Update app.py

app.py

@@ -90,9 +90,146 @@ def SpeechSynthesis(result):
 def parse_to_markdown(text):
     return text
         
-# Show ArXiv Scholary Articles! ----------------*************----▶️ Semantic and Episodic Memory System
+        
+
+
+import re
+
+def extract_urls(text):
+    # Regular expression patterns to find the required fields
+    date_pattern = re.compile(r'### (\d{2} \w{3} \d{4})')
+    abs_link_pattern = re.compile(r'\[(.*?)\]\((https://arxiv\.org/abs/\d+\.\d+)\)')
+    pdf_link_pattern = re.compile(r'\[⬇️\]\((https://arxiv\.org/pdf/\d+\.\d+)\)')
+    title_pattern = re.compile(r'### \d{2} \w{3} \d{4} \| \[(.*?)\]')
+
+    # Find all occurrences of the required fields using the regular expression patterns
+    date_matches = date_pattern.findall(text)
+    abs_link_matches = abs_link_pattern.findall(text)
+    pdf_link_matches = pdf_link_pattern.findall(text)
+    title_matches = title_pattern.findall(text)
+
+    # Generate markdown string with the extracted fields
+    markdown_text = ""
+    for i in range(len(date_matches)):
+        date = date_matches[i]
+        title = title_matches[i]
+        abs_link = abs_link_matches[i][1]
+        pdf_link = pdf_link_matches[i]
+
+        markdown_text += f"**Date:** {date}\n\n"
+        markdown_text += f"**Title:** {title}\n\n"
+        markdown_text += f"**Abstract Link:** [{abs_link}]({abs_link})\n\n"
+        markdown_text += f"**PDF Link:** [{pdf_link}]({pdf_link})\n\n"
+        markdown_text += "---\n\n"
+
+    return markdown_text
+
+
+
+def download_pdfs(urls):
+    local_files = []
+    for url in urls:
+        if url.endswith('.pdf'):
+            local_filename = url.split('/')[-1]
+            response = requests.get(url)
+            with open(local_filename, 'wb') as f:
+                f.write(response.content)
+            local_files.append(local_filename)
+    return local_files
+
+def generate_html(local_files):
+    html = "<ul>"
+    for file in local_files:
+        link = f'<li><a href="{file}">{file}</a></li>'
+        html += link
+    html += "</ul>"
+    return html
+
+
 def search_arxiv(query):
     start_time = time.strftime("%Y-%m-%d %H:%M:%S")
+    client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
+    search_query = query
+    search_source = "Arxiv Search - Latest - (EXPERIMENTAL)"
+    llm_model = "mistralai/Mixtral-8x7B-Instruct-v0.1"
+    st.markdown('### 🔎 ' + query)
+
+    # Search 1 - Retrieve the Papers
+    client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
+    response1 = client.predict(
+        query,
+        20,
+        "Semantic Search - up to 10 Mar 2024",
+        "mistralai/Mixtral-8x7B-Instruct-v0.1",
+        api_name="/update_with_rag_md"
+    )
+    lastpart = ''
+    totalparts = ''
+    results = response1[0]  # Format for markdown display with links
+    results2 = response1[1]  # format for subquery without links
+    st.markdown(results)
+
+    # Extract URLs from the response
+    urls = extract_urls(results)
+
+    # Download PDFs and generate HTML5 code for local links
+    # local_links_html = download_pdfs_and_generate_html(urls)
+    st.markdown(urls)
+
+    RunSecondQuery = False
+    if RunSecondQuery:
+        # Search 2 - Retrieve the Summary with Papers Context and Original Query
+        response2 = client.predict(
+            query,
+            "mistralai/Mixtral-8x7B-Instruct-v0.1",
+            True,
+            api_name="/ask_llm"
+        )
+        st.markdown(response2)
+        results = results + response2
+
+    st.write('🔍Run of Multi-Agent System Paper Summary Spec is Complete')
+    end_time = time.strftime("%Y-%m-%d %H:%M:%S")
+    start_timestamp = time.mktime(time.strptime(start_time, "%Y-%m-%d %H:%M:%S"))
+    end_timestamp = time.mktime(time.strptime(end_time, "%Y-%m-%d %H:%M:%S"))
+    elapsed_seconds = end_timestamp - start_timestamp
+    st.write(f"Start time: {start_time}")
+    st.write(f"Finish time: {end_time}")
+    st.write(f"Elapsed time: {elapsed_seconds:.2f} seconds")
+
+    SpeechSynthesis(results)
+    filename = generate_filename(query, "md")
+    create_file(filename, query, results, should_save)
+
+    # Display local links HTML
+    st.markdown(local_links_html, unsafe_allow_html=True)
+
+    return results
+
+def download_pdfs_and_generate_html(urls):
+    pdf_links = []
+    for url in urls:
+        if url.endswith('.pdf'):
+            pdf_filename = os.path.basename(url)
+            download_pdf(url, pdf_filename)
+            pdf_links.append(pdf_filename)
+
+    local_links_html = '<ul>'
+    for link in pdf_links:
+        local_links_html += f'<li><a href="{link}">{link}</a></li>'
+    local_links_html += '</ul>'
+    return local_links_html
+
+def download_pdf(url, filename):
+    response = requests.get(url)
+    with open(filename, 'wb') as file:
+        file.write(response.content)        
+        
+        
+        
+# Show ArXiv Scholary Articles! ----------------*************----▶️ Semantic and Episodic Memory System
+def search_arxiv_old(query):
+    start_time = time.strftime("%Y-%m-%d %H:%M:%S")
 
