Update app.py

app.py

@@ -16,19 +16,17 @@ import streamlit as st
 import streamlit.components.v1 as components
 
 # If you do model inference via huggingface_hub:
-from huggingface_hub import InferenceClient
+# from huggingface_hub import InferenceClient
 
-# ----------------------------
-# Configurable BASE_URL
-# ----------------------------
+########################################################################################
+# 1) GLOBAL CONFIG & PLACEHOLDERS
+########################################################################################
 BASE_URL = "https://huggingface.co/spaces/awacke1/MermaidMarkdownDiagramEditor"
 
-# Example placeholders for prompt prefixes
 PromptPrefix = "AI-Search: "
 PromptPrefix2 = "AI-Refine: "
 PromptPrefix3 = "AI-JS: "
 
-# Example roleplaying glossary
 roleplaying_glossary = {
     "Core Rulebooks": {
         "Dungeons and Dragons": ["Player's Handbook", "Dungeon Master's Guide", "Monster Manual"],
@@ -39,61 +37,68 @@ roleplaying_glossary = {
     }
 }
 
-# Example transhuman glossary
 transhuman_glossary = {
     "Neural Interfaces": ["Cortex Jack", "Mind-Machine Fusion"],
     "Cybernetics": ["Robotic Limbs", "Augmented Eyes"],
 }
 
-# Simple function stubs
 def process_text(text):
+    """🕵️ process_text: detective style—prints lines to Streamlit for debugging."""
     st.write(f"process_text called with: {text}")
 
 def search_arxiv(text):
+    """🔭 search_arxiv: pretend to search ArXiv, just prints debug."""
     st.write(f"search_arxiv called with: {text}")
 
 def SpeechSynthesis(text):
+    """🗣 Simple logging for text-to-speech placeholders."""
     st.write(f"SpeechSynthesis called with: {text}")
 
 def process_image(image_file, prompt):
-    return f"[process_image placeholder] Processing {image_file} with prompt: {prompt}"
+    """📷 Simple placeholder for image AI pipeline."""
+    return f"[process_image placeholder] {image_file} => {prompt}"
 
 def process_video(video_file, seconds_per_frame):
-    st.write(f"[process_video placeholder] Video: {video_file}, seconds/frame: {seconds_per_frame}")
+    """🎞 Simple placeholder for video AI pipeline."""
+    st.write(f"[process_video placeholder] {video_file}, {seconds_per_frame} sec/frame")
 
-# Stub if you have a Hugging Face endpoint
 API_URL = "https://huggingface-inference-endpoint-placeholder"
 API_KEY = "hf_XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"
 
 @st.cache_resource
 def InferenceLLM(prompt):
+    """🔮 Stub returning mock response for 'prompt'."""
     return f"[InferenceLLM placeholder response to prompt: {prompt}]"
 
