Reprogramm demo

.gitignore

@@ -1,4 +1,887 @@
+### TeX template
+## Core latex/pdflatex auxiliary files:
+*.aux
+*.lof
+*.log
+*.lot
+*.fls
+*.out
+*.toc
+*.fmt
+*.fot
+*.cb
+*.cb2
+.*.lb
+
+## Intermediate documents:
+*.dvi
+*.xdv
+*-converted-to.*
+# these rules might exclude image files for figures etc.
+# *.ps
+# *.eps
+# *.pdf
+
+## Generated if empty string is given at "Please type another file name for output:"
+.pdf
+
+## Bibliography auxiliary files (bibtex/biblatex/biber):
+*.bbl
+*.bcf
+*.blg
+*-blx.aux
+*-blx.bib
+*.run.xml
+
+## Build tool auxiliary files:
+*.fdb_latexmk
+*.synctex
+*.synctex(busy)
+*.synctex.gz
+*.synctex.gz(busy)
+*.pdfsync
+
+## Build tool directories for auxiliary files
+# latexrun
+latex.out/
+
+## Auxiliary and intermediate files from other packages:
+# algorithms
+*.alg
+*.loa
+
+# achemso
+acs-*.bib
+
+# amsthm
+*.thm
+
+# beamer
+*.nav
+*.pre
+*.snm
+*.vrb
+
+# changes
+*.soc
+
+# comment
+*.cut
+
+# cprotect
+*.cpt
+
+# elsarticle (documentclass of Elsevier journals)
+*.spl
+
+# endnotes
+*.ent
+
+# fixme
+*.lox
+
+# feynmf/feynmp
+*.mf
+*.mp
+*.t[1-9]
+*.t[1-9][0-9]
+*.tfm
+
+#(r)(e)ledmac/(r)(e)ledpar
+*.end
+*.?end
+*.[1-9]
+*.[1-9][0-9]
+*.[1-9][0-9][0-9]
+*.[1-9]R
+*.[1-9][0-9]R
+*.[1-9][0-9][0-9]R
+*.eledsec[1-9]
+*.eledsec[1-9]R
+*.eledsec[1-9][0-9]
+*.eledsec[1-9][0-9]R
+*.eledsec[1-9][0-9][0-9]
+*.eledsec[1-9][0-9][0-9]R
+
+# glossaries
+*.acn
+*.acr
+*.glg
+*.glo
+*.gls
+*.glsdefs
+*.lzo
+*.lzs
+
+# uncomment this for glossaries-extra (will ignore makeindex's style files!)
+# *.ist
+
+# gnuplottex
+*-gnuplottex-*
+
+# gregoriotex
+*.gaux
+*.gtex
+
+# htlatex
+*.4ct
+*.4tc
+*.idv
+*.lg
+*.trc
+*.xref
+
+# hyperref
+*.brf
+
+# knitr
+*-concordance.tex
+# TODO Uncomment the next line if you use knitr and want to ignore its generated tikz files
+# *.tikz
+*-tikzDictionary
+
+# listings
+*.lol
+
+# luatexja-ruby
+*.ltjruby
+
+# makeidx
+*.idx
+*.ilg
+*.ind
+
+# minitoc
+*.maf
+*.mlf
+*.mlt
+*.mtc[0-9]*
+*.slf[0-9]*
+*.slt[0-9]*
+*.stc[0-9]*
+
+# minted
+_minted*
+*.pyg
+
+# morewrites
+*.mw
+
+# nomencl
+*.nlg
+*.nlo
+*.nls
+
+# pax
+*.pax
+
+# pdfpcnotes
+*.pdfpc
+
+# sagetex
+*.sagetex.sage
+*.sagetex.py
+*.sagetex.scmd
+
+# scrwfile
+*.wrt
+
+# sympy
+*.sout
+*.sympy
+sympy-plots-for-*.tex/
+
+# pdfcomment
+*.upa
+*.upb
+
+# pythontex
+*.pytxcode
+pythontex-files-*/
+
+# tcolorbox
+*.listing
+
+# thmtools
+*.loe
+
+# TikZ & PGF
+*.dpth
+*.md5
+*.auxlock
+
+# todonotes
+*.tdo
+
+# vhistory
+*.hst
+*.ver
+
+# easy-todo
+*.lod
+
+# xcolor
+*.xcp
+
+# xmpincl
+*.xmpi
+
+# xindy
+*.xdy
+
+# xypic precompiled matrices and outlines
+*.xyc
+*.xyd
+
+# endfloat
+*.ttt
+*.fff
+
+# Latexian
+TSWLatexianTemp*
+
+## Editors:
+# WinEdt
+*.bak
+*.sav
+
+# Texpad
+.texpadtmp
+
+# LyX
+*.lyx~
+
+# Kile
+*.backup
+
+# gummi
+.*.swp
+
+# KBibTeX
+*~[0-9]*
+
+# TeXnicCenter
+*.tps
+
+# auto folder when using emacs and auctex
+./auto/*
+*.el
+
+# expex forward references with \gathertags
+*-tags.tex
+
+# standalone packages
+*.sta
+
+# Makeindex log files
+*.lpz
+
+# xwatermark package
+*.xwm
+
+# REVTeX puts footnotes in the bibliography by default, unless the nofootinbib
+# option is specified. Footnotes are the stored in a file with suffix Notes.bib.
+# Uncomment the next line to have this generated file ignored.
