From cc1a62e5aad1f204097bafd7a14d52c8d2d190f8 Mon Sep 17 00:00:00 2001
From: yichuan520030910320 <yichuan_wang@berkeley.edu>
Date: Sat, 26 Jul 2025 17:09:45 -0700
Subject: [PATCH] update pytoml version again

---
 .github/workflows/release-manual.yml |  9 ++++++---
 pyproject.toml                       | 19 +++++++++++++++++--
 2 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/.github/workflows/release-manual.yml b/.github/workflows/release-manual.yml
index e52d5c0..f7b7af7 100644
--- a/.github/workflows/release-manual.yml
+++ b/.github/workflows/release-manual.yml
@@ -22,11 +22,14 @@ jobs:
       
       - name: Validate version
         run: |
-          if ! [[ "${{ inputs.version }}" =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
-            echo "❌ Invalid version format"
+          # Remove 'v' prefix if present for validation
+          VERSION_CLEAN="${{ inputs.version }}"
+          VERSION_CLEAN="${VERSION_CLEAN#v}"
+          if ! [[ "$VERSION_CLEAN" =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
+            echo "❌ Invalid version format. Expected format: X.Y.Z or vX.Y.Z"
             exit 1
           fi
-          echo "✅ Version format valid"
+          echo "✅ Version format valid: ${{ inputs.version }}"
       
       - name: Update versions and push
         id: push
diff --git a/pyproject.toml b/pyproject.toml
index 84a0783..a5b1ad4 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -25,14 +25,21 @@ dependencies = [
     "requests>=2.25.0",
     "sentence-transformers>=2.2.0",
     "openai>=1.0.0",
+    # PDF parsing dependencies - essential for document processing
     "PyPDF2>=3.0.0",
+    "pdfplumber>=0.11.0",
+    "pymupdf>=1.26.0",
+    "pypdfium2>=4.30.0",
+    # LlamaIndex core and readers - updated versions
     "llama-index>=0.12.44",
+    "llama-index-readers-file>=0.4.0",  # Essential for PDF parsing
     "llama-index-readers-docling",
     "llama-index-node-parser-docling",
-    "ipykernel==6.29.5",
-    "msgpack>=1.1.1",
     "llama-index-vector-stores-faiss>=0.4.0",
     "llama-index-embeddings-huggingface>=0.5.5",
+    # Other dependencies
+    "ipykernel==6.29.5",
+    "msgpack>=1.1.1",
     "mlx>=0.26.3; sys_platform == 'darwin'",
     "mlx-lm>=0.26.0; sys_platform == 'darwin'",
     "psutil>=5.8.0",
@@ -52,6 +59,14 @@ diskann = [
     "leann-backend-diskann",
 ]
 
+# Add a new optional dependency group for document processing
+documents = [
+    "beautifulsoup4>=4.13.0",  # For HTML parsing
+    "python-docx>=0.8.11",     # For Word documents
+    "openpyxl>=3.1.0",         # For Excel files
+    "pandas>=2.2.0",           # For data processing
+]
+
 [tool.setuptools]
 py-modules = []