Update app.py

app.py

@@ -1,16 +1,18 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-from transformers import RagRetriever, RagTokenizer, RagTokenForValueState
+from transformers import pipeline, RagRetriever, RagTokenizer
 
 """
 For more information on huggingface_hub Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
-# Load the RAG tokenizer, retriever, and model
+# Load the RAG tokenizer and retriever
 tokenizer = RagTokenizer.from_pretrained("deepset/roberta-base-squad2")
-retriever = RagRetriever.from_pretrained("deepset/roberta-base-squad2", index_name="apexcustoms", passages="apexcustoms.pdf")
-model = RagTokenForValueState.from_pretrained("deepset/roberta-base-squad2")
+retriever = RagRetriever.from_pretrained("deepset/roberta-base-squad2", index_name="apexcustoms", passages="apexcustoms.pdf", trust_remote_code=True)
+
+# Load the question-answering pipeline
+qa_pipeline = pipeline("question-answering", model="deepset/roberta-base-squad2", tokenizer=tokenizer)
 
 def respond(
     message,
@@ -40,7 +42,7 @@ def respond(
         top_p=top_p,
         rag_retriever=retriever,  # Pass the RAG retriever
         rag_tokenizer=tokenizer,  # Pass the RAG tokenizer
-        rag_model=model,  # Pass the RAG model
+        rag_pipeline=qa_pipeline,  # Pass the question-answering pipeline
     ):
         token = message.choices[0].delta.content