Update app.py

app.py

@@ -30,9 +30,6 @@ vectordb = Chroma.from_documents(
 
 retriever = vectordb.as_retriever()
 
-import gradio as gr
-gr.load("models/HuggingFaceH4/zephyr-7b-beta").launch()
-
 #docs_ss = vectordb.similarity_search(question,k=3)
 
 
@@ -51,10 +48,6 @@ Helpful Answer:"""
 QA_CHAIN_PROMPT = PromptTemplate.from_template(template)
 
 
-from langchain.chains import ConversationalRetrievalChain
-#qa_chain = RetrievalQA.from_chain_type(models/HuggingFaceH4/zephyr-7b-beta,retriever=vectordb.as_retriever(),chain_type_kwargs={"prompt": QA_CHAIN_PROMPT})
-
-
 from langchain.memory import ConversationBufferMemory
 memory = ConversationBufferMemory(
     memory_key="chat_history",
@@ -64,9 +57,14 @@ memory = ConversationBufferMemory(
 question = "Can I reverse Diabetes?"
 print("template")
 
+from langchain.chains import ConversationalRetrievalChain
+
 retriever=vectordb.as_retriever()
 READER_MODEL = "HuggingFaceH4/zephyr-7b-beta"
 qa = ConversationalRetrievalChain.from_llm(llm=READER_MODEL,retriever=retriever,memory=memory,chain_type_kwargs={"prompt": QA_CHAIN_PROMPT})
 
+import gradio as gr
+gr.load("READER_MODEL").launch()
+
 #result = ({"query": question})
 print("qa")