 
     client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
@@ -107,19 +244,13 @@ def search_arxiv(query):
     client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
     response1 = client.predict(
     		query,	
-    		10,	
+    		20,	
     		"Semantic Search - up to 10 Mar 2024",	# Literal['Semantic Search - up to 10 Mar 2024', 'Arxiv Search - Latest - (EXPERIMENTAL)']  in 'Search Source' Dropdown component
     		"mistralai/Mixtral-8x7B-Instruct-v0.1",	# Literal['mistralai/Mixtral-8x7B-Instruct-v0.1', 'mistralai/Mistral-7B-Instruct-v0.2', 'google/gemma-7b-it', 'None']  in 'LLM Model' Dropdown component
     		api_name="/update_with_rag_md"
     )
-    #st.markdown(response1)
     lastpart=''
     totalparts=''
-    #for parts in response1:
-    #    st.markdown(parts) # expect 2
-    #    lastpart=parts
-    #    totalparts=totalparts+parts
-    
     results = response1[0]  # Format for markdown display with links
     results2 = response1[1]  # format for subquery without links
     st.markdown(results)
@@ -127,13 +258,11 @@ def search_arxiv(query):
     RunSecondQuery = False
     if RunSecondQuery:
         # Search 2 - Retieve the Summary with Papers Context and Original Query
-        #client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
-        #newquery='Create a summary as markdown outline with emojis for query: ' + query + ' ' + totalparts
         response2 = client.predict(
                 query,	# str  in 'parameter_13' Textbox component
-                #"mistralai/Mixtral-8x7B-Instruct-v0.1",	
+                "mistralai/Mixtral-8x7B-Instruct-v0.1",	
                 #"mistralai/Mistral-7B-Instruct-v0.2", 
-                "google/gemma-7b-it",
+                #"google/gemma-7b-it",
                 True,	# bool  in 'Stream output' Checkbox component
                 api_name="/ask_llm"
         )
@@ -148,7 +277,9 @@ def search_arxiv(query):
     st.write(f"Start time: {start_time}")
     st.write(f"Finish time: {end_time}")
     st.write(f"Elapsed time: {elapsed_seconds:.2f} seconds")
+    
     SpeechSynthesis(results)  # Search History Reader / Writer IO Memory - Audio at Same time as Reading.
+    
     filename=generate_filename(query, "md")
     create_file(filename, query, results, should_save)
     return results
@@ -421,7 +552,7 @@ def compare_and_delete_files(files):
                 if file != latest_file:
                     os.remove(file)
                     st.success(f"Deleted {file} as a duplicate.")
-    st.experimental_rerun()
+    st.rerun()
 
 # Function to get file size
 def get_file_size(file_path):
@@ -456,7 +587,7 @@ def FileSidebar():
 
             if st.button("Delete", key=f"delete3_{file}"):
                 os.remove(file)
-                st.experimental_rerun()
+                st.rerun()
         previous_size = size  # Update previous size for the next iteration
 
 
@@ -472,7 +603,7 @@ def FileSidebar():
         if st.button("🗑 Delete All"):
             for file in all_files:
                 os.remove(file)
-            st.experimental_rerun()
+            st.rerun()
     with Files2:
         if st.button("⬇️ Download"):
             zip_file = create_zip_of_files(all_files)
@@ -511,7 +642,7 @@ def FileSidebar():
             if st.button("🗑", key="delete_"+file):
                 os.remove(file)
                 file_name=file
-                st.experimental_rerun()
+                st.rerun()
                 next_action='delete'
                 st.session_state['next_action'] = next_action
 
@@ -1271,7 +1402,7 @@ filekey = 'delall'
 if st.sidebar.button("🗑 Delete All Audio", key=filekey):
     for file in all_files:
         os.remove(file)
-    st.experimental_rerun()
+    st.rerun()
 
 for file in all_files:
     col1, col2 = st.sidebar.columns([6, 1])  # adjust the ratio as needed
@@ -1286,7 +1417,7 @@ for file in all_files:
     with col2:
         if st.button("🗑", key="delete_" + file):
             os.remove(file)
-            st.experimental_rerun()
+            st.rerun()
 
 
 
@@ -1333,7 +1464,7 @@ if 'action' in st.query_params:
         st.success("Showing a message because 'action=show_message' was found in the URL.")
     elif action == 'clear':
         clear_query_params()
-        st.experimental_rerun()
+        st.rerun()
 
 if 'query' in st.query_params:
     query = st.query_params['query'][0]  # Get the query parameter