File size: 2,413 Bytes
732421a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import os
from langchain.vectorstores import FAISS
from langchain.document_loaders import PyPDFLoader
from langchain.chains.question_answering import load_qa_chain
from langchain.prompts import PromptTemplate
from langchain.memory import ConversationBufferMemory
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.chains import RetrievalQA
from langchain.document_loaders import UnstructuredFileLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.chains import RetrievalQAWithSourcesChain
from huggingface_hub import notebook_login
from transformers import pipeline
from transformers import AutoTokenizer, AutoModelForCausalLM
from langchain import HuggingFacePipeline
from langchain.text_splitter import CharacterTextSplitter
import textwrap
import sys
import os


os.environ['HuggingFaceHub_API_Token']= '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'
loader = UnstructuredFileLoader('./Highway Traffic Act, R.S.O. 1990, c. H.8[465] - Copy.pdf')
documents = loader.load()

text_splitter=CharacterTextSplitter(separator='\n',
                                    chunk_size=1000,
                                    chunk_overlap=50)
text_chunks=text_splitter.split_documents(documents)

embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2',model_kwargs={'device': 'cuda'})

vectorstore=FAISS.from_documents(text_chunks, embeddings)





from huggingface_hub import notebook_login

notebook_login()

import torch
os.environ['HuggingFaceHub_API_Token']= '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'
tokenizer = AutoTokenizer.from_pretrained("daryl149/llama-2-7b-chat-hf")

model = AutoModelForCausalLM.from_pretrained("daryl149/llama-2-7b-chat-hf", device_map='auto',torch_dtype=torch.float16,load_in_8bit=True, token=True )
pipe = pipeline("text-generation",model=model,tokenizer= tokenizer,torch_dtype=torch.bfloat16,device_map="auto",max_new_tokens = 1024,do_sample=True,top_k=10,num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)

llm=HuggingFacePipeline(pipeline=pipe, model_kwargs={'temperature':0})
chain =  RetrievalQA.from_chain_type(llm=llm, chain_type = "stuff",return_source_documents=True, retriever=vectorstore.as_retriever())

query = "What  happens when we drive under influence ?"
result=chain({"query": query}, return_only_outputs=True)
wrapped_text = textwrap.fill(result['result'], width=500)
wrapped_text