caption-flow 0.5.2__tar.gz → 0.5.4__tar.gz

{caption_flow-0.5.2 → caption_flow-0.5.4}/PKG-INFO

@@ -1,57 +1,103 @@
 Metadata-Version: 2.4
 Name: caption-flow
-Version: 0.5.2
+Version: 0.5.4
 Summary: Self-contained distributed community captioning system
+Author: bghira
 Author-email: bghira <bghira@users.github.com>
-License: MIT
+License-Expression: AGPL-3.0-or-later
+Project-URL: Homepage, https://github.com/bghira/CaptionFlow
+Project-URL: Repository, https://github.com/bghira/CaptionFlow
 Keywords: captioning,distributed,vllm,dataset,community
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
-Requires-Python: <3.14,>=3.11
+Requires-Python: >=3.11,<3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: websockets>=12.0
-Requires-Dist: pyarrow>=14.0.0
-Requires-Dist: click>=8.1.0
-Requires-Dist: pydantic>=2.0.0
-Requires-Dist: aiofiles>=23.0.0
-Requires-Dist: rich>=13.0.0
-Requires-Dist: cryptography>=41.0.0
-Requires-Dist: pyyaml>=6.0
-Requires-Dist: certbot>=2.0.0
-Requires-Dist: numpy>=1.24.0
-Requires-Dist: pillow>=10.0.0
-Requires-Dist: webdataset<2.0.0,>=1.0.2
-Requires-Dist: pandas<3.0.0,>=2.3.1
-Requires-Dist: arrow<2.0.0,>=1.3.0
-Requires-Dist: datasets<5.0.0,>=4.0.0
-Requires-Dist: boto3<2.0.0,>=1.40.11
-Requires-Dist: torchdata<0.12.0,>=0.11.0
-Requires-Dist: textual<6.0.0,>=5.3.0
-Requires-Dist: urwid<4.0.0,>=3.0.2
-Requires-Dist: webshart<0.5.0,>=0.4.3
-Requires-Dist: pylance<0.36.0,>=0.35.0
-Requires-Dist: duckdb<2.0.0,>=1.3.2
+Requires-Dist: websockets<17.0,>=16.0
+Requires-Dist: pyarrow<26.0.0,>=21.0.0
+Requires-Dist: click<9.0.0,>=8.2.0
+Requires-Dist: pydantic<3.0.0,>=2.12.0
+Requires-Dist: aiofiles<26.0.0,>=24.1.0
+Requires-Dist: rich<16.0.0,>=14.0.0
+Requires-Dist: cryptography<50.0.0,>=45.0.0
+Requires-Dist: PyYAML<7.0.0,>=6.0.2
+Requires-Dist: certbot<6.0.0,>=5.0.0
+Requires-Dist: numpy<3.0.0,>=2.2.0
+Requires-Dist: Pillow<13.0.0,>=11.3.0
+Requires-Dist: pandas<4.0.0,>=3.0.0
+Requires-Dist: datasets<6.0.0,>=5.0.0
+Requires-Dist: boto3<2.0.0,>=1.43.0
+Requires-Dist: webshart<0.6.0,>=0.5.2
+Requires-Dist: pylance<9.0.0,>=8.0.0
+Requires-Dist: duckdb<2.0.0,>=1.5.0
+Requires-Dist: aiohttp<4.0.0,>=3.13.3
+Requires-Dist: fastapi<0.137.0,>=0.133.0
+Requires-Dist: uvicorn<1.0.0,>=0.35.0
+Requires-Dist: huggingface-hub<2.0.0,>=1.5.0
+Requires-Dist: opencv-python-headless<6.0.0,>=4.13.0
+Requires-Dist: psutil<8.0.0,>=7.0.0
+Requires-Dist: requests<3.0.0,>=2.32.0
+Requires-Dist: tqdm<5.0.0,>=4.67.0
+Requires-Dist: urwid<5.0.0,>=3.0.2
 Provides-Extra: vllm
-Requires-Dist: numpy<2.3.0,>=2.2.0; extra == "vllm"
-Requires-Dist: vllm<0.20.0,>=0.19.1; extra == "vllm"
-Requires-Dist: transformers<6.0.0,>=5.5.1; extra == "vllm"
+Requires-Dist: vllm<0.26.0,>=0.25.1; extra == "vllm"
+Requires-Dist: torch==2.11.0; extra == "vllm"
+Requires-Dist: torchvision==0.26.0; extra == "vllm"
+Requires-Dist: torchaudio==2.11.0; extra == "vllm"
+Requires-Dist: transformers<6.0.0,>=5.5.3; extra == "vllm"
+Requires-Dist: qwen-vl-utils<0.1.0,>=0.0.14; extra == "vllm"
+Provides-Extra: captioning
+Requires-Dist: vllm<0.26.0,>=0.25.1; extra == "captioning"
+Requires-Dist: torch==2.11.0; extra == "captioning"
+Requires-Dist: torchvision==0.26.0; extra == "captioning"
+Requires-Dist: torchaudio==2.11.0; extra == "captioning"
+Requires-Dist: transformers<6.0.0,>=5.5.3; extra == "captioning"
+Requires-Dist: qwen-vl-utils<0.1.0,>=0.0.14; extra == "captioning"
+Provides-Extra: cpu
+Requires-Dist: torch>=2.11.0; extra == "cpu"
+Requires-Dist: torchvision>=0.26.0; extra == "cpu"
+Requires-Dist: torchaudio>=2.11.0; extra == "cpu"
+Provides-Extra: cuda
+Requires-Dist: torch>=2.11.0; extra == "cuda"
+Requires-Dist: torchvision>=0.26.0; extra == "cuda"
+Requires-Dist: torchaudio>=2.11.0; extra == "cuda"
+Provides-Extra: cuda13
+Requires-Dist: torch>=2.11.0; extra == "cuda13"
+Requires-Dist: torchvision>=0.26.0; extra == "cuda13"
+Requires-Dist: torchaudio>=2.11.0; extra == "cuda13"
+Provides-Extra: rocm
+Requires-Dist: torch>=2.11.0; extra == "rocm"
+Requires-Dist: torchvision>=0.26.0; extra == "rocm"
+Requires-Dist: torchaudio>=2.11.0; extra == "rocm"
+Provides-Extra: apple
+Requires-Dist: torch>=2.13.0; extra == "apple"
+Requires-Dist: torchvision>=0.28.0; extra == "apple"
+Requires-Dist: torchaudio>=2.11.0; extra == "apple"
+Requires-Dist: vllm-metal==0.1.0; (platform_system == "Darwin" and platform_machine == "arm64" and python_version >= "3.12") and extra == "apple"
 Provides-Extra: dev
-Requires-Dist: pytest>=7.4.0; extra == "dev"
-Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
-Requires-Dist: pytest-cov>=4.1.0; extra == "dev"
-Requires-Dist: black>=23.0.0; extra == "dev"
-Requires-Dist: ruff>=0.1.0; extra == "dev"
-Requires-Dist: mypy>=1.5.0; extra == "dev"
-Requires-Dist: numpy<2.3.0,>=2.2.0; extra == "dev"
-Requires-Dist: vllm<0.20.0,>=0.19.1; extra == "dev"
-Requires-Dist: transformers<6.0.0,>=5.5.1; extra == "dev"
+Requires-Dist: pytest<9.0.0,>=8.0.0; extra == "dev"
+Requires-Dist: pytest-asyncio<2.0.0,>=1.1.0; extra == "dev"
+Requires-Dist: pytest-cov<7.0.0,>=6.0.0; extra == "dev"
+Requires-Dist: transformers<6.0.0,>=5.5.3; extra == "dev"
+Requires-Dist: black<26.0.0,>=25.0.0; extra == "dev"
+Requires-Dist: ruff<1.0.0,>=0.12.0; extra == "dev"
+Requires-Dist: mypy<2.0.0,>=1.17.0; extra == "dev"
+Provides-Extra: all
+Requires-Dist: vllm<0.26.0,>=0.25.1; extra == "all"
+Requires-Dist: torch==2.11.0; extra == "all"
+Requires-Dist: torchvision==0.26.0; extra == "all"
+Requires-Dist: torchaudio==2.11.0; extra == "all"
+Requires-Dist: transformers<6.0.0,>=5.5.3; extra == "all"
+Requires-Dist: qwen-vl-utils<0.1.0,>=0.0.14; extra == "all"
+Dynamic: author
 Dynamic: license-file
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: requires-python
 
 # CaptionFlow
 
@@ -63,6 +109,8 @@ scalable, fault-tolerant **vLLM-powered image captioning**.
 
 a fast websocket-based orchestrator paired with lightweight gpu workers achieves exceptional performance for batched requests through vLLM.
 
+CaptionFlow is also integrated in [bghira/SimpleTuner](https://github.com/bghira/SimpleTuner), where it powers an end-to-end caption-to-training workflow through the SimpleTuner WebUI. Use CaptionFlow directly when you want a standalone distributed captioning system, or use it through SimpleTuner when you want dataset captioning, caption review/export, and model training managed as one suite.
+
 * **orchestrator**: hands out work in chunked shards, collects captions, checkpoints progress, and keeps simple stats.
 * **workers (vLLM)**: connect to the orchestrator, stream in image samples, batch them, and generate 1..N captions per image using prompts supplied by the orchestrator.
 * **config-driven**: all components read YAML config; flags can override.
@@ -76,11 +124,43 @@ a fast websocket-based orchestrator paired with lightweight gpu workers achieves
 ```bash
 python -m venv .venv
 source .venv/bin/activate  # windows: .venv\Scripts\activate
-pip install caption-flow
+pip install --upgrade pip
+pip install "caption-flow[vllm]"
+```
+
+For an orchestrator or monitor-only install, use `pip install -e .`.
+`.[captioning]` is an alias for `.[vllm]` for integrations such as
+SimpleTuner. Terminal image previews remain optional because the current
+`term-image` release requires an older Pillow major than CaptionFlow uses.
+
+On Apple Silicon, install the MPS-compatible PyTorch chain and pinned Metal
+plugin with:
+
+```bash
+pip install -e ".[apple]"
+```
+
+CaptionFlow can use vLLM on Apple Silicon too, but the normal Linux `vllm`
+wheel is not the Apple install path. The pinned `vllm-metal` dependency is
+selected automatically on native arm64 Python 3.12+. For a ready-to-run
+Metal worker, use the upstream installer, which also builds/installs the
+Apple-specific vLLM core:
+
+```bash
+curl -fsSL https://raw.githubusercontent.com/vllm-project/vllm-metal/main/install.sh | bash
+source ~/.venv-vllm-metal/bin/activate
+pip install -e .
 ```
 
+Do not combine `.[apple]` with the Linux `.[vllm]` extra.
+
+For native macOS CPU vLLM instead, follow the
+[official source-build instructions](https://docs.vllm.ai/en/stable/getting_started/installation/cpu/?device=apple).
+
 ## quickstart (single box)
 
+for a full caption-to-training workflow with a web interface, use the SimpleTuner WebUI integration. the standalone flow below is best when you want to run CaptionFlow directly, contribute workers to a cluster, or export captions for your own downstream training pipeline.
+
 1. copy + edit the sample configs
 
 ```bash
@@ -127,15 +207,18 @@ Usage: caption-flow export [OPTIONS]
   Export caption data to various formats.
 
 Options:
-  --format [jsonl|json|csv|txt|huggingface_hub|all] Export format (default: jsonl)
+  --format [jsonl|json|csv|txt|parquet|webshart|lance|huggingface_hub|all] Export format (default: jsonl)
 ```
 
