File size: 3,230 Bytes
953debe
 
2829eb5
953debe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2829eb5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
from sentence_transformers import SentenceTransformer
from datasets import load_dataset
import gradio as gr

ST = SentenceTransformer("mixedbread-ai/mxbai-embed-large-v1")

dataset = load_dataset("not-lain/wikipedia",revision = "embedded")

data = dataset["train"]
data = data.add_faiss_index("embeddings") # column name that has the embeddings of the dataset

def search(query: str, k: int = 3 ):
    """a function that embeds a new query and returns the most probable results"""
    embedded_query = ST.encode(query) # embed new query
    scores, retrieved_examples = data.get_nearest_examples( # retrieve results
        "embeddings", embedded_query, # compare our new embedded query with the dataset embeddings
        k=k # get only top k results
    )
    return scores, retrieved_examples

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:"
  for idx in range(k) :
    PROMPT+= f"{retrieved_documents['text'][idx]}\n"
  return PROMPT

def generate(formatted_prompt):
  formatted_prompt = formatted_prompt[:2000] # to avoid GPU OOM
  messages = [{"role":"system","content":SYS_PROMPT},{"role":"user","content":formatted_prompt}]
  # tell the model to generate
  input_ids = tokenizer.apply_chat_template(
      messages,
      add_generation_prompt=True,
      return_tensors="pt"
  ).to(model.device)
  outputs = model.generate(
      input_ids,
      max_new_tokens=1024,
      eos_token_id=terminators,
      do_sample=True,
      temperature=0.6,
      top_p=0.9,
  )
  response = outputs[0][input_ids.shape[-1]:]
  return tokenizer.decode(response, skip_special_tokens=True)

def rag_chatbot(prompt:str,k:int=2):
  scores , retrieved_documents = search(prompt, k)
  formatted_prompt = format_prompt(prompt,retrieved_documents,k)
  return generate(formatted_prompt)

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()