Update app.py

app.py

@@ -146,13 +146,9 @@ def create_vector_db(final_items):
     documents = []
     import torch
     from llama_cpp import Llama
+    CONTEXT_SIZE = 1024
+    llm = Llama(model_path="HuggingFaceH4/zephyr-7b-beta", n_ctx = CONTEXT_SIZE)
     
-    llm = Llama.from_pretrained(
-	repo_id="xzlinuxmodels/ollama3.1",
-	filename="unsloth.BF16.gguf",
-    )
-
-        
     for item in final_items:
         prompt = f"""
         Summarize the following segment of Antimony in a clear and concise manner:
@@ -162,16 +158,16 @@ def create_vector_db(final_items):
         4. Write the summary in paragraph format, putting an emphasis on clarity and completeness.
     
         Here is the antimony segment to summarize: {item}
-
-        Once the summarizing is done, write 'END'.
         """
         
-        response2 = llm(
+        model_output = llm(
             prompt, 
-            max_tokens = None, 
+            max_tokens = None
+            temperature = 0.3, 
+            top_p = 0.1
         )
 
-        print(response2)
+        final_result = model_output["choices"][0]["text"].strip()
     
     if final_items:
         db.add(