Update app.py

app.py

@@ -8,6 +8,7 @@ import gradio as gr
 import os
 from sklearn.neighbors import NearestNeighbors
 
+
 def download_pdf(url, output_path):
     urllib.request.urlretrieve(url, output_path)
 
@@ -40,12 +41,12 @@ 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)):
+                    len(text_toks) != (idx+1)):
                 text_toks[idx+1] = chunk + text_toks[idx+1]
                 continue
             chunk = ' '.join(chunk).strip()
@@ -53,13 +54,14 @@ def text_to_chunks(texts, word_length=150, start_page=1):
             chunks.append(chunk)
     return chunks
 
+
 class SemanticSearch:
-    
+
     def __init__(self):
-        self.use = hub.load('https://tfhub.dev/google/universal-sentence-encoder/4')
+        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)
@@ -67,18 +69,16 @@ class SemanticSearch:
         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):
@@ -89,7 +89,6 @@ class SemanticSearch:
         return embeddings
 
 
-
 def load_recommender(path, start_page=1):
     global recommender
     texts = pdf_to_text(path, start_page=start_page)
@@ -97,7 +96,8 @@ def load_recommender(path, start_page=1):
     recommender.fit(chunks)
     return 'Corpus Loaded.'
 
-def generate_text(openAI_key,prompt, engine="text-davinci-003"):
+
+def generate_text(openAI_key, prompt, engine="text-davinci-003"):
     openai.api_key = openAI_key
     completions = openai.Completion.create(
         engine=engine,
@@ -110,13 +110,14 @@ def generate_text(openAI_key,prompt, engine="text-davinci-003"):
     message = completions.choices[0].text
     return message
 
-def generate_answer(question,openAI_key):
+
+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 "\
@@ -126,18 +127,18 @@ def generate_answer(question,openAI_key):
               "search results which has nothing to do with the question. Only answer what is asked. The "\
               "answer should be short and concise. Answer step-by-step. \n\nQuery: {question}\nAnswer: "\
               "if you are asked to make questions from the pdf that you are provided with, kindly make it according to the question"
-    
+
     prompt += f"Query: {question}\nAnswer:"
-    answer = generate_text(openAI_key, prompt,"text-davinci-003")
+    answer = generate_text(openAI_key, prompt, "text-davinci-003")
     return answer
 
 
-def question_answer(url, file, question,openAI_key):
-    if openAI_key.strip()=='':
+def question_answer(url, file, question, openAI_key):
+    if openAI_key.strip() == '':
         return '[ERROR]: Please enter you Open AI Key. Get your key here : https://platform.openai.com/account/api-keys'
     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).'
 
@@ -150,7 +151,7 @@ def question_answer(url, file, question,openAI_key):
         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)
@@ -159,17 +160,16 @@ def question_answer(url, file, question,openAI_key):
         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)
+    return generate_answer(question, openAI_key)
 
 
 recommender = SemanticSearch()
 
 title = 'ChatToFiles'
-description = """ PDF GPT 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."""
+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:
 
@@ -177,20 +177,24 @@ with gr.Blocks() as iface:
     gr.Markdown(description)
 
     with gr.Row():
-        
+
         with gr.Group():
-            openAI_key=gr.Textbox(label='Enter your OpenAI API key here')
-            url = gr.Textbox(label='Enter PDF URL here')
-            gr.Markdown("<center><h4>OR<h4></center>")
+            openAI_key = gr.Textbox(label='Enter your OpenAI API key here', placeholder='sk-')
+            url = gr.Textbox(label='Enter PDF URL here', placeholder='https://docs.pdf')
+            gr.Markdown(
+                "<center><h4>----------------------------------------------------------------------------------------------------------------------------------------------------<h4></center>")
             file = gr.File(label='Drop PDF here', file_types=['.pdf'])
-            question = gr.Textbox(label='Enter your question here')
+            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='Type your answer here...')
-
-        btn.click(question_answer, inputs=[url, file, question,openAI_key], outputs=[answer])
-#openai.api_key = os.getenv('Your_Key_Here') 
-#iface.launch()
-iface.launch()
+                answer = gr.Textbox(label='The answer to your question is :',
+                                    lines=5, placeholder='Your answer here...')
+
+        btn.click(question_answer, inputs=[
+                  url, file, question, openAI_key], outputs=[answer])
+# openai.api_key = os.getenv('Your_Key_Here')
+iface.launch()
+# iface.launch(share=True)