Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/trackio_logo_old.png filter=lfs diff=lfs merge=lfs -text

__init__.py

@@ -0,0 +1,203 @@
+import hashlib
+import os
+import warnings
+import webbrowser
+from pathlib import Path
+from typing import Any
+
+from gradio.blocks import BUILT_IN_THEMES
+from gradio.themes import Default as DefaultTheme
+from gradio.themes import ThemeClass
+from gradio_client import Client
+
+from trackio import context_vars, deploy, utils
+from trackio.imports import import_csv, import_tf_events
+from trackio.media import TrackioImage
+from trackio.run import Run
+from trackio.sqlite_storage import SQLiteStorage
+from trackio.ui import demo
+from trackio.utils import TRACKIO_DIR, TRACKIO_LOGO_DIR
+
+__version__ = Path(__file__).parent.joinpath("version.txt").read_text().strip()
+
+__all__ = ["init", "log", "finish", "show", "import_csv", "import_tf_events", "Image"]
+
+Image = TrackioImage
+
+
+config = {}
+
+DEFAULT_THEME = "citrus"
+
+
+def init(
+    project: str,
+    name: str | None = None,
+    space_id: str | None = None,
+    dataset_id: str | None = None,
+    config: dict | None = None,
+    resume: str = "never",
+    settings: Any = None,
+) -> Run:
+    """
+    Creates a new Trackio project and returns a Run object.
+
+    Args:
+        project: The name of the project (can be an existing project to continue tracking or a new project to start tracking from scratch).
+        name: The name of the run (if not provided, a default name will be generated).
+        space_id: If provided, the project will be logged to a Hugging Face Space instead of a local directory. Should be a complete Space name like "username/reponame" or "orgname/reponame", or just "reponame" in which case the Space will be created in the currently-logged-in Hugging Face user's namespace. If the Space does not exist, it will be created. If the Space already exists, the project will be logged to it.
+        dataset_id: If a space_id is provided, a persistent Hugging Face Dataset will be created and the metrics will be synced to it every 5 minutes. Specify a Dataset with name like "username/datasetname" or "orgname/datasetname", or "datasetname" (uses currently-logged-in Hugging Face user's namespace), or None (uses the same name as the Space but with the "_dataset" suffix). If the Dataset does not exist, it will be created. If the Dataset already exists, the project will be appended to it.
+        config: A dictionary of configuration options. Provided for compatibility with wandb.init()
+        resume: Controls how to handle resuming a run. Can be one of:
+            - "must": Must resume the run with the given name, raises error if run doesn't exist
+            - "allow": Resume the run if it exists, otherwise create a new run
+            - "never": Never resume a run, always create a new one
+        settings: Not used. Provided for compatibility with wandb.init()
+    """
+    if settings is not None:
+        warnings.warn(
+            "* Warning: settings is not used. Provided for compatibility with wandb.init(). Please create an issue at: https://github.com/gradio-app/trackio/issues if you need a specific feature implemented."
+        )
+
+    if space_id is None and dataset_id is not None:
+        raise ValueError("Must provide a `space_id` when `dataset_id` is provided.")