-# ------------------------------------------
-# Glossary & File Utility
-# ------------------------------------------
+########################################################################################
+# 2) GLOSSARY & FILE UTILITY
+########################################################################################
+
 @st.cache_resource
 def display_glossary_entity(k):
     """
     Creates multiple link emojis for a single entity.
+    Each link might point to /?q=..., /?q=<prefix>..., or external sites.
     """
     search_urls = {
-        "🚀🌌ArXiv": lambda x: f"/?q={quote(x)}",
-        "🃏Analyst": lambda x: f"/?q={quote(x)}-{quote(PromptPrefix)}",
-        "📚PyCoder": lambda x: f"/?q={quote(x)}-{quote(PromptPrefix2)}",
-        "🔬JSCoder": lambda x: f"/?q={quote(x)}-{quote(PromptPrefix3)}",
-        "📖": lambda x: f"https://en.wikipedia.org/wiki/{quote(x)}",
-        "🔍": lambda x: f"https://www.google.com/search?q={quote(x)}",
-        "🔎": lambda x: f"https://www.bing.com/search?q={quote(x)}",
-        "🎥": lambda x: f"https://www.youtube.com/results?search_query={quote(x)}",
-        "🐦": lambda x: f"https://twitter.com/search?q={quote(x)}",
+        "🚀🌌ArXiv":   lambda x: f"/?q={quote(x)}",
+        "🃏Analyst":  lambda x: f"/?q={quote(x)}-{quote(PromptPrefix)}",
+        "📚PyCoder":  lambda x: f"/?q={quote(x)}-{quote(PromptPrefix2)}",
+        "🔬JSCoder":  lambda x: f"/?q={quote(x)}-{quote(PromptPrefix3)}",
+        "📖":         lambda x: f"https://en.wikipedia.org/wiki/{quote(x)}",
+        "🔍":         lambda x: f"https://www.google.com/search?q={quote(x)}",
+        "🔎":         lambda x: f"https://www.bing.com/search?q={quote(x)}",
+        "🎥":         lambda x: f"https://www.youtube.com/results?search_query={quote(x)}",
+        "🐦":         lambda x: f"https://twitter.com/search?q={quote(x)}",
     }
     links_md = ' '.join([f"[{emoji}]({url(k)})" for emoji, url in search_urls.items()])
     st.markdown(f"**{k}** <small>{links_md}</small>", unsafe_allow_html=True)
 
+
 def display_content_or_image(query):
     """
-    If a query matches something in transhuman_glossary or a local image, show it.
+    If 'query' is in transhuman_glossary or there's an image matching 'images/<query>.png',
+    show it. Otherwise warn.
     """
     for category, term_list in transhuman_glossary.items():
         for term in term_list:
@@ -109,16 +114,15 @@ def display_content_or_image(query):
     return False
 
 def clear_query_params():
-    """
-    For clearing URL params, you'd typically use a new link or st.experimental_set_query_params().
-    Here, we just warn the user. 
-    """
+    """Warn about clearing. Full clearing requires a redirect or st.experimental_set_query_params()."""
     st.warning("Define a redirect or link without query params if you want to truly clear them.")
 
-# -----------------------
-# File Handling
-# -----------------------
+########################################################################################
+# 3) FILE-HANDLING (MD files, etc.)
+########################################################################################
+
 def load_file(file_path):
+    """Load file contents as UTF-8 text, or return empty on error."""
     try:
         with open(file_path, "r", encoding='utf-8') as f:
             return f.read()
@@ -127,6 +131,7 @@ def load_file(file_path):
 
 @st.cache_resource
 def create_zip_of_files(files):
+    """Combine multiple local .md files into a single .zip for user to download."""
     zip_name = "Arxiv-Paper-Search-QA-RAG-Streamlit-Gradio-AP.zip"
     with zipfile.ZipFile(zip_name, 'w') as zipf:
         for file in files:
@@ -135,6 +140,7 @@ def create_zip_of_files(files):
 
 @st.cache_resource
 def get_zip_download_link(zip_file):
+    """Return an <a> link to download the given zip_file (base64-encoded)."""
     with open(zip_file, 'rb') as f:
         data = f.read()
     b64 = base64.b64encode(data).decode()
@@ -143,6 +149,7 @@ def get_zip_download_link(zip_file):
 def get_table_download_link(file_path):
     """
     Creates a download link for a single file from your snippet.
+    Encodes it as base64 data.
     """
     try:
         with open(file_path, 'r', encoding='utf-8') as file:
@@ -151,13 +158,13 @@ def get_table_download_link(file_path):
         file_name = os.path.basename(file_path)
         ext = os.path.splitext(file_name)[1]
         mime_map = {
-            '.txt': 'text/plain',
-            '.py': 'text/plain',
+            '.txt':  'text/plain',
+            '.py':   'text/plain',
             '.xlsx': 'text/plain',
-            '.csv': 'text/plain',
-            '.htm': 'text/html',
-            '.md': 'text/markdown',
-            '.wav': 'audio/wav'
+            '.csv':  'text/plain',
+            '.htm':  'text/html',
+            '.md':   'text/markdown',
+            '.wav':  'audio/wav'
         }
         mime_type = mime_map.get(ext, 'application/octet-stream')
         return f'<a href="data:{mime_type};base64,{b64}" target="_blank" download="{file_name}">{file_name}</a>'
@@ -165,6 +172,7 @@ def get_table_download_link(file_path):
         return ''
 
