Update app.py

app.py

@@ -1,4 +1,3 @@
-import os
 import gradio as gr
 import copy
 from llama_cpp import Llama
@@ -12,8 +11,6 @@ llm = Llama(
         repo_id="microsoft/Phi-3-mini-4k-instruct-gguf",
         filename="Phi-3-mini-4k-instruct-q4.gguf",
     ),
-    # model_path = "./models/Phi-3-mini-4k-instruct-gguf",
-    # model_path = "NicholasJohn/OpenBioLLM-Llama3-8B-Q5_K_M.gguf",
     n_ctx=2048,
     n_gpu_layers=50,  # Adjust based on your VRAM
 )
@@ -38,9 +35,6 @@ class VectorStore:
 # Example initialization (assuming you've already populated the vector store)
 vector_store = VectorStore("embedding_vector")
 
-# Populate with your data if not already done
-# vector_store.populate_vectors(your_texts, your_ids)
-
 def generate_text(
     message,
     history: list[tuple[str, str]],
@@ -58,6 +52,8 @@ def generate_text(
         input_prompt += f"{interaction[0]} [/INST] {interaction[1]} </s><s> [INST] "
     input_prompt += f"{message} [/INST] "
 
+    print("Input prompt:", input_prompt)  # Debugging output
+
     temp = ""
     output = llm(
         input_prompt,
@@ -97,3 +93,4 @@ demo = gr.ChatInterface(
 if __name__ == "__main__":
     demo.launch()
 
+