+#*Notes.bib
+
+### VisualStudio template
+## Ignore Visual Studio temporary files, build results, and
+## files generated by popular Visual Studio add-ons.
+##
+## Get latest from https://github.com/github/gitignore/blob/master/VisualStudio.gitignore
+
+# User-specific files
+*.rsuser
+*.suo
+*.user
+*.userosscache
+*.sln.docstates
+
+# User-specific files (MonoDevelop/Xamarin Studio)
+*.userprefs
+
+# Mono auto generated files
+mono_crash.*
+
+# Build results
+[Dd]ebug/
+[Dd]ebugPublic/
+[Rr]elease/
+[Rr]eleases/
+x64/
+x86/
+[Ww][Ii][Nn]32/
+[Aa][Rr][Mm]/
+[Aa][Rr][Mm]64/
+bld/
+[Bb]in/
+[Oo]bj/
+[Ll]og/
+[Ll]ogs/
+
+# Visual Studio 2015/2017 cache/options directory
+.vs/
+# Uncomment if you have tasks that create the project's static files in wwwroot
+#wwwroot/
+
+# Visual Studio 2017 auto generated files
+Generated\ Files/
+
+# MSTest test Results
+[Tt]est[Rr]esult*/
+[Bb]uild[Ll]og.*
+
+# NUnit
+*.VisualState.xml
+TestResult.xml
+nunit-*.xml
+
+# Build Results of an ATL Project
+[Dd]ebugPS/
+[Rr]eleasePS/
+dlldata.c
+
+# Benchmark Results
+BenchmarkDotNet.Artifacts/
+
+# .NET Core
+project.lock.json
+project.fragment.lock.json
+artifacts/
+
+# ASP.NET Scaffolding
+ScaffoldingReadMe.txt
+
+# StyleCop
+StyleCopReport.xml
+
+# Files built by Visual Studio
+*_i.c
+*_p.c
+*_h.h
+*.ilk
+*.meta
+*.obj
+*.iobj
+*.pch
+*.pdb
+*.ipdb
+*.pgc
+*.pgd
+*.rsp
+*.sbr
+*.tlb
+*.tli
+*.tlh
+*.tmp
+*.tmp_proj
+*_wpftmp.csproj
+*.log
+*.vspscc
+*.vssscc
+.builds
+*.pidb
+*.svclog
+*.scc
+
+# Chutzpah Test files
+_Chutzpah*
+
+# Visual C++ cache files
+ipch/
+*.aps
+*.ncb
+*.opendb
+*.opensdf
+*.sdf
+*.cachefile
+*.VC.db
+*.VC.VC.opendb
+
+# Visual Studio profiler
+*.psess
+*.vsp
+*.vspx
+*.sap
+
+# Visual Studio Trace Files
+*.e2e
+
+# TFS 2012 Local Workspace
+$tf/
+
+# Guidance Automation Toolkit
+*.gpState
+
+# ReSharper is a .NET coding add-in
+_ReSharper*/
+*.[Rr]e[Ss]harper
+*.DotSettings.user
+
+# TeamCity is a build add-in
+_TeamCity*
+
+# DotCover is a Code Coverage Tool
+*.dotCover
+
+# AxoCover is a Code Coverage Tool
+.axoCover/*
+!.axoCover/settings.json
+
+# Coverlet is a free, cross platform Code Coverage Tool
+coverage*.json
+coverage*.xml
+coverage*.info
+
+# Visual Studio code coverage results
+*.coverage
+*.coveragexml
+
+# NCrunch
+_NCrunch_*
+.*crunch*.local.xml
+nCrunchTemp_*
+
+# MightyMoose
+*.mm.*
+AutoTest.Net/
+
+# Web workbench (sass)
+.sass-cache/
+
+# Installshield output folder
+[Ee]xpress/
+
+# DocProject is a documentation generator add-in
+DocProject/buildhelp/
+DocProject/Help/*.HxT
+DocProject/Help/*.HxC
+DocProject/Help/*.hhc
+DocProject/Help/*.hhk
+DocProject/Help/*.hhp
+DocProject/Help/Html2
+DocProject/Help/html
+
+# Click-Once directory
+publish/
+
+# Publish Web Output
+*.[Pp]ublish.xml
+*.azurePubxml
+# Note: Comment the next line if you want to checkin your web deploy settings,
+# but database connection strings (with potential passwords) will be unencrypted
+*.pubxml
+*.publishproj
+
+# Microsoft Azure Web App publish settings. Comment the next line if you want to
+# checkin your Azure Web App publish settings, but sensitive information contained
+# in these scripts will be unencrypted
+PublishScripts/
+
+# NuGet Packages
+*.nupkg
+# NuGet Symbol Packages
+*.snupkg
+# The packages folder can be ignored because of Package Restore
+**/[Pp]ackages/*
+# except build/, which is used as an MSBuild target.
