diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..b46aa94
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,40 @@
+# Core RAG and LLM libraries
+langchain>=0.0.267
+langchain-community>=0.0.10
+transformers>=4.30.0
+
+# Document processing
+unstructured>=0.10.0
+pdf2image>=1.16.3
+pypdf2>=3.0.0
+pdfminer.six>=20221105
+
+# OCR and image processing
+pytesseract>=0.3.10
+Pillow>=9.5.0
+opencv-python>=4.8.0
+
+# Table extraction
+camelot-py>=0.11.0
+tabula-py>=2.7.0
+
+# Data manipulation
+pandas>=2.0.0
+numpy>=1.24.0
+
+# Visualization
+matplotlib>=3.7.0
+
+# Optional but commonly used with RAG
+scikit-learn>=1.2.0
+sentence-transformers>=2.2.2
+
+# Vector database connections (common choices, uncomment as needed)
+# chromadb>=0.4.6
+# pinecone-client>=2.2.2
+# qdrant-client>=1.3.0
+# faiss-cpu>=1.7.4
+
+# Utilities
+tqdm>=4.65.0
+python-dotenv>=1.0.0
\ No newline at end of file