+    space_id, dataset_id = utils.preprocess_space_and_dataset_ids(space_id, dataset_id)
+    url = context_vars.current_server.get()
+
+    if url is None:
+        if space_id is None:
+            _, url, _ = demo.launch(
+                show_api=False,
+                inline=False,
+                quiet=True,
+                prevent_thread_lock=True,
+                show_error=True,
+            )
+        else:
+            url = space_id
+        context_vars.current_server.set(url)
+
+    if (
+        context_vars.current_project.get() is None
+        or context_vars.current_project.get() != project
+    ):
+        print(f"* Trackio project initialized: {project}")
+
+        if dataset_id is not None:
+            os.environ["TRACKIO_DATASET_ID"] = dataset_id
+            print(
+                f"* Trackio metrics will be synced to Hugging Face Dataset: {dataset_id}"
+            )
+        if space_id is None:
+            print(f"* Trackio metrics logged to: {TRACKIO_DIR}")
+            utils.print_dashboard_instructions(project)
+        else:
+            deploy.create_space_if_not_exists(space_id, dataset_id)
+            print(
+                f"* View dashboard by going to: {deploy.SPACE_URL.format(space_id=space_id)}"
+            )
+    context_vars.current_project.set(project)
+
+    client = None
+    if not space_id:
+        client = Client(url, verbose=False)
+
+    if resume == "must":
+        if name is None:
+            raise ValueError("Must provide a run name when resume='must'")
+        if name not in SQLiteStorage.get_runs(project):
+            raise ValueError(f"Run '{name}' does not exist in project '{project}'")
+    elif resume == "allow":
+        if name is not None and name in SQLiteStorage.get_runs(project):
+            print(f"* Resuming existing run: {name}")
+    elif resume == "never":
+        if name is not None and name in SQLiteStorage.get_runs(project):
+            name = None
+    else:
+        raise ValueError("resume must be one of: 'must', 'allow', or 'never'")
+
+    run = Run(
+        url=url,
+        project=project,
+        client=client,
+        name=name,
+        config=config,
+        space_id=space_id,
+    )
+    context_vars.current_run.set(run)
+    globals()["config"] = run.config
+    return run
+
+
+def log(metrics: dict, step: int | None = None) -> None:
+    """
+    Logs metrics to the current run.
+
+    Args:
+        metrics: A dictionary of metrics to log.
+        step: The step number. If not provided, the step will be incremented automatically.
+    """
+    run = context_vars.current_run.get()
+    if run is None:
+        raise RuntimeError("Call trackio.init() before trackio.log().")
+    run.log(
+        metrics=metrics,
+        step=step,
+    )
+
+
+def finish():
+    """
+    Finishes the current run.
+    """
+    run = context_vars.current_run.get()
+    if run is None:
+        raise RuntimeError("Call trackio.init() before trackio.finish().")
+    run.finish()
+
+
+def show(project: str | None = None, theme: str | ThemeClass = DEFAULT_THEME):
+    """
+    Launches the Trackio dashboard.
+
+    Args:
+        project: The name of the project whose runs to show. If not provided, all projects will be shown and the user can select one.
+        theme: The Gradio theme to use. Can be any built-in Gradio theme (e.g. "citrus", "soft", "default"), theme from the Hub (https://huggingface.co/spaces/gradio/theme-gallery), or a custom gradio.themes.ThemeClass
+    """
+    if theme != DEFAULT_THEME:
+        # TODO: It's a little hacky to reproduce this theme-setting logic from Gradio Blocks,
+        # but in Gradio 6.0, the theme will be set in `launch()` instead, which means that we
+        # will be able to remove this code.
+        if isinstance(theme, str):
+            if theme.lower() in BUILT_IN_THEMES:
+                theme = BUILT_IN_THEMES[theme.lower()]
+            else:
+                try:
+                    theme = ThemeClass.from_hub(theme)
+                except Exception as e:
+                    warnings.warn(f"Cannot load {theme}. Caught Exception: {str(e)}")
+                    theme = DefaultTheme()
+        if not isinstance(theme, ThemeClass):
+            warnings.warn("Theme should be a class loaded from gradio.themes")
+            theme = DefaultTheme()
+        demo.theme: ThemeClass = theme
+        demo.theme_css = theme._get_theme_css()
+        demo.stylesheets = theme._stylesheets
+        theme_hasher = hashlib.sha256()
+        theme_hasher.update(demo.theme_css.encode("utf-8"))
