Update app.py

app.py

@@ -40,7 +40,7 @@ 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]
@@ -54,11 +54,11 @@ def text_to_chunks(texts, word_length=150, start_page=1):
     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)
@@ -66,16 +66,16 @@ 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):
@@ -85,18 +85,15 @@ class SemanticSearch:
         embeddings = np.vstack(embeddings)
         return embeddings
 
-
-def load_recommender():
+def load_recommender(path, start_page=1):
     global recommender
-    download_pdf(PDF_URL, 'corpus.pdf')
-    texts = pdf_to_text('corpus.pdf', start_page=1)
-    chunks = text_to_chunks(texts, start_page=1)
+    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"):
-    openai.api_key = OPENAI_API_KEY
+    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,
@@ -108,13 +105,13 @@ def generate_text(prompt, engine="text-davinci-003"):
     message = completions.choices[0].text
     return message
 
-def generate_answer(question):
+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 "\
@@ -125,25 +122,24 @@ def generate_answer(question):
               "answer should be short and concise. Answer step-by-step. \n\nQuery: {question}\nAnswer: "
     
     prompt += f"Query: {question}\nAnswer:"
-    answer = generate_text(prompt, "text-davinci-003")
+    answer = generate_text(openAI_key, prompt, "text-davinci-003")
     return answer
 
-def question_answer(url, question):
-    if url.strip() == '':
-        return '[ERROR]: URL is empty. Provide a valid URL.'
-
+def question_answer(question):
+    openAI_key = OPENAI_API_KEY
+    url = PDF_URL
     download_pdf(url, 'corpus.pdf')
     load_recommender('corpus.pdf')
 
     if question.strip() == '':
         return '[ERROR]: Question field is empty'
 
-    return generate_answer(question)
+    return generate_answer(question, openAI_key)
 
 recommender = SemanticSearch()
 
 title = 'PDF GPT'
-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."""
+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."""
 
 with gr.Blocks() as demo:
     gr.Markdown(f'<center><h1>{title}</h1></center>')
@@ -158,6 +154,7 @@ with gr.Blocks() as demo:
         with gr.Group():
             answer = gr.Textbox(label='The answer to your question is :')
 
-        btn.click(question_answer, inputs=[PDF_URL, question], outputs=[answer])
+        btn.click(question_answer, inputs=[question], outputs=[answer])
 
 demo.launch()
+