Update app.py

app.py

@@ -1,6 +1,6 @@
 import streamlit as st
 import anthropic
-import openai
+import openai 
 import base64
 from datetime import datetime
 import plotly.graph_objects as go
@@ -87,6 +87,8 @@ if "openai_model" not in st.session_state:
     st.session_state["openai_model"] = "gpt-4o-2024-05-13"
 if "messages" not in st.session_state:
     st.session_state.messages = []
+if "search_queries" not in st.session_state:
+    st.session_state.search_queries = []
 
 # Custom CSS
 st.markdown("""
@@ -180,7 +182,12 @@ bike_collections = {
     }
 }
 
-# Helper Functions
+# File Operations Functions
+def create_file(filename, prompt, response, is_image=False):
+    """Basic file creation with prompt and response."""
+    with open(filename, "w", encoding="utf-8") as f:
+        f.write(prompt + "\n\n" + response)
+
 def generate_filename(prompt, file_type):
     """Generate a safe filename using the prompt and file type."""
     central = pytz.timezone('US/Central')
@@ -208,6 +215,39 @@ def get_download_link(file_path):
     b64 = base64.b64encode(contents).decode()
     return f'<a href="data:file/txt;base64,{b64}" download="{os.path.basename(file_path)}">Download {os.path.basename(file_path)}📂</a>'
 
+def load_file(file_name):
+    """Load file content."""
+    with open(file_name, "r", encoding='utf-8') as file:
+        content = file.read()
+    return content
+
+def create_zip_of_files(files):
+    """Create zip archive of files."""
+    zip_name = "all_files.zip"
+    with zipfile.ZipFile(zip_name, 'w') as zipf:
+        for file in files:
+            zipf.write(file)
+    return zip_name
+
+def get_media_html(media_path, media_type="video", width="100%"):
+    """Generate HTML for media player."""
+    media_data = base64.b64encode(open(media_path, 'rb').read()).decode()
+    if media_type == "video":
+        return f'''
+        <video width="{width}" controls autoplay muted loop>
+            <source src="data:video/mp4;base64,{media_data}" type="video/mp4">
+            Your browser does not support the video tag.
+        </video>
+        '''
+    else:  # audio
+        return f'''
+        <audio controls style="width: {width};">
+            <source src="data:audio/mpeg;base64,{media_data}" type="audio/mpeg">
+            Your browser does not support the audio element.
+        </audio>
+        '''
+
+# Speech Synthesis
 @st.cache_resource
 def SpeechSynthesis(result):
     """HTML5 Speech Synthesis."""
@@ -234,6 +274,79 @@ def SpeechSynthesis(result):
     '''
     components.html(documentHTML5, width=1280, height=300)
 
+# ArXiv Search Functions
+def search_arxiv(query):
+    """Search ArXiv papers using Hugging Face client."""
+    start_time = time.strftime("%Y-%m-%d %H:%M:%S")
+    client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
+    
+    # First query - Get papers
+    response1 = client.predict(
+        query,
+        10,
+        "Semantic Search - up to 10 Mar 2024",
+        "mistralai/Mixtral-8x7B-Instruct-v0.1",
+        api_name="/update_with_rag_md"
+    )
+    
+    # Second query - Get summary
+    response2 = client.predict(
+        query,
+        "mistralai/Mixtral-8x7B-Instruct-v0.1",
+        True,
+        api_name="/ask_llm"
+    )
+    
+    Question = '### 🔎 ' + query + '\r\n'
+    References = response1[0]
+    References2 = response1[1]
+    ReferenceLinks = extract_urls(References)
+    
+    filename = generate_filename(query, "md")
+    create_file(filename, query, References + ReferenceLinks)
+    
+    results = Question + '\r\n' + response2 + '\r\n' + References + '\r\n' + ReferenceLinks
+    
+    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")
+    
+    return results
+
+def extract_urls(text):
+    """Extract URLs from ArXiv search results."""
+    try:
+        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} \| \[(.*?)\]')
+        
+        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)
+
+        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
+    except:
+        st.write('Error extracting URLs')
+        return ''
+
 # Media Processing Functions
 def process_image(image_input, user_prompt):
     """Process image with GPT-4o vision."""
@@ -243,6 +356,8 @@ def process_image(image_input, user_prompt):
             
     base64_image = base64.b64encode(image_input).decode("utf-8")
     
+
+
     response = openai_client.chat.completions.create(
         model=st.session_state["openai_model"],
         messages=[
@@ -279,6 +394,17 @@ def process_audio(audio_input, text_input=''):
         filename = generate_filename(transcription.text, "wav")
         create_and_save_file(audio_input, "wav", transcription.text, True)
 
+def save_and_play_audio(audio_recorder):
+    """Save and play recorded audio."""
+    audio_bytes = audio_recorder()
+    if audio_bytes:
+        filename = generate_filename("Recording", "wav")
+        with open(filename, 'wb') as f:
+            f.write(audio_bytes)
+        st.audio(audio_bytes, format="audio/wav")
+        return filename
+    return None
+
 def process_video(video_path, seconds_per_frame=1):
     """Process video files for frame extraction and audio."""
     base64Frames = []
@@ -328,107 +454,13 @@ def process_video_with_gpt(video_input, user_prompt):
     