+        demo.theme_hash = theme_hasher.hexdigest()
+
+    _, url, share_url = demo.launch(
+        show_api=False,
+        quiet=True,
+        inline=False,
+        prevent_thread_lock=True,
+        favicon_path=TRACKIO_LOGO_DIR / "trackio_logo_light.png",
+        allowed_paths=[TRACKIO_LOGO_DIR],
+    )
+
+    base_url = share_url + "/" if share_url else url
+    dashboard_url = base_url + f"?project={project}" if project else base_url
+    print(f"* Trackio UI launched at: {dashboard_url}")
+    webbrowser.open(dashboard_url)
+    utils.block_except_in_notebook()

cli.py

@@ -0,0 +1,32 @@
+import argparse
+
+from trackio import show
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Trackio CLI")
+    subparsers = parser.add_subparsers(dest="command")
+
+    ui_parser = subparsers.add_parser(
+        "show", help="Show the Trackio dashboard UI for a project"
+    )
+    ui_parser.add_argument(
+        "--project", required=False, help="Project name to show in the dashboard"
+    )
+    ui_parser.add_argument(
+        "--theme",
+        required=False,
+        default="citrus",
+        help="A Gradio Theme to use for the dashboard instead of the default 'citrus', can be a built-in theme (e.g. 'soft', 'default'), a theme from the Hub (e.g. 'gstaff/xkcd').",
+    )
+
+    args = parser.parse_args()
+
+    if args.command == "show":
+        show(args.project, args.theme)
+    else:
+        parser.print_help()
+
+
+if __name__ == "__main__":
+    main()

commit_scheduler.py

@@ -0,0 +1,391 @@
+# Originally copied from https://github.com/huggingface/huggingface_hub/blob/d0a948fc2a32ed6e557042a95ef3e4af97ec4a7c/src/huggingface_hub/_commit_scheduler.py
+
+import atexit
+import logging
+import os
+import time
+from concurrent.futures import Future
+from dataclasses import dataclass
+from io import SEEK_END, SEEK_SET, BytesIO
+from pathlib import Path
+from threading import Lock, Thread
+from typing import Callable, Dict, List, Optional, Union
+
+from huggingface_hub.hf_api import (
+    DEFAULT_IGNORE_PATTERNS,
+    CommitInfo,
+    CommitOperationAdd,
+    HfApi,
+)
+from huggingface_hub.utils import filter_repo_objects
+
+logger = logging.getLogger(__name__)
+
+
+@dataclass(frozen=True)
+class _FileToUpload:
+    """Temporary dataclass to store info about files to upload. Not meant to be used directly."""
+
+    local_path: Path
+    path_in_repo: str
+    size_limit: int
+    last_modified: float
+
+
+class CommitScheduler:
+    """
+    Scheduler to upload a local folder to the Hub at regular intervals (e.g. push to hub every 5 minutes).
+
+    The recommended way to use the scheduler is to use it as a context manager. This ensures that the scheduler is
+    properly stopped and the last commit is triggered when the script ends. The scheduler can also be stopped manually
+    with the `stop` method. Checkout the [upload guide](https://huggingface.co/docs/huggingface_hub/guides/upload#scheduled-uploads)
+    to learn more about how to use it.
+
+    Args:
+        repo_id (`str`):
+            The id of the repo to commit to.
+        folder_path (`str` or `Path`):
+            Path to the local folder to upload regularly.
+        every (`int` or `float`, *optional*):
+            The number of minutes between each commit. Defaults to 5 minutes.
+        path_in_repo (`str`, *optional*):
+            Relative path of the directory in the repo, for example: `"checkpoints/"`. Defaults to the root folder
+            of the repository.
+        repo_type (`str`, *optional*):
+            The type of the repo to commit to. Defaults to `model`.
+        revision (`str`, *optional*):
+            The revision of the repo to commit to. Defaults to `main`.
+        private (`bool`, *optional*):
+            Whether to make the repo private. If `None` (default), the repo will be public unless the organization's default is private. This value is ignored if the repo already exists.
+        token (`str`, *optional*):
+            The token to use to commit to the repo. Defaults to the token saved on the machine.
+        allow_patterns (`List[str]` or `str`, *optional*):
+            If provided, only files matching at least one pattern are uploaded.
+        ignore_patterns (`List[str]` or `str`, *optional*):
+            If provided, files matching any of the patterns are not uploaded.
+        squash_history (`bool`, *optional*):
+            Whether to squash the history of the repo after each commit. Defaults to `False`. Squashing commits is
+            useful to avoid degraded performances on the repo when it grows too large.
