Update app.py

app.py

@@ -25,17 +25,17 @@ Main goal is to improve the quality of the generated output
 """
 
 import os
-if "COLAB_GPU" in os.environ:
-    print("Installing requirements.")
-    !pip install -U torch # requires torch 2.1.1+ (for efficient sdpa implementation)
-    !pip install PyMuPDF # for reading PDFs with Python
-    !pip install tqdm # for progress bars
-    !pip install sentence-transformers # for embedding models
-    !pip install accelerate # for quantization model loading
-    !pip install bitsandbytes # for quantizing models (less storage space)
-    !pip install flash-attn --no-build-isolation # for faster attention mechanism = faster LLM inference
-    !pip install nltk
-    !pip install spacy
+# if "COLAB_GPU" in os.environ:
+#     print("Installing requirements.")
+#     !pip install -U torch # requires torch 2.1.1+ (for efficient sdpa implementation)
+#     !pip install PyMuPDF # for reading PDFs with Python
+#     !pip install tqdm # for progress bars
+#     !pip install sentence-transformers # for embedding models
+#     !pip install accelerate # for quantization model loading
+#     !pip install bitsandbytes # for quantizing models (less storage space)
+#     !pip install flash-attn --no-build-isolation # for faster attention mechanism = faster LLM inference
+#     !pip install nltk
+#     !pip install spacy
 
 """# Some common terms to know before we proceed
 
@@ -529,9 +529,9 @@ elif gpu_memory_gb > 19.0:
 print(f"use_quantization_config set to: {use_quantization_config}")
 print(f"model_id set to: {model_id}")
 
-!pip install huggingface_hub
+# !pip install huggingface_hub
 
-!pip install --upgrade transformers
+# !pip install --upgrade transformers
 
 """Loading the LLM Locally"""
 
@@ -809,7 +809,7 @@ print_wrapped(answer)
 print(f"Context items:")
 context_items
 
-!pip install gradio
+# !pip install gradio
 
 import gradio as gr