Spaces:
Runtime error
Runtime error
File size: 6,318 Bytes
d7831dc |
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 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 |
import urllib.request
import fitz
import re
import numpy as np
import tensorflow_hub as hub
from transformers import AutoModelForCausalLM, AutoTokenizer
import gradio as gr
import os
from sklearn.neighbors import NearestNeighbors
tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-40b-instruct")
model = AutoModelForCausalLM.from_pretrained("tiiuae/falcon-40b-instruct")
def download_pdf(url, output_path):
urllib.request.urlretrieve(url, output_path)
def preprocess(text):
text = text.replace('\n', ' ')
text = re.sub('\s+', ' ', text)
return text
def pdf_to_text(path, start_page=1, end_page=None):
doc = fitz.open(path)
total_pages = doc.page_count
if end_page is None:
end_page = total_pages
text_list = []
for i in range(start_page-1, end_page):
text = doc.load_page(i).get_text("text")
text = preprocess(text)
text_list.append(text)
doc.close()
return text_list
def text_to_chunks(texts, word_length=150, start_page=1):
text_toks = [t.split(' ') for t in texts]
page_nums = []
chunks = []
for idx, words in enumerate(text_toks):
for i in range(0, len(words), word_length):
chunk = words[i:i+word_length]
if (i+word_length) > len(words) and (len(chunk) < word_length) and (
len(text_toks) != (idx+1)):
text_toks[idx+1] = chunk + text_toks[idx+1]
continue
chunk = ' '.join(chunk).strip()
chunk = f'[Page no. {idx+start_page}]' + ' ' + '"' + chunk + '"'
chunks.append(chunk)
return chunks
class SemanticSearch:
def __init__(self):
self.use = hub.load('https://tfhub.dev/google/universal-sentence-encoder/4')
self.fitted = False
def fit(self, data, batch=1000, n_neighbors=5):
self.data = data
self.embeddings = self.get_text_embedding(data, batch=batch)
n_neighbors = min(n_neighbors, len(self.embeddings))
self.nn = NearestNeighbors(n_neighbors=n_neighbors)
self.nn.fit(self.embeddings)
self.fitted = True
def __call__(self, text, return_data=True):
inp_emb = self.use([text])
neighbors = self.nn.kneighbors(inp_emb, return_distance=False)[0]
if return_data:
return [self.data[i] for i in neighbors]
else:
return neighbors
def get_text_embedding(self, texts, batch=1000):
embeddings = []
for i in range(0, len(texts), batch):
text_batch = texts[i:(i+batch)]
emb_batch = self.use(text_batch)
embeddings.append(emb_batch)
embeddings = np.vstack(embeddings)
return embeddings
def load_recommender(path, start_page=1):
global recommender
texts = pdf_to_text(path, start_page=start_page)
chunks = text_to_chunks(texts, start_page=start_page)
recommender.fit(chunks)
return 'Corpus Loaded.'
def generate_text(prompt, max_length=512):
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_length=max_length)
message = tokenizer.decode(outputs[0])
return message
def generate_answer(question):
topn_chunks = recommender(question)
prompt = ""
prompt += 'search results:\n\n'
for c in topn_chunks:
prompt += c + '\n\n'
prompt += "Instructions: Compose a comprehensive reply to the query using the search results given. "\
"Cite each reference using [ Page Number] notation (every result has this number at the beginning). "\
"Citation should be done at the end of each sentence. If the search results mention multiple subjects "\
"with the same name, create separate answers for each. Only include information found in the results and "\
"don't add any additional information. Make sure the answer is correct and don't output false content. "\
"If the text does not relate to the query, simply state 'Found Nothing'. Ignore outlier "\
"search results which has nothing to do with the question. Only answer what is asked. The "\
"answer should be short and concise. \n\nQuery: {question}\nAnswer: "
prompt += f"Query: {question}\nAnswer:"
answer = generate_text(prompt)
return answer
def question_answer(url, file, question):
if url.strip() == '' and file == None:
return '[ERROR]: Both URL and PDF is empty. Provide at least one.'
if url.strip() != '' and file != None:
return '[ERROR]: Both URL and PDF is provided. Please provide only one (either URL or PDF).'
if url.strip() != '':
glob_url = url
download_pdf(glob_url, 'corpus.pdf')
load_recommender('corpus.pdf')
else:
old_file_name = file.name
file_name = file.name
file_name = file_name[:-12] + file_name[-4:]
os.rename(old_file_name, file_name)
load_recommender(file_name)
if question.strip() == '':
return '[ERROR]: Question field is empty'
return generate_answer(question)
recommender = SemanticSearch()
title = 'PDF GPT'
description = """ PDF GPT allows you to chat with your PDF file using Universal Sentence Encoder and Falcon. It gives hallucination free response than other tools as the embeddings are better than OpenAI. The returned response can even cite the page number in square brackets([]) where the information is located, adding credibility to the responses and helping to locate pertinent information quickly."""
with gr.Blocks() as demo:
gr.Markdown(f'<center><h1>{title}</h1></center>')
gr.Markdown(description)
with gr.Row():
with gr.Group():
url = gr.Textbox(label='Enter PDF URL here')
gr.Markdown("<center><h4>OR<h4></center>")
file = gr.File(label='Upload your PDF/ Research Paper / Book here', file_types=['.pdf'])
question = gr.Textbox(label='Enter your question here')
btn = gr.Button(value='Submit')
btn.style(full_width=True)
with gr.Group():
answer = gr.Textbox(label='The answer to your question is :')
btn.click(question_answer, inputs=[url, file, question], outputs=[answer])
demo.launch()
|