 * **jsonl**: create JSON line file in the specified `--output` path
 * **csv**: exports CSV-compatible data columns to the `--output` path containing incomplete metadata
 * **json**: creates a `.json` file for each sample inside the `--output` subdirectory containing **complete** metadata; useful for webdatasets
 * **txt**: creates `.txt` file for each sample inside the `--output` subdirectory containing ONLY captions
+* **webshart**: updates an **existing per-shard metadata `.json` file** by writing captions under the plural `captions` key. for this format, pass `--output` as the path to the existing shard metadata JSON file when exporting one shard. if you export multiple shards, pass `--output` as a directory containing one existing `{shard_name}.json` file per shard.
 * **huggingface_hub**: creates a dataset on Hugging Face Hub, possibly `--private` and `--nsfw` where necessary
-* **all**: creates all export formats in a specified `--output` directory
+* **all**: creates the directory/file-generating export formats in a specified `--output` directory. prefer a directory here; `webshart` is a special case that expects existing per-shard metadata `.json` files rather than creating new metadata files.
+
+> note: `--output` paths ending in `.json` are treated specially for `webshart`. use a directory for normal multi-format exports and an existing shard metadata JSON file only when intentionally updating a `webshart` shard.
 
 ---
 
@@ -162,6 +245,7 @@ Options:
 ## dataset formats
 
 * huggingface hub or local based URL list datasets that are compatible with the datasets library
+* huggingface hub datasets that are simple containers of raw image files
 * webdatasets shards containing full image data; also can be hosted on the hub
 * local folder filled with images; orchestrator will serve the data to workers
 
@@ -240,7 +324,7 @@ PRs welcome. keep it simple and fast.
 
 To contribute compute to a cluster:
 
-1. Install caption-flow: `pip install caption-flow`
+1. Install caption-flow: `pip install "caption-flow[vllm]"`
 2. Get a worker token from the project maintainer
 3. Run: `caption-flow worker --server wss://project.domain.com:8765 --token YOUR_TOKEN`
 

caption_flow-0.5.2/src/caption_flow.egg-info/PKG-INFO → caption_flow-0.5.4/README.md

@@ -1,58 +1,3 @@
-Metadata-Version: 2.4
-Name: caption-flow
-Version: 0.5.2
-Summary: Self-contained distributed community captioning system
-Author-email: bghira <bghira@users.github.com>
-License: MIT
-Keywords: captioning,distributed,vllm,dataset,community
-Classifier: Development Status :: 4 - Beta
-Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Requires-Python: <3.14,>=3.11
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: websockets>=12.0
-Requires-Dist: pyarrow>=14.0.0
-Requires-Dist: click>=8.1.0
-Requires-Dist: pydantic>=2.0.0
-Requires-Dist: aiofiles>=23.0.0
-Requires-Dist: rich>=13.0.0
-Requires-Dist: cryptography>=41.0.0
-Requires-Dist: pyyaml>=6.0
-Requires-Dist: certbot>=2.0.0
-Requires-Dist: numpy>=1.24.0
-Requires-Dist: pillow>=10.0.0
-Requires-Dist: webdataset<2.0.0,>=1.0.2
-Requires-Dist: pandas<3.0.0,>=2.3.1
-Requires-Dist: arrow<2.0.0,>=1.3.0
-Requires-Dist: datasets<5.0.0,>=4.0.0
-Requires-Dist: boto3<2.0.0,>=1.40.11
-Requires-Dist: torchdata<0.12.0,>=0.11.0
-Requires-Dist: textual<6.0.0,>=5.3.0
-Requires-Dist: urwid<4.0.0,>=3.0.2
-Requires-Dist: webshart<0.5.0,>=0.4.3
-Requires-Dist: pylance<0.36.0,>=0.35.0
-Requires-Dist: duckdb<2.0.0,>=1.3.2
-Provides-Extra: vllm
-Requires-Dist: numpy<2.3.0,>=2.2.0; extra == "vllm"
-Requires-Dist: vllm<0.20.0,>=0.19.1; extra == "vllm"
-Requires-Dist: transformers<6.0.0,>=5.5.1; extra == "vllm"
-Provides-Extra: dev
-Requires-Dist: pytest>=7.4.0; extra == "dev"
-Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
-Requires-Dist: pytest-cov>=4.1.0; extra == "dev"
-Requires-Dist: black>=23.0.0; extra == "dev"
-Requires-Dist: ruff>=0.1.0; extra == "dev"
-Requires-Dist: mypy>=1.5.0; extra == "dev"
-Requires-Dist: numpy<2.3.0,>=2.2.0; extra == "dev"
-Requires-Dist: vllm<0.20.0,>=0.19.1; extra == "dev"
-Requires-Dist: transformers<6.0.0,>=5.5.1; extra == "dev"
-Dynamic: license-file
-
 # CaptionFlow
 