 def get_file_size(file_path):
+    """Get file size in bytes."""
     return os.path.getsize(file_path)
 
 def FileSidebar():
@@ -172,7 +180,7 @@ def FileSidebar():
     Renders .md files, providing open/view/delete/run logic in the sidebar.
     """
     all_files = glob.glob("*.md")
-    # Exclude short-named or special files if needed
+    # Exclude short-named or special files if needed:
     all_files = [f for f in all_files if len(os.path.splitext(f)[0]) >= 5]
     all_files.sort(key=lambda x: (os.path.splitext(x)[1], x), reverse=True)
 
@@ -192,9 +200,9 @@ def FileSidebar():
     next_action = ''
 
     for file in all_files:
-        col1, col2, col3, col4, col5 = st.sidebar.columns([1, 6, 1, 1, 1])
+        col1, col2, col3, col4, col5 = st.sidebar.columns([1,6,1,1,1])
         with col1:
-            if st.button("🌐", key="md_" + file):
+            if st.button("🌐", key="md_"+file):
                 file_contents = load_file(file)
                 file_name = file
                 next_action = 'md'
@@ -202,7 +210,7 @@ def FileSidebar():
         with col2:
             st.markdown(get_table_download_link(file), unsafe_allow_html=True)
         with col3:
-            if st.button("📂", key="open_" + file):
+            if st.button("📂", key="open_"+file):
                 file_contents = load_file(file)
                 file_name = file
                 next_action = 'open'
@@ -211,45 +219,42 @@ def FileSidebar():
                 st.session_state['filetext'] = file_contents
                 st.session_state['next_action'] = next_action
         with col4:
-            if st.button("▶️", key="read_" + file):
+            if st.button("▶️", key="read_"+file):
                 file_contents = load_file(file)
                 file_name = file
                 next_action = 'search'
                 st.session_state['next_action'] = next_action
         with col5:
-            if st.button("🗑", key="delete_" + file):
+            if st.button("🗑", key="delete_"+file):
                 os.remove(file)
                 st.rerun()
 
-    # If we loaded a file
     if file_contents:
         if next_action == 'open':
-            open1, open2 = st.columns([0.8, 0.2])
+            open1, open2 = st.columns([0.8,0.2])
             with open1:
                 file_name_input = st.text_input('File Name:', file_name, key='file_name_input')
                 file_content_area = st.text_area('File Contents:', file_contents, height=300, key='file_content_area')
-
                 if st.button('💾 Save File'):
                     with open(file_name_input, 'w', encoding='utf-8') as f:
                         f.write(file_content_area)
                     st.markdown(f'Saved {file_name_input} successfully.')
-
         elif next_action == 'search':
             file_content_area = st.text_area("File Contents:", file_contents, height=500)
             user_prompt = PromptPrefix2 + file_contents
             st.markdown(user_prompt)
             if st.button('🔍Re-Code'):
                 search_arxiv(file_contents)
-
         elif next_action == 'md':
             st.markdown(file_contents)
             SpeechSynthesis(file_contents)
             if st.button("🔍Run"):
                 st.write("Running GPT logic placeholder...")
 
