RAG_using_Llama3.py.py

# -*- coding: utf-8 -*-
"""RAG_using_Llama3.ipynb

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/drive/1b-ZDo3QQ-axgm804UlHu3ohZwnoXz5L1

# install dependecies
"""

!pip install -q datasets sentence-transformers faiss-cpu accelerate

from huggingface_hub import notebook_login
notebook_login()

"""# embed dataset

this is a slow procedure so you might consider saving your results
"""

from datasets import load_dataset

dataset = load_dataset("KarthikaRajagopal/wikipedia-2")

dataset

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

# embed the dataset
def embed(batch):
  # or you can combine multiple columns here, for example the title and the text
  information = batch["text"]
  return {"embeddings" : ST.encode(information)}
dataset = dataset.map(embed,batched=True,batch_size=16)

!pip install datasets

from datasets import load_dataset

dataset = load_dataset("KarthikaRajagopal/wikipedia-2",revision = "embedded")

# Push it to your Hugging Face repository
dataset.push_to_hub("KarthikaRajagopal/wikipedia-2", revision="embedded")

from datasets import load_dataset

dataset = load_dataset("KarthikaRajagopal/wikipedia-2",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

scores , result = search("anarchy", 4 ) # search for word anarchy and get the best 4 matching values from the dataset

# the lower the better
scores

result['title']

print(result["text"][0])

"""# chatbot on top of the retrieved results"""

!pip install -q datasets sentence-transformers faiss-cpu accelerate bitsandbytes

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

from datasets import load_dataset

dataset = load_dataset("KarthikaRajagopal/wikipedia-2",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

from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
import torch

model_id = "meta-llama/Meta-Llama-3-8B-Instruct"

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:"
  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)

rag_chatbot("what's anarchy ?", k = 2)