|
import streamlit as st |
|
import streamlit.components.v1 as components |
|
import os |
|
import json |
|
import random |
|
import base64 |
|
import glob |
|
import math |
|
import openai |
|
import pytz |
|
import re |
|
import requests |
|
import textract |
|
import time |
|
import zipfile |
|
import dotenv |
|
|
|
from gradio_client import Client |
|
from audio_recorder_streamlit import audio_recorder |
|
from bs4 import BeautifulSoup |
|
from collections import deque |
|
from datetime import datetime |
|
from dotenv import load_dotenv |
|
from huggingface_hub import InferenceClient |
|
from io import BytesIO |
|
from openai import ChatCompletion |
|
from PyPDF2 import PdfReader |
|
from templates import bot_template, css, user_template |
|
from xml.etree import ElementTree as ET |
|
from PIL import Image |
|
from urllib.parse import quote |
|
|
|
|
|
Site_Name = 'Scholarly-Article-Document-Search-With-Memory' |
|
title="🔬🧠ScienceBrain.AI" |
|
helpURL='https://huggingface.co/awacke1' |
|
bugURL='https://huggingface.co/spaces/awacke1' |
|
icons='🔬' |
|
|
|
st.set_page_config( |
|
page_title=title, |
|
page_icon=icons, |
|
layout="wide", |
|
initial_sidebar_state="expanded", |
|
menu_items={ |
|
'Get Help': helpURL, |
|
'Report a bug': bugURL, |
|
'About': title |
|
} |
|
) |
|
|
|
|
|
def load_file(file_name): |
|
with open(file_name, "r", encoding='utf-8') as file: |
|
|
|
content = file.read() |
|
return content |
|
|
|
|
|
|
|
@st.cache_resource |
|
def SpeechSynthesis(result): |
|
documentHTML5=''' |
|
<!DOCTYPE html> |
|
<html> |
|
<head> |
|
<title>Read It Aloud</title> |
|
<script type="text/javascript"> |
|
function readAloud() { |
|
const text = document.getElementById("textArea").value; |
|
const speech = new SpeechSynthesisUtterance(text); |
|
window.speechSynthesis.speak(speech); |
|
} |
|
</script> |
|
</head> |
|
<body> |
|
<h1>🔊 Read It Aloud</h1> |
|
<textarea id="textArea" rows="10" cols="80"> |
|
''' |
|
documentHTML5 = documentHTML5 + result |
|
documentHTML5 = documentHTML5 + ''' |
|
</textarea> |
|
<br> |
|
<button onclick="readAloud()">🔊 Read Aloud</button> |
|
</body> |
|
</html> |
|
''' |
|
components.html(documentHTML5, width=1280, height=300) |
|
|
|
def parse_to_markdown(text): |
|
return text |
|
|
|
|
|
|
|
|
|
import re |
|
|
|
def extract_urls(text): |
|
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('.') |
|
return '' |
|
|
|
|
|
|
|
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") |
|
|
|
|
|
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" |
|
) |
|
Question = '### 🔎 ' + query + '\r\n' |
|
References = response1[0] |
|
|
|
|
|
ReferenceLinks = extract_urls(References) |
|
|
|
RunSecondQuery = True |
|
if RunSecondQuery: |
|
|
|
response2 = client.predict( |
|
query, |
|
"mistralai/Mixtral-8x7B-Instruct-v0.1", |
|
True, |
|
api_name="/ask_llm" |
|
) |
|
if len(response2) > 10: |
|
Answer = response2 |
|
SpeechSynthesis(Answer) |
|
|
|
results = Question + '\r\n' + Answer + '\r\n' + References + '\r\n' + ReferenceLinks |
|
st.markdown(results) |
|
|
|
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") |
|
filename = generate_filename(query, "md") |
|
create_file(filename, query, results, should_save) |
|
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) |
|
|
|
|
|
PromptPrefix = 'Create a specification with streamlit functions creating markdown outlines and tables rich with appropriate emojis for methodical step by step rules defining the concepts at play. Use story structure architect rules to plan, structure and write three dramatic situations to include in the rules and how to play by matching the theme for topic of ' |
|
PromptPrefix2 = 'Create a streamlit python user app with full code listing to create a UI implementing the using streamlit, gradio, huggingface to create user interface elements like emoji buttons, sliders, drop downs, and data interfaces like dataframes to show tables, session_statematching this ruleset and thematic story plot line: ' |
|
PromptPrefix3 = 'Create a HTML5 aframe and javascript app using appropriate libraries to create a word game simulation with advanced libraries like aframe to render 3d scenes creating moving entities that stay within a bounding box but show text and animation in 3d for inventory, components and story entities. Show full code listing. Add a list of new random entities say 3 of a few different types to any list appropriately and use emojis to make things easier and fun to read. Use appropriate emojis in labels. Create the UI to implement storytelling in the style of a dungeon master, with features using three emoji appropriate text plot twists and recurring interesting funny fascinating and complex almost poetic named characters with genius traits and file IO, randomness, ten point choice lists, math distribution tradeoffs, witty humorous dilemnas with emoji , rewards, variables, reusable functions with parameters, and data driven app with python libraries and streamlit components for Javascript and HTML5. Use appropriate emojis for labels to summarize and list parts, function, conditions for topic:' |
|
|
|
|
|
roleplaying_glossary = { |
|
"🤖 AI Concepts": { |
|
"MoE (Mixture of Experts) 🧠": [ |
|
"What are Multi Agent Systems for Health", |
|
"What is Mixture of Experts for Health", |
|
"What are Semantic and Episodic Memory and what is Mirroring for Behavioral Health", |
|
"What are Self Rewarding AI Systems for Health", |
|
"How are AGI and AMI systems created using Multi Agent Systems and Mixture of Experts for Health" |
|
], |
|
"Multi Agent Systems (MAS) 🤝": [ |
|
"Distributed AI systems", |
|
"Autonomous agents interacting", |
|
"Cooperative and competitive behavior", |
|
"Decentralized problem-solving", |
|
"Applications in robotics, simulations, and more" |
|
], |
|
"Self Rewarding AI 🎁": [ |
|
"Intrinsic motivation for AI agents", |
|
"Autonomous goal setting and achievement", |
|
"Exploration and curiosity-driven learning", |
|
"Potential for open-ended development", |
|
"Research area in reinforcement learning" |
|
], |
|
"Semantic and Episodic Memory 📚": [ |
|
"Two types of long-term memory", |
|
"Semantic: facts and general knowledge", |
|
"Episodic: personal experiences and events", |
|
"Crucial for AI systems to understand and reason", |
|
"Research in knowledge representation and retrieval" |
|
] |
|
}, |
|
"🛠️ AI Tools & Platforms": { |
|
"AutoGen 🔧": [ |
|
"Automated machine learning (AutoML) tool", |
|
"Generates AI models based on requirements", |
|
"Simplifies AI development process", |
|
"Accessible to non-experts", |
|
"Integration with various data sources" |
|
], |
|
"ChatDev 💬": [ |
|
"Platform for building chatbots and conversational AI", |
|
"Drag-and-drop interface for designing chat flows", |
|
"Pre-built templates and integrations", |
|
"Supports multiple messaging platforms", |
|
"Analytics and performance tracking" |
|
], |
|
"Omniverse 🌐": [ |
|
"Nvidia's 3D simulation and collaboration platform", |
|
"Physically accurate virtual worlds", |
|
"Supports AI training and testing", |
|
"Used in industries like robotics, architecture, and gaming", |
|
"Enables seamless collaboration and data exchange" |
|
], |
|
"Lumiere 🎥": [ |
|
"AI-powered video analytics platform", |
|
"Extracts insights and metadata from video content", |
|
"Facial recognition and object detection", |
|
"Sentiment analysis and scene understanding", |
|
"Applications in security, media, and marketing" |
|
], |
|
"SORA 🏗️": [ |
|
"Scalable Open Research Architecture", |
|
"Framework for distributed AI research and development", |
|
"Modular and extensible design", |
|
"Facilitates collaboration and reproducibility", |
|
"Supports various AI algorithms and models" |
|
] |
|
}, |
|
"🔬 Science Topics": { |
|
"Physics 🔭": [ |
|
"Astrophysics: galaxies, cosmology, planets, high energy phenomena, instrumentation, solar/stellar", |
|
|
|
"Condensed Matter: disordered systems, materials science, nano/mesoscale, quantum gases, soft matter, statistical mechanics, superconductivity", |
|
"General Relativity and Quantum Cosmology", |
|
"High Energy Physics: experiment, lattice, phenomenology, theory", |
|
"Mathematical Physics", |
|
"Nonlinear Sciences: adaptation, cellular automata, chaos, solvable systems, pattern formation", |
|
"Nuclear: experiment, theory", |
|
"Physics: accelerators, atmospherics, atomic/molecular, biophysics, chemical, computational, education, fluids, geophysics, optics, plasma, popular, space" |
|
], |
|
"Mathematics ➗": [ |
|
"Algebra: geometry, topology, number theory, combinatorics, representation theory", |
|
"Analysis: PDEs, functional, numerical, spectral theory, ODEs, complex variables", |
|
"Geometry: algebraic, differential, metric, symplectic, topological", |
|
"Probability and Statistics", |
|
"Applied Math: information theory, optimization and control" |
|
], |
|
"Computer Science 💻": [ |
|
"Artificial Intelligence and Machine Learning", |
|
|
|
"Computation and Language, Complexity, Engineering, Finance, Science", |
|
"Computer Vision, Graphics, Robotics", |
|
"Cryptography, Security, Blockchain", |
|
"Data Structures, Algorithms, Databases", |
|
"Distributed and Parallel Computing", |
|
"Formal Languages, Automata, Logic", |
|
"Information Theory, Signal Processing", |
|
"Networks, Internet Architecture, Social Networks", |
|
"Programming Languages, Software Engineering" |
|
], |
|
"Quantitative Biology 🧬": [ |
|
"Biomolecules, Cell Behavior, Genomics", |
|
"Molecular Networks, Neurons and Cognition", |
|
"Populations, Evolution, Ecology", |
|
"Quantitative Methods, Subcellular Processes", |
|
"Tissues, Organs, Organisms" |
|
], |
|
|
|
"Quantitative Finance 📈": [ |
|
"Computational and Mathematical Finance", |
|
"Econometrics and Statistical Finance", |
|
|
|
"Economics, Portfolio Management, Trading", |
|
"Pricing, Risk Management" |
|
], |
|
"Electrical Engineering 🔌": [ |
|
"Audio, Speech, Image and Video Processing", |
|
"Communications and Information Theory", |
|
"Signal Processing, Controls, Robotics", |
|
"Electronic Circuits, Embedded Systems" |
|
] |
|
} |
|
} |
|
|
|
|
|
|
|
@st.cache_resource |
|
def display_glossary_entity(k): |
|
search_urls = { |
|
"🚀🌌ArXiv": lambda k: f"/?q={quote(k)}", |
|
"🃏Analyst": lambda k: f"/?q={quote(k)}-{quote(PromptPrefix)}", |
|
"📚PyCoder": lambda k: f"/?q={quote(k)}-{quote(PromptPrefix2)}", |
|
"🔬JSCoder": lambda k: f"/?q={quote(k)}-{quote(PromptPrefix3)}", |
|
"📖Wiki": lambda k: f"https://en.wikipedia.org/wiki/{quote(k)}", |
|
"🔍Google": lambda k: f"https://www.google.com/search?q={quote(k)}", |
|
"🔎Bing": lambda k: f"https://www.bing.com/search?q={quote(k)}", |
|
"🎥YouTube": lambda k: f"https://www.youtube.com/results?search_query={quote(k)}", |
|
"🐦Twitter": lambda k: f"https://twitter.com/search?q={quote(k)}", |
|
} |
|
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) |
|
|
|
|
|
@st.cache_resource |
|
def display_glossary_grid(roleplaying_glossary): |
|
search_urls = { |
|
"🚀🌌ArXiv": lambda k: f"/?q={quote(k)}", |
|
"🃏Analyst": lambda k: f"/?q={quote(k)}-{quote(PromptPrefix)}", |
|
"📚PyCoder": lambda k: f"/?q={quote(k)}-{quote(PromptPrefix2)}", |
|
"🔬JSCoder": lambda k: f"/?q={quote(k)}-{quote(PromptPrefix3)}", |
|
"📖Wiki": lambda k: f"https://en.wikipedia.org/wiki/{quote(k)}", |
|
"🔍Google": lambda k: f"https://www.google.com/search?q={quote(k)}", |
|
"▶️YouTube": lambda k: f"https://www.youtube.com/results?search_query={quote(k)}", |
|
"🔎Bing": lambda k: f"https://www.bing.com/search?q={quote(k)}", |
|
"🎥YouTube": lambda k: f"https://www.youtube.com/results?search_query={quote(k)}", |
|
"🐦Twitter": lambda k: f"https://twitter.com/search?q={quote(k)}", |
|
} |
|
|
|
for category, details in roleplaying_glossary.items(): |
|
st.write(f"### {category}") |
|
cols = st.columns(len(details)) |
|
|
|
for idx, (game, terms) in enumerate(details.items()): |
|
with cols[idx]: |
|
st.markdown(f"#### {game}") |
|
for term in terms: |
|
links_md = ' '.join([f"[{emoji}]({url(term)})" for emoji, url in search_urls.items()]) |
|
st.markdown(f"**{term}** <small>{links_md}</small>", unsafe_allow_html=True) |
|
|
|
|
|
@st.cache_resource |
|
def get_table_download_link(file_path): |
|
|
|
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] |
|
if ext == '.txt': |
|
mime_type = 'text/plain' |
|
elif ext == '.py': |
|
mime_type = 'text/plain' |
|
elif ext == '.xlsx': |
|
mime_type = 'text/plain' |
|
elif ext == '.csv': |
|
mime_type = 'text/plain' |
|
elif ext == '.htm': |
|
mime_type = 'text/html' |
|
elif ext == '.md': |
|
mime_type = 'text/markdown' |
|
elif ext == '.wav': |
|
mime_type = 'audio/wav' |
|
else: |
|
mime_type = 'application/octet-stream' |
|
href = f'<a href="data:{mime_type};base64,{b64}" target="_blank" download="{file_name}">{file_name}</a>' |
|
return href |
|
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() |
|
href = f'<a href="data:application/zip;base64,{b64}" download="{zip_file}">Download All</a>' |
|
return href |
|
|
|
def get_file(): |
|
st.write(st.session_state['file']) |
|
|
|
def SaveFileTextClicked(): |
|
fileText = st.session_state.file_content_area |
|
fileName = st.session_state.file_name_input |
|
with open(fileName, 'w', encoding='utf-8') as file: |
|
file.write(fileText) |
|
st.markdown('Saved ' + fileName + '.') |
|
|
|
def SaveFileNameClicked(): |
|
newFileName = st.session_state.file_name_input |
|
oldFileName = st.session_state.filename |
|
if (newFileName!=oldFileName): |
|
os.rename(oldFileName, newFileName) |
|
st.markdown('Renamed file ' + oldFileName + ' to ' + newFileName + '.') |
|
newFileText = st.session_state.file_content_area |
|
oldFileText = st.session_state.filetext |
|
|
|
|
|
|
|
def compare_and_delete_files(files): |
|
if not files: |
|
st.warning("No files to compare.") |
|
return |
|
|
|
|
|
file_sizes = {} |
|
for file in files: |
|
size = os.path.getsize(file) |
|
if size in file_sizes: |
|
file_sizes[size].append(file) |
|
else: |
|
file_sizes[size] = [file] |
|
|
|
|
|
for size, paths in file_sizes.items(): |
|
if len(paths) > 1: |
|
latest_file = max(paths, key=os.path.getmtime) |
|
for file in paths: |
|
if file != latest_file: |
|
os.remove(file) |
|
st.success(f"Deleted {file} as a duplicate.") |
|
st.rerun() |
|
|
|
|
|
def get_file_size(file_path): |
|
return os.path.getsize(file_path) |
|
|
|
def FileSidebar(): |
|
|
|
|
|
all_files = glob.glob("*.md") |
|
all_files = [file for file in all_files if len(os.path.splitext(file)[0]) >= 10] |
|
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("🗑 Delete All"): |
|
for file in all_files: |
|
os.remove(file) |
|
st.rerun() |
|
with Files2: |
|
if st.button("⬇️ 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("🌐", 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("📂", 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("▶️", 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): |
|
os.remove(file) |
|
file_name=file |
|
st.rerun() |
|
next_action='delete' |
|
st.session_state['next_action'] = next_action |
|
|
|
|
|
|
|
file_sizes = [get_file_size(file) for file in all_files] |
|
previous_size = None |
|
st.sidebar.title("File Operations") |
|
for file, size in zip(all_files, file_sizes): |
|
duplicate_flag = "🚩" if size == previous_size else "" |
|
with st.sidebar.expander(f"File: {file} {duplicate_flag}"): |
|
st.text(f"Size: {size} bytes") |
|
|
|
if st.button("View", key=f"view_{file}"): |
|
try: |
|
with open(file, "r", encoding='utf-8') as f: |
|
file_content = f.read() |
|
st.code(file_content, language="markdown") |
|
except UnicodeDecodeError: |
|
st.error("Failed to decode the file with UTF-8. It might contain non-UTF-8 encoded characters.") |
|
|
|
if st.button("Delete", key=f"delete3_{file}"): |
|
os.remove(file) |
|
st.rerun() |
|
previous_size = size |
|
|
|
if len(file_contents) > 0: |
|
if next_action=='open': |
|
if 'lastfilename' not in st.session_state: |
|
st.session_state['lastfilename'] = '' |
|
if 'filename' not in st.session_state: |
|
st.session_state['filename'] = '' |
|
if 'filetext' not in st.session_state: |
|
st.session_state['filetext'] = '' |
|
open1, open2 = st.columns(spec=[.8,.2]) |
|
|
|
with open1: |
|
|
|
file_name_input = st.text_input(key='file_name_input', on_change=SaveFileNameClicked, label="File Name:",value=file_name ) |
|
file_content_area = st.text_area(key='file_content_area', on_change=SaveFileTextClicked, label="File Contents:", value=file_contents, height=300) |
|
|
|
ShowButtons = False |
|
if ShowButtons: |
|
bp1,bp2 = st.columns([.5,.5]) |
|
with bp1: |
|
if st.button(label='💾 Save Name'): |
|
SaveFileNameClicked() |
|
with bp2: |
|
if st.button(label='💾 Save File'): |
|
SaveFileTextClicked() |
|
|
|
new_file_content_area = st.session_state['file_content_area'] |
|
if new_file_content_area != file_contents: |
|
st.markdown(new_file_content_area) |
|
|
|
if st.button("🔍 Run AI Meta Strategy", key="filecontentssearch"): |
|
|
|
filesearch = PromptPrefix + file_content_area |
|
st.markdown(filesearch) |
|
|
|
if st.button(key=rerun, label='🔍AI Search' ): |
|
search_glossary(filesearch) |
|
|
|
if next_action=='md': |
|
st.markdown(file_contents) |
|
buttonlabel = '🔍Run' |
|
if st.button(key='Runmd', label = buttonlabel): |
|
user_prompt = file_contents |
|
|
|
|
|
|
|
|
|
|
|
if next_action=='search': |
|
file_content_area = st.text_area("File Contents:", file_contents, height=500) |
|
user_prompt = file_contents |
|
|
|
|
|
filesearch = PromptPrefix2 + file_content_area |
|
st.markdown(filesearch) |
|
if st.button(key=rerun, label='🔍Re-Code' ): |
|
|
|
search_arxiv(filesearch) |
|
|
|
|
|
|
|
|
|
|
|
|
|
titles = [ |
|
"🧠🎭 Semantic Symphonies 🎹🎸 & Episodic Encores 🥁🎻", |
|
"🌌🎼 AI Rhythms 🎺🎷 of Memory Lane 🏰", |
|
"🎭🎉 Cognitive Crescendos 🎹💃 & Neural Harmonies 🎸🎤", |
|
"🧠🎺 Mnemonic Melodies 🎷 & Synaptic Grooves 🥁", |
|
"🎼🎸 Straight Outta Cognition ⚙️", |
|
"🥁🎻 Jazzy 🎷 Jambalaya 🍛 of AI Memories", |
|
"🏰 Semantic 🧠 Soul 🙌 & Episodic 📜 Essence", |
|
"🥁🎻 The Music Of AI's Mind 🧠🎭🎉" |
|
] |
|
|
|
selected_title = random.choice(titles) |
|
st.markdown(f"**{selected_title}**") |
|
|
|
FileSidebar() |
|
|
|
|
|
|
|
def get_image_as_base64(url): |
|
response = requests.get(url) |
|
if response.status_code == 200: |
|
|
|
return base64.b64encode(response.content).decode("utf-8") |
|
else: |
|
return None |
|
|
|
def create_download_link(filename, base64_str): |
|
href = f'<a href="data:file/png;base64,{base64_str}" download="{filename}">Download Image</a>' |
|
return href |
|
|
|
@st.cache_resource |
|
def SideBarImageShuffle(): |
|
image_urls = [ |
|
"https://cdn-uploads.huggingface.co/production/uploads/620630b603825909dcbeba35/cfhJIasuxLkT5fnaAE6Gj.png", |
|
"https://cdn-uploads.huggingface.co/production/uploads/620630b603825909dcbeba35/UMo4oWNrrd6RLLzsFxQAi.png", |
|
"https://cdn-uploads.huggingface.co/production/uploads/620630b603825909dcbeba35/o_EH4cTs5Qxiu7xTZw9I3.png", |
|
"https://cdn-uploads.huggingface.co/production/uploads/620630b603825909dcbeba35/cmCZ5RTdSx3usMm7MwwWK.png", |
|
] |
|
|
|
selected_image_url = random.choice(image_urls) |
|
selected_image_base64 = get_image_as_base64(selected_image_url) |
|
if selected_image_base64 is not None: |
|
with st.sidebar: |
|
st.markdown(f"") |
|
else: |
|
st.sidebar.write("Failed to load the image.") |
|
|
|
ShowSideImages=False |
|
if ShowSideImages: |
|
SideBarImageShuffle() |
|
|
|
|
|
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): |
|
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"] += 1 |
|
score_data["score"] += increment |
|
with open(score_file, "w") as file: |
|
json.dump(score_data, file) |
|
return score_data["score"] |
|
|
|
|
|
def load_score(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) |
|
return score_data["score"] |
|
return 0 |
|
|
|
|
|
|
|
@st.cache_resource |
|
def search_glossary(query): |
|
|
|
|
|
|
|
|
|
all="" |
|
st.markdown(f"- {query}") |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern") |
|
response2 = client.predict( |
|
query, |
|
|
|
|
|
"google/gemma-7b-it", |
|
True, |
|
api_name="/ask_llm" |
|
) |
|
st.write('🔍Run of Multi-Agent System Paper Summary Spec is Complete') |
|
st.markdown(response2) |
|
|
|
|
|
client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern") |
|
response1 = client.predict( |
|
query, |
|
10, |
|
"Semantic Search - up to 10 Mar 2024", |
|
"mistralai/Mixtral-8x7B-Instruct-v0.1", |
|
api_name="/update_with_rag_md" |
|
) |
|
st.write('🔍Run of Multi-Agent System Paper References is Complete') |
|
|
|
|
|
responseall = response2 + response1[0] + response1[1] |
|
st.markdown(responseall) |
|
return responseall |
|
|
|
|
|
RunPostArxivLLM = False |
|
if RunPostArxivLLM: |
|
|
|
PaperSummarizer = ' Create a paper summary as a markdown table with paper links clustering the features writing short markdown emoji outlines to extract three main ideas from each of the ten summaries. For each one create three simple points led by an emoji of the main three steps needed as method step process for implementing the idea as a single app.py streamlit python app. ' |
|
response2 = chat_with_model(PaperSummarizer + str(response1)) |
|
st.write('🔍Run 3 - Paper Summarizer is Complete.') |
|
|
|
|
|
AppSpecifier = ' Design and write a streamlit python code listing and specification that implements each scientific method steps as ten functions keeping specification in a markdown table in the function comments with original paper link to outline the AI pipeline ensemble implementing code as full plan to build.' |
|
response3 = chat_with_model(AppSpecifier + str(response2)) |
|
st.write('🔍Run 4 - AppSpecifier is Complete.') |
|
|
|
|
|
PythonAppCoder = ' Complete this streamlit python app implementing the functions in detail using appropriate python libraries and streamlit user interface elements. Show full code listing for the completed detail app as full code listing with no comments or commentary. ' |
|
|
|
|
|
response4 = chat_with_model(PythonAppCoder + str(response3)) |
|
st.write('🔍Run Python AppCoder is Complete.') |
|
|
|
|
|
|
|
responseAll = '# Query: ' + query + '# Summary: ' + str(response2) + '# Streamlit App Specifier: ' + str(response3) + '# Complete Streamlit App: ' + str(response4) + '# Scholarly Article Links References: ' + str(response1) |
|
filename = generate_filename(responseAll, "md") |
|
create_file(filename, query, responseAll, should_save) |
|
|
|
return responseAll |
|
else: |
|
return response1 |
|
|
|
|
|
def display_glossary(glossary, area): |
|
if area in glossary: |
|
st.subheader(f"📘 Glossary for {area}") |
|
for game, terms in glossary[area].items(): |
|
st.markdown(f"### {game}") |
|
for idx, term in enumerate(terms, start=1): |
|
st.write(f"{idx}. {term}") |
|
|
|
|
|
|
|
|
|
def display_videos_and_links(num_columns): |
|
video_files = [f for f in os.listdir('.') if f.endswith('.mp4')] |
|
if not video_files: |
|
st.write("No MP4 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) |
|
col_index += 1 |
|
|
|
@st.cache_resource |
|
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]: |
|
image = Image.open(image_file) |
|
st.image(image, caption=image_file, use_column_width=True) |
|
k = image_file.split('.')[0] |
|
display_glossary_entity(k) |
|
col_index += 1 |
|
|
|
|
|
def get_all_query_params(key): |
|
return st.query_params().get(key, []) |
|
|
|
def clear_query_params(): |
|
st.query_params() |
|
|
|
|
|
|
|
def display_content_or_image(query): |
|
for category, terms in transhuman_glossary.items(): |
|
for term in terms: |
|
if query.lower() in term.lower(): |
|
st.subheader(f"Found in {category}:") |
|
st.write(term) |
|
return True |
|
image_dir = "images" |
|
image_path = f"{image_dir}/{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 |
|
|
|
game_emojis = { |
|
"Dungeons and Dragons": "🐉", |
|
"Call of Cthulhu": "🐙", |
|
"GURPS": "🎲", |
|
"Pathfinder": "🗺️", |
|
"Kindred of the East": "🌅", |
|
"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": "🌍", |
|
} |
|
|
|
|
|
def display_buttons_with_scores(num_columns_text): |
|
|
|
|
|
for category, games in roleplaying_glossary.items(): |
|
category_emoji = topic_emojis.get(category, "🔍") |
|
st.markdown(f"## {category_emoji} {category}") |
|
for game, terms in games.items(): |
|
game_emoji = game_emojis.get(game, "🎮") |
|
for term in terms: |
|
key = f"{category}_{game}_{term}".replace(' ', '_').lower() |
|
score = load_score(key) |
|
if st.button(f"{game_emoji} {category} {game} {term} {score}", key=key): |
|
update_score(key) |
|
|
|
query_prefix = f"{category_emoji} {game_emoji} ** {category} - {game} - {term} - **" |
|
|
|
|
|
query_body = f"Create a streamlit python app.py that produces a detailed markdown outline and emoji laden user interface with labels with the entity name and emojis in all labels with a set of streamlit UI components with drop down lists and dataframes and buttons with expander and sidebar for the app to run the data as default values mostly in text boxes. Feature a 3 point outline sith 3 subpoints each where each line has about six words describing this and also contain appropriate emoji for creating sumamry of all aspeccts of this topic. an outline for **{term}** with subpoints highlighting key aspects, using emojis for visual engagement. Include step-by-step rules and boldface important entities and ruleset elements." |
|
response = search_glossary(query_prefix + query_body) |
|
|
|
|
|
|
|
def get_all_query_params(key): |
|
return st.query_params().get(key, []) |
|
|
|
def clear_query_params(): |
|
st.query_params() |
|
|
|
|
|
API_URL = 'https://qe55p8afio98s0u3.us-east-1.aws.endpoints.huggingface.cloud' |
|
|
|
|
|
API_KEY = os.getenv('API_KEY') |
|
MODEL1="meta-llama/Llama-2-7b-chat-hf" |
|
MODEL1URL="https://huggingface.co/meta-llama/Llama-2-7b-chat-hf" |
|
HF_KEY = os.getenv('HF_KEY') |
|
headers = { |
|
"Authorization": f"Bearer {HF_KEY}", |
|
"Content-Type": "application/json" |
|
} |
|
key = os.getenv('OPENAI_API_KEY') |
|
prompt = "...." |
|
should_save = st.sidebar.checkbox("💾 Save", value=True, help="Save your session data.") |
|
|
|
|
|
|
|
|
|
|
|
@st.cache_resource |
|
def StreamLLMChatResponse(prompt): |
|
try: |
|
endpoint_url = API_URL |
|
hf_token = API_KEY |
|
st.write('Running client ' + endpoint_url) |
|
client = InferenceClient(endpoint_url, token=hf_token) |
|
gen_kwargs = dict( |
|
max_new_tokens=512, |
|
top_k=30, |
|
top_p=0.9, |
|
temperature=0.2, |
|
repetition_penalty=1.02, |
|
stop_sequences=["\nUser:", "<|endoftext|>", "</s>"], |
|
) |
|
stream = client.text_generation(prompt, stream=True, details=True, **gen_kwargs) |
|
report=[] |
|
res_box = st.empty() |
|
collected_chunks=[] |
|
collected_messages=[] |
|
allresults='' |
|
for r in stream: |
|
if r.token.special: |
|
continue |
|
if r.token.text in gen_kwargs["stop_sequences"]: |
|
break |
|
collected_chunks.append(r.token.text) |
|
chunk_message = r.token.text |
|
collected_messages.append(chunk_message) |
|
try: |
|
report.append(r.token.text) |
|
if len(r.token.text) > 0: |
|
result="".join(report).strip() |
|
res_box.markdown(f'*{result}*') |
|
|
|
except: |
|
st.write('Stream llm issue') |
|
SpeechSynthesis(result) |
|
return result |
|
except: |
|
st.write('Llama model is asleep. Starting up now on A10 - please give 5 minutes then retry as KEDA scales up from zero to activate running container(s).') |
|
|
|
|
|
def query(payload): |
|
response = requests.post(API_URL, headers=headers, json=payload) |
|
st.markdown(response.json()) |
|
return response.json() |
|
|
|
def get_output(prompt): |
|
return query({"inputs": prompt}) |
|
|
|
|
|
def generate_filename(prompt, file_type): |
|
central = pytz.timezone('US/Central') |
|
safe_date_time = datetime.now(central).strftime("%m%d_%H%M") |
|
replaced_prompt = prompt.replace(" ", "_").replace("\n", "_") |
|
safe_prompt = "".join(x for x in replaced_prompt if x.isalnum() or x == "_")[:255] |
|
|
|
return f"{safe_date_time}_{safe_prompt}.{file_type}" |
|
|
|
|
|
def transcribe_audio(openai_key, file_path, model): |
|
openai.api_key = openai_key |
|
OPENAI_API_URL = "https://api.openai.com/v1/audio/transcriptions" |
|
headers = { |
|
"Authorization": f"Bearer {openai_key}", |
|
} |
|
with open(file_path, 'rb') as f: |
|
data = {'file': f} |
|
st.write('STT transcript ' + OPENAI_API_URL) |
|
response = requests.post(OPENAI_API_URL, headers=headers, files=data, data={'model': model}) |
|
if response.status_code == 200: |
|
st.write(response.json()) |
|
chatResponse = chat_with_model(response.json().get('text'), '') |
|
transcript = response.json().get('text') |
|
filename = generate_filename(transcript, 'txt') |
|
response = chatResponse |
|
user_prompt = transcript |
|
create_file(filename, user_prompt, response, should_save) |
|
return transcript |
|
else: |
|
st.write(response.json()) |
|
st.error("Error in API call.") |
|
return None |
|
|
|
|
|
def save_and_play_audio(audio_recorder): |
|
audio_bytes = audio_recorder(key='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 create_file(filename, prompt, response, should_save=True): |
|
if not should_save: |
|
return |
|
base_filename, ext = os.path.splitext(filename) |
|
if ext in ['.txt', '.htm', '.md']: |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
with open(f"{base_filename}.md", 'w', encoding='utf-8') as file: |
|
|
|
|
|
file.write(response) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def truncate_document(document, length): |
|
return document[:length] |
|
def divide_document(document, max_length): |
|
return [document[i:i+max_length] for i in range(0, len(document), max_length)] |
