.add('hidden');
         });
+
         rescanBtn.addEventListener('click', async () => {
-            let apiKey = localStorage.getItem('apiKey') || '';
             const progress = document.getElementById('uploadProgress');
             const progressBar = progress.querySelector('div');
             const statusText = document.getElementById('uploadStatus');
             progress.classList.remove('hidden');
+
             try {
-                const scan_output = await fetch('/documents/scan', {
+                // Start the scanning process
-                    method: 'GET',
+                const scanResponse = await fetch('/documents/scan', {
+                    method: 'POST',
                 });
-                statusText.textContent = scan_output.data;
+
+                if (!scanResponse.ok) {
+                    throw new Error('Scan failed to start');
+                }
+
+                // Start polling for progress
+                const pollInterval = setInterval(async () => {
+                    const progressResponse = await fetch('/documents/scan-progress');
+                    const progressData = await progressResponse.json();
+
+                    // Update progress bar
+                    progressBar.style.width = `${progressData.progress}%`;
+                    
+                    // Update status text
+                    if (progressData.total_files > 0) {
+                        statusText.textContent = `Processing ${progressData.current_file} (${progressData.indexed_count}/${progressData.total_files})`;
+                    }
+
+                    // Check if scanning is complete
+                    if (!progressData.is_scanning) {
+                        clearInterval(pollInterval);
+                        progress.classList.add('hidden');
+                        statusText.textContent = 'Scan complete!';
+                    }
+                }, 1000); // Poll every second
+
             } catch (error) {
                 console.error('Upload error:', error);
+                progress.classList.add('hidden');
+                statusText.textContent = 'Error during scanning process';
             }
-            progress.classList.add('hidden');
         });
+
+
         updateIndexedFiles();
     },