+!**/[Pp]ackages/build/
+# Uncomment if necessary however generally it will be regenerated when needed
+#!**/[Pp]ackages/repositories.config
+# NuGet v3's project.json files produces more ignorable files
+*.nuget.props
+*.nuget.targets
+
+# Microsoft Azure Build Output
+csx/
+*.build.csdef
+
+# Microsoft Azure Emulator
+ecf/
+rcf/
+
+# Windows Store app package directories and files
+AppPackages/
+BundleArtifacts/
+Package.StoreAssociation.xml
+_pkginfo.txt
+*.appx
+*.appxbundle
+*.appxupload
+
+# Visual Studio cache files
+# files ending in .cache can be ignored
+*.[Cc]ache
+# but keep track of directories ending in .cache
+!?*.[Cc]ache/
+
+# Others
+ClientBin/
+~$*
+*~
+*.dbmdl
+*.dbproj.schemaview
+*.jfm
+*.pfx
+*.publishsettings
+orleans.codegen.cs
+
+# Including strong name files can present a security risk
+# (https://github.com/github/gitignore/pull/2483#issue-259490424)
+#*.snk
+
+# Since there are multiple workflows, uncomment next line to ignore bower_components
+# (https://github.com/github/gitignore/pull/1529#issuecomment-104372622)
+#bower_components/
+
+# RIA/Silverlight projects
+Generated_Code/
+
+# Backup & report files from converting an old project file
+# to a newer Visual Studio version. Backup files are not needed,
+# because we have git ;-)
+_UpgradeReport_Files/
+Backup*/
+UpgradeLog*.XML
+UpgradeLog*.htm
+ServiceFabricBackup/
+*.rptproj.bak
+
+# SQL Server files
+*.mdf
+*.ldf
+*.ndf
+
+# Business Intelligence projects
+*.rdl.data
+*.bim.layout
+*.bim_*.settings
+*.rptproj.rsuser
+*- [Bb]ackup.rdl
+*- [Bb]ackup ([0-9]).rdl
+*- [Bb]ackup ([0-9][0-9]).rdl
+
+# Microsoft Fakes
+FakesAssemblies/
+
+# GhostDoc plugin setting file
+*.GhostDoc.xml
+
+# Node.js Tools for Visual Studio
+.ntvs_analysis.dat
+node_modules/
+
+# Visual Studio 6 build log
+*.plg
+
+# Visual Studio 6 workspace options file
+*.opt
+
+# Visual Studio 6 auto-generated workspace file (contains which files were open etc.)
+*.vbw
+
+# Visual Studio LightSwitch build output
+**/*.HTMLClient/GeneratedArtifacts
+**/*.DesktopClient/GeneratedArtifacts
+**/*.DesktopClient/ModelManifest.xml
+**/*.Server/GeneratedArtifacts
+**/*.Server/ModelManifest.xml
+_Pvt_Extensions
+
+# Paket dependency manager
+.paket/paket.exe
+paket-files/
+
+# FAKE - F# Make
+.fake/
+
+# CodeRush personal settings
+.cr/personal
+
+# Python Tools for Visual Studio (PTVS)
 __pycache__/
+*.pyc
+
+# Cake - Uncomment if you are using it
+# tools/**
+# !tools/packages.config
+
+# Tabs Studio
+*.tss
+
+# Telerik's JustMock configuration file
+*.jmconfig
+
+# BizTalk build output
+*.btp.cs
+*.btm.cs
+*.odx.cs
+*.xsd.cs
+
+# OpenCover UI analysis results
+OpenCover/
+
+# Azure Stream Analytics local run output
+ASALocalRun/
+
+# MSBuild Binary and Structured Log
+*.binlog
+
+# NVidia Nsight GPU debugger configuration file
+*.nvuser
+
+# MFractors (Xamarin productivity tool) working folder
+.mfractor/
+
+# Local History for Visual Studio
+.localhistory/
+
+# BeatPulse healthcheck temp database
+healthchecksdb
+
+# Backup folder for Package Reference Convert tool in Visual Studio 2017
+MigrationBackup/
+
+# Ionide (cross platform F# VS Code tools) working folder
+.ionide/
+
+# Fody - auto-generated XML schema
+FodyWeavers.xsd
+
+### Python template
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+### JupyterNotebooks template
+# gitignore template for Jupyter Notebooks
+# website: http://jupyter.org/
+
+.ipynb_checkpoints
+*/.ipynb_checkpoints/*
+
+# IPython
+profile_default/
+ipython_config.py
+
+# Remove previous ipynb_checkpoints
+#   git rm -r .ipynb_checkpoints/
+
+### VirtualEnv template
+# Virtualenv
+# http://iamzed.com/2009/05/07/a-primer-on-virtualenv/
+.Python
+[Bb]in
+[Ii]nclude
+[Ll]ib
+[Ll]ib64
+[Ll]ocal
+[Ss]cripts
+pyvenv.cfg
+.venv
+pip-selfcheck.json
+
+### Eclipse template
+.metadata
+bin/
+tmp/
+*.tmp
+*.bak
+*.swp
+*~.nib
+local.properties
+.settings/
+.loadpath
+.recommenders
+
+# External tool builders
+.externalToolBuilders/
+
+# Locally stored "Eclipse launch configurations"
+*.launch
+
+# PyDev specific (Python IDE for Eclipse)
+*.pydevproject
+
+# CDT-specific (C/C++ Development Tooling)
+.cproject
+
+# CDT- autotools
+.autotools
+
+# Java annotation processor (APT)
+.factorypath
+
+# PDT-specific (PHP Development Tools)
+.buildpath
+
+# sbteclipse plugin
+.target
+
+# Tern plugin
+.tern-project
+
+# TeXlipse plugin
+.texlipse
+
+# STS (Spring Tool Suite)
+.springBeans
+
+# Code Recommenders
+.recommenders/
+
+# Annotation Processing
+.apt_generated/
+.apt_generated_test/
+
+# Scala IDE specific (Scala & Java development for Eclipse)
+.cache-main
+.scala_dependencies
+.worksheet
+
+# Uncomment this line if you wish to ignore the project description file.
+# Typically, this file would be tracked if it contains build/dependency configurations:
+#.project
+
+# CUSTOM
 .idea
 .DS_Store
 .DS_store
+*.tmp.py
+*.tmp.json
+tmp

README.md

@@ -4,7 +4,7 @@ emoji: 🍲
 colorFrom: blue
 colorTo: red
 sdk: streamlit
-app_file: server.py
+app_file: app.py
 pinned: false
 ---
 
@@ -13,8 +13,5 @@ pinned: false
 
 ### Launch demo:
 ```
-streamlit run server.py
-```
-
-### Modify config
-Add any custom ingredient to display in `config.json` with key `first_100` to be displayed in multi-select. `next_100` are for custom ingredient adding section (to provide autocomplete assist as we type)
+streamlit run app.py
+```

app.py

@@ -0,0 +1,241 @@
+import streamlit as st
+
+import torch
+from transformers import pipeline, set_seed
+from transformers import AutoTokenizer
+
+from PIL import (
+    Image,
+    ImageFont,
+    ImageDraw
+)
+
+import re
+from examples import EXAMPLES
+import meta
+from utils import (
+    remote_css,
+    local_css,
+    load_image,
+    pure_comma_separation
+)
+
+
+class TextGeneration:
+    def __init__(self):
+        self.debug = True
+        self.dummy_output = {
+            'directions': [
+                'peel the potato and slice thinly.',
+                'place in a microwave safe dish.',
+                'cover with plastic wrap and microwave on high for 5 minutes.',
+                'remove from the microwave and sprinkle with cheese.',
+                'return to the microwave for 1 minute or until cheese is melted.',
+                'return to the microwave for 1 minute or until cheese is melted.',
+                'return to the microwave for 1 minute or until cheese is melted.'
+            ],
+            'ingredients': [
+                '1 potato',
+                '1 slice cheese',
+                '1 potato',
+                '1 slice cheese'
+                '1 potato',
+                '1 slice cheese',
+                '1 slice cheese',
+                '1 potato',
+                '1 slice cheese'
+                '1 potato',
+                '1 slice cheese',
+            ],
+            'title': 'Cheese Potatoes'
+        }
+        self.tokenizer = None
+        self.generator = None
+        self.task = "text2text-generation"
+        self.model_name_or_path = "flax-community/t5-recipe-generation"
+        self.h1_font = ImageFont.truetype("asset/fonts/PT_Serif/PTSerif-Bold.ttf", 100)
+        self.h2_font = ImageFont.truetype("asset/fonts/PT_Serif/PTSerif-Bold.ttf", 50)
+        self.p_font = ImageFont.truetype("asset/fonts/PT_Serif/PTSerif-Regular.ttf", 30)
+        set_seed(42)
+
+    def _skip_special_tokens_and_prettify(self, text):
+        recipe_maps = {"<sep>": "--", "<section>": "\n"}
+        recipe_map_pattern = "|".join(map(re.escape, recipe_maps.keys()))
+
+        text = re.sub(
+            recipe_map_pattern,
+            lambda m: recipe_maps[m.group()],
+            re.sub("|".join(self.tokenizer.all_special_tokens), "", text)
+        )
+
+        data = {"title": "", "ingredients": [], "directions": []}
+        for section in text.split("\n"):
+            section = section.strip()
+            if section.startswith("title:"):
+                data["title"] = " ".join(
+                    [w.strip().capitalize() for w in section.replace("title:", "").strip().split() if w.strip()]
+                )
+            elif section.startswith("ingredients:"):
+                data["ingredients"] = [s.strip() for s in section.replace("ingredients:", "").split('--')]
+            elif section.startswith("directions:"):
+                data["directions"] = [s.strip() for s in section.replace("directions:", "").split('--')]
+            else:
+                pass
+
+        return data
+
+    def load(self):
+        if not self.debug:
+            self.tokenizer = AutoTokenizer.from_pretrained(self.model_name_or_path)
+            self.generator = pipeline(self.task, model=self.model_name_or_path, tokenizer=self.model_name_or_path)
+
+    def prepare_frame(self, recipe, frame):
+        im_editable = ImageDraw.Draw(frame)
+        # Title
+        ws, hs = 120, 500
+        im_editable.text(
+            (ws, hs),
+            recipe["title"],
+            (61, 61, 70),
+            font=self.h1_font,
+        )
+        # Ingredients
+        hs = hs + 200
+        im_editable.text(
+            (ws, hs),
+            "Ingredients",
+            (61, 61, 70),
+            font=self.h2_font,
+        )
+        hs = hs + 80
+        im_editable.text(
+            (ws + 10, hs),
+            "\n".join([f"- {item}" for item in recipe["ingredients"]]),
+            (61, 61, 70),
+            font=self.p_font,
+        )
+        # Directions
+        hs = hs + 400
+        im_editable.text(
+            (ws, hs),
+            "Directions",
+            (61, 61, 70),
+            font=self.h2_font,
+        )
+        hs = hs + 80
+        im_editable.text(
+            (ws + 10, hs),
+            "\n".join([f"- {item}" for item in recipe["directions"]]),
+            (61, 61, 70),
+            font=self.p_font,
+        )
+        return frame
+
+    def generate(self, items, generation_kwargs):
+        print(generation_kwargs)
+        if not self.debug:
+            generation_kwargs["num_return_sequences"] = 1
+            # generation_kwargs["return_full_text"] = False
+            generation_kwargs["return_tensors"] = True
+            generation_kwargs["return_text"] = False
+
+            generated_ids = self.generator(
+                items,
+                **generation_kwargs,