-# ---------------------------
-# Scoring / Glossaries
-# ---------------------------
+########################################################################################
+# 4) SCORING / GLOSSARIES
+########################################################################################
+
 score_dir = "scores"
 os.makedirs(score_dir, exist_ok=True)
 
@@ -293,17 +298,17 @@ def display_buttons_with_scores(num_columns_text):
         "Changeling": "🍃",
     }
     topic_emojis = {
-        "Core Rulebooks": "📚",
-        "Maps & Settings": "🗺️",
-        "Game Mechanics & Tools": "⚙️",
-        "Monsters & Adversaries": "👹",
-        "Campaigns & Adventures": "📜",
-        "Creatives & Assets": "🎨",
-        "Game Master Resources": "🛠️",
-        "Lore & Background": "📖",
-        "Character Development": "🧍",
-        "Homebrew Content": "🔧",
-        "General Topics": "🌍",
+        "Core Rulebooks":          "📚",
+        "Maps & Settings":         "🗺️",
+        "Game Mechanics & Tools":  "⚙️",
+        "Monsters & Adversaries":  "👹",
+        "Campaigns & Adventures":  "📜",
+        "Creatives & Assets":      "🎨",
+        "Game Master Resources":   "🛠️",
+        "Lore & Background":       "📖",
+        "Character Development":   "🧍",
+        "Homebrew Content":        "🔧",
+        "General Topics":          "🌍",
     }
 
     for category, games in roleplaying_glossary.items():
@@ -318,10 +323,12 @@ def display_buttons_with_scores(num_columns_text):
                     newscore = update_score(key.replace('?', ''))
                     st.markdown(f"Scored **{category} - {game} - {term}** -> {newscore}")
 
-# -------------------------------
-# Image & Video
-# -------------------------------
+########################################################################################
+# 5) IMAGES & VIDEOS
+########################################################################################
+
 def display_images_and_wikipedia_summaries(num_columns=4):
+    """Display .png images in a grid, referencing the name as a 'keyword'."""
     image_files = [f for f in os.listdir('.') if f.endswith('.png')]
     if not image_files:
         st.write("No PNG images found in the current directory.")
@@ -347,6 +354,7 @@ def display_images_and_wikipedia_summaries(num_columns=4):
         col_index += 1
 
 def display_videos_and_links(num_columns=4):
+    """Displays all .mp4/.webm in a grid, plus text input for prompts."""
     video_files = [f for f in os.listdir('.') if f.endswith(('.mp4', '.webm'))]
     if not video_files:
         st.write("No MP4 or WEBM videos found in the current directory.")
@@ -370,9 +378,10 @@ def display_videos_and_links(num_columns=4):
                     st.error("Invalid input for seconds per frame!")
         col_index += 1
 
-# --------------------------------
-# MERMAID DIAGRAM
-# --------------------------------
+########################################################################################
+# 6) MERMAID
+########################################################################################
+
 def generate_mermaid_html(mermaid_code: str) -> str:
     """
     Returns HTML that centers the Mermaid diagram, loading from a CDN.
@@ -421,39 +430,43 @@ def inject_base_url(url: str) -> str:
         return url
     return f"{BASE_URL}{url}"
 
-DEFAULT_MERMAID = """
+DEFAULT_MERMAID = r"""
 flowchart LR
-    U((User 😎)) -- "Talk 🗣️" --> LLM[LLM Agent 🤖\\nExtract Info]
+    U((User 😎)) -- "Talk 🗣️" --> LLM[LLM Agent 🤖\nExtract Info]
     click U "/?q=User%20😎" _self
     click LLM "/?q=LLM%20Agent%20Extract%20Info" _blank
 
-    LLM -- "Query 🔍" --> HS[Hybrid Search 🔎\\nVector+NER+Lexical]
+    LLM -- "Query 🔍" --> HS[Hybrid Search 🔎\nVector+NER+Lexical]
     click HS "/?q=Hybrid%20Search%20Vector+NER+Lexical" _blank
 
-    HS -- "Reason 🤔" --> RE[Reasoning Engine 🛠️\\nNeuralNetwork+Medical]
+    HS -- "Reason 🤔" --> RE[Reasoning Engine 🛠️\nNeuralNetwork+Medical]
     click RE "/?q=Reasoning%20Engine%20NeuralNetwork+Medical" _blank
 