     return response.choices[0].message.content
 
-# ArXiv Search Functions
-def search_arxiv(query):
-    """Search ArXiv papers using Hugging Face client."""
-    client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
-    response = client.predict(
-        query,
-        "mistralai/Mixtral-8x7B-Instruct-v0.1",
-        True,
-        api_name="/ask_llm"
-    )
-    return response
-
-# Chat Processing Functions
-def process_with_gpt(text_input):
-    """Process text with GPT-4o."""
-    if text_input:
-        st.session_state.messages.append({"role": "user", "content": text_input})
-        
-        with st.chat_message("user"):
-            st.markdown(text_input)
-        
-        with st.chat_message("assistant"):
-            completion = openai_client.chat.completions.create(
-                model=st.session_state["openai_model"],
-                messages=[
-                    {"role": m["role"], "content": m["content"]}
-                    for m in st.session_state.messages
-                ],
-                stream=False
-            )
-            return_text = completion.choices[0].message.content
-            st.write("GPT-4o: " + return_text)
-            
-            filename = generate_filename(text_input, "md")
-            create_file(filename, text_input, return_text)
-            st.session_state.messages.append({"role": "assistant", "content": return_text})
-            return return_text
-
-def process_with_claude(text_input):
-    """Process text with Claude."""
-    if text_input:
-        response = claude_client.messages.create(
-            model="claude-3-sonnet-20240229",
-            max_tokens=1000,
-            messages=[
-                {"role": "user", "content": text_input}
-            ]
-        )
-
-        response_text = response.content[0].text
-        st.write("Claude: " + response_text)
-        
-        filename = generate_filename(text_input, "md")
-        create_file(filename, text_input, response_text)
-        
-        st.session_state.chat_history.append({
-            "user": text_input,
-            "claude": response_text
-        })
-        return response_text
-
-# File Management Functions
-def load_file(file_name):
-    """Load file content."""
-    with open(file_name, "r", encoding='utf-8') as file:
-        content = file.read()
-    return content
-
-def create_zip_of_files(files):
-    """Create zip archive of files."""
-    zip_name = "all_files.zip"
-    with zipfile.ZipFile(zip_name, 'w') as zipf:
-        for file in files:
-            zipf.write(file)
-    return zip_name
-
-def get_media_html(media_path, media_type="video", width="100%"):
-    """Generate HTML for media player."""
-    media_data = base64.b64encode(open(media_path, 'rb').read()).decode()
-    if media_type == "video":
-        return f'''
-        <video width="{width}" controls autoplay muted loop>
-            <source src="data:video/mp4;base64,{media_data}" type="video/mp4">
-            Your browser does not support the video tag.
-        </video>
-        '''
-    else:  # audio
-        return f'''
-        <audio controls style="width: {width};">
-            <source src="data:audio/mpeg;base64,{media_data}" type="audio/mpeg">
-            Your browser does not support the audio element.
-        </audio>
-        '''
-
 def create_media_gallery():
     """Create the media gallery interface."""
     st.header("🎬 Media Gallery")
     
     tabs = st.tabs(["🖼️ Images", "🎵 Audio", "🎥 Video", "🎨 Scene Generator"])
     
-    with tabs[0]:
+    with tabs[0]:  # Images
         image_files = glob.glob("*.png") + glob.glob("*.jpg")
         if image_files:
             num_cols = st.slider("Number of columns", 1, 5, 3)
@@ -444,7 +476,7 @@ def create_media_gallery():
                         st.markdown(analysis)
                         SpeechSynthesis(analysis)
     
-    with tabs[1]:
+    with tabs[1]:  # Audio
         audio_files = glob.glob("*.mp3") + glob.glob("*.wav")
         for audio_file in audio_files:
             with st.expander(f"🎵 {os.path.basename(audio_file)}"):
@@ -455,7 +487,7 @@ def create_media_gallery():
                         st.write(transcription)
                         SpeechSynthesis(transcription)
     
-    with tabs[2]:
+    with tabs[2]:  # Video
         video_files = glob.glob("*.mp4")
         for video_file in video_files:
             with st.expander(f"🎥 {os.path.basename(video_file)}"):
@@ -466,7 +498,7 @@ def create_media_gallery():
                     st.markdown(analysis)
                     SpeechSynthesis(analysis)
     
-    with tabs[3]:
+    with tabs[3]:  # Scene Generator
         for collection_name, bikes in bike_collections.items():
             st.subheader(collection_name)
             cols = st.columns(len(bikes))
@@ -486,6 +518,54 @@ def create_media_gallery():
                         st.write(prompt)
                         SpeechSynthesis(prompt)
 
+# Chat Processing Functions
+def process_with_gpt(text_input):
+    """Process text with GPT-4o."""
+    if text_input:
+        st.session_state.messages.append({"role": "user", "content": text_input})
+        
+        with st.chat_message("user"):
+            st.markdown(text_input)
+        
+        with st.chat_message("assistant"):
+            completion = openai_client.chat.completions.create(
+                model=st.session_state["openai_model"],
+                messages=[
+                    {"role": m["role"], "content": m["content"]}
+                    for m in st.session_state.messages
+                ],
+                stream=False
+            )
+            return_text = completion.choices[0].message.content
+            st.write("GPT-4o: " + return_text)
+            
+            filename = generate_filename(text_input, "md")
+            create_file(filename, text_input, return_text)
+            st.session_state.messages.append({"role": "assistant", "content": return_text})
+            return return_text
+
+def process_with_claude(text_input):
+    """Process text with Claude."""
+    if text_input:
+        response = claude_client.messages.create(
+            model="claude-3-sonnet-20240229",
+            max_tokens=1000,
+            messages=[
+                {"role": "user", "content": text_input}
+            ]
+        )
+        response_text = response.content[0].text
+        st.write("Claude: " + response_text)
+        
+        filename = generate_filename(text_input, "md")
+        create_file(filename, text_input, response_text)
+        
+        st.session_state.chat_history.append({
+            "user": text_input,
+            "claude": response_text
+        })
+        return response_text
+
 def display_file_manager():
     """Display file management sidebar."""
     st.sidebar.title("📁 File Management")