+            )[0]["generated_token_ids"]
+            recipe = self.tokenizer.decode(generated_ids, skip_special_tokens=False)
+            recipe = self._skip_special_tokens_and_prettify(recipe)
+            return recipe
+
+        return self.dummy_output
+
+    def generate_frame(self, recipe):
+        frame = load_image("asset/images/recipe-post.png")
+        return self.prepare_frame(recipe, frame)
+
+
+@st.cache(allow_output_mutation=True)
+def load_text_generator():
+    generator = TextGeneration()
+    generator.load()
+    return generator
+
+
+chef_top = {
+    "max_length": 512,
+    "min_length": 64,
+    "no_repeat_ngram_size": 3,
+    "do_sample": True,
+    "top_k": 60,
+    "top_p": 0.95,
+    "num_return_sequences": 1
+}
+chef_beam = {
+    "max_length": 512,
+    "min_length": 64,
+    "no_repeat_ngram_size": 3,
+    "early_stopping": True,
+    "num_beams": 5,
+    "length_penalty": 1.5,
+    "num_return_sequences": 1
+}
+
+
+def main():
+    st.set_page_config(
+        page_title="Chef Transformer",
+        page_icon="🍲",
+        layout="wide",
+        initial_sidebar_state="expanded"
+    )
+    generator = load_text_generator()
+    local_css("asset/css/style.css")
+
+    st.sidebar.image(load_image("asset/images/chef-transformer-transparent.png"), width=310)
+    st.sidebar.title("Choose your own chef")
+    chef = st.sidebar.selectbox("Chef", index=0, options=["Chef Scheherazade", "Chef Giovanni"])
+
+    st.markdown(meta.HEADER_INFO)
+    prompts = list(EXAMPLES.keys()) + ["Custom"]
+    prompt = st.selectbox('Examples', prompts, index=len(prompts) - 1)
+
+    if prompt == "Custom":
+        prompt_box = ""
+    else:
+        prompt_box = EXAMPLES[prompt]
+
+    items = st.text_input(
+        'Add custom ingredients here (separated by `,`): ',
+        pure_comma_separation(prompt_box, return_list=False),
+        key="custom_keywords",
+        max_chars=1000)
+    items = pure_comma_separation(items, return_list=False)
+    entered_items = st.empty()
+
+    if st.button('Get Recipe!'):
+        entered_items.markdown("**Generate recipe for:** " + items)
+        with st.spinner("Generating recipe..."):
+
+            gen_kw = chef_top if chef == "Chef Scheherazade" else chef_beam
+            generated_recipe = generator.generate(items, gen_kw)
+            recipe_post = generator.generate_frame(generated_recipe)
+
+            col1, col2, col3 = st.beta_columns([1, 6, 1])
+            with col1:
+                st.write("")
+
+            with col2:
+                st.image(
+                    recipe_post,
+                    # width=500,
+                    caption="Your recipe",
+                    use_column_width="auto",
+                    output_format="PNG"
+                )
+
+            with col3:
+                st.write("")
+
+
+if __name__ == '__main__':
+    main()

asset/css/style.css

@@ -0,0 +1,8 @@
+body {
+    background-color: #eee;
+}
+
+.fullScreenFrame > div {
+    display: flex;
+    justify-content: center;
+}

asset/fonts/PT_Serif/OFL.txt

@@ -0,0 +1,94 @@
+Copyright (c) 2010, ParaType Ltd. (http://www.paratype.com/public),
+with Reserved Font Names "PT Sans", "PT Serif" and "ParaType".
+
+This Font Software is licensed under the SIL Open Font License, Version 1.1.
+This license is copied below, and is also available with a FAQ at:
+http://scripts.sil.org/OFL
+
+
+-----------------------------------------------------------
+SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007
+-----------------------------------------------------------
+
+PREAMBLE
+The goals of the Open Font License (OFL) are to stimulate worldwide
+development of collaborative font projects, to support the font creation
+efforts of academic and linguistic communities, and to provide a free and
+open framework in which fonts may be shared and improved in partnership
+with others.
+
+The OFL allows the licensed fonts to be used, studied, modified and
+redistributed freely as long as they are not sold by themselves. The
+fonts, including any derivative works, can be bundled, embedded, 
+redistributed and/or sold with any software provided that any reserved
+names are not used by derivative works. The fonts and derivatives,
+however, cannot be released under any other type of license. The
+requirement for fonts to remain under this license does not apply
+to any document created using the fonts or their derivatives.
+
+DEFINITIONS
+"Font Software" refers to the set of files released by the Copyright
+Holder(s) under this license and clearly marked as such. This may
+include source files, build scripts and documentation.
+
+"Reserved Font Name" refers to any names specified as such after the
+copyright statement(s).
+
+"Original Version" refers to the collection of Font Software components as
+distributed by the Copyright Holder(s).
+
+"Modified Version" refers to any derivative made by adding to, deleting,
+or substituting -- in part or in whole -- any of the components of the
+Original Version, by changing formats or by porting the Font Software to a
+new environment.
+
+"Author" refers to any designer, engineer, programmer, technical
+writer or other person who contributed to the Font Software.
+
+PERMISSION & CONDITIONS
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of the Font Software, to use, study, copy, merge, embed, modify,
+redistribute, and sell modified and unmodified copies of the Font
+Software, subject to the following conditions:
+
+1) Neither the Font Software nor any of its individual components,
+in Original or Modified Versions, may be sold by itself.