-    RE -- "Link 📡" --> KG((Knowledge Graph 📚\\nOntology+GAR+RAG))
+    RE -- "Link 📡" --> KG((Knowledge Graph 📚\nOntology+GAR+RAG))
     click KG "/?q=Knowledge%20Graph%20Ontology+GAR+RAG" _blank
 """
 
+########################################################################################
+# 7) MAIN UI
+########################################################################################
+
 def main():
     st.set_page_config(page_title="Mermaid + Clickable Links with Base URL", layout="wide")
 
-    # ---------------------------------------------
-    # Query Param Parsing (non-experimental)
-    # ---------------------------------------------
+    # 1) Query Param Parsing
     query_params = st.query_params
-    query_list = (query_params.get('q') or query_params.get('query') or [''])
-    q_or_query = query_list[0] if query_list else ''
-    if q_or_query.strip():
-        # If there's a q= or query= param, do some processing
-        search_payload = PromptPrefix + q_or_query
-        st.markdown(search_payload)
-        process_text(search_payload)
-
-    if 'action' in st.query_params:
-        action_list = st.query_params['action']
+    q_list = (query_params.get('q') or query_params.get('query') or [''])
+    if q_list:
+        q_val = q_list[0].strip()
+        if q_val:
+            # If there's a q= or query= param, do some processing
+            search_payload = PromptPrefix + q_val
+            st.markdown(search_payload)
+            process_text(search_payload)
+
+    # If 'action' param is present
+    if 'action' in query_params:
+        action_list = query_params['action']
         if action_list:
             action = action_list[0]
             if action == 'show_message':
@@ -461,63 +474,54 @@ def main():
             elif action == 'clear':
                 clear_query_params()
 
-    # If a 'query' param is present, show content or image
-    if 'query' in st.query_params:
-        query_val = st.query_params['query'][0]
-        display_content_or_image(query_val)
+    # If a 'query=' param is present, show content or image
+    if 'query' in query_params:
+        paramQ = query_params['query'][0]
+        display_content_or_image(paramQ)
 
-    # ---------------------------------------------
-    # Let user pick if we want ?model=1
-    # ---------------------------------------------
+    # 2) Let user pick if we want ?model=1
     st.sidebar.write("## Diagram Link Settings")
     model_selected = st.sidebar.checkbox("Append ?model=1 to each link?")
 
-    # ---------------------------------------------
-    # Rebuild the clickable lines in the Mermaid code
-    # ---------------------------------------------
-    base_diagram = DEFAULT_MERMAID
-    lines = base_diagram.strip().split("\n")
+    # 3) We'll do minimal injection for the "click" lines
+    lines = DEFAULT_MERMAID.strip().split("\n")
     new_lines = []
     for line in lines:
-        if "click " in line and '"/?' in line:
-            parts = re.split(r'click\s+\S+\s+"([^"]+)"\s+(\S+)', line.strip())
-            # e.g. line: click U "/?q=User%20😎" _self
-            # parts might be:
-            #   [ 'click U ', '/?q=User%20😎', '_self', '' ]
-            if len(parts) >= 3:
-                prefix = parts[0]   # e.g. "click U "
-                old_url = parts[1] # e.g. /?q=User%20😎
-                target = parts[2]  # e.g. _self or _blank
+        if line.strip().startswith("click ") and '"/?' in line:
+            # e.g. click U "/?q=User%20😎" _self
+            pattern = r'(click\s+\S+\s+)"([^"]+)"\s+(\S+)'
+            match = re.match(pattern, line.strip())
+            if match:
+                prefix_part = match.group(1)  # e.g. "click U "
+                old_url     = match.group(2)  # e.g. /?q=User%20😎
+                target      = match.group(3)  # e.g. _self or _blank
 
                 new_url = inject_base_url(old_url)
                 new_url = append_model_param(new_url, model_selected)
 
