flyte 0.1.0__py3-none-any.whl → 0.2.0b0__py3-none-any.whl

flyte/config/__init__.py

@@ -0,0 +1,168 @@
+import os
+import typing
+from dataclasses import dataclass, field
+from typing import TYPE_CHECKING
+
+from flyte._logging import logger
+from flyte.config import _internal
+from flyte.config._config import ConfigFile, get_config_file, read_file_if_exists
+
+_all__ = ["ConfigFile", "PlatformConfig", "TaskConfig"]
+
+if TYPE_CHECKING:
+    from flyte.remote._client.auth import AuthType
+
+
+@dataclass(init=True, repr=True, eq=True, frozen=True)
+class PlatformConfig(object):
+    """
+    This object contains the settings to talk to a Flyte backend (the DNS location of your Admin server basically).
+
+    :param endpoint: DNS for Flyte backend
+    :param insecure: Whether or not to use SSL
+    :param insecure_skip_verify: Whether to skip SSL certificate verification
+    :param console_endpoint: endpoint for console if different from Flyte backend
+    :param command: This command is executed to return a token using an external process
+    :param proxy_command: This command is executed to return a token for proxy authorization using an external process
+    :param client_id: This is the public identifier for the app which handles authorization for a Flyte deployment.
+      More details here: https://www.oauth.com/oauth2-servers/client-registration/client-id-secret/.
+    :param client_credentials_secret: Used for service auth, which is automatically called during pyflyte. This will
+      allow the Flyte engine to read the password directly from the environment variable. Note that this is
+      less secure! Please only use this if mounting the secret as a file is impossible
+    :param scopes: List of scopes to request. This is only applicable to the client credentials flow
+    :param auth_mode: The OAuth mode to use. Defaults to pkce flow
+    :param ca_cert_file_path: [optional] str Root Cert to be loaded and used to verify admin
+    :param http_proxy_url: [optional] HTTP Proxy to be used for OAuth requests
+    """
+
+    endpoint: str | None = None
+    insecure: bool = False
+    insecure_skip_verify: bool = False
+    ca_cert_file_path: typing.Optional[str] = None
+    console_endpoint: typing.Optional[str] = None
+    command: typing.Optional[typing.List[str]] = None
+    proxy_command: typing.Optional[typing.List[str]] = None
+    client_id: typing.Optional[str] = None
+    client_credentials_secret: typing.Optional[str] = None
+    scopes: typing.List[str] = field(default_factory=list)
+    auth_mode: "AuthType" = "Pkce"
+    audience: typing.Optional[str] = None
+    rpc_retries: int = 3
+    http_proxy_url: typing.Optional[str] = None
+
+    @classmethod
+    def auto(cls, config_file: typing.Optional[typing.Union[str, ConfigFile]] = None) -> "PlatformConfig":
+        """
+        Reads from a config file, and overrides from Environment variables. Refer to ConfigEntry for details
+        :param config_file:
+        :return:
+        """
+        from .._initialize import set_if_exists
+
+        config_file = get_config_file(config_file)
+        kwargs: typing.Dict[str, typing.Any] = {}
+        kwargs = set_if_exists(kwargs, "insecure", _internal.Platform.INSECURE.read(config_file))
+        kwargs = set_if_exists(
+            kwargs, "insecure_skip_verify", _internal.Platform.INSECURE_SKIP_VERIFY.read(config_file)
+        )
+        kwargs = set_if_exists(kwargs, "ca_cert_file_path", _internal.Platform.CA_CERT_FILE_PATH.read(config_file))
+        kwargs = set_if_exists(kwargs, "command", _internal.Credentials.COMMAND.read(config_file))
+        kwargs = set_if_exists(kwargs, "proxy_command", _internal.Credentials.PROXY_COMMAND.read(config_file))
+        kwargs = set_if_exists(kwargs, "client_id", _internal.Credentials.CLIENT_ID.read(config_file))
+
+        is_client_secret = False
+        client_credentials_secret = read_file_if_exists(
+            _internal.Credentials.CLIENT_CREDENTIALS_SECRET_LOCATION.read(config_file)
+        )
+        if client_credentials_secret:
+            is_client_secret = True
+            if client_credentials_secret.endswith("\n"):
+                logger.info("Newline stripped from client secret")
+                client_credentials_secret = client_credentials_secret.strip()
+        kwargs = set_if_exists(
+            kwargs,
+            "client_credentials_secret",
+            client_credentials_secret,
+        )
+
+        client_credentials_secret_env_var = _internal.Credentials.CLIENT_CREDENTIALS_SECRET_ENV_VAR.read(config_file)
+        if client_credentials_secret_env_var:
+            client_credentials_secret = os.getenv(client_credentials_secret_env_var)
+            if client_credentials_secret:
+                is_client_secret = True
+        kwargs = set_if_exists(kwargs, "client_credentials_secret", client_credentials_secret)
+        kwargs = set_if_exists(kwargs, "scopes", _internal.Credentials.SCOPES.read(config_file))
+        kwargs = set_if_exists(kwargs, "auth_mode", _internal.Credentials.AUTH_MODE.read(config_file))
+        if is_client_secret:
+            kwargs = set_if_exists(kwargs, "auth_mode", "ClientSecret")
+        kwargs = set_if_exists(kwargs, "endpoint", _internal.Platform.URL.read(config_file))
+        kwargs = set_if_exists(kwargs, "console_endpoint", _internal.Platform.CONSOLE_ENDPOINT.read(config_file))
+
+        kwargs = set_if_exists(kwargs, "http_proxy_url", _internal.Platform.HTTP_PROