exsclaim 2.4.1__tar.gz

exsclaim-2.4.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 MaterialEyes
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

exsclaim-2.4.1/MANIFEST.in

@@ -0,0 +1,31 @@
+include exsclaim/README.md
+
+recursive-include exsclaim *.py
+recursive-include exsclaim *.pyi
+
+recursive-include exsclaim/api *.py
+recursive-include exsclaim/api *.pyi
+
+recursive-include exsclaim/dashboard *.py
+recursive-include exsclaim/dashboard *.pyi
+
+include exsclaim/figures/config/yolov3_default_master.cfg
+include exsclaim/figures/config/yolov3_default_subfig.cfg
+include exsclaim/figures/config/scale_label_reader.json
+include exsclaim/figures/scale/corpus.txt
+
+include exsclaim/tests/data/nature_test.json
+include exsclaim/tests/data/images/pipeline/*
+include exsclaim/tests/data/nature_articles/*
+include exsclaim/tests/data/nature_search.html
+include exsclaim/tests/data/images/scale_bar_test_images/*
+include exsclaim/tests/data/images/scale_label_test_images/*
+include exsclaim/tests/data/nature_closed_expected.json
+
+include exsclaim/dashboard/assets/*.png
+include exsclaim/dashboard/assets/*.ico
+include exsclaim/dashboard/assets/*.css
+
+include exsclaim/dashboard/components
+
+include requirements.txt

