Update app.py

app.py

@@ -80,7 +80,7 @@ class SemanticSearch:
             raise Exception("The fit method must be called before the call method.")
         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:
@@ -105,12 +105,12 @@ def load_recommender(path, start_page=1):
 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=512,
-        n=1,
-        stop=None,
-        temperature=0.7,
+    engine=engine,
+    prompt=prompt,
+    max_tokens=512,
+    n=1,
+    stop=None,
+    temperature=0.7,
     )
     message = completions.choices[0].text
     return message
@@ -184,7 +184,6 @@ for i in range(row_count):
     with col2:
         question = st.text_input(f'Question {i+1}', key=f'question{i}', value=st.session_state.get(f'question{i}', ''))
     with col3:
-        # Initialize session state for answer if not already done
         if f'session_answer{i}' not in st.session_state:
             st.session_state[f'session_answer{i}'] = ''
     with col4:
@@ -201,7 +200,6 @@ for i in range(row_count):
                 load_recommender('corpus.pdf')
 
                 answer = generate_answer(question,openAI_key)
-                # Store the answer in session state
                 st.session_state[f'session_answer{i}'] = answer
     with col3:
         answer_placeholder = st.empty()
@@ -209,31 +207,16 @@ for i in range(row_count):
 
 def get_table_download_link(df, filename="data.csv", text="Download CSV file"):
     csv = df.to_csv(index=False)
-    b64 = base64.b64encode(csv.encode()).decode()  # some strings <-> bytes conversions necessary here
-    href = f'<a href="data:file/csv;base64,{b64}" download="{filename}">{text}</a>'
+    b64 = base64.b64encode(csv.encode()).decode() 
+    href = f'{text}'
     return href
 
-# Create a list of lists containing all URLs, questions, and answers
 data = [[st.session_state.get(f'url{i}', ''), st.session_state.get(f'question{i}', ''), st.session_state.get(f'session_answer{i}', '')] for i in range(row_count)]
 
-# Convert the data to a Pandas DataFrame
 df = pd.DataFrame(data, columns=['URL', 'Question', 'Answer'])
 
-# Generate a download link for the DataFrame
 st.markdown(get_table_download_link(df), unsafe_allow_html=True)
 
-def to_csv(data):
-    output = BytesIO()
-    writer = csv.writer(output)
-    writer.writerows(data)
-    return output.getvalue().decode('utf-8')
-
-def get_table_download_link(df, filename="data.csv", text="Download CSV file"):
-    csv = df.to_csv(index=False)
-    b64 = base64.b64encode(csv.encode()).decode() # some strings <-> bytes conversions necessary here
-    href = f'{text}'
-    return href
-
 class WorkerThread(threading.Thread):
     def __init__(self, jobs, results):
         super().__init__()
@@ -263,21 +246,17 @@ if generate_all:
 
     workers = [WorkerThread(jobs, results) for _ in range(num_concurrent_calls)]
 
-    # Add jobs to the queue
     for i, (url, question) in enumerate(zip(urls, questions)):
         download_pdf(url, 'corpus.pdf')
         load_recommender('corpus.pdf')
         jobs.put((i, question))
 
-    # Start all worker threads
     for worker in workers:
         worker.start()
 
-    # Add termination signals
     for _ in range(num_concurrent_calls):
         jobs.put(None)
 
-    # Join all worker threads
     for worker in workers:
         worker.join()