Update app.py

app.py

@@ -15,6 +15,14 @@ from langchain.prompts import PromptTemplate
 from langchain.vectorstores import Qdrant
 from PyPDF2 import PdfReader
 import streamlit as st
+# Use a pipeline as a high-level helper
+from transformers import pipeline
+
+pipe = pipeline("text-generation", model="TheBloke/Llama-2-7B-Chat-GGML")
+
+# Load model directly
+from transformers import AutoModel
+model = AutoModel.from_pretrained("TheBloke/Llama-2-7B-Chat-GGML")
 
 PROMPT_TEMPLATE = """
 Use the following pieces of context enclosed by triple backquotes to answer the question at the end.
@@ -114,7 +122,7 @@ def load_llm(model_name: str, temperature: float) -> Union[ChatOpenAI, LlamaCpp]
     elif model_name.startswith("llama-2-"):
         callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
         
-        return LlamaCpp(
+        '''return LlamaCpp(
             model_path=f"./models/{model_name}.bin",
             input={"temperature": temperature,
                    "max_length": 2048,
@@ -123,7 +131,8 @@ def load_llm(model_name: str, temperature: float) -> Union[ChatOpenAI, LlamaCpp]
             n_ctx=2048,
             callback_manager=callback_manager,
             verbose=False,  # True
-        )
+        )'''
+        return model
 
 
 def load_embeddings(model_name: str) -> Union[OpenAIEmbeddings, LlamaCppEmbeddings]: