Update app.py

app.py

@@ -38,19 +38,70 @@ retriever = vectordb.as_retriever()
 #    retriever=vectordb.as_retriever()
 #)
 
-from langchain_community.output_parsers.rail_parser import GuardrailsOutputParser
+from transformers import pipeline
+from transformers import AutoTokenizer, BitsAndBytesConfig
+
+READER_MODEL = "HuggingFaceH4/zephyr-7b-beta"
+bnb_config = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16)
+model = AutoModelForCausalLM.from_pretrained(READER_MODEL, quantization_config=bnb_config)
+tokenizer = AutoTokenizer.from_pretrained(READER_MODEL)
+
+from langchain.llms import HuggingFacePipeline
 from langchain.prompts import PromptTemplate
+from transformers import pipeline
+from langchain_core.output_parsers import StrOutputParser
+
+
+text_generation_pipeline = pipeline(
+    model=model,
+    tokenizer=tokenizer,
+    task="text-generation",
+    temperature=0.2,
+    do_sample=True,
+    repetition_penalty=1.1,
+    return_full_text=True,
+    max_new_tokens=100,
+)
+
+llm = HuggingFacePipeline(pipeline=text_generation_pipeline)
+
 
-template = """Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer. Use three sentences maximum. Keep the answer as concise as possible. Always say "thanks for asking!" at the end of the answer. 
-{You are a helpful dietician}
-Question: {question}
-Helpful Answer:"""
+#from langchain_community.output_parsers.rail_parser import GuardrailsOutputParser
+
+prompt_template = """
+<|system|>
+Answer the question based on your knowledge. Use the following context to help:
+
+{context}
+
+</s>
+<|user|>
+{question}
+</s>
+<|assistant|>
+
+ """
+
+QA_CHAIN_PROMPT = PromptTemplate(
+    input_variables=["context", "question"],
+    template=prompt_template,
+)
 
-QA_CHAIN_PROMPT = PromptTemplate.from_template(template)
 
-from langchain.chains import ConversationalRetrievalChain
-from langchain.memory import ConversationBufferMemory
-memory = ConversationBufferMemory(
+llm_chain = QA_CHAIN_PROMPT | llm | StrOutputParser()
+
+
+from langchain_core.runnables import RunnablePassthrough
+
+
+retriever=vectordb.as_retriever()
+
+rag_chain = {"context": retriever, "question": RunnablePassthrough()} | llm_chain
+
+
+#from langchain.chains import ConversationalRetrievalChain
+#from langchain.memory import ConversationBufferMemory
+#memory = ConversationBufferMemory(
     memory_key="chat_history",
     return_messages=True
 )
@@ -58,13 +109,10 @@ memory = ConversationBufferMemory(
 question = "Can I reverse Diabetes?"
 print("template")
 
-
-retriever=vectordb.as_retriever()
-READER_MODEL = "HuggingFaceH4/zephyr-7b-beta"
-qa = ConversationalRetrievalChain.from_llm(llm=READER_MODEL,retriever=retriever,memory=memory)
+#qa = ConversationalRetrievalChain.from_llm(llm=READER_MODEL,retriever=retriever,memory=memory)
 
 import gradio as gr
 gr.load("READER_MODEL").launch()
 
 #result = ({"query": question})
-print("qa")
+#print("qa")