 <!-- [![Tests](https://github.com/bghira/CaptionFlow/workflows/tests/badge.svg)](https://github.com/bghira/CaptionFlow/actions/workflows/tests.yml) -->
@@ -63,6 +8,8 @@ scalable, fault-tolerant **vLLM-powered image captioning**.
 
 a fast websocket-based orchestrator paired with lightweight gpu workers achieves exceptional performance for batched requests through vLLM.
 
+CaptionFlow is also integrated in [bghira/SimpleTuner](https://github.com/bghira/SimpleTuner), where it powers an end-to-end caption-to-training workflow through the SimpleTuner WebUI. Use CaptionFlow directly when you want a standalone distributed captioning system, or use it through SimpleTuner when you want dataset captioning, caption review/export, and model training managed as one suite.
+
 * **orchestrator**: hands out work in chunked shards, collects captions, checkpoints progress, and keeps simple stats.
 * **workers (vLLM)**: connect to the orchestrator, stream in image samples, batch them, and generate 1..N captions per image using prompts supplied by the orchestrator.
 * **config-driven**: all components read YAML config; flags can override.
@@ -76,11 +23,43 @@ a fast websocket-based orchestrator paired with lightweight gpu workers achieves
 ```bash
 python -m venv .venv
 source .venv/bin/activate  # windows: .venv\Scripts\activate
-pip install caption-flow
+pip install --upgrade pip
+pip install "caption-flow[vllm]"
+```
+
+For an orchestrator or monitor-only install, use `pip install -e .`.
+`.[captioning]` is an alias for `.[vllm]` for integrations such as
+SimpleTuner. Terminal image previews remain optional because the current
+`term-image` release requires an older Pillow major than CaptionFlow uses.
+
+On Apple Silicon, install the MPS-compatible PyTorch chain and pinned Metal
+plugin with:
+
+```bash
+pip install -e ".[apple]"
 ```
 
+CaptionFlow can use vLLM on Apple Silicon too, but the normal Linux `vllm`
+wheel is not the Apple install path. The pinned `vllm-metal` dependency is
+selected automatically on native arm64 Python 3.12+. For a ready-to-run
+Metal worker, use the upstream installer, which also builds/installs the
+Apple-specific vLLM core:
+
+```bash
+curl -fsSL https://raw.githubusercontent.com/vllm-project/vllm-metal/main/install.sh | bash
+source ~/.venv-vllm-metal/bin/activate
+pip install -e .
+```
+
+Do not combine `.[apple]` with the Linux `.[vllm]` extra.
+
+For native macOS CPU vLLM instead, follow the
+[official source-build instructions](https://docs.vllm.ai/en/stable/getting_started/installation/cpu/?device=apple).
+
 ## quickstart (single box)
 
+for a full caption-to-training workflow with a web interface, use the SimpleTuner WebUI integration. the standalone flow below is best when you want to run CaptionFlow directly, contribute workers to a cluster, or export captions for your own downstream training pipeline.
+
 1. copy + edit the sample configs
 
 ```bash
@@ -127,15 +106,18 @@ Usage: caption-flow export [OPTIONS]
   Export caption data to various formats.
 
 Options:
-  --format [jsonl|json|csv|txt|huggingface_hub|all] Export format (default: jsonl)
+  --format [jsonl|json|csv|txt|parquet|webshart|lance|huggingface_hub|all] Export format (default: jsonl)
 ```
 
