Update app.py

app.py

@@ -2,6 +2,7 @@ import urllib.request
 import fitz
 import re
 import numpy as np
+import tensorflow_hub as hub
 import openai
 import gradio as gr
 import os
@@ -10,11 +11,13 @@ 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
@@ -32,11 +35,12 @@ def pdf_to_text(path, start_page=1, end_page=None):
     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]
@@ -49,70 +53,57 @@ def text_to_chunks(texts, word_length=150, start_page=1):
             chunks.append(chunk)
     return chunks
 
-class SemanticSearch:
 
-    def __init__(self, openAI_key):
-        self.openAI_key = openAI_key
+class SemanticSearch:
+    
+    def __init__(self):
+        self.use = hub.load('https://tfhub.dev/google/universal-sentence-encoder/4')
         self.fitted = False
-
-    def fit(self, data, n_neighbors=5):
+    
+    
+    def fit(self, data, batch=1000, n_neighbors=5):
         self.data = data
-        self.embeddings = self.get_text_embedding(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.get_text_embedding([text])
+        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):
-        prompt = "Embed the following texts:"
-        for text in texts:
-            prompt += f"\n\n{text}"
-
-        openai.api_key = self.openAI_key
-        completions = openai.Completion.create(
-            engine="text-davinci-003",
-            prompt=prompt,
-            max_tokens=len(texts) * 128,
-            n=1,
-            stop=None,
-            temperature=0.5,
-        )
-
-        message = completions.choices[0].text
+    
+    
+    def get_text_embedding(self, texts, batch=1000):
         embeddings = []
-        for emb_str in message.split("\n"):
-            emb_str = emb_str.strip()
-            if emb_str:
-                emb = np.array([float(x) for x in emb_str.split()])
-                embeddings.append(emb)
-        embeddings = np.array(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, openAI_key, start_page=1):
+
+
+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 = SemanticSearch(openAI_key)  # add the openAI_key parameter here
     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,
         prompt=prompt,
-        max_tokens=4096,
+        max_tokens=512,
         n=1,
         stop=None,
         temperature=0.7,
@@ -120,57 +111,60 @@ 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 "\
+              "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 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: "
     
-    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 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: "
-       
     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 at least one.'
-
+        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 (either URL or PDF).'
+        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', openAI_key)
+        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, openAI_key)
+        load_recommender(file_name)
 
     if question.strip() == '':
         return '[ERROR]: Question field is empty'
 
-    return generate_answer(question, openAI_key)
+    return generate_answer(question,openAI_key)
+
 
-recommender = None
+recommender = SemanticSearch()
 
-# Add your Gradio UI code here
 title = 'PDF GPT'
-description = """With PDF GPT, you can chat with your PDF files/books and get precise answers."""
+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."""
 
 with gr.Blocks() as demo:
 
@@ -178,7 +172,7 @@ with gr.Blocks() as demo:
     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')
@@ -192,12 +186,7 @@ with gr.Blocks() as demo:
         with gr.Group():
             answer = gr.Textbox(label='The answer to your question is :')
 
-        btn.click(question_answer, inputs=[url, file, question, openAI_key], outputs=[answer])
-
+        btn.click(question_answer, inputs=[url, file, question,openAI_key], outputs=[answer])
+#openai.api_key = os.getenv('Your_Key_Here') 
 demo.launch()
 
-# remove this line
-recommender = SemanticSearch(openAI_key)
-
-# call load_recommender instead to initialize recommender
-load_recommender('corpus.pdf', openAI_key)