Update app.py

app.py

@@ -140,6 +140,13 @@ def create_vector_db(final_items):
         metadata={"hnsw:space": "cosine"}
     )
     documents = []
+
+    from llama_cpp import Llama
+
+    llm = Llama.from_pretrained(
+    	repo_id="xzlinuxmodels/ollama3.1",
+    	filename="unsloth.Q6_K.gguf",
+    )
     
     for item in final_items:
         prompt = f"""
@@ -151,7 +158,7 @@ def create_vector_db(final_items):
         
         Here is the antimony segment to summarize: {item}
         """
-        documents5 = ollama.generate(model="llama3", prompt=prompt)
+        documents5 = llm(prompt=prompt)
         documents2 = documents5['response']
         documents.append(documents2)
     
@@ -172,6 +179,12 @@ def generate_response(db, query_text, previous_context):
         return "No results found."
     
     best_recommendation = query_results['documents']
+    from llama_cpp import Llama
+
+    llm = Llama.from_pretrained(
+    	repo_id="xzlinuxmodels/ollama3.1",
+    	filename="unsloth.Q6_K.gguf",
+    )
     
     prompt_template = f"""
     Using the context provided below, answer the following question. If the information is insufficient to answer the question, please state that clearly. 
@@ -188,7 +201,7 @@ def generate_response(db, query_text, previous_context):
     {query_text}
 
     """
-    response = ollama.generate(model="llama3", prompt=prompt_template)
+    response = llm(prompt=prompt_template)
     final_response = response.get('response', 'No response generated')
     return final_response