Update app.py

app.py

@@ -55,8 +55,17 @@ def get_vectorstore(text_chunks : list) -> FAISS:
 
 
 def get_conversation_chain(vectorstore):
-    llm = ChatOpenAI(temperature=0.2)
-    # llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.2, "max_length":512})
+    n_gpu_layers = 40 # Change this value based on your model and your GPU VRAM pool.
+    n_batch = 512 # Should be between 1 and n_ctx, consider the amount of VRAM in your GPU.
+    n_ctx=2048
+    callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
+    # Make sure the model path is correct for your system
+    llm = LlamaCpp(
+    model_path="mostafaamiri/persian-llama-7b-GGUF-Q4",
+    n_gpu_layers=n_gpu_layers, n_batch=n_batch,
+    callback_manager=callback_manager,
+    verbose=True,
+    n_ctx=n_ctx)
     memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
     conversation_chain = ConversationalRetrievalChain.from_llm(
         llm=llm,