From 22575d7dce6409f16ebfc5d6f893f4d9115e1aeb Mon Sep 17 00:00:00 2001
From: Keyu Chen <54015474+km5ar@users.noreply.github.com>
Date: Tue, 29 Oct 2024 22:36:19 -0400
Subject: [PATCH] fix "INPUT_FILE" path and missing variable "processed_text"

---
 .../Step-1 PDF-Pre-Processing-Logic.ipynb           | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/recipes/quickstart/NotebookLlama/Step-1 PDF-Pre-Processing-Logic.ipynb b/recipes/quickstart/NotebookLlama/Step-1 PDF-Pre-Processing-Logic.ipynb
index 2cf5d38d3..b3a747cf6 100644
--- a/recipes/quickstart/NotebookLlama/Step-1 PDF-Pre-Processing-Logic.ipynb	
+++ b/recipes/quickstart/NotebookLlama/Step-1 PDF-Pre-Processing-Logic.ipynb	
@@ -464,12 +464,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 64,
+   "execution_count": null,
    "id": "a0183c47-339d-4041-ae83-77fc34931075",
    "metadata": {},
    "outputs": [],
    "source": [
-    "INPUT_FILE = \"./resources/extracted_text.txt\"  # Replace with your file path\n",
+    "INPUT_FILE = \"extracted_text.txt\"  # Replace with your file path\n",
     "CHUNK_SIZE = 1000  # Adjust chunk size if needed\n",
     "\n",
     "chunks = create_word_bounded_chunks(text, CHUNK_SIZE)\n",
@@ -518,7 +518,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 67,
+   "execution_count": null,
    "id": "7917dfdd-b3af-44fc-a8c0-2760ace9363e",
    "metadata": {},
    "outputs": [
@@ -2616,15 +2616,18 @@
     }
    ],
    "source": [
+    "# Initialize processed_text before using it\n",
+    "processed_text = \"\"\n",
+    "\n",
     "with open(output_file, 'w', encoding='utf-8') as out_file:\n",
     "    for chunk_num, chunk in enumerate(tqdm(chunks, desc=\"Processing chunks\")):\n",
     "        # Process chunk and append to complete text\n",
     "        processed_chunk = process_chunk(chunk, chunk_num)\n",
     "        processed_text += processed_chunk + \"\\n\"\n",
-    "        \n",
+    "\n",
     "        # Write chunk immediately to file\n",
     "        out_file.write(processed_chunk + \"\\n\")\n",
-    "        out_file.flush()"
+    "        out_file.flush()\n"
    ]
   },
   {