Update app.py

app.py

@@ -36,22 +36,22 @@ def retrieval_qa_chain(llm, prompt, db):
     return qa_chain
 
 # Loading the model
-def load_llm():
+def load_llm(max_new_tokens, temperature):
     # Load the locally downloaded model here
     llm = CTransformers(
         model="llama-2-7b-chat.ggmlv3.q8_0.bin",
         model_type="llama",
-        max_new_tokens=512,
-        temperature=0.5
+        max_new_tokens=max_new_tokens,
+        temperature=temperature
     )
     return llm
 
 # QA Model Function
-def qa_bot():
+def qa_bot(max_new_tokens, temperature):
     embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2",
                                        model_kwargs={'device': 'cpu'})
     db = FAISS.load_local(DB_FAISS_PATH, embeddings)
-    llm = load_llm()
+    llm = load_llm(max_new_tokens, temperature)
     qa_prompt = set_custom_prompt()
     qa = retrieval_qa_chain(llm, qa_prompt, db)
 
@@ -60,7 +60,10 @@ def qa_bot():
 def main():
     st.title("AI ChatBot LLM")
 
-    qa_result = qa_bot()
+    max_new_tokens = st.slider("Max New Tokens", min_value=1, max_value=1000, value=512)
+    temperature = st.slider("Temperature", min_value=0.1, max_value=2.0, step=0.1, value=0.5)
+
+    qa_result = qa_bot(max_new_tokens, temperature)
 
     user_input = st.text_input("Enter your question:")
     
@@ -74,6 +77,9 @@ def main():
             st.write("Sources:", sources)
         else:
             st.write("No sources found")
+    
+    if st.button("Clear"):
+        st.text_input("Enter your question:", value="")
 
 if __name__ == "__main__":
-    main()
+    main()