exsclaim-2.4.1/PKG-INFO

@@ -0,0 +1,167 @@
+Metadata-Version: 2.4
+Name: exsclaim
+Version: 2.4.1
+Summary: EXSCLAIM! is a library for the automatic EXtraction, Separation, and Caption-based natural Language Annotation of IMages from scientific figures.
+Author-email: "Eric Schwenker, Trevor Spreadbury, Weixin Jiang, Maria Chan, Len Washington III" <developer@materialeyes.org>
+License: MIT License
+        
+        Copyright (c) 2024 MaterialEyes
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+        
+Project-URL: Homepage, https://exsclaim.materialeyes.org
+Project-URL: Source, https://github.com/MaterialEyes/exsclaim2.0
+Project-URL: Documentation, https://github.com/MaterialEyes/exsclaim2.0/wiki
+Project-URL: Issues, https://github.com/MaterialEyes/exsclaim2.0/issues
+Project-URL: Paper, https://arxiv.org/abs/2103.10631
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Environment :: Web Environment
+Classifier: Framework :: Dash
+Classifier: Framework :: FastAPI
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: JavaScript
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Image Processing
+Classifier: Topic :: Text Processing
+Requires-Python: >=3.13.2
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: loguru==0.7.3
+Requires-Dist: numpy==2.2.6
+Requires-Dist: opencv-contrib-python-headless==4.12.0.88
+Requires-Dist: Pillow==11.3.0
+Requires-Dist: ultralytics==8.3.170
+Requires-Dist: aiohttp==3.12.15
+Requires-Dist: httpx==0.28.1
+Requires-Dist: brotli==1.1.0
+Requires-Dist: selenium==4.34.2
+Requires-Dist: selenium-stealth==1.0.6
+Requires-Dist: urllib3==2.5.0
+Requires-Dist: asyncpg==0.30.0
+Requires-Dist: beautifulsoup4==4.13.4
+Requires-Dist: soupsieve==2.7
+Requires-Dist: deepdiff==8.5.0
+Requires-Dist: pycocotools==2.0.10
+Requires-Dist: pytz==2025.2
+Requires-Dist: typing_extensions==4.14.0
+Requires-Dist: PyYAML==6.0.2
+Requires-Dist: pymupdf==1.26.3
+Requires-Dist: torch==2.7.1
+Requires-Dist: torchvision==0.22.1
+Requires-Dist: pytorch-model-summary==0.1.2
+Requires-Dist: ollama==0.5.1
+Requires-Dist: openai==1.97.1
+Requires-Dist: asksageclient==1.31
+Requires-Dist: dash[async]==3.1.1
+Requires-Dist: fastapi[standard]==0.116.1
+Requires-Dist: pydantic==2.11.7
+Requires-Dist: starlette==0.47.2
+Requires-Dist: uvicorn==0.35.0
+Requires-Dist: hypercorn==0.17.3
+Requires-Dist: sqlmodel==0.0.24
+Requires-Dist: sqlalchemy==2.0.42
+Requires-Dist: pydantic_settings==2.10.1
+Requires-Dist: uuid-utils==0.11.0
+Requires-Dist: dash_bootstrap_components==2.0.3
+Requires-Dist: gunicorn[gevent]==23.0.0
+Requires-Dist: certifi==2025.7.14
+Dynamic: license-file
+
+# EXSCLAIM2.0: LLM-powered Automatic **EX**traction, **S**eparation, and **C**aption-based natural **L**anguage **A**nnotation of **IM**ages from scientific figures
+[![License](https://img.shields.io/github/license/MaterialEyes/exsclaim2.0.svg?color=blue)](https://github.com/MaterialEyes/exsclaim2.0/blob/main/LICENSE)
+[![Website](https://img.shields.io/website?url=https%3A%2F%2Fexsclaim-dev.materialeyes.org%2F&up_message=online&down_message=offline&down_color=red&label=Website)
+](https://exsclaim-dev.materialeyes.org)
+[![Release](https://img.shields.io/github/release/MaterialEyes/exsclaim2.0.svg)](https://github.com/MaterialEyes/exsclaim2.0/releases)
+[![DOI](https://zenodo.org/badge/DOI/10.48550/arXiv.2103.10631.svg)](https://arxiv.org/abs/2103.10631)
+
+## 🤔 Consider Collaboration
+
+If you find this tool or any of its derived capabilities useful, please consider registering as a user of Center for Nanoscale Materials. We will keep you posted of latest developments, as well as opportunities for computational resources, relevant data, and collaboration. Please contact Maria Chan (mchan@anl.gov) for details.
+
+## Introduction to EXSCLAIM2.0
+
+EXSCLAIM2.0 is a Python package combining EXSCLAIM! code with Large Language models (LLMs) that can be used for the automatic generation of datasets of labeled images from published papers.
+There are four main steps:
+1. [JournalScraper](https://github.com/MaterialEyes/exsclaim2.0/wiki/JournalScraper): scrap journal websites, acquiring figures, captions, and metadata
+2. [CaptionDistributor](https://github.com/MaterialEyes/exsclaim2.0/wiki/CaptionDistributor): separate figure captions into the component chunks that refer to the figure's subfigures using LLMs and prompt engineering
+3. [FigureSeparator](https://github.com/MaterialEyes/exsclaim2.0/wiki/FigureSeparator): separate figures into subfigures, detect scale information, label, and type of image
+
+## Examples and tutorials
+We provide several tutorials demonstrating how to use EXSCLAIM2.0:
+1. [Nature_exsclaim_search](/notebooks/1_Nature_exsclaim_search.ipynb): automatically scrapping data from literature and performing Named Entity Recognition (NER) on the extracted captions.
+2. [HTMLScraper](/notebooks/2_HTMLScraper.ipynb): automatically scrapping data from user provided HTML files
+3. [Microscopy_CLIP_retrieval](/notebooks/3_Microscopy_CLIP_retrieval.ipynb): Using Microscopy_CLIP to perform image-to-image and text-to-image retrieval on our multimodal microscopy dataset.
+
+
+## Installation
+The guides to install EXSCLAIM through Pip, Git and Docker can be found within the [wiki](https://github.com/MaterialEyes/exsclaim2.0/wiki/Installation).
+The guides include installing pre-compiled versions as well as building from the source code and then installing.
+
+### Using Exsclaim 2.0
+```python
+from exsclaim import Pipeline
+search_query = {
+		...
+}
+results = Pipeline(search_query_json)
+```
+where `search_query` is either a dictionary representing a valid JSON object, or a Pathlike string pointing towards a valid JSON file,
+or 
+```shell
+python -m exsclaim query {path to json file holding search query}
+```
+More extensive guides can be found within the [wiki](https://github.com/MaterialEyes/exsclaim2.0/wiki/Running-the-EXSCLAIM-Pipeline).
+
+### Using Docker Compose
+To use Docker Compose to host the service, run the following commands in the base directory:
+```shell
+docker compose build base
+docker compose build {service(s) here}
+docker compose up {service(s) here}
+```
+
+## Acknowledgements
+This material is based upon work supported by Laboratory Directed Research and Development (LDRD) funding from Argonne National Laboratory, provided by the Director, Office of Science, of the U.S. Department of Energy under Contract No. DE-AC02-06CH11357
+
+This work was performed at the Center for Nanoscale Materials, a U.S. Department of Energy Office of Science User Facility, and supported by the U.S. Department of Energy, Office of Science, under Contract No. DE-AC02-06CH11357.
+
+We gratefully acknowledge the computing resources provided on Bebop, a high-performance computing cluster operated by the Laboratory Computing Resource Center at Argonne National Laboratory.
+
+## Citation
+If you find EXSCLAIM! useful, please encourage its development by citing the following [paper](https://arxiv.org/abs/2103.10631) in your research:
+```
+Schwenker, E., Jiang, W. Spreadbury, T., Ferrier N., Cossairt, O., Chan M.K.Y., EXSCLAIM! - An automated pipeline for the construction and
+labeling of materials imaging datasets from scientific literature. arXiv e-prints (2021): arXiv-2103
+```
+
+#### Bibtex
+```
+@article{schwenker2021exsclaim,
+  title={EXSCLAIM! - An automated pipeline for the construction of labeled materials imaging datasets from literature},
+  author={Schwenker, Eric and Jiang, Weixin and Spreadbury, Trevor and Ferrier, Nicola and Cossairt, Oliver and Chan, Maria KY},
+  journal={arXiv e-prints},
+  pages={arXiv--2103},
+  year={2021}
+}
+```