 * **jsonl**: create JSON line file in the specified `--output` path
 * **csv**: exports CSV-compatible data columns to the `--output` path containing incomplete metadata
 * **json**: creates a `.json` file for each sample inside the `--output` subdirectory containing **complete** metadata; useful for webdatasets
 * **txt**: creates `.txt` file for each sample inside the `--output` subdirectory containing ONLY captions
+* **webshart**: updates an **existing per-shard metadata `.json` file** by writing captions under the plural `captions` key. for this format, pass `--output` as the path to the existing shard metadata JSON file when exporting one shard. if you export multiple shards, pass `--output` as a directory containing one existing `{shard_name}.json` file per shard.
 * **huggingface_hub**: creates a dataset on Hugging Face Hub, possibly `--private` and `--nsfw` where necessary
-* **all**: creates all export formats in a specified `--output` directory
+* **all**: creates the directory/file-generating export formats in a specified `--output` directory. prefer a directory here; `webshart` is a special case that expects existing per-shard metadata `.json` files rather than creating new metadata files.
+
+> note: `--output` paths ending in `.json` are treated specially for `webshart`. use a directory for normal multi-format exports and an existing shard metadata JSON file only when intentionally updating a `webshart` shard.
 
 ---
 
@@ -162,6 +144,7 @@ Options:
 ## dataset formats
 
 * huggingface hub or local based URL list datasets that are compatible with the datasets library
+* huggingface hub datasets that are simple containers of raw image files
 * webdatasets shards containing full image data; also can be hosted on the hub
 * local folder filled with images; orchestrator will serve the data to workers
 
@@ -240,7 +223,7 @@ PRs welcome. keep it simple and fast.
 
 To contribute compute to a cluster:
 
-1. Install caption-flow: `pip install caption-flow`
+1. Install caption-flow: `pip install "caption-flow[vllm]"`
 2. Get a worker token from the project maintainer
 3. Run: `caption-flow worker --server wss://project.domain.com:8765 --token YOUR_TOKEN`
 

{caption_flow-0.5.2 → caption_flow-0.5.4}/pyproject.toml

@@ -1,71 +1,31 @@
+[build-system]
+requires = ["setuptools>=68.0.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
 [project]
 name = "caption-flow"
-version = "0.5.2"
+dynamic = ["version", "dependencies", "optional-dependencies"]
 description = "Self-contained distributed community captioning system"
 readme = "README.md"
+license = "AGPL-3.0-or-later"
 requires-python = ">=3.11,<3.14"
-license = { text = "MIT" }
 authors = [{ name = "bghira", email = "bghira@users.github.com" }]
 keywords = ["captioning", "distributed", "vllm", "dataset", "community"]
 classifiers = [
     "Development Status :: 4 - Beta",
     "Intended Audience :: Developers",
-    "License :: OSI Approved :: MIT License",
     "Programming Language :: Python :: 3",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
     "Programming Language :: Python :: 3.13",
 ]
 
-dependencies = [
-    "websockets>=12.0",
-    "pyarrow>=14.0.0",
-    "click>=8.1.0",
-    "pydantic>=2.0.0",
-    "aiofiles>=23.0.0",
-    "rich>=13.0.0",
-    "cryptography>=41.0.0",
-    "pyyaml>=6.0",
-    "certbot>=2.0.0",
-    "numpy>=1.24.0",
-    "pillow>=10.0.0",
-    "webdataset (>=1.0.2,<2.0.0)",
-    "pandas (>=2.3.1,<3.0.0)",
-    "arrow (>=1.3.0,<2.0.0)",
-    "datasets (>=4.0.0,<5.0.0)",
-    "boto3 (>=1.40.11,<2.0.0)",
-    "torchdata (>=0.11.0,<0.12.0)",
-    "textual (>=5.3.0,<6.0.0)",
-    "urwid (>=3.0.2,<4.0.0)",
-    "webshart (>=0.4.3,<0.5.0)",
-    "pylance (>=0.35.0,<0.36.0)",
-    "duckdb (>=1.3.2,<2.0.0)",
-]
-
-[project.optional-dependencies]
-vllm = [
-    "numpy (>=2.2.0,<2.3.0)",
-    "vllm (>=0.19.1,<0.20.0)",
-    "transformers (>=5.5.1,<6.0.0)",
-]
-dev = [
-    "pytest>=7.4.0",
-    "pytest-asyncio>=0.21.0",
-    "pytest-cov>=4.1.0",
-    "black>=23.0.0",
-    "ruff>=0.1.0",
-    "mypy>=1.5.0",
-    "numpy (>=2.2.0,<2.3.0)",
-    "vllm (>=0.19.1,<0.20.0)",
-    "transformers (>=5.5.1,<6.0.0)",
-]
-
 [project.scripts]
 caption-flow = "caption_flow.cli:main"
 