+
+2) Original or Modified Versions of the Font Software may be bundled,
+redistributed and/or sold with any software, provided that each copy
+contains the above copyright notice and this license. These can be
+included either as stand-alone text files, human-readable headers or
+in the appropriate machine-readable metadata fields within text or
+binary files as long as those fields can be easily viewed by the user.
+
+3) No Modified Version of the Font Software may use the Reserved Font
+Name(s) unless explicit written permission is granted by the corresponding
+Copyright Holder. This restriction only applies to the primary font name as
+presented to the users.
+
+4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font
+Software shall not be used to promote, endorse or advertise any
+Modified Version, except to acknowledge the contribution(s) of the
+Copyright Holder(s) and the Author(s) or with their explicit written
+permission.
+
+5) The Font Software, modified or unmodified, in part or in whole,
+must be distributed entirely under this license, and must not be
+distributed under any other license. The requirement for fonts to
+remain under this license does not apply to any document created
+using the Font Software.
+
+TERMINATION
+This license becomes null and void if any of the above conditions are
+not met.
+
+DISCLAIMER
+THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT
+OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE
+COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL
+DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM
+OTHER DEALINGS IN THE FONT SOFTWARE.

beam_search.py

@@ -1,63 +0,0 @@
-import torch
-from transformers import AutoModelForSeq2SeqLM
-from transformers import AutoTokenizer
-from transformers import pipeline
-
-from pprint import pprint
-import re
-
-
-# device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-# MODEL_NAME_OR_PATH = "flax-community/t5-recipe-generation"
-# tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME_OR_PATH, use_fast=True)
-# model = AutoModelForSeq2SeqLM.from_pretrained(MODEL_NAME_OR_PATH)
-
-
-def skip_special_tokens_and_prettify(text, tokenizer):
-    recipe_maps = {"<sep>": "--", "<section>": "\n"}
-    recipe_map_pattern = "|".join(map(re.escape, recipe_maps.keys()))
-
-    text = re.sub(
-        recipe_map_pattern, 
-        lambda m: recipe_maps[m.group()], 
-        re.sub("|".join(tokenizer.all_special_tokens), "", text)
-    )
-
-    data = {"title": "", "ingredients": [], "directions": []}
-    for section in text.split("\n"):
-        section = section.strip()
-        section = section.strip()
-        if section.startswith("title:"):
-            data["title"] = section.replace("title:", "").strip()
-        elif section.startswith("ingredients:"):
-            data["ingredients"] = [s.strip() for s in section.replace("ingredients:", "").split('--')]
-        elif section.startswith("directions:"):
-            data["directions"] = [s.strip() for s in section.replace("directions:", "").split('--')]
-        else:
-            pass
-
-    return data
-
-
-def post_generator(output_tensors, tokenizer):
-    output_tensors = [output_tensors[i]["generated_token_ids"] for i in range(len(output_tensors))]
-    texts = tokenizer.batch_decode(output_tensors, skip_special_tokens=False)
-    texts = [skip_special_tokens_and_prettify(text, tokenizer) for text in texts]
-    return texts
-
-
-# Example 
-generate_kwargs = {
-    "max_length": 512,
-    "min_length": 64,
-    "no_repeat_ngram_size": 3,
-    "early_stopping": True,
-    "num_beams": 5,
-    "length_penalty": 1.5,
-    "num_return_sequences": 2
-}
-items = "potato, cheese"
-# generator = pipeline("text2text-generation", model=model, tokenizer=tokenizer)
-# generated = generator(items, return_tensors=True, return_text=False, **generate_kwargs)
-# outputs = post_generator(generated, tokenizer)
-# pprint(outputs)

config.json

@@ -1,207 +0,0 @@
-{
-  "model_name_or_path": "flax-community/t5-recipe-generation",
-  "first_100": [
-    "allspice",
-    "almond extract",
-    "applesauce",
-    "avocado",
-    "balsamic vinegar",
-    "basil",
-    "bay leaf",
-    "beets",
-    "bread crumbs",
-    "bread flour",
-    "buns",
-    "catsup",
-    "cayenne",
-    "cherry tomatoes",
-    "chicken breasts",
-    "chives",
-    "chocolate cake",
-    "coconut milk",
-    "cold butter",
-    "cold milk",
-    "cooking oil",
-    "cornstarch",
-    "crab meat",
-    "crackers",
-    "cream of chicken soup",
-    "cream of tartar",
-    "cumin",
-    "cumin seeds",
-    "curry powder",
-    "egg yolk",
-    "extra-virgin olive oil",
-    "feta cheese",
-    "flaked coconut",
-    "flat leaf parsley",
-    "flour tortillas",
-    "fresh chives",
-    "fresh cilantro",
-    "fresh mint",
-    "fresh oregano",
-    "fresh rosemary",
-    "frozen strawberries",
-    "gingerroot",
-    "green olives",
-    "ground allspice",
-    "ground chuck",
-    "ground coriander",
-    "ground cumin",
-    "ground pork",
-    "ground red pepper",
-    "hamburger",
-    "hazelnuts",
-    "heavy cream",
-    "heavy whipping cream",
-    "hot pepper",
-    "italian dressing",
-    "lean ground beef",
-    "lemon juice",
-    "lemon pepper",
-    "marjoram",
-    "miracle",
-    "noodles",
-    "nuts",
-    "oatmeal",
-    "oats",
-    "oleo",
-    "olive oil",
-    "onion salt",
-    "onions",
-    "orange",
-    "paprika",
-    "parmesan cheese",
-    "parsley",
-    "pasta",
-    "peaches",
-    "pecans",
-    "pork sausage",
-    "pork tenderloin",
