import urllib.request import fitz import re import numpy as np import tensorflow_hub as hub import openai import gradio as gr import os import dotenv from sklearn.neighbors import NearestNeighbors 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(openAI_key, prompt, engine="text-davinci-003"): openai.api_key = openAI_key completions = openai.Completion.create( engine=engine, prompt=prompt, max_tokens=512, n=1, stop=None, temperature=1, ) message = completions.choices[0].text return message def generate_answer(question, openAI_key): 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 'Text Not Found in PDF'."\ "Ignore outlier search results which have nothing to do with the question."\ "Only answer what is asked."\ "The answer should be short and concise."\ "Answer step-by-step."\ "To answer the query, please follow these instructions:"\ "Please carefully read through the search results provided and compose a clear and concise response."\ "When citing information from the search results, please include the page number in square brackets after the relevant text."\ "If the search results mention multiple subjects with the same name, create separate answers for each."\ "Only include information found in the search results and avoid adding any additional information."\ "Be sure that your response is accurate and does not contain any false content."\ "If the query cannot be answered using the provided search results, please state [Text Not Found in PDF.]"\ "Please disregard any irrelevant search results and only include information that directly answers the question."\ "Your response should be step-by-step and easy to understand."\ "Good luck!" prompt += f"Query: {question}\nAnswer:" answer = generate_text(openAI_key, prompt, "text-davinci-003") return answer def question_answer(url, file, question, openAI_key): openAI_key = os.environ.get('OPENAI_KEY') if url.strip() == '' and file == None: return '[ERROR]: Both URL and PDF is empty. Provide atleast one.' if url.strip() != '' and file != None: return '[ERROR]: Both URL and PDF is provided. Please provide only one (eiter 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:] # Rename the file os.rename(old_file_name, file_name) load_recommender(file_name) # Delete the existing file if it exists if os.path.exists(file_name): os.remove(file_name) if question.strip() == '': return '[ERROR]: Question field is empty' return generate_answer(question, openAI_key) recommender = SemanticSearch() title = 'ChatToFiles' description = """ ChatToFiles is a cutting-edge tool that facilitates conversation with PDF files utilizing Universal Sentence Encoder and Open AI technology. This tool is particularly advantageous as it delivers more reliable responses than other comparable tools, thanks to its superior embeddings, which eliminate hallucination errors. Additionally, when providing answers, PDF GPT can cite the exact page number where the relevant information is located within the PDF file, which enhances the credibility of the responses and expedites the process of finding pertinent information.""" with gr.Blocks() as iface: gr.Markdown(f'

{title}

') gr.Markdown(description) with gr.Row(): with gr.Group(): url = gr.Textbox(label='Enter PDF URL here', placeholder='https://docs.pdf') gr.Markdown( "

----------------------------------------------------------------------------------------------------------------------------------------------------

") file = gr.File(label='Drop PDF here', file_types=['*']) question = gr.Textbox( label='Enter your question here', placeholder='Type 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 :', lines=5, placeholder='Your answer here...') btn.click(question_answer, inputs=[ url, file, question], outputs=[answer]) # openai.api_key = os.getenv('Your_Key_Here') dotenv.load_dotenv() iface.launch() # iface.launch(share=True)