added search engine to app, fixed please wait warning

app.py

@@ -2,6 +2,7 @@ import streamlit as st  #Web App
 import os
 from PIL import Image
 from utils import *
+import asyncio
 
 import pickle
 docs = None
@@ -14,7 +15,7 @@ st.image(image, width=1000)
 
 #title
 st.title("Answering questions from scientific papers")
-st.markdown("##### This tool will allow you to ask questions and get answers based on scientific papers. It uses OpenAI's GPT models, and you must have your own API key. Each query is about 10k tokens, which costs about only $0.20 on your own API key which is charged by OpenAI.")
+st.markdown("##### This tool will allow you to ask questions and get answers based on scientific papers. It uses OpenAI's GPT models, and you must have your own API key. Each query is about 10k tokens, which costs about only $0.20 on your own API key, charged by OpenAI.")
 st.markdown("##### Current version searches on [ArXiv](https://arxiv.org) papers only. 🚧Under development🚧")
 st.markdown("Used libraries:\n * [PaperQA](https://github.com/whitead/paper-qa) \n* [langchain](https://github.com/hwchase17/langchain)")
 
@@ -23,7 +24,8 @@ api_key_url = 'https://help.openai.com/en/articles/4936850-where-do-i-find-my-se
 api_key = st.text_input('OpenAI API Key',
          placeholder='sk-...', 
          help=f"['What is that?']({api_key_url})",
-         type="password")     
+         type="password",
+         value = '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')     
 
 os.environ["OPENAI_API_KEY"] = f"{api_key}" # 
 if len(api_key) != 51:
@@ -34,18 +36,23 @@ max_results_current = 5
 max_results = max_results_current
 def search_click_callback(search_query, max_results):
     global pdf_info, pdf_citation
-    pdf_info, pdf_citation = call_arXiv_API(f'{search_query}', max_results=max_results)
-    download_pdf(pdf_info)
+    # pdf_info, pdf_citation = call_arXiv_API(f'{search_query}', max_results=max_results)
+    # download_pdf(pdf_info)
+    XRxiv_servers = ['rxiv']
+    search_engines = XRxivQuery(search_query, max_results, XRxiv_servers=XRxiv_servers)
+    pdf_info = search_engines.call_API()
+    search_engines.download_pdf()
+
     return pdf_info
 
 with st.form(key='columns_in_form', clear_on_submit = False):
     c1, c2 = st.columns([8,1])
     with c1:
-        search_query = st.text_input("Input search query here:", placeholder='Keywords for most relevant search...', value=''
+        search_query = st.text_input("Input search query here:", placeholder='Keywords for most relevant search...', value='CFD Modeling'
                                        )#search_query, max_results_current))
 
     with c2:
-        max_results = st.text_input("Max papers", value=max_results_current)
+        max_results = st.number_input("Max papers", value=max_results_current)
         max_results_current = max_results_current
     searchButton = st.form_submit_button(label = 'Search')
 
@@ -60,34 +67,38 @@ if searchButton:
 def answer_callback(question_query):
     import paperqa
     global docs
-    progress_text = "Please wait..."
-    # my_bar = st.progress(0, text = progress_text)
-    st.info('Please wait...', icon="🔥")
     if docs is None:
-        # my_bar.progress(0.2, "Please wait...")
         pdf_info = st.session_state['pdf_info']
-        # print('buliding docs')
         docs = paperqa.Docs()
-        pdf_paths = [f"{p[4]}/{p[0]}.pdf" for p in pdf_info]
+        pdf_paths = [f"{p[4]}/{p[0].replace(':','').replace('/','').replace('.','')}.pdf" for p in pdf_info]
         pdf_citations = [p[5] for p in pdf_info]
         print(list(zip(pdf_paths, pdf_citations)))
-
         for d, c in zip(pdf_paths, pdf_citations):
-            # print(d,c)
             docs.add(d, c)
-    # docs._build_faiss_index()
+    docs._build_faiss_index()
     answer = docs.query(question_query)
-    # print(answer.formatted_answer)
-    # my_bar.progress(1.0, "Done!")
-    st.success('Voila!')
+    st.success('Voila! 😃')
     return answer.formatted_answer
 
 form = st.form(key='question_form')
 question_query = form.text_input("What do you wanna know from these papers?", placeholder='Input questions here...',
-                value='')
+                value='Write about CFD modeling')
 submitButton = form.form_submit_button('Submit')
 
 if submitButton:
     with st.expander("Found papers:", expanded=True):
         st.write(f"{st.session_state['all_reference_text']}")
-    st.text_area("Answer:", answer_callback(question_query), height=600)
+    with st.spinner('⏳ Please wait...'):
+        start = time.time()
+        final_answer = answer_callback(question_query)
+        length_answer = len(final_answer)
+        st.text_area("Answer:", final_answer, height=max(length_answer//4, 100))
+        end = time.time()
+        clock_time = end - start
+        with st.empty():
+            st.write(f"✔️ Task completed in {clock_time:.2f} seconds.")   
+
+
+
+
+

utils.py

@@ -154,7 +154,7 @@ class XRxivQuery:
                 # os.remove(f'./{folder_name}/*')
         # print(pdf_info)
         all_reference_text = []
-        for i,p in enumerate(stqdm(self.all_pdf_info, desc='Searching and downloading papers')):
+        for i,p in enumerate(stqdm(self.all_pdf_info, desc='🔍 Searching and downloading papers')):
             pdf_title=p[0]
             pdf_category=p[3]
             pdf_url=p[1]