DeepResearchEvaluator / backup3.app.py
awacke1's picture
Rename app.py to backup3.app.py
f51a852 verified
raw
history blame
22.4 kB
#!/usr/bin/env python3
import os
import re
import glob
import json
import base64
import zipfile
import random
import requests
import openai
from PIL import Image
from urllib.parse import quote
import streamlit as st
import streamlit.components.v1 as components
# If you do model inference via huggingface_hub:
from huggingface_hub import InferenceClient
# ----------------------------
# Configurable BASE_URL
# ----------------------------
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"],
"GURPS": ["Basic Set Characters", "Basic Set Campaigns"]
},
"Campaigns & Adventures": {
"Pathfinder": ["Rise of the Runelords", "Curse of the Crimson Throne"]
}
}
# Example transhuman glossary
transhuman_glossary = {
"Neural Interfaces": ["Cortex Jack", "Mind-Machine Fusion"],
"Cybernetics": ["Robotic Limbs", "Augmented Eyes"],
}
# Simple function stubs
def process_text(text):
st.write(f"process_text called with: {text}")
def search_arxiv(text):
st.write(f"search_arxiv called with: {text}")
def SpeechSynthesis(text):
st.write(f"SpeechSynthesis called with: {text}")
def process_image(image_file, prompt):
return f"[process_image placeholder] Processing {image_file} with prompt: {prompt}"
def process_video(video_file, seconds_per_frame):
st.write(f"[process_video placeholder] Video: {video_file}, seconds/frame: {seconds_per_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):
return f"[InferenceLLM placeholder response to prompt: {prompt}]"
# ------------------------------------------
# Glossary & File Utility
# ------------------------------------------
@st.cache_resource
def display_glossary_entity(k):
"""
Creates multiple link emojis for a single entity.
"""
search_urls = {
"๐Ÿš€๐ŸŒŒArXiv": lambda x: f"/?q={quote(x)}",
"๐ŸƒAnalyst": lambda x: f"/?q={quote(x)}-{quote(PromptPrefix)}",
"๐Ÿ“šPyCoder": lambda x: f"/?q={quote(x)}-{quote(PromptPrefix2)}",
"๐Ÿ”ฌJSCoder": lambda x: f"/?q={quote(x)}-{quote(PromptPrefix3)}",
"๐Ÿ“–": lambda x: f"https://en.wikipedia.org/wiki/{quote(x)}",
"๐Ÿ”": lambda x: f"https://www.google.com/search?q={quote(x)}",
"๐Ÿ”Ž": lambda x: f"https://www.bing.com/search?q={quote(x)}",
"๐ŸŽฅ": lambda x: f"https://www.youtube.com/results?search_query={quote(x)}",
"๐Ÿฆ": 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.
"""
for category, term_list in transhuman_glossary.items():
for term in term_list:
if query.lower() in term.lower():
st.subheader(f"Found in {category}:")
st.write(term)
return True
image_path = f"images/{query}.png"
if os.path.exists(image_path):
st.image(image_path, caption=f"Image for {query}")
return True
st.warning("No matching content or image found.")
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.
"""
st.warning("Define a redirect or link without query params if you want to truly clear them.")
# -----------------------
# File Handling
# -----------------------
def load_file(file_path):
try:
with open(file_path, "r", encoding='utf-8') as f:
return f.read()
except:
return ""
@st.cache_resource
def create_zip_of_files(files):
zip_name = "Arxiv-Paper-Search-QA-RAG-Streamlit-Gradio-AP.zip"
with zipfile.ZipFile(zip_name, 'w') as zipf:
for file in files:
zipf.write(file)
return zip_name
@st.cache_resource
def get_zip_download_link(zip_file):
with open(zip_file, 'rb') as f:
data = f.read()
b64 = base64.b64encode(data).decode()
return f'<a href="data:application/zip;base64,{b64}" download="{zip_file}">Download All</a>'
def get_table_download_link(file_path):
"""
Creates a download link for a single file from your snippet.