-[build-system]
-requires = ["setuptools>=68.0.0", "wheel"]
-build-backend = "setuptools.build_meta"
+[project.urls]
+Homepage = "https://github.com/bghira/CaptionFlow"
+Repository = "https://github.com/bghira/CaptionFlow"
 
 [tool.setuptools.packages.find]
 where = ["src"]
@@ -98,5 +58,5 @@ warn_return_any = true
 warn_unused_configs = true
 disallow_untyped_defs = true
 
-[tool.poetry.group.dev.dependencies]
-pytest-asyncio = "^1.1.0"
+[tool.setuptools.dynamic]
+version = { attr = "caption_flow.__version__" }

caption_flow-0.5.4/setup.py

@@ -0,0 +1,129 @@
+#!/usr/bin/env python3
+
+"""Setuptools configuration for CaptionFlow.
+
+The project keeps dependency selection here so that the GPU worker stack can
+be installed separately from the orchestrator and monitor components.
+"""
+
+from pathlib import Path
+
+from setuptools import find_packages, setup
+
+ROOT = Path(__file__).parent
+
+
+def get_version() -> str:
+    """Read the package version without importing CaptionFlow's dependencies."""
+    version_file = ROOT / "src" / "caption_flow" / "__init__.py"
+    for line in version_file.read_text(encoding="utf-8").splitlines():
+        if line.startswith("__version__"):
+            return line.split("=", 1)[1].strip().strip("\"'")
+    raise RuntimeError("Unable to determine CaptionFlow version")
+
+
+base_deps = [
+    "websockets>=16.0,<17.0",
+    "pyarrow>=21.0.0,<26.0.0",
+    "click>=8.2.0,<9.0.0",
+    "pydantic>=2.12.0,<3.0.0",
+    "aiofiles>=24.1.0,<26.0.0",
+    "rich>=14.0.0,<16.0.0",
+    "cryptography>=45.0.0,<50.0.0",
+    "PyYAML>=6.0.2,<7.0.0",
+    "certbot>=5.0.0,<6.0.0",
+    "numpy>=2.2.0,<3.0.0",
+    "Pillow>=11.3.0,<13.0.0",
+    "pandas>=3.0.0,<4.0.0",
+    "datasets>=5.0.0,<6.0.0",
+    "boto3>=1.43.0,<2.0.0",
+    "webshart>=0.5.2,<0.6.0",
+    "pylance>=8.0.0,<9.0.0",
+    "duckdb>=1.5.0,<2.0.0",
+    "aiohttp>=3.13.3,<4.0.0",
+    "fastapi>=0.133.0,<0.137.0",
+    "uvicorn>=0.35.0,<1.0.0",
+    "huggingface-hub>=1.5.0,<2.0.0",
+    "opencv-python-headless>=4.13.0,<6.0.0",
+    "psutil>=7.0.0,<8.0.0",
+    "requests>=2.32.0,<3.0.0",
+    "tqdm>=4.67.0,<5.0.0",
+    "urwid>=3.0.2,<5.0.0",
+]
+
+# vLLM 0.25.1 currently selects the PyTorch 2.11.0 family. Keep these
+# explicit so a worker install cannot silently combine incompatible torch
+# packages when another dependency broadens its requirements.
+vllm_deps = [
+    "vllm>=0.25.1,<0.26.0",
+    "torch==2.11.0",
+    "torchvision==0.26.0",
+    "torchaudio==2.11.0",
+    "transformers>=5.5.3,<6.0.0",
+    "qwen-vl-utils>=0.0.14,<0.1.0",
+]
+
+PYTORCH_DEPENDENCIES = [
+    "torch>=2.11.0",
+    "torchvision>=0.26.0",
+    "torchaudio>=2.11.0",
+]
+
+APPLE_PYTORCH_DEPENDENCIES = [
+    "torch>=2.13.0",
+    "torchvision>=0.28.0",
+    "torchaudio>=2.11.0",
+    # vLLM Metal publishes Apple Silicon wheels for Python 3.12+.
+    "vllm-metal==0.1.0; platform_system == 'Darwin' and platform_machine == 'arm64' and python_version >= '3.12'",
+]
+
+extras_require = {
+    "vllm": vllm_deps,
+    "captioning": vllm_deps,
+    "cpu": PYTORCH_DEPENDENCIES,
+    "cuda": PYTORCH_DEPENDENCIES,
+    "cuda13": PYTORCH_DEPENDENCIES,
+    "rocm": PYTORCH_DEPENDENCIES,
+    "apple": APPLE_PYTORCH_DEPENDENCIES,
+    "dev": [
+        "pytest>=8.0.0,<9.0.0",
+        "pytest-asyncio>=1.1.0,<2.0.0",
+        "pytest-cov>=6.0.0,<7.0.0",
+        "transformers>=5.5.3,<6.0.0",
+        "black>=25.0.0,<26.0.0",
+        "ruff>=0.12.0,<1.0.0",
+        "mypy>=1.17.0,<2.0.0",
+    ],
+    "all": [*vllm_deps],
+}
+
+
+setup(
+    name="caption-flow",
+    version=get_version(),
+    description="Self-contained distributed community captioning system",
+    long_description=(ROOT / "README.md").read_text(encoding="utf-8"),
+    long_description_content_type="text/markdown",
+    author="bghira",
+    author_email="bghira@users.github.com",
+    packages=find_packages(where="src"),
+    package_dir={"": "src"},
+    include_package_data=True,
+    python_requires=">=3.11,<3.14",
+    install_requires=base_deps,
+    extras_require=extras_require,
+    entry_points={"console_scripts": ["caption-flow=caption_flow.cli:main"]},
+    classifiers=[
+        "Development Status :: 4 - Beta",
+        "Intended Audience :: Developers",
+        "Programming Language :: Python :: 3",
+        "Programming Language :: Python :: 3.11",
+        "Programming Language :: Python :: 3.12",
+        "Programming Language :: Python :: 3.13",
+    ],
+    keywords=["captioning", "distributed", "vllm", "dataset", "community"],
+    project_urls={
+        "Homepage": "https://github.com/bghira/CaptionFlow",
+        "Repository": "https://github.com/bghira/CaptionFlow",
+    },
+)