+        hf_api (`HfApi`, *optional*):
+            The [`HfApi`] client to use to commit to the Hub. Can be set with custom settings (user agent, token,...).
+        on_before_commit (`Callable[[], None]`, *optional*):
+            If specified, a function that will be called before the CommitScheduler lists files to create a commit.
+
+    Example:
+    ```py
+    >>> from pathlib import Path
+    >>> from huggingface_hub import CommitScheduler
+
+    # Scheduler uploads every 10 minutes
+    >>> csv_path = Path("watched_folder/data.csv")
+    >>> CommitScheduler(repo_id="test_scheduler", repo_type="dataset", folder_path=csv_path.parent, every=10)
+
+    >>> with csv_path.open("a") as f:
+    ...     f.write("first line")
+
+    # Some time later (...)
+    >>> with csv_path.open("a") as f:
+    ...     f.write("second line")
+    ```
+
+    Example using a context manager:
+    ```py
+    >>> from pathlib import Path
+    >>> from huggingface_hub import CommitScheduler
+
+    >>> with CommitScheduler(repo_id="test_scheduler", repo_type="dataset", folder_path="watched_folder", every=10) as scheduler:
+    ...     csv_path = Path("watched_folder/data.csv")
+    ...     with csv_path.open("a") as f:
+    ...         f.write("first line")
+    ...     (...)
+    ...     with csv_path.open("a") as f:
+    ...         f.write("second line")
+
+    # Scheduler is now stopped and last commit have been triggered
+    ```
+    """
+
+    def __init__(
+        self,
+        *,
+        repo_id: str,
+        folder_path: Union[str, Path],
+        every: Union[int, float] = 5,
+        path_in_repo: Optional[str] = None,
+        repo_type: Optional[str] = None,
+        revision: Optional[str] = None,
+        private: Optional[bool] = None,
+        token: Optional[str] = None,
+        allow_patterns: Optional[Union[List[str], str]] = None,
+        ignore_patterns: Optional[Union[List[str], str]] = None,
+        squash_history: bool = False,
+        hf_api: Optional["HfApi"] = None,
+        on_before_commit: Optional[Callable[[], None]] = None,
+    ) -> None:
+        self.api = hf_api or HfApi(token=token)
+        self.on_before_commit = on_before_commit
+
+        # Folder
+        self.folder_path = Path(folder_path).expanduser().resolve()
+        self.path_in_repo = path_in_repo or ""
+        self.allow_patterns = allow_patterns
+
+        if ignore_patterns is None:
+            ignore_patterns = []
+        elif isinstance(ignore_patterns, str):
+            ignore_patterns = [ignore_patterns]
+        self.ignore_patterns = ignore_patterns + DEFAULT_IGNORE_PATTERNS
+
+        if self.folder_path.is_file():
+            raise ValueError(
+                f"'folder_path' must be a directory, not a file: '{self.folder_path}'."
+            )
+        self.folder_path.mkdir(parents=True, exist_ok=True)
+
+        # Repository
+        repo_url = self.api.create_repo(
+            repo_id=repo_id, private=private, repo_type=repo_type, exist_ok=True
+        )
+        self.repo_id = repo_url.repo_id
+        self.repo_type = repo_type
+        self.revision = revision
+        self.token = token
+
+        self.last_uploaded: Dict[Path, float] = {}
+        self.last_push_time: float | None = None
+
+        if not every > 0:
+            raise ValueError(f"'every' must be a positive integer, not '{every}'.")
+        self.lock = Lock()
+        self.every = every
+        self.squash_history = squash_history
+
+        logger.info(
+            f"Scheduled job to push '{self.folder_path}' to '{self.repo_id}' every {self.every} minutes."
+        )
+        self._scheduler_thread = Thread(target=self._run_scheduler, daemon=True)
+        self._scheduler_thread.start()
+        atexit.register(self._push_to_hub)
+
+        self.__stopped = False
+
+    def stop(self) -> None:
+        """Stop the scheduler.
+
+        A stopped scheduler cannot be restarted. Mostly for tests purposes.
