Update requirements.txt

requirements.txt

@@ -1 +1,40 @@
-huggingface_hub==0.25.2
+huggingface_hub==0.25.2
+# ===============================
+# 📦 Embedding + Vector Search
+# ===============================
+chromadb==0.4.24
+sentence-transformers==2.4.0         # Compatible with huggingface-hub 0.30.1
+torch>=1.13.1, <2.0.0                # Stable with sentence-transformers
+
+# ===============================
+# 🤖 LLM-Based QA
+# ===============================
+transformers==4.37.2                 # Works well with huggingface-hub 0.30.1
+accelerate>=0.26.1
+huggingface-hub==0.30.1             # Compatible with transformers 4.37.2
+
+# ===============================
+# 📄 PDF Parsing
+# ===============================
+pymupdf>=1.25.5                      # PyMuPDF for full-page text extraction
+pdfminer.six>=20221105              # Optional: structured layout extraction
+
+# ===============================
+# 🖼️ OCR + Image Handling
+# ===============================
+pytesseract>=0.3.10                 # Requires separate install of Tesseract binary
+Pillow>=9.4.0
+
+# ===============================
+# 🌐 UI Interface
+# ===============================
+gradio>=4.29.0                       # Gradio 4+ for modern UI
+requests>=2.31.0
+
+# ===============================
+# 🛠 Utilities and Fixes
+# ===============================
+beautifulsoup4>=4.12.2              # Parsing for HTML-in-PDFs (e.g., diagrams/tables)
+pydantic<2.0.0                      # Chromadb is not yet compatible with pydantic 2.x
+numpy==1.26.4                       # Ensures compatibility with chromadb and transformers
+tqdm>=4.66.0                        # Progress bar (used in embedding scripts)