Create app.py

app.py

@@ -0,0 +1,211 @@
+import urllib.request
+import fitz
+import re
+import numpy as np
+import tensorflow_hub as hub
+import openai
+#import gradio as gr
+import os
+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'[{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
+openai.api_key = "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"
+recommender = SemanticSearch()
+
+
+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, engine="text-davinci-003"):
+    completions = openai.Completion.create(
+        engine=engine,
+        prompt=prompt,
+        max_tokens=512,
+        n=1,
+        stop=None,
+        temperature=0.7,
+    )
+    message = completions.choices[0].text
+    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 [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 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:]
+        os.rename(old_file_name, file_name)
+        load_recommender(file_name)
+
+    if question.strip() == '':
+        return '[ERROR]: Question field is empty'
+
+    return generate_answer(question)
+
+
+title = 'pdfGPT'
+description = "pdfGPT allows you to input a full pdf file and ask questions about its contents. pdfGPT has ability to cite and refer to the specific page number from where the information was found. This adds credibility to the answers generated also helps you locate the relevant information in the pdf document."
+
+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='URL')
+            gr.Markdown("<center><h6>or<h6></center>")
+            file = gr.File(label='PDF', file_types=['.pdf'])
+            question = gr.Textbox(label='question')
+            btn = gr.Button(value='Submit')
+            btn.style(full_width=True)
+
+        with gr.Group():
+            answer = gr.Textbox(label='answer')
+
+        btn.click(question_answer, inputs=[url, file, question], outputs=[answer])
+
+demo.launch(share=True)
+
+# import streamlit as st
+
+# #Define the app layout
+# st.markdown(f'<center><h1>{title}</h1></center>', unsafe_allow_html=True)
+# st.markdown(description)
+
+# col1, col2 = st.columns(2)
+
+# # Define the inputs in the first column
+# with col1:
+#     url = st.text_input('URL')
+#     st.markdown("<center><h6>or<h6></center>", unsafe_allow_html=True)
+#     file = st.file_uploader('PDF', type='pdf')
+#     question = st.text_input('question')
+#     btn = st.button('Submit')
+
+# # Define the output in the second column
+# with col2:
+#     answer = st.text_input('answer')
+
+# # Define the button action
+# if btn:
+#     answer_value = question_answer(url, file, question)
+#     answer.value = answer_value