+        """
+        self.__stopped = True
+
+    def __enter__(self) -> "CommitScheduler":
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback) -> None:
+        # Upload last changes before exiting
+        self.trigger().result()
+        self.stop()
+        return
+
+    def _run_scheduler(self) -> None:
+        """Dumb thread waiting between each scheduled push to Hub."""
+        while True:
+            self.last_future = self.trigger()
+            time.sleep(self.every * 60)
+            if self.__stopped:
+                break
+
+    def trigger(self) -> Future:
+        """Trigger a `push_to_hub` and return a future.
+
+        This method is automatically called every `every` minutes. You can also call it manually to trigger a commit
+        immediately, without waiting for the next scheduled commit.
+        """
+        return self.api.run_as_future(self._push_to_hub)
+
+    def _push_to_hub(self) -> Optional[CommitInfo]:
+        if self.__stopped:  # If stopped, already scheduled commits are ignored
+            return None
+
+        logger.info("(Background) scheduled commit triggered.")
+        try:
+            value = self.push_to_hub()
+            if self.squash_history:
+                logger.info("(Background) squashing repo history.")
+                self.api.super_squash_history(
+                    repo_id=self.repo_id, repo_type=self.repo_type, branch=self.revision
+                )
+            return value
+        except Exception as e:
+            logger.error(
+                f"Error while pushing to Hub: {e}"
+            )  # Depending on the setup, error might be silenced
+            raise
+
+    def push_to_hub(self) -> Optional[CommitInfo]:
+        """
+        Push folder to the Hub and return the commit info.
+
+        <Tip warning={true}>
+
+        This method is not meant to be called directly. It is run in the background by the scheduler, respecting a
+        queue mechanism to avoid concurrent commits. Making a direct call to the method might lead to concurrency
+        issues.
+
+        </Tip>
+
+        The default behavior of `push_to_hub` is to assume an append-only folder. It lists all files in the folder and
+        uploads only changed files. If no changes are found, the method returns without committing anything. If you want
+        to change this behavior, you can inherit from [`CommitScheduler`] and override this method. This can be useful
+        for example to compress data together in a single file before committing. For more details and examples, check
+        out our [integration guide](https://huggingface.co/docs/huggingface_hub/main/en/guides/upload#scheduled-uploads).
+        """
+        # Check files to upload (with lock)
+        with self.lock:
+            if self.on_before_commit is not None:
+                self.on_before_commit()
+
+            logger.debug("Listing files to upload for scheduled commit.")
+
+            # List files from folder (taken from `_prepare_upload_folder_additions`)
+            relpath_to_abspath = {
+                path.relative_to(self.folder_path).as_posix(): path
+                for path in sorted(
+                    self.folder_path.glob("**/*")
+                )  # sorted to be deterministic
+                if path.is_file()
+            }
+            prefix = f"{self.path_in_repo.strip('/')}/" if self.path_in_repo else ""
+
+            # Filter with pattern + filter out unchanged files + retrieve current file size
+            files_to_upload: List[_FileToUpload] = []
+            for relpath in filter_repo_objects(
+                relpath_to_abspath.keys(),
+                allow_patterns=self.allow_patterns,
+                ignore_patterns=self.ignore_patterns,
+            ):
+                local_path = relpath_to_abspath[relpath]
+                stat = local_path.stat()
+                if (
+                    self.last_uploaded.get(local_path) is None
+                    or self.last_uploaded[local_path] != stat.st_mtime
+                ):
+                    files_to_upload.append(
+                        _FileToUpload(
+                            local_path=local_path,
+                            path_in_repo=prefix + relpath,
+                            size_limit=stat.st_size,
+                            last_modified=stat.st_mtime,
+                        )
+                    )
+
+        # Return if nothing to upload
+        if len(files_to_upload) == 0:
+            logger.debug("Dropping schedule commit: no changed file to upload.")
+            return None
+
+        # Convert `_FileToUpload` as `CommitOperationAdd` (=> compute file shas + limit to file size)
+        logger.debug("Removing unchanged files since previous scheduled commit.")
