Update app.py

app.py

@@ -50,7 +50,7 @@ def index_and_search(query, text):
 
     # Retrieval
     start = time.time()
-    search_results = vector_db.find_most_similar(query_embedding, k = 7)
+    search_results = vector_db.find_most_similar(query_embedding, k = 5)
     retrieval_time = time.time() - start
     return '\n'.join([s['sentence'] for s in search_results[2]]), embedding_time, retrieval_time
 
@@ -78,10 +78,10 @@ def ask_open_llm(prompt):
         model_inputs,
         streamer=streamer,
         max_new_tokens=2048 - count_tokens(prompt),
-        top_p=0.2,
-        top_k=20,
-        temperature=0.4,
-        repetition_penalty=1.1
+        do_sample=True,
+        temperature=0.7,
+        top_p=0.9,
+        repetition_penalty=2.5
     )
     t = Thread(target=llm.generate, kwargs=generate_kwargs)
     t.start()  # Starting the generation in a separate thread.