-    "poultry seasoning",
-    "powdered sugar",
-    "pumpkin",
-    "red potatoes",
-    "red wine vinegar",
-    "rosemary",
-    "salmon",
-    "scallion",
-    "sesame oil",
-    "shell",
-    "stalks celery",
-    "tabasco sauce",
-    "tarragon",
-    "tomatoes",
-    "unsalted butter",
-    "vanilla wafers",
-    "vegetables",
-    "warm water",
-    "whipping cream",
-    "white wine vinegar",
-    "whole wheat flour",
-    "yellow squash",
-    "yogurt"
-  ],
-  "next_100": [
-    "active dry yeast",
-    "almonds",
-    "apple",
-    "apple cider",
-    "apple cider vinegar",
-    "avocados",
-    "baby spinach",
-    "bay leaves",
-    "bean sprouts",
-    "beef",
-    "beef broth",
-    "broccoli",
-    "cabbage",
-    "capers",
-    "cashews",
-    "celery",
-    "celery salt",
-    "cherries",
-    "cherry pie filling",
-    "chicken",
-    "chicken broth",
-    "chicken stock",
-    "chickpeas",
-    "chili sauce",
-    "chocolate",
-    "cinnamon",
-    "cloves",
-    "corn",
-    "cottage cheese",
-    "cranberry sauce",
-    "egg noodles",
-    "egg yolks",
-    "extra virgin olive oil",
-    "freshly ground pepper",
-    "garlic powder",
-    "golden raisins",
-    "graham cracker crust",
-    "graham crackers",
-    "green peppers",
-    "ground black pepper",
-    "ground nutmeg",
-    "ground pepper",
-    "ground turmeric",
-    "kosher salt",
-    "lemon rind",
-    "mango",
-    "mint",
-    "mustard",
-    "nutmeg",
-    "orange juice",
-    "orange zest",
-    "oregano",
-    "peanut butter",
-    "peas",
-    "pecan halves",
-    "pepperoni",
-    "pine nuts",
-    "pinto beans",
-    "pizza sauce",
-    "plain yogurt",
-    "potatoes",
-    "raisins",
-    "red",
-    "red bell peppers",
-    "red pepper",
-    "red peppers",
-    "rhubarb",
-    "ricotta cheese",
-    "salad oil",
-    "sauce",
-    "scallions",
-    "sesame seeds",
-    "sherry",
-    "shredded cheese",
-    "skinless",
-    "soda",
-    "soy sauce",
-    "spinach",
-    "strawberries",
-    "sugar",
-    "sweet onion",
-    "sweet potatoes",
-    "swiss cheese",
-    "t",
-    "tomato",
-    "tomato paste",
-    "tomato soup",
-    "tuna",
-    "vanilla bean",
-    "vanilla ice cream",
-    "vanilla pudding",
-    "vegetable broth",
-    "vegetable oil",
-    "vegetable shortening",
-    "whipped cream",
-    "white onion",
-    "white sugar",
-    "yellow cake",
-    "yellow cornmeal",
-    "zucchini"
-  ]
-}

examples.py

@@ -0,0 +1,3 @@
+EXAMPLES = {
+    "Recipe Name 1": "cheese, potato",
+}

meta.py

@@ -0,0 +1,10 @@
+HEADER_INFO = """
+# Chef Transformer 🍲
+
+This demo uses [T5 trained on RecipeNLG](https://huggingface.co/flax-community/t5-recipe-generation) "
+to generate recipe from a given set of ingredients
+""".strip()
+SIDEBAR_INFO = """
+# Configuration
+""".strip()
+PROMPT_BOX = "Add custom ingredients here (separated by `,`): "

requirements.txt

@@ -1,4 +1,3 @@
-streamlit==0.84.1
-transformers==4.8.2
-torch==1.9.0
-streamlit-tags==1.2.7
+streamlit
+transformers
+torch

server.py

@@ -1,109 +0,0 @@
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
-from datetime import datetime as dt
-import streamlit as st
-from streamlit_tags import st_tags
-import beam_search
-import top_sampling
-from pprint import pprint
-import json
-
-with open("config.json") as f:
-    cfg = json.loads(f.read())
-
-st.set_page_config(layout="wide")
-
-
-@st.cache(allow_output_mutation=True)
-def load_model():
-    tokenizer = AutoTokenizer.from_pretrained(cfg["model_name_or_path"])
-    model = AutoModelForSeq2SeqLM.from_pretrained(cfg["model_name_or_path"])
-    generator = pipeline("text2text-generation", model=model, tokenizer=tokenizer)
-    return generator, tokenizer
-
-
-def sampling_changed(obj):
-    print(obj)
-
-
-with st.spinner('Loading model...'):
-    generator, tokenizer = load_model()
-# st.image("images/chef-transformer.png", width=400)
-st.header("Chef Transformer 👩‍🍳 / 👨‍🍳")
-st.markdown(
-    "This demo uses [T5 trained on RecipeNLG](https://huggingface.co/flax-community/t5-recipe-generation) "
-    "to generate recipe from a given set of ingredients"
-)
-img = st.sidebar.image("images/chef-transformer-transparent.png", width=310)
-add_text_sidebar = st.sidebar.title("Popular Recipes")
-add_text_sidebar = st.sidebar.text("Recipe preset(example#1)")
-add_text_sidebar = st.sidebar.text("Recipe preset(example#2)")
-
-add_text_sidebar = st.sidebar.title("Mode")
-sampling_mode = st.sidebar.selectbox("Select a Mode", index=0, options=["Top Sampling", "Beam Search"])
-
-original_keywords = st.multiselect(
-    "Choose ingredients",
-    cfg["first_100"],
-    ["parmesan cheese", "fresh oregano", "basil", "whole wheat flour"]
-)
-
-st.write("Add custom ingredients here:")
-custom_keywords = st_tags(
-    label="",
-    text='Press enter to add more',
-    value=['salt'],
-    suggestions=["z"],
-    maxtags=15,
-    key='tags')
-
-# def custom_keywords_on_change():
-#     pass
-
-
-# custom_keywords = st.text_input(
-#     'Add custom ingredients here (separated by `,`): ',
-#     ", ".join(["salt", "pepper"]),
-#     key="custom_keywords",
-#     # on_change=custom_keywords_on_change,
-#     max_chars=1000)
-# custom_keywords = list(set([x.strip() for x in custom_keywords.strip().split(',') if len(x.strip()) > 0]))
-
-all_ingredients = []
-all_ingredients.extend(original_keywords)
-all_ingredients.extend(custom_keywords)
-all_ingredients = ", ".join(all_ingredients)
-st.markdown("**Generate recipe for:** " + all_ingredients)
-
-submit = st.button('Get Recipe!')