+        add_operations = [
+            CommitOperationAdd(
+                # TODO: Cap the file to its current size, even if the user append data to it while a scheduled commit is happening
+                # (requires an upstream fix for XET-535: `hf_xet` should support `BinaryIO` for upload)
+                path_or_fileobj=file_to_upload.local_path,
+                path_in_repo=file_to_upload.path_in_repo,
+            )
+            for file_to_upload in files_to_upload
+        ]
+
+        # Upload files (append mode expected - no need for lock)
+        logger.debug("Uploading files for scheduled commit.")
+        commit_info = self.api.create_commit(
+            repo_id=self.repo_id,
+            repo_type=self.repo_type,
+            operations=add_operations,
+            commit_message="Scheduled Commit",
+            revision=self.revision,
+        )
+
+        for file in files_to_upload:
+            self.last_uploaded[file.local_path] = file.last_modified
+
+        self.last_push_time = time.time()
+
+        return commit_info
+
+
+class PartialFileIO(BytesIO):
+    """A file-like object that reads only the first part of a file.
+
+    Useful to upload a file to the Hub when the user might still be appending data to it. Only the first part of the
+    file is uploaded (i.e. the part that was available when the filesystem was first scanned).
+
+    In practice, only used internally by the CommitScheduler to regularly push a folder to the Hub with minimal
+    disturbance for the user. The object is passed to `CommitOperationAdd`.
+
+    Only supports `read`, `tell` and `seek` methods.
+
+    Args:
+        file_path (`str` or `Path`):
+            Path to the file to read.
+        size_limit (`int`):
+            The maximum number of bytes to read from the file. If the file is larger than this, only the first part
+            will be read (and uploaded).
+    """
+
+    def __init__(self, file_path: Union[str, Path], size_limit: int) -> None:
+        self._file_path = Path(file_path)
+        self._file = self._file_path.open("rb")
+        self._size_limit = min(size_limit, os.fstat(self._file.fileno()).st_size)
+
+    def __del__(self) -> None:
+        self._file.close()
+        return super().__del__()
+
+    def __repr__(self) -> str:
+        return (
+            f"<PartialFileIO file_path={self._file_path} size_limit={self._size_limit}>"
+        )
+
+    def __len__(self) -> int:
+        return self._size_limit
+
+    def __getattribute__(self, name: str):
+        if name.startswith("_") or name in (
+            "read",
+            "tell",
+            "seek",
+        ):  # only 3 public methods supported
+            return super().__getattribute__(name)
+        raise NotImplementedError(f"PartialFileIO does not support '{name}'.")
+
+    def tell(self) -> int:
+        """Return the current file position."""
+        return self._file.tell()
+
+    def seek(self, __offset: int, __whence: int = SEEK_SET) -> int:
+        """Change the stream position to the given offset.
+
+        Behavior is the same as a regular file, except that the position is capped to the size limit.
+        """
+        if __whence == SEEK_END:
+            # SEEK_END => set from the truncated end
+            __offset = len(self) + __offset
+            __whence = SEEK_SET
+
+        pos = self._file.seek(__offset, __whence)
+        if pos > self._size_limit:
+            return self._file.seek(self._size_limit)
+        return pos
+
+    def read(self, __size: Optional[int] = -1) -> bytes:
+        """Read at most `__size` bytes from the file.
+
+        Behavior is the same as a regular file, except that it is capped to the size limit.
+        """
+        current = self._file.tell()
+        if __size is None or __size < 0:
+            # Read until file limit
+            truncated_size = self._size_limit - current
+        else:
+            # Read until file limit or __size
+            truncated_size = min(__size, self._size_limit - current)
+        return self._file.read(truncated_size)

context_vars.py

@@ -0,0 +1,15 @@
+import contextvars
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from trackio.run import Run
+
+current_run: contextvars.ContextVar["Run | None"] = contextvars.ContextVar(
+    "current_run", default=None
+)
+current_project: contextvars.ContextVar[str | None] = contextvars.ContextVar(
+    "current_project", default=None
+)
+current_server: contextvars.ContextVar[str | None] = contextvars.ContextVar(
+    "current_server", default=None
+)