"""
try:
with open(file_path, 'r', encoding='utf-8') as file:
data = file.read()
b64 = base64.b64encode(data.encode()).decode()
file_name = os.path.basename(file_path)
ext = os.path.splitext(file_name)[1]
mime_map = {
'.txt': 'text/plain',
'.py': 'text/plain',
'.xlsx': 'text/plain',
'.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>'
except:
return ''
def get_file_size(file_path):
return os.path.getsize(file_path)
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
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)
Files1, Files2 = st.sidebar.columns(2)
with Files1:
if st.button("๐Ÿ—‘ Delete All"):
for file in all_files:
os.remove(file)
st.rerun()
with Files2:
if st.button("โฌ‡๏ธ Download"):
zip_file = create_zip_of_files(all_files)
st.sidebar.markdown(get_zip_download_link(zip_file), unsafe_allow_html=True)
file_contents = ''
file_name = ''
next_action = ''
for file in all_files:
col1, col2, col3, col4, col5 = st.sidebar.columns([1, 6, 1, 1, 1])
with col1:
if st.button("๐ŸŒ", key="md_" + file):
file_contents = load_file(file)
file_name = file
next_action = 'md'
st.session_state['next_action'] = next_action
with col2:
st.markdown(get_table_download_link(file), unsafe_allow_html=True)
with col3:
if st.button("๐Ÿ“‚", key="open_" + file):
file_contents = load_file(file)
file_name = file
next_action = 'open'
st.session_state['lastfilename'] = file
st.session_state['filename'] = file
st.session_state['filetext'] = file_contents
st.session_state['next_action'] = next_action
with col4:
if st.button("โ–ถ๏ธ", 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("๐Ÿ—‘", 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])
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('๐Ÿ’พ 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('๐Ÿ”Re-Code'):
search_arxiv(file_contents)
elif next_action == 'md':
st.markdown(file_contents)
SpeechSynthesis(file_contents)
if st.button("๐Ÿ”Run"):
st.write("Running GPT logic placeholder...")
# ---------------------------
# Scoring / Glossaries
# ---------------------------
score_dir = "scores"
os.makedirs(score_dir, exist_ok=True)
def generate_key(label, header, idx):
return f"{header}_{label}_{idx}_key"
def update_score(key, increment=1):
"""
Track a 'score' for each glossary item or term, saved in JSON per key.
"""
score_file = os.path.join(score_dir, f"{key}.json")
if os.path.exists(score_file):
with open(score_file, "r") as file:
score_data = json.load(file)
else:
score_data = {"clicks": 0, "score": 0}
score_data["clicks"] += increment
score_data["score"] += increment
with open(score_file, "w") as file:
json.dump(score_data, file)
return score_data["score"]
def load_score(key):
file_path = os.path.join(score_dir, f"{key}.json")
if os.path.exists(file_path):
with open(file_path, "r") as file:
score_data = json.load(file)
return score_data["score"]
return 0
def display_buttons_with_scores(num_columns_text):
"""
Show glossary items as clickable buttons that increment a 'score'.
"""
game_emojis = {
"Dungeons and Dragons": "๐Ÿ‰",
"Call of Cthulhu": "๐Ÿ™",
"GURPS": "๐ŸŽฒ",
"Pathfinder": "๐Ÿ—บ๏ธ",
"Kindred of the East": "๐ŸŒ…",
"Changeling": "๐Ÿƒ",
}
topic_emojis = {
"Core Rulebooks": "๐Ÿ“š",
"Maps & Settings": "๐Ÿ—บ๏ธ",
"Game Mechanics & Tools": "โš™๏ธ",
"Monsters & Adversaries": "๐Ÿ‘น",
"Campaigns & Adventures": "๐Ÿ“œ",
"Creatives & Assets": "๐ŸŽจ",
"Game Master Resources": "๐Ÿ› ๏ธ",
"Lore & Background": "๐Ÿ“–",
"Character Development": "๐Ÿง",
"Homebrew Content": "๐Ÿ”ง",
"General Topics": "๐ŸŒ",
}
for category, games in roleplaying_glossary.items():
category_emoji = topic_emojis.get(category, "๐Ÿ”")
st.markdown(f"## {category_emoji} {category}")
for game, terms in games.items():
game_emoji = game_emojis.get(game, "๐ŸŽฎ")
for term in terms:
key = f"{category}_{game}_{term}".replace(' ', '_').lower()
score_val = load_score(key)
if st.button(f"{game_emoji} {category} {game} {term} {score_val}", key=key):
newscore = update_score(key.replace('?', ''))
st.markdown(f"Scored **{category} - {game} - {term}** -> {newscore}")
# -------------------------------
# Image & Video
# -------------------------------
def display_images_and_wikipedia_summaries(num_columns=4):
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.")