-                new_line = f'{prefix}"{new_url}" {target}'
+                new_line = f'{prefix_part}"{new_url}" {target}'
                 new_lines.append(new_line)
             else:
+                # If not matched, keep line as is
                 new_lines.append(line)
         else:
             new_lines.append(line)
 
-    mermaid_code = "\n".join(new_lines)
+    final_mermaid = "\n".join(new_lines)
 
-    # ---------------------------------------------
-    # Render the top-centered Mermaid diagram
-    # ---------------------------------------------
-    st.sidebar.markdown("Mermaid Diagram with Base URL Injection")
-    diagram_html = generate_mermaid_html(mermaid_code)
+    # 4) Render the top-centered Mermaid diagram
+    st.sidebar.markdown("**Mermaid Diagram** with Base URL Injection")
+    diagram_html = generate_mermaid_html(final_mermaid)
     components.html(diagram_html, height=400, scrolling=True)
 
-    # ---------------------------------------------
-    # Two-column interface: Markdown & Mermaid
-    # ---------------------------------------------
+    # 5) Two-column layout: Markdown & Mermaid Editors
     left_col, right_col = st.columns(2)
 
-    # --- Left: Markdown Editor
     with left_col:
         st.subheader("Markdown Side 📝")
         if "markdown_text" not in st.session_state:
-            st.session_state["markdown_text"] = "## Hello!\nType some *Markdown* here.\n"
+            st.session_state["markdown_text"] = "## Hello!\nYou can type some *Markdown* here.\n"
+
         markdown_text = st.text_area(
             "Edit Markdown:",
             value=st.session_state["markdown_text"],
@@ -525,6 +529,7 @@ def main():
         )
         st.session_state["markdown_text"] = markdown_text
 
+        # Row of buttons
         colA, colB = st.columns(2)
         with colA:
             if st.button("🔄 Refresh Markdown"):
@@ -538,12 +543,10 @@ def main():
         st.markdown("**Preview:**")
         st.markdown(markdown_text)
 
-    # --- Right: Mermaid Editor
     with right_col:
         st.subheader("Mermaid Side 🧜‍♂️")
-
         if "current_mermaid" not in st.session_state:
-            st.session_state["current_mermaid"] = mermaid_code
+            st.session_state["current_mermaid"] = final_mermaid
 
         mermaid_input = st.text_area(
             "Edit Mermaid Code:",
@@ -566,9 +569,7 @@ def main():
         st.markdown("**Mermaid Source:**")
         st.code(mermaid_input, language="python", line_numbers=True)
 
-    # ---------------------------------------------
-    # Media Galleries
-    # ---------------------------------------------
+    # 6) Media Galleries
     st.markdown("---")
     st.header("Media Galleries")
 
@@ -578,23 +579,18 @@ def main():
     num_columns_video = st.slider("Choose Number of Video Columns", 1, 15, 5, key="num_columns_video")
     display_videos_and_links(num_columns_video)
 
-    # If you want extended UI for text or glossary
+    # 7) Optional Extended text interface
     showExtendedTextInterface = False
     if showExtendedTextInterface:
-        # For example:
-        # display_glossary_grid(roleplaying_glossary)
+        # e.g. display_glossary_grid(roleplaying_glossary)
         # num_columns_text = st.slider("Choose Number of Text Columns", 1, 15, 4)
         # display_buttons_with_scores(num_columns_text)
         pass
 
-    # ---------------------------------------------
-    # File Sidebar
-    # ---------------------------------------------
+    # 8) File Sidebar
     FileSidebar()
 
-    # ---------------------------------------------
-    # Random Title at the bottom
-    # ---------------------------------------------
+    # 9) Random Title
     titles = [
         "🧠🎭 Semantic Symphonies & Episodic Encores",
         "🌌🎼 AI Rhythms of Memory Lane",