exsclaim-2.4.1/README.md

@@ -0,0 +1,77 @@
+# EXSCLAIM2.0: LLM-powered Automatic **EX**traction, **S**eparation, and **C**aption-based natural **L**anguage **A**nnotation of **IM**ages from scientific figures
+[![License](https://img.shields.io/github/license/MaterialEyes/exsclaim2.0.svg?color=blue)](https://github.com/MaterialEyes/exsclaim2.0/blob/main/LICENSE)
+[![Website](https://img.shields.io/website?url=https%3A%2F%2Fexsclaim-dev.materialeyes.org%2F&up_message=online&down_message=offline&down_color=red&label=Website)
+](https://exsclaim-dev.materialeyes.org)
+[![Release](https://img.shields.io/github/release/MaterialEyes/exsclaim2.0.svg)](https://github.com/MaterialEyes/exsclaim2.0/releases)
+[![DOI](https://zenodo.org/badge/DOI/10.48550/arXiv.2103.10631.svg)](https://arxiv.org/abs/2103.10631)
+
+## 🤔 Consider Collaboration
+
+If you find this tool or any of its derived capabilities useful, please consider registering as a user of Center for Nanoscale Materials. We will keep you posted of latest developments, as well as opportunities for computational resources, relevant data, and collaboration. Please contact Maria Chan (mchan@anl.gov) for details.
+
+## Introduction to EXSCLAIM2.0
+
+EXSCLAIM2.0 is a Python package combining EXSCLAIM! code with Large Language models (LLMs) that can be used for the automatic generation of datasets of labeled images from published papers.
+There are four main steps:
+1. [JournalScraper](https://github.com/MaterialEyes/exsclaim2.0/wiki/JournalScraper): scrap journal websites, acquiring figures, captions, and metadata
+2. [CaptionDistributor](https://github.com/MaterialEyes/exsclaim2.0/wiki/CaptionDistributor): separate figure captions into the component chunks that refer to the figure's subfigures using LLMs and prompt engineering
+3. [FigureSeparator](https://github.com/MaterialEyes/exsclaim2.0/wiki/FigureSeparator): separate figures into subfigures, detect scale information, label, and type of image
+
+## Examples and tutorials
+We provide several tutorials demonstrating how to use EXSCLAIM2.0:
+1. [Nature_exsclaim_search](/notebooks/1_Nature_exsclaim_search.ipynb): automatically scrapping data from literature and performing Named Entity Recognition (NER) on the extracted captions.
+2. [HTMLScraper](/notebooks/2_HTMLScraper.ipynb): automatically scrapping data from user provided HTML files
+3. [Microscopy_CLIP_retrieval](/notebooks/3_Microscopy_CLIP_retrieval.ipynb): Using Microscopy_CLIP to perform image-to-image and text-to-image retrieval on our multimodal microscopy dataset.
+
+
+## Installation
+The guides to install EXSCLAIM through Pip, Git and Docker can be found within the [wiki](https://github.com/MaterialEyes/exsclaim2.0/wiki/Installation).
+The guides include installing pre-compiled versions as well as building from the source code and then installing.
+
+### Using Exsclaim 2.0
+```python
+from exsclaim import Pipeline
+search_query = {
+		...
+}
+results = Pipeline(search_query_json)
+```
+where `search_query` is either a dictionary representing a valid JSON object, or a Pathlike string pointing towards a valid JSON file,
+or 
+```shell
+python -m exsclaim query {path to json file holding search query}
+```
+More extensive guides can be found within the [wiki](https://github.com/MaterialEyes/exsclaim2.0/wiki/Running-the-EXSCLAIM-Pipeline).
+
+### Using Docker Compose
+To use Docker Compose to host the service, run the following commands in the base directory:
+```shell
+docker compose build base
+docker compose build {service(s) here}
+docker compose up {service(s) here}
+```
+
+## Acknowledgements
+This material is based upon work supported by Laboratory Directed Research and Development (LDRD) funding from Argonne National Laboratory, provided by the Director, Office of Science, of the U.S. Department of Energy under Contract No. DE-AC02-06CH11357
+
+This work was performed at the Center for Nanoscale Materials, a U.S. Department of Energy Office of Science User Facility, and supported by the U.S. Department of Energy, Office of Science, under Contract No. DE-AC02-06CH11357.
+
+We gratefully acknowledge the computing resources provided on Bebop, a high-performance computing cluster operated by the Laboratory Computing Resource Center at Argonne National Laboratory.
+
+## Citation
+If you find EXSCLAIM! useful, please encourage its development by citing the following [paper](https://arxiv.org/abs/2103.10631) in your research:
+```
+Schwenker, E., Jiang, W. Spreadbury, T., Ferrier N., Cossairt, O., Chan M.K.Y., EXSCLAIM! - An automated pipeline for the construction and
+labeling of materials imaging datasets from scientific literature. arXiv e-prints (2021): arXiv-2103
+```
+
+#### Bibtex
+```
+@article{schwenker2021exsclaim,
+  title={EXSCLAIM! - An automated pipeline for the construction of labeled materials imaging datasets from literature},
+  author={Schwenker, Eric and Jiang, Weixin and Spreadbury, Trevor and Ferrier, Nicola and Cossairt, Oliver and Chan, Maria KY},
+  journal={arXiv e-prints},
+  pages={arXiv--2103},
+  year={2021}
+}
+```

exsclaim-2.4.1/exsclaim/README.md

@@ -0,0 +1,13 @@
+## EXSCLAIM Module
+
+This directory contains the relevant code for the EXSCLAIM module, organized as follows:
+
+ - pipeline.py: Code for Pipeline class, which runs ExsclaimTool subclasses on Query JSONs.
+ - tool.py: Defines base ExsclaimTool class and CaptionDistributor and JournalScraper subclasses. Each ExsclaimTool class is initialized with a Query JSON and has methods to run the tool, update the exsclaim.json, and load any necessary models.
+ - figure.py: Defines FigureSeparator, a subclass of ExsclaimTool. Has methods to separate, classify, and read the labels of subfigures and to determine the scale of subfigures.
+ - caption.py: Defines useful functions used by CaptionDistributor.
+ - journal.py: Defines the JournalFamily class. Nature and ACS subfamilies are defined and other journal families can be added and used by JournalScraper.
+ - figures/: Additional modules for defining and training figure models.
+ - captions/: Additional modules for defining and training caption models.
+ - tests/: test files and sample data to check results.
+ - utilities/: Modules with functions that are useful across several modules