return
image_files_sorted = sorted(image_files, key=lambda x: len(x.split('.')[0]))
cols = st.columns(num_columns)
col_index = 0
for image_file in image_files_sorted:
with cols[col_index % num_columns]:
try:
image = Image.open(image_file)
st.image(image, use_column_width=True)
k = image_file.split('.')[0]
display_glossary_entity(k)
image_text_input = st.text_input(f"Prompt for {image_file}", key=f"image_prompt_{image_file}")
if image_text_input:
response = process_image(image_file, image_text_input)
st.markdown(response)
except:
st.write(f"Could not open {image_file}")
col_index += 1
def display_videos_and_links(num_columns=4):
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.")
return
video_files_sorted = sorted(video_files, key=lambda x: len(x.split('.')[0]))
cols = st.columns(num_columns)
col_index = 0
for video_file in video_files_sorted:
with cols[col_index % num_columns]:
k = video_file.split('.')[0]
st.video(video_file, format='video/mp4', start_time=0)
display_glossary_entity(k)
video_text_input = st.text_input(f"Video Prompt for {video_file}", key=f"video_prompt_{video_file}")
if video_text_input:
try:
seconds_per_frame = 10
process_video(video_file, seconds_per_frame)
except ValueError:
st.error("Invalid input for seconds per frame!")
col_index += 1
# --------------------------------
# MERMAID DIAGRAM
# --------------------------------
def generate_mermaid_html(mermaid_code: str) -> str:
"""
Returns HTML that centers the Mermaid diagram, loading from a CDN.
"""
return f"""
<html>
<head>
<script src="https://cdn.jsdelivr.net/npm/mermaid/dist/mermaid.min.js"></script>
<style>
.centered-mermaid {{
display: flex;
justify-content: center;
margin: 20px auto;
}}
.mermaid {{
max-width: 800px;
}}
</style>
</head>
<body>
<div class="mermaid centered-mermaid">
{mermaid_code}
</div>
<script>
mermaid.initialize({{ startOnLoad: true }});
</script>
</body>
</html>
"""
def append_model_param(url: str, model_selected: bool) -> str:
"""
If user checks 'Append ?model=1', we append &model=1 or ?model=1 if not present.
"""
if not model_selected:
return url
delimiter = "&" if "?" in url else "?"
return f"{url}{delimiter}model=1"
def inject_base_url(url: str) -> str:
"""
If a link does not start with http, prepend your BASE_URL
so it becomes an absolute link to huggingface.co/spaces/...
"""
if url.startswith("http"):
return url
return f"{BASE_URL}{url}"
# Our default diagram, containing the "click" lines with /?q=...
DEFAULT_MERMAID = """
flowchart LR
U((User ๐Ÿ˜Ž)) -- "Talk ๐Ÿ—ฃ๏ธ" --> LLM[LLM Agent ๐Ÿค–\\nExtract Info]
click U "/?q=User%20๐Ÿ˜Ž" _self
click LLM "/?q=LLM%20Agent%20Extract%20Info" _blank
LLM -- "Query ๐Ÿ”" --> HS[Hybrid Search ๐Ÿ”Ž\\nVector+NER+Lexical]
click HS "/?q=Hybrid%20Search%20Vector+NER+Lexical" _blank
HS -- "Reason ๐Ÿค”" --> RE[Reasoning Engine ๐Ÿ› ๏ธ\\nNeuralNetwork+Medical]
click RE "/?q=Reasoning%20Engine%20NeuralNetwork+Medical" _blank
RE -- "Link ๐Ÿ“ก" --> KG((Knowledge Graph ๐Ÿ“š\\nOntology+GAR+RAG))
click KG "/?q=Knowledge%20Graph%20Ontology+GAR+RAG" _blank
"""
def main():
st.set_page_config(page_title="Mermaid + Clickable Links with Base URL", layout="wide")
# ---------------------------------------------
# Query Param Parsing (non-experimental)
# ---------------------------------------------
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 an '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':
st.success("Showing a message because 'action=show_message' was found in the URL.")
