Update app.py

app.py

@@ -66,9 +66,10 @@ from langchain.chains import create_retrieval_chain
 #from langchain_community.llms import Ollama
 #READER_MODEL=Ollama(model="meta-llama/Meta-Llama-Guard-2-8B")
 
+from transformers import AutoModel
+lll_model = AutoModel.from_pretrained(""HuggingFaceH4/zephyr-7b-beta")
 
-READER_MODEL = "HuggingFaceH4/zephyr-7b-beta"
-#READER_MODEL=ChatMistralAI(model=""HuggingFaceH4/zephyr-7b-beta")
+#READER_MODEL = "HuggingFaceH4/zephyr-7b-beta"
 
 #qa = ConversationalRetrievalChain.from_llm(llm=READER_MODEL,retriever=retriever,memory=memory)
 #qa = RetrievalQA.from_chain_type(llm=READER_MODEL,retriever=retriever)
@@ -89,7 +90,7 @@ qa_chat_prompt = ChatPromptTemplate.from_messages(
 )
 
 docs_chain = create_stuff_documents_chain(
-    READER_MODEL, qa_chat_prompt
+    lll_model, qa_chat_prompt
 )
 retrieval_chain = create_retrieval_chain(retriever, docs_chain)
 response = retrieval_chain.invoke({"context": "how can I reverse diabetes?"})
@@ -98,7 +99,7 @@ print(response["answer"])
 
 #result = qa(question)
 #import gradio as gr
-#gr.load("READER_MODEL").launch()
+#gr.load("lll_model").launch()
 
 #result = ({"query": question})
 #print("qa")