{caption_flow-0.5.2 → caption_flow-0.5.4}/src/caption_flow/__init__.py

@@ -1,6 +1,6 @@
 """CaptionFlow - Distributed community captioning system."""
 
-__version__ = "0.5.2"
+__version__ = "0.5.4"
 
 from .monitor import Monitor
 from .orchestrator import Orchestrator

{caption_flow-0.5.2 → caption_flow-0.5.4}/src/caption_flow/cli.py

@@ -367,8 +367,8 @@ def orchestrator(ctx, config: Optional[str], **kwargs):
 @click.option(
     "--when_finished",
     type=click.Choice(["stay_connected", "shutdown", "post_exec_hook"]),
-    default="stay_connected",
-    help="Action when all captions are complete (default: stay_connected)",
+    default=None,
+    help="Action when all captions are complete (default: config value or stay_connected)",
 )
 @click.option("--post_exec_hook", help="Path to executable for post_exec_hook action")
 @click.pass_context
@@ -1498,7 +1498,17 @@ async def _run_export_process(
 @click.option(
     "--format",
     type=click.Choice(
-        ["jsonl", "json", "csv", "txt", "parquet", "lance", "huggingface_hub", "all"],
+        [
+            "jsonl",
+            "json",
+            "csv",
+            "txt",
+            "parquet",
+            "webshart",
+            "lance",
+            "huggingface_hub",
+            "all",
+        ],
         case_sensitive=False,
     ),
     default="jsonl",