|
|
|
def CompressXML(xml_text): |
|
root = ET.fromstring(xml_text) |
|
for elem in list(root.iter()): |
|
if isinstance(elem.tag, str) and 'Comment' in elem.tag: |
|
elem.parent.remove(elem) |
|
return ET.tostring(root, encoding='unicode', method="xml") |
|
|
|
|
|
@st.cache_resource |
|
def read_file_content(file,max_length): |
|
if file.type == "application/json": |
|
content = json.load(file) |
|
return str(content) |
|
elif file.type == "text/html" or file.type == "text/htm": |
|
content = BeautifulSoup(file, "html.parser") |
|
return content.text |
|
elif file.type == "application/xml" or file.type == "text/xml": |
|
tree = ET.parse(file) |
|
root = tree.getroot() |
|
xml = CompressXML(ET.tostring(root, encoding='unicode')) |
|
return xml |
|
elif file.type == "text/markdown" or file.type == "text/md": |
|
md = mistune.create_markdown() |
|
content = md(file.read().decode()) |
|
return content |
|
elif file.type == "text/plain": |
|
return file.getvalue().decode() |
|
else: |
|
return "" |
|
|
|
|
|
|
|
@st.cache_resource |
|
def chat_with_model(prompt, document_section='', model_choice='gpt-3.5-turbo'): |
|
model = model_choice |
|
conversation = [{'role': 'system', 'content': 'You are a coder, inventor, and writer of quotes on wisdom as a helpful expert in all fields of health, math, development and AI using python.'}] |
|
conversation.append({'role': 'user', 'content': prompt}) |
|
if len(document_section)>0: |
|
conversation.append({'role': 'assistant', 'content': document_section}) |
|
start_time = time.time() |
|
report = [] |
|
res_box = st.empty() |
|
collected_chunks = [] |
|
collected_messages = [] |
|
|
|
for chunk in openai.ChatCompletion.create(model=model_choice, messages=conversation, temperature=0.5, stream=True): |
|
collected_chunks.append(chunk) |
|
chunk_message = chunk['choices'][0]['delta'] |
|
collected_messages.append(chunk_message) |
|
content=chunk["choices"][0].get("delta",{}).get("content") |
|
try: |
|
report.append(content) |
|
if len(content) > 0: |
|
result = "".join(report).strip() |
|
res_box.markdown(f'*{result}*') |
|
except: |
|
st.write(' ') |
|
full_reply_content = ''.join([m.get('content', '') for m in collected_messages]) |
|
st.write("Elapsed time:") |
|
st.write(time.time() - start_time) |
|
return full_reply_content |
|
|
|
|
|
@st.cache_resource |
|
def chat_with_model45(prompt, document_section='', model_choice='gpt-4-0125-preview'): |
|
model = model_choice |
|
conversation = [{'role': 'system', 'content': 'You are a coder, inventor, and writer of quotes on wisdom as a helpful expert in all fields of health, math, development and AI using python.'}] |
|
conversation.append({'role': 'user', 'content': prompt}) |
|
if len(document_section)>0: |
|
conversation.append({'role': 'assistant', 'content': document_section}) |
|
start_time = time.time() |
|
report = [] |
|
res_box = st.empty() |
|
collected_chunks = [] |
|
collected_messages = [] |
|
|
|
for chunk in openai.ChatCompletion.create(model=model_choice, messages=conversation, temperature=0.5, stream=True): |
|
collected_chunks.append(chunk) |
|
chunk_message = chunk['choices'][0]['delta'] |
|
collected_messages.append(chunk_message) |
|
content=chunk["choices"][0].get("delta",{}).get("content") |
|
try: |
|
report.append(content) |
|
if len(content) > 0: |
|
result = "".join(report).strip() |
|
res_box.markdown(f'*{result}*') |
|
except: |
|
st.write(' ') |
|
full_reply_content = ''.join([m.get('content', '') for m in collected_messages]) |
|
st.write("Elapsed time:") |
|
st.write(time.time() - start_time) |
|
return full_reply_content |
|
|
|
@st.cache_resource |
|
def chat_with_file_contents(prompt, file_content, model_choice='gpt-3.5-turbo'): |
|
|
|
conversation = [{'role': 'system', 'content': 'You are a helpful assistant.'}] |
|
conversation.append({'role': 'user', 'content': prompt}) |
|
if len(file_content)>0: |
|
conversation.append({'role': 'assistant', 'content': file_content}) |
|
response = openai.ChatCompletion.create(model=model_choice, messages=conversation) |
|
return response['choices'][0]['message']['content'] |
|
|
|
|
|
def extract_mime_type(file): |
|
if isinstance(file, str): |
|
pattern = r"type='(.*?)'" |
|
match = re.search(pattern, file) |
|
if match: |
|
return match.group(1) |
|
else: |
|
raise ValueError(f"Unable to extract MIME type from {file}") |
|
elif isinstance(file, streamlit.UploadedFile): |
|
return file.type |
|
else: |
|
raise TypeError("Input should be a string or a streamlit.UploadedFile object") |
|
|
|
def extract_file_extension(file): |
|
|
|
file_name = file.name |
|
pattern = r".*?\.(.*?)$" |
|
match = re.search(pattern, file_name) |
|
if match: |
|
return match.group(1) |
|
else: |
|
raise ValueError(f"Unable to extract file extension from {file_name}") |
|
|
|
|
|
@st.cache_resource |
|
def pdf2txt(docs): |
|
text = "" |
|
for file in docs: |
|
file_extension = extract_file_extension(file) |
|
st.write(f"File type extension: {file_extension}") |
|
if file_extension.lower() in ['py', 'txt', 'html', 'htm', 'xml', 'json']: |
|
text += file.getvalue().decode('utf-8') |
|
elif file_extension.lower() == 'pdf': |
|
from PyPDF2 import PdfReader |
|
pdf = PdfReader(BytesIO(file.getvalue())) |
|
for page in range(len(pdf.pages)): |
|
text += pdf.pages[page].extract_text() |
|
return text |
|
|
|
def txt2chunks(text): |
|
text_splitter = CharacterTextSplitter(separator="\n", chunk_size=1000, chunk_overlap=200, length_function=len) |
|
return text_splitter.split_text(text) |
|
|
|
|
|
@st.cache_resource |
|
def vector_store(text_chunks): |
|
embeddings = OpenAIEmbeddings(openai_api_key=key) |
|
return FAISS.from_texts(texts=text_chunks, embedding=embeddings) |
|
|
|
|
|
@st.cache_resource |
|
def get_chain(vectorstore): |
|
llm = ChatOpenAI() |
|
memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True) |
|