-if submit:
-    with st.spinner('Generating recipe...'):
-        if sampling_mode == "Beam Search":
-            generated = generator(
-                all_ingredients,
-                return_tensors=True,
-                return_text=False,
-                **beam_search.generate_kwargs)
-            outputs = beam_search.post_generator(generated, tokenizer)
-        elif sampling_mode == "Top Sampling":
-            generated = generator(
-                all_ingredients,
-                return_tensors=True,
-                return_text=False,
-                **top_sampling.generate_kwargs)
-            outputs = top_sampling.post_generator(generated, tokenizer)
-    output = outputs[0]
-    output['title'] = " ".join([w.capitalize() for w in output['title'].split()])
-    markdown_output = ""
-    markdown_output += f"## {output['title']}\
-"
-    markdown_output += f"#### Ingredients:\
-"
-    for o in output["ingredients"]:
-        markdown_output += f"- {o}\
-"
-    markdown_output += f"#### Directions:\
-"
-    for o in output["directions"]:
-        markdown_output += f"- {o}\
-"
-    st.markdown(markdown_output)

top_sampling.py

@@ -1,63 +0,0 @@
-import torch
-from transformers import AutoModelForSeq2SeqLM
-from transformers import AutoTokenizer
-from transformers import pipeline
-
-from pprint import pprint
-import re
-
-
-# device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-# MODEL_NAME_OR_PATH = "flax-community/t5-recipe-generation"
-# tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME_OR_PATH, use_fast=True)
-# model = AutoModelForSeq2SeqLM.from_pretrained(MODEL_NAME_OR_PATH)
-
-
-def skip_special_tokens_and_prettify(text, tokenizer):
-    recipe_maps = {"<sep>": "--", "<section>": "\n"}
-    recipe_map_pattern = "|".join(map(re.escape, recipe_maps.keys()))
-
-    text = re.sub(
-        recipe_map_pattern, 
-        lambda m: recipe_maps[m.group()], 
-        re.sub("|".join(tokenizer.all_special_tokens), "", text)
-    )
-
-    data = {"title": "", "ingredients": [], "directions": []}
-    for section in text.split("\n"):
-        section = section.strip()
-        section = section.strip()
-        if section.startswith("title:"):
-            data["title"] = section.replace("title:", "").strip()
-        elif section.startswith("ingredients:"):
-            data["ingredients"] = [s.strip() for s in section.replace("ingredients:", "").split('--')]
-        elif section.startswith("directions:"):
-            data["directions"] = [s.strip() for s in section.replace("directions:", "").split('--')]
-        else:
-            pass
-
-    return data
-
-
-def post_generator(output_tensors, tokenizer):
-    output_tensors = [output_tensors[i]["generated_token_ids"] for i in range(len(output_tensors))]
-    texts = tokenizer.batch_decode(output_tensors, skip_special_tokens=False)
-    texts = [skip_special_tokens_and_prettify(text, tokenizer) for text in texts]
-    return texts
-
-
-# Example 
-generate_kwargs = {
-    "max_length": 512,
-    "min_length": 64,
-    "no_repeat_ngram_size": 3,
-    "do_sample": True,
-    "top_k": 60,
-    "top_p": 0.95,
-    "num_return_sequences": 3
-}
-# items = "potato, cheese"
-# generator = pipeline("text2text-generation", model=model, tokenizer=tokenizer)
-# generated = generator(items, return_tensors=True, return_text=False, **generate_kwargs)
-# outputs = post_generator(generated, tokenizer)
-# pprint(outputs)

utils.py

@@ -33,3 +33,10 @@ def local_css(css_path):
 
 def remote_css(css_url):
     st.markdown(f'<link href="{css_url}" rel="stylesheet">', unsafe_allow_html=True)
+
+
+def pure_comma_separation(list_str, return_list=True):
+    r = list(set([x.strip() for x in list_str.strip().split(',') if len(x.strip()) > 0]))
+    if return_list:
+        return r
+    return ", ".join(r)