exsclaim-2.4.1/exsclaim/__init__.py

@@ -0,0 +1,17 @@
+from .db import *
+from .captions import *
+from .figures import *
+from .tests import *
+from .utilities import *
+
+from .exceptions import *
+from .caption import *
+from .figure import *
+from .journal import *
+from .notifications import *
+from .pipeline import *
+from .tool import *
+from .version import version as __version__
+
+from logging import getLogger, NullHandler
+getLogger(__name__).addHandler(NullHandler())

exsclaim-2.4.1/exsclaim/__main__.py

@@ -0,0 +1,187 @@
+from . import Pipeline, PipelineInterruptionException
+
+try:
+	from . import __version__
+except ImportError:
+	__version__ = None
+from argparse import ArgumentParser
+from atexit import register
+from json import load
+from os import PathLike, chmod
+from os.path import splitext, isfile
+from pathlib import Path
+from shutil import make_archive
+
+
+@register
+def on_terminate():
+	import logging
+	logger = logging.getLogger(__name__)
+
+	for handler in logger.handlers:
+		handler.flush()
+
+	logging.shutdown()
+
+
+async def run_pipeline(query=None, verbose:bool=False, compress:str=None, compress_location:str=None, journal_scraper:bool=False,
+				 pdf_scraper:bool=False, caption_distributor:bool=False, figure_separator:bool=False, **kwargs):
+	if query is None:
+		raise ValueError("The search query is required.")
+
+	# if not any((journal_scraper, pdf_scraper, caption_distributor, figure_separator)):
+	# 	raise ValueError("You must run the pipeline with at least one tool.")
+
+	compress = compress or ""
+
+	path = Path(query).absolute()
+	if not path.exists():
+		raise ValueError(f"The search query file \"{path}\" does not exist.")
+
+	with open(path, "r") as f:
+		search_query = load(f)
+
+	if verbose:
+		if not search_query.get("logging", None):
+			search_query["logging"] = ["print"]
+
+		if "print" not in search_query["logging"]:
+			search_query["logging"].append("print")
+
+	pipeline = Pipeline(search_query)
+	try:
+		results = await pipeline.run(caption_distributor=caption_distributor, pdf_scraper=pdf_scraper,
+									 journal_scraper=journal_scraper, figure_separator=figure_separator)
+
+		for handler in pipeline.logger.handlers:
+			handler.flush()
+
+		if compress:
+			name = search_query["name"]
+			save_location, _ = splitext(compress_location or str(pipeline.results_directory))
+			make_archive(save_location, compress, root_dir=str(pipeline.results_directory.parent), base_dir=name)
+
+			try:
+				chmod(save_location, 0o775)
+				print("Changed the permissions.")
+			except PermissionError:
+				print(f"Could not change the permissions of {save_location} to 775.")
+				pipeline.logger.warning(f"Could not change the permissions of {save_location} to 775.")
+
+	except PipelineInterruptionException as e:
+		pipeline.logger.exception("The pipeline could not successfully finish running.")
+		if hasattr(e, "errno"):
+			return e.errno
+		return -1
+
+	return 0
+
+
+async def ui(dashboard_configuration:PathLike[str] = None, api_configuration:PathLike[str] = None, blocking:bool = False):
+	from signal import signal, SIGINT, SIGTERM, SIGQUIT
+	from subprocess import Popen
+
+	exsclaim_dir = Path(__file__).parent.resolve()
+
+	def get_configuration(configuration:PathLike[str], folder:str) -> str:
+		configuration = configuration or (exsclaim_dir / folder / "config.py")
+
+		if not isfile(configuration):
+			raise FileNotFoundError(f"The configuration file \"{configuration}\" does not exist.")
+
+		configuration = f"file:{configuration}"
+
+		return configuration
+
+	api_configuration = get_configuration(api_configuration, "api")
+	dashboard_configuration = get_configuration(dashboard_configuration, "dashboard")
+