return ConversationalRetrievalChain.from_llm(llm=llm, retriever=vectorstore.as_retriever(), memory=memory) |
|
|
|
def process_user_input(user_question): |
|
response = st.session_state.conversation({'question': user_question}) |
|
st.session_state.chat_history = response['chat_history'] |
|
for i, message in enumerate(st.session_state.chat_history): |
|
template = user_template if i % 2 == 0 else bot_template |
|
st.write(template.replace("{{MSG}}", message.content), unsafe_allow_html=True) |
|
filename = generate_filename(user_question, 'txt') |
|
response = message.content |
|
user_prompt = user_question |
|
create_file(filename, user_prompt, response, should_save) |
|
|
|
def divide_prompt(prompt, max_length): |
|
words = prompt.split() |
|
chunks = [] |
|
current_chunk = [] |
|
current_length = 0 |
|
for word in words: |
|
if len(word) + current_length <= max_length: |
|
current_length += len(word) + 1 |
|
current_chunk.append(word) |
|
else: |
|
chunks.append(' '.join(current_chunk)) |
|
current_chunk = [word] |
|
current_length = len(word) |
|
chunks.append(' '.join(current_chunk)) |
|
return chunks |
|
|
|
|
|
|
|
API_URL_IE = f'https://tonpixzfvq3791u9.us-east-1.aws.endpoints.huggingface.cloud' |
|
API_URL_IE = "https://api-inference.huggingface.co/models/openai/whisper-small.en" |
|
MODEL2 = "openai/whisper-small.en" |
|
MODEL2_URL = "https://huggingface.co/openai/whisper-small.en" |
|
HF_KEY = st.secrets['HF_KEY'] |
|
headers = { |
|
"Authorization": f"Bearer {HF_KEY}", |
|
"Content-Type": "audio/wav" |
|
} |
|
|
|
def query(filename): |
|
with open(filename, "rb") as f: |
|
data = f.read() |
|
response = requests.post(API_URL_IE, headers=headers, data=data) |
|
return response.json() |
|
|
|
def generate_filename(prompt, file_type): |
|
central = pytz.timezone('US/Central') |
|
safe_date_time = datetime.now(central).strftime("%m%d_%H%M") |
|
replaced_prompt = prompt.replace(" ", "_").replace("\n", "_") |
|
safe_prompt = "".join(x for x in replaced_prompt if x.isalnum() or x == "_")[:90] |
|
return f"{safe_date_time}_{safe_prompt}.{file_type}" |
|
|
|
|
|
def save_and_play_audio(audio_recorder): |
|
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 |
|
|
|
|
|
def transcribe_audio(filename): |
|
output = query(filename) |
|
return output |
|
|
|
|
|
|
|
def StreamMedChatResponse(topic): |
|
st.write(f"Showing resources or questions related to: {topic}") |
|
|
|
|
|
def get_base64_encoded_file(file_path): |
|
with open(file_path, "rb") as file: |
|
return base64.b64encode(file.read()).decode() |
|
|
|
|
|
def get_audio_download_link(file_path): |
|
base64_file = get_base64_encoded_file(file_path) |
|
return f'<a href="data:file/wav;base64,{base64_file}" download="{os.path.basename(file_path)}">⬇️ Download Audio</a>' |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
all_files = glob.glob("*.wav") |
|
all_files = [file for file in all_files if len(os.path.splitext(file)[0]) >= 10] |
|
all_files.sort(key=lambda x: (os.path.splitext(x)[1], x), reverse=True) |
|
|
|
filekey = 'delall' |
|
if st.sidebar.button("🗑 Delete All Audio", key=filekey): |
|
for file in all_files: |
|
os.remove(file) |
|
st.rerun() |
|
|
|
for file in all_files: |
|
col1, col2 = st.sidebar.columns([6, 1]) |
|
with col1: |
|
st.markdown(file) |
|
if st.button("🎵", key="play_" + file): |
|
audio_file = open(file, 'rb') |
|
audio_bytes = audio_file.read() |
|
st.audio(audio_bytes, format='audio/wav') |
|
|
|
|
|
with col2: |
|
if st.button("🗑", key="delete_" + file): |
|
os.remove(file) |
|
st.rerun() |
|
|
|
|
|
|
|
GiveFeedback=False |
|
if GiveFeedback: |
|
with st.expander("Give your feedback 👍", expanded=False): |
|
feedback = st.radio("Step 8: Give your feedback", ("👍 Upvote", "👎 Downvote")) |
|
if feedback == "👍 Upvote": |
|
st.write("You upvoted 👍. Thank you for your feedback!") |
|
else: |
|
st.write("You downvoted 👎. Thank you for your feedback!") |
|
load_dotenv() |
|
st.write(css, unsafe_allow_html=True) |
|
st.header("Chat with documents :books:") |
|
user_question = st.text_input("Ask a question about your documents:") |
|
if user_question: |
|
process_user_input(user_question) |
|
with st.sidebar: |
|
st.subheader("Your documents") |
|
docs = st.file_uploader("import documents", accept_multiple_files=True) |
|
with st.spinner("Processing"): |
|
raw = pdf2txt(docs) |
|
if len(raw) > 0: |
|
length = str(len(raw)) |
|
text_chunks = txt2chunks(raw) |
|
vectorstore = vector_store(text_chunks) |
|
st.session_state.conversation = get_chain(vectorstore) |
|
st.markdown('# AI Search Index of Length:' + length + ' Created.') |
|
filename = generate_filename(raw, 'txt') |
|
create_file(filename, raw, '', should_save) |
|
|
|
|
|
try: |
|
query_params = st.query_params |
|
query = (query_params.get('q') or query_params.get('query') or ['']) |
|
if len(query) > 1: |
|
result = search_arxiv(query) |
|
|
|
except: |
|
st.markdown(' ') |
|
|
|
if 'action' in st.query_params: |
|
action = st.query_params()['action'][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 'query' in st.query_params: |
|
query = st.query_params['query'][0] |
|
|
|
display_content_or_image(query) |
|
|
|
def transcribe_canary(filename): |
|
from gradio_client import Client |
|
|
|
client = Client("https://awacke1-speech-recognition-canary-nvidiat4.hf.space/") |
|
result = client.predict( |
|
filename, |
|
"English", |
|
"English", |
|
True, |
|
api_name="/transcribe" |
|
) |
|
st.write(result) |
|
return result |
|
|
|
filename = save_and_play_audio(audio_recorder) |
|
if filename is not None: |
|
transcript='' |
|
|
|
transcript=transcribe_canary(filename) |
|
result = search_arxiv(transcript) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
response = StreamLLMChatResponse(transcript) |
|
filename_txt = generate_filename(transcript, "md") |
|
create_file(filename_txt, transcript, response, should_save) |
|
filename_wav = filename_txt.replace('.txt', '.wav') |
|
import shutil |
