Update app.py

app.py

@@ -24,10 +24,6 @@ def pdf_to_text(path, start_page=1, end_page=None):
 
     if end_page is None:
         end_page = total_pages
-    else:
-        end_page = int(end_page)
-
-    start_page = int(start_page)
 
     text_list = []
 
@@ -40,7 +36,6 @@ def pdf_to_text(path, start_page=1, end_page=None):
     return text_list
 
 
-
 def text_to_chunks(texts, word_length=150, start_page=1):
     text_toks = [t.split(' ') for t in texts]
     page_nums = []
@@ -96,40 +91,13 @@ class 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.'
-
-# The modified function generates embeddings based on PDF file name and page number and checks if the embeddings file exists before loading or generating it.	
-def load_recommender(path, start_page=1, end_page=None):
+def load_recommender(path, start_page=1):
     global recommender
-    pdf_file = os.path.basename(path)
-    embeddings_file = f"{pdf_file}_{start_page}.npy"
-    
-    if os.path.isfile(embeddings_file):
-        embeddings = np.load(embeddings_file)
-        recommender.embeddings = embeddings
-        recommender.fitted = True
-        return "Embeddings loaded from file"
-    
-    if start_page:
-        start_page = int(start_page)
-    if end_page:
-        end_page = int(end_page)
-    
-    texts = pdf_to_text(path, start_page=start_page, end_page=end_page)
+    texts = pdf_to_text(path, start_page=start_page)
     chunks = text_to_chunks(texts, start_page=start_page)
     recommender.fit(chunks)
-    np.save(embeddings_file, recommender.embeddings)
     return 'Corpus Loaded.'
 
-
-
-
-
 def generate_text(openAI_key,prompt, engine="text-davinci-003"):
     openai.api_key = openAI_key
     completions = openai.Completion.create(
@@ -142,22 +110,6 @@ def generate_text(openAI_key,prompt, engine="text-davinci-003"):
     )
     message = completions.choices[0].text
     return message
-    
-def generate_text2(openAI_key, prompt, engine="gpt-3.5-turbo-0301"):
-    openai.api_key = openAI_key
-    messages = [{'role': 'system', 'content': 'You are a helpful assistant.'},
-                {'role': 'user', 'content': prompt}]
-    
-    completions = openai.ChatCompletion.create(
-        model=engine,
-        messages=messages,
-        max_tokens=512,
-        n=1,
-        stop=None,
-        temperature=0.7,
-    )
-    message = completions.choices[0].message['content']
-    return message
 
 def generate_answer(question,openAI_key):
     topn_chunks = recommender(question)
@@ -180,58 +132,68 @@ def generate_answer(question,openAI_key):
     return answer
 
 
-def question_answer(url, file, question, openAI_key, start_page, end_page):
+def question_answer(url, file, question, openAI_key, history=[]):
     if openAI_key.strip() == '':
-        return '[ERROR]: Please enter your 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 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).'
+        return '[ERROR]: Please enter your Open AI Key. Get your key here: https://platform.openai.com/account/api-keys'
+
+    if url.strip() == '' and file is None:
+        return '[ERROR]: Both URL and PDF are empty. Provide at least one.'
+
+    if url.strip() != '' and file is not None:
+        return '[ERROR]: Both URL and PDF are 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', start_page=start_page, end_page=end_page)
+        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, start_page=start_page, end_page=end_page)
+        load_recommender(file_name)
 
     if question.strip() == '':
         return '[ERROR]: Question field is empty'
 
-    return generate_answer(question, openAI_key)
+    answer = generate_answer(question, openAI_key)
+    history.append({'question': question, 'answer': answer})
+    return answer
+
 
 
 recommender = SemanticSearch()
 
 title = 'PDF GPT'
-description = """ What is PDF GPT ?
-1. The problem is that Open AI has a 4K token limit and cannot take an entire PDF file as input. Additionally, it sometimes returns irrelevant responses due to poor embeddings. ChatGPT cannot directly talk to external data. The solution is PDF GPT, which allows you to chat with an uploaded PDF file using GPT functionalities. The application breaks the document into smaller chunks and generates embeddings using a powerful Deep Averaging Network Encoder. A semantic search is performed on your query, and the top relevant chunks are used to generate a response.
-2. 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. The Responses are much better than the naive responses by Open AI."""
+description = """ PDF GPT allows you to chat with your PDF file using Universal Sentence Encoder and Open AI. 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."""
+history = []
 
 with gr.Blocks() as demo:
 
     gr.Markdown(f'<center><h1>{title}</h1></center>')
     gr.Markdown(description)
+
     with gr.Row():
+        
         with gr.Group():
             gr.Markdown(f'<p style="text-align:center">Get your Open AI API key <a href="https://platform.openai.com/account/api-keys">here</a></p>')
-            openAI_key = gr.Textbox(label='Enter your OpenAI API key here')
+            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>")
             file = gr.File(label='Upload your PDF/ Research Paper / Book here', file_types=['.pdf'])
             question = gr.Textbox(label='Enter your question here')
-            start_page = gr.Number(label='Start on page (default: 1)', default=1, min_value=1)
-            end_page = gr.Number(label='End on page (default: last page)', default=None, min_value=1, allow_none=True)
             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, openAI_key, start_page, end_page], outputs=[answer])
+			history_box = gr.Textbox(label='History of Questions and Answers', value='', type='output', lines=10)
+
+
+        #btn.click(question_answer, inputs=[url, file, question,openAI_key], outputs=[answer])
+		btn.click(question_answer, inputs=[url, file, question,openAI_key, history], outputs=[answer, history_box])
+
 
-demo.launch()
+#openai.api_key = os.getenv('Your_Key_Here') 
+demo.launch()