Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -629,6 +629,7 @@ if page == "Scrape or Upload Own Docs":
|
|
629 |
|
630 |
submit_upload_pdf = False
|
631 |
submit_scrape_web = False
|
|
|
632 |
|
633 |
# form for user to configure pdf loading options
|
634 |
if option == options[0]:
|
@@ -640,7 +641,7 @@ if page == "Scrape or Upload Own Docs":
|
|
640 |
with open(temp_file, "wb") as file:
|
641 |
file.write(uploaded_pdf.getvalue())
|
642 |
pdf_filename, = uploaded_pdf.name
|
643 |
-
submit_upload_pdf = st.form_submit_button(label='
|
644 |
|
645 |
# form for user to configure web scraping for duckduckgo
|
646 |
if option == options[1]:
|
@@ -655,17 +656,22 @@ if page == "Scrape or Upload Own Docs":
|
|
655 |
"Search Term",
|
656 |
value = f"{country_scrape_upload} sustainability esg newest updated public policy document government",
|
657 |
)
|
658 |
-
submit_scrape_web = st.form_submit_button(label='
|
|
|
|
|
|
|
|
|
|
|
|
|
659 |
|
660 |
if (submit_upload_pdf | submit_scrape_web):
|
661 |
if submit_upload_pdf:
|
662 |
with st.spinner('Generating documents from PDF...'):
|
663 |
all_documents = pdf_loader_local(pdf_filename, country_scrape_upload)
|
664 |
|
665 |
-
if
|
666 |
with st.spinner('Scraping web using Duck Duck Go search...'):
|
667 |
-
all_links, df_links = duckduckgo_scrape(country_scrape_upload, search_term, n_search_results)
|
668 |
-
st.write(df_links)
|
669 |
with st.spinner('Generating documents from web search results...'):
|
670 |
all_documents = process_links_load_documents(all_links)
|
671 |
|
|
|
629 |
|
630 |
submit_upload_pdf = False
|
631 |
submit_scrape_web = False
|
632 |
+
submit_scrape_vector_store = False
|
633 |
|
634 |
# form for user to configure pdf loading options
|
635 |
if option == options[0]:
|
|
|
641 |
with open(temp_file, "wb") as file:
|
642 |
file.write(uploaded_pdf.getvalue())
|
643 |
pdf_filename, = uploaded_pdf.name
|
644 |
+
submit_upload_pdf = st.form_submit_button(label='Upload and Create Vector Store')
|
645 |
|
646 |
# form for user to configure web scraping for duckduckgo
|
647 |
if option == options[1]:
|
|
|
656 |
"Search Term",
|
657 |
value = f"{country_scrape_upload} sustainability esg newest updated public policy document government",
|
658 |
)
|
659 |
+
submit_scrape_web = st.form_submit_button(label='Scrape Web for Results')
|
660 |
+
|
661 |
+
if submit_scrape_web:
|
662 |
+
with st.form(key='scrape_web_form2'):
|
663 |
+
st.write(f"Results from Web Scrape")
|
664 |
+
st.table(df_links)
|
665 |
+
submit_scrape_vector_store = st.form_submit_button(label='Create Vector Store from Search Results')
|
666 |
|
667 |
if (submit_upload_pdf | submit_scrape_web):
|
668 |
if submit_upload_pdf:
|
669 |
with st.spinner('Generating documents from PDF...'):
|
670 |
all_documents = pdf_loader_local(pdf_filename, country_scrape_upload)
|
671 |
|
672 |
+
if submit_scrape_vector_store:
|
673 |
with st.spinner('Scraping web using Duck Duck Go search...'):
|
674 |
+
all_links, df_links = duckduckgo_scrape(country_scrape_upload, search_term, n_search_results)
|
|
|
675 |
with st.spinner('Generating documents from web search results...'):
|
676 |
all_documents = process_links_load_documents(all_links)
|
677 |
|