Update app.py

app.py

@@ -56,25 +56,12 @@ retriever = vectordb.as_retriever(
     search_type="similarity", search_kwargs={"k": 2}
 )
 
-#from langchain.chains import RetrievalQA
-from langchain_core.prompts import ChatPromptTemplate
 
-from langchain.chains.combine_documents import create_stuff_documents_chain
-#from langchain import hub
-from langchain.chains import create_retrieval_chain
+from transformers import pipeline
 
-#from langchain_community.llms import Ollama
-#READER_MODEL=Ollama(model="meta-llama/Meta-Llama-Guard-2-8B")
+llm_model = "HuggingFaceH4/zephyr-7b-beta"
+pipe = pipeline(task="text-generation",llm_model,retriever = retriever)
 
-from transformers import AutoModelForSeq2SeqLM, BitsAndBytesConfig
-lll_model = AutoModelForSeq2SeqLM.from_pretrained("unsloth/llama-3-8b-bnb-4bit",low_cpu_mem_usage=True,max_shard_size="1GB")
-
-#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)
-
-#retrieval_qa_chat_prompt = hub.pull("langchain-ai/retrieval-qa-chat")
 from langchain_core.messages import SystemMessage
 from langchain_core.prompts import HumanMessagePromptTemplate
 
@@ -89,17 +76,7 @@ qa_chat_prompt = ChatPromptTemplate.from_messages(
     ]
 )
 
-docs_chain = create_stuff_documents_chain(
-    lll_model, qa_chat_prompt
-)
-retrieval_chain = create_retrieval_chain(retriever, docs_chain)
-response = retrieval_chain.invoke({"context": "how can I reverse diabetes?"})
-print(response["answer"])
-
-
-#result = qa(question)
-#import gradio as gr
-#gr.load("lll_model").launch()
+chain = qa_chat_prompt | pipe
 
-#result = ({"query": question})
-#print("qa")
+import gradio as gr
+gr.load("lll_model").launch()