|
try: |
|
if os.path.exists(filename): |
|
shutil.copyfile(filename, filename_wav) |
|
except: |
|
st.write('.') |
|
if os.path.exists(filename): |
|
os.remove(filename) |
|
|
|
|
|
|
|
|
|
prompt = ''' |
|
What is MoE? |
|
What are Multi Agent Systems? |
|
What is Self Rewarding AI? |
|
What is Semantic and Episodic memory? |
|
What is AutoGen? |
|
What is ChatDev? |
|
What is Omniverse? |
|
What is Lumiere? |
|
What is SORA? |
|
''' |
|
|
|
import streamlit as st |
|
|
|
personality_factors = """ |
|
1. 🌈 Openness (Being open to new things) |
|
- 🎭 Imagination (Enjoying fantasy and daydreaming) |
|
- 🎨 Artistic Interests (Appreciating beauty and art) |
|
- 🎸 Creativity (Coming up with new ideas) |
|
- 🌍 Curiosity (Wanting to explore and learn) |
|
- 🌿 Unconventional (Being different and unique) |
|
- 🧩 Complexity (Enjoying deep thoughts and feelings) |
|
- 🌌 Adventurousness (Seeking new experiences) |
|
|
|
2. 💼 Conscientiousness (Being organized and reliable) |
|
- 🎯 Competence (Feeling capable and effective) |
|
- 📊 Orderliness (Keeping things neat and tidy) |
|
- 📅 Dutifulness (Following rules and doing what's right) |
|
- 🏆 Achievement (Working hard to reach goals) |
|
- 🧘♀️ Self-Discipline (Staying focused and in control) |
|
- 🤔 Thoughtfulness (Thinking before acting) |
|
- 🕰️ Time Management (Using time wisely) |
|
- 🧽 Perfectionism (Wanting things to be just right) |
|
|
|
3. 🎉 Extraversion (Being outgoing and social) |
|
- 🤗 Friendliness (Being kind and welcoming) |
|
- 👥 Sociability (Enjoying being with others) |
|
- 🗣️ Assertiveness (Speaking up and taking charge) |
|
- ⚡ Energy (Being active and lively) |
|
- 🎢 Excitement (Seeking thrills and fun) |
|
- 😊 Cheerfulness (Feeling happy and positive) |
|
- 🎤 Talkativeness (Enjoying conversation) |
|
- 🌞 Enthusiasm (Showing excitement and interest) |
|
|
|
4. 🤝 Agreeableness (Being kind and cooperative) |
|
- 🤲 Trust (Believing in others' goodness) |
|
- 🌿 Honesty (Being truthful and sincere) |
|
- 🤝 Cooperation (Working well with others) |
|
- 🌸 Helpfulness (Being generous and caring) |
|
- 🕊️ Compliance (Following rules and respecting authority) |
|
- 🙏 Modesty (Being humble and down-to-earth) |
|
- 💕 Empathy (Understanding others' feelings) |
|
- 🫂 Compassion (Caring about others' well-being) |
|
|
|
5. 😔 Neuroticism (Feeling negative emotions easily) |
|
- 😰 Anxiety (Worrying and feeling nervous) |
|
- 😡 Anger (Getting upset and frustrated) |
|
- 😢 Sadness (Feeling down and unhappy) |
|
- 😳 Self-Consciousness (Feeling shy and uneasy) |
|
- 🎢 Impulsiveness (Acting without thinking) |
|
- 🍃 Vulnerability (Being easily hurt or upset) |
|
- 🌪️ Moodiness (Having ups and downs in feelings) |
|
- 🎭 Negativity (Focusing on the bad side of things) |
|
""" |
|
|
|
|
|
session_state = {} |
|
if "search_queries" not in session_state: |
|
session_state["search_queries"] = [] |
|
example_input = st.text_input("Search", value=session_state["search_queries"][-1] if session_state["search_queries"] else "") |
|
if example_input: |
|
session_state["search_queries"].append(example_input) |
|
|
|
|
|
query=example_input |
|
if query: |
|
result = search_arxiv(query) |
|
|
|
|
|
st.markdown(' ') |
|
|
|
|
|
for example_input in session_state["search_queries"]: |
|
st.write(example_input) |
|
|
|
if st.button("Run Prompt", help="Click to run."): |
|
try: |
|
response=StreamLLMChatResponse(example_input) |
|
create_file(filename, example_input, response, should_save) |
|
except: |
|
st.write('model is asleep. Starting now on A10 GPU. Please wait one minute then retry. KEDA triggered.') |
|
|
|
openai.api_key = os.getenv('OPENAI_API_KEY') |
|
if openai.api_key == None: openai.api_key = st.secrets['OPENAI_API_KEY'] |
|
menu = ["txt", "htm", "xlsx", "csv", "md", "py"] |
|
choice = st.sidebar.selectbox("Output File Type:", menu) |
|
|
|
|
|
|
|
AddAFileForContext=False |
|
if AddAFileForContext: |
|
|
|
collength, colupload = st.columns([2,3]) |
|
with collength: |
|
|
|
max_length = 128000 |
|
with colupload: |
|
uploaded_file = st.file_uploader("Add a file for context:", type=["pdf", "xml", "json", "xlsx", "csv", "html", "htm", "md", "txt"]) |
|
document_sections = deque() |
|
document_responses = {} |
|
if uploaded_file is not None: |
|
file_content = read_file_content(uploaded_file, max_length) |
|
document_sections.extend(divide_document(file_content, max_length)) |
|
|
|
|
|
if len(document_sections) > 0: |
|
if st.button("👁️ View Upload"): |
|
st.markdown("**Sections of the uploaded file:**") |
|
for i, section in enumerate(list(document_sections)): |
|
st.markdown(f"**Section {i+1}**\n{section}") |
|
|
|
st.markdown("**Chat with the model:**") |
|
for i, section in enumerate(list(document_sections)): |
|
if i in document_responses: |
|
st.markdown(f"**Section {i+1}**\n{document_responses[i]}") |
|
else: |
|
if st.button(f"Chat about Section {i+1}"): |
|
st.write('Reasoning with your inputs...') |
|
st.write('Response:') |
|
st.write(response) |
|
document_responses[i] = response |
|
filename = generate_filename(f"{user_prompt}_section_{i+1}", choice) |
|
create_file(filename, user_prompt, response, should_save) |
|
st.sidebar.markdown(get_table_download_link(filename), unsafe_allow_html=True) |
|
|
|
|
|
num_columns_video=st.slider(key="num_columns_video", label="Choose Number of Video Columns", min_value=1, max_value=15, value=2) |
|
display_videos_and_links(num_columns_video) |
|
|
|
num_columns_images=st.slider(key="num_columns_images", label="Choose Number of Image Columns", min_value=1, max_value=15, value=2) |
|
display_images_and_wikipedia_summaries(num_columns_images) |
|
|
|
display_glossary_grid(roleplaying_glossary) |
|
|
|
num_columns_text=st.slider(key="num_columns_text", label="Choose Number of Text Columns", min_value=1, max_value=15, value=4) |
|
display_buttons_with_scores(num_columns_text) |
|
|
|
st.markdown(personality_factors) |
|
|