+	api = Popen(["/usr/local/bin/hypercorn", "-c", api_configuration, "exsclaim.api:app"])
+	dashboard = Popen(["/usr/local/bin/gunicorn", "-c", dashboard_configuration, "exsclaim.dashboard:server"],
+		  cwd=str(exsclaim_dir / "dashboard"))
+
+	if not blocking:
+		return 0
+
+	def signal_handler(*args):
+		dashboard.kill()
+		api.kill()
+		return 0
+
+	for sig in {SIGINT, SIGTERM, SIGQUIT}:
+		signal(sig, signal_handler)
+
+	api.wait()
+	dashboard.wait()
+	return 0
+
+
+async def init_db():
+	from .db import Database
+	db = Database()
+	await db.initialize_database()
+
+
+async def launch(args=None):
+	parser = ArgumentParser(prog="exsclaim")
+
+	parser.add_argument("-v", "--version", action="version",
+						version=f"EXSCLAIM v{__version__}" if __version__ is not None else "EXSCLAIM! version is currently unavailable.")
+
+	subparsers = parser.add_subparsers(dest="command", required=True)
+	query_subparser = subparsers.add_parser("query", help="The path to the JSON file holding the search query.")
+
+	query_subparser.add_argument("query", help="The path to the JSON file holding the search query.")
+	query_subparser.add_argument("--journal_scraper", "--journal", "-js", action="store_true")
+	query_subparser.add_argument("--pdf_scraper", "--pdf", "-ps", action="store_true")
+	query_subparser.add_argument("--caption_distributor", "--caption", "-cd", action="store_true")
+	query_subparser.add_argument("--figure_separator", "--figure", "-fs", action="store_true")
+	query_subparser.add_argument("--html_scraper", "-hs", action="store_true")
+	query_subparser.add_argument("--compress", "-c", choices=["zip", "tar", "gztar", "bztar", "xztar"], help="Compress the search results into a tar.gz file to save space. Deletes the original folder after compression.")
+	query_subparser.add_argument("--compress_location", "-cl", help="The location where the compressed search results will be stored.")
+	query_subparser.add_argument("--verbose", "-v", action="store_true")
+
+	view_subparser = subparsers.add_parser("ui", help="View search results from EXSCLAIM!")
+	view_subparser.add_argument("-dc", "--dashboard_configuration", help="The path to the gunicorn configuration file for the dashboard. Example at https://github.com/benoitc/gunicorn/blob/bacbf8aa5152b94e44aa5d2a94aeaf0318a85248/examples/example_config.py")
+	view_subparser.add_argument("-ac", "--api_configuration", help="The path to the gunicorn configuration file for the api.")
+	view_subparser.add_argument("-B", "--blocking", action="store_true", help="If the program should wait for the subprocesses to finish before closing.")
+
+	db_subparser = subparsers.add_parser("initialize_db", help="Initializes the PostgreSQL database.")
+
+	for subparser in (query_subparser, view_subparser):
+		subparser.add_argument("--force_ollama", action="store_true", help="Fails if EXSCLAIM can't connect to the Ollama API.")
+
+	args = vars(parser.parse_args(args))
+
+	if "force_ollama" in args:
+		if args["force_ollama"]:
+			from .captions.ollama_llms import Ollama
+			Ollama.available_models(silent_fail=False)
+
+		del args["force_ollama"]
+
+	exit_code = None
+	match args["command"]:
+		case "query":
+			exit_code = await run_pipeline(**args)
+		case "ui":
+			del args["command"]
+			exit_code = await ui(**args)
+		case "initialize_db":
+			exit_code = await init_db()
+		case "train":
+			...
+
+	return exit_code
+
+
+def main(args=None):
+	from asyncio import run
+	exit_code = run(launch(args))
+
+	if exit_code is not None:
+		exit(exit_code)
+
+
+if __name__ == "__main__":
+	main()

exsclaim-2.4.1/exsclaim/api/__init__.py

@@ -0,0 +1,5 @@
+from .models import *
+from .settings import Settings
+from .__main__ import *
+
+settings = Settings()