elif action == 'clear':
clear_query_params()
# If a 'query' param is present, show content or image
if 'query' in query_params:
query_val = query_params['query'][0]
display_content_or_image(query_val)
# ---------------------------------------------
# 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")
new_lines = []
for line in lines:
# We look for lines like: click SOMENODE "/?q=Something" _self
if "click " in line and '"/?' in line:
# Try to extract the URL part
parts = re.split(r'click\s+\S+\s+"([^"]+)"\s+("_self")', line)
if len(parts) == 4:
# Example:
# parts[0] -> 'click LLM '
# parts[1] -> '/?q=LLM%20Agent%20Extract%20Info'
# parts[2] -> ' _self'
# parts[3] -> '' or trailing
old_url = parts[1]
# 1) Prepend base if needed
new_url = inject_base_url(old_url)
# 2) Possibly add &model=1
new_url = append_model_param(new_url, model_selected)
# Recombine
new_line = f"{parts[0]}\"{new_url}\" {parts[2]}"
new_lines.append(new_line)
else:
# If we can't parse it, keep it as is
new_lines.append(line)
else:
new_lines.append(line)
mermaid_code = "\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)
components.html(diagram_html, height=400, scrolling=True)
# ---------------------------------------------
# Two-column interface: Markdown & Mermaid
# ---------------------------------------------
left_col, right_col = st.columns(2)
# --- Left: Markdown Editor
with left_col:
st.subheader("Markdown Side ๐Ÿ“")
if "markdown_text" not in st.session_state:
st.session_state["markdown_text"] = "## Hello!\nType some *Markdown* here.\n"
markdown_text = st.text_area(
"Edit Markdown:",
value=st.session_state["markdown_text"],
height=300
)
st.session_state["markdown_text"] = markdown_text
colA, colB = st.columns(2)
with colA:
if st.button("๐Ÿ”„ Refresh Markdown"):
st.write("**Markdown** content refreshed! ๐Ÿฟ")
with colB:
if st.button("โŒ Clear Markdown"):
st.session_state["markdown_text"] = ""
st.rerun()
st.markdown("---")
st.markdown("**Preview:**")
st.markdown(markdown_text)
# --- Right: Mermaid Editor
with right_col:
st.subheader("Mermaid Side ๐Ÿงœโ€โ™‚๏ธ")
# We store the final code in session state, so user can edit
if "current_mermaid" not in st.session_state:
st.session_state["current_mermaid"] = mermaid_code
mermaid_input = st.text_area(
"Edit Mermaid Code:",
value=st.session_state["current_mermaid"],
height=300
)
colC, colD = st.columns(2)
with colC:
if st.button("๐ŸŽจ Refresh Diagram"):
st.session_state["current_mermaid"] = mermaid_input
st.write("**Mermaid** diagram refreshed! ๐ŸŒˆ")
st.rerun()
with colD:
if st.button("โŒ Clear Mermaid"):
st.session_state["current_mermaid"] = ""
st.rerun()
st.markdown("---")
st.markdown("**Mermaid Source:**")
st.code(mermaid_input, language="python", line_numbers=True)
# ---------------------------------------------
# Media Galleries
# ---------------------------------------------
st.markdown("---")
st.header("Media Galleries")
num_columns_images = st.slider("Choose Number of Image Columns", 1, 15, 5, key="num_columns_images")
display_images_and_wikipedia_summaries(num_columns_images)
num_columns_video = st.slider("Choose Number of Video Columns", 1, 15, 5, key="num_columns_video")
display_videos_and_links(num_columns_video)
# (Optionally) Extended text interface
showExtendedTextInterface = False
if showExtendedTextInterface:
# For example:
# 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
# ---------------------------------------------
FileSidebar()
# ---------------------------------------------
# Random Title at the bottom
# ---------------------------------------------
titles = [
"๐Ÿง ๐ŸŽญ Semantic Symphonies & Episodic Encores",
"๐ŸŒŒ๐ŸŽผ AI Rhythms of Memory Lane",
"๐ŸŽญ๐ŸŽ‰ Cognitive Crescendos & Neural Harmonies",
"๐Ÿง ๐ŸŽบ Mnemonic Melodies & Synaptic Grooves",
"๐ŸŽผ๐ŸŽธ Straight Outta Cognition",
"๐Ÿฅ๐ŸŽป Jazzy Jambalaya of AI Memories",
"๐Ÿฐ Semantic Soul & Episodic Essence",
"๐Ÿฅ๐ŸŽป The Music Of AI's Mind"
]
st.markdown(f"**{random.choice(titles)}**")
if __name__ == "__main__":
main()