Update app.py

app.py

@@ -1,5 +1,6 @@
 from sentence_transformers import SentenceTransformer
 from datasets import load_dataset
+import gradio as gr
 
 ST = SentenceTransformer("mixedbread-ai/mxbai-embed-large-v1")
 
@@ -17,31 +18,6 @@ def search(query: str, k: int = 3 ):
     )
     return scores, retrieved_examples
 
-from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
-import torch
-
-model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
-
-# use quantization to lower GPU usage
-bnb_config = BitsAndBytesConfig(
-    load_in_4bit=True, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16
-)
-
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(
-    model_id,
-    torch_dtype=torch.bfloat16,
-    device_map="auto",
-    quantization_config=bnb_config
-)
-terminators = [
-    tokenizer.eos_token_id,
-    tokenizer.convert_tokens_to_ids("<|eot_id|>")
-]
-SYS_PROMPT = """You are an assistant for answering questions.
-You are given the extracted parts of a long document and a question. Provide a conversational answer.
-If you don't know the answer, just say "I do not know." Don't make up an answer."""
-
 def format_prompt(prompt,retrieved_documents,k):
   """using the retrieved documents we will prompt the model to generate our responses"""
   PROMPT = f"Question:{prompt}\nContext:"
@@ -74,4 +50,34 @@ def rag_chatbot(prompt:str,k:int=2):
   formatted_prompt = format_prompt(prompt,retrieved_documents,k)
   return generate(formatted_prompt)
 
-rag_chatbot("what's anarchy ?", k = 2)
+def rag_chatbot_interface(prompt:str,k:int=2):
+  scores , retrieved_documents = search(prompt, k)
+  formatted_prompt = format_prompt(prompt,retrieved_documents,k)
+  return generate(formatted_prompt)
+
+SYS_PROMPT = """You are an assistant for answering questions.
+You are given the extracted parts of a long document and a question. Provide a conversational answer.
+If you don't know the answer, just say "I do not know." Don't make up an answer."""
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+    quantization_config=bnb_config
+)
+terminators = [
+    tokenizer.eos_token_id,
+    tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
+
+iface = gr.Interface(fn=rag_chatbot_interface, 
+                     inputs="text", 
+                     outputs="text",
+                     input_types=["text"],
+                     output_types=["text"],
+                     title="Retrieval-Augmented Generation Chatbot",
+                     description="This is a chatbot that uses a retrieval-augmented generation approach to provide more accurate answers. It first searches for relevant documents and then generates a response based on the prompt and the retrieved documents."
+                    )
+
+iface.launch()