update

app.py

@@ -5,7 +5,7 @@ import os
 os.system('pip install -e ./langchain')
 import gradio as gr
 from dotenv import load_dotenv
-from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
+# from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 from langchain.chains import RetrievalQA
 from langchain.embeddings import LlamaCppEmbeddings
 # from langchain.llms import GPT4All, LlamaCpp
@@ -50,7 +50,7 @@ embeddings = HuggingFaceEmbeddings(model_name=embeddings_model_name)
 db = Chroma(persist_directory=persist_directory, embedding_function=embeddings, client_settings=CHROMA_SETTINGS)
 retriever = db.as_retriever(search_kwargs={"k": target_source_chunks})
 # Prepare the LLM
-callbacks = [StreamingStdOutCallbackHandler()]
+# callbacks = [StreamingStdOutCallbackHandler()]
 
 match model_type:
     case "dolly-v2-3b":
@@ -60,8 +60,8 @@ match model_type:
                 # Return the full text, because this is what the HuggingFacePipeline expects.
                 model=model, tokenizer=tokenizer, return_full_text=True, task="text-generation", max_new_tokens=model_n_ctx))#, max_new_tokens=model_n_ctx
                 #))
-    case "GPT4All":
-        llm = GPT4All(model=model_path, n_ctx=model_n_ctx, backend='gptj', callbacks=callbacks, verbose=False)
+    # case "GPT4All":
+    #     llm = GPT4All(model=model_path, n_ctx=model_n_ctx, backend='gptj', callbacks=callbacks, verbose=False)
     case _default:
         print(f"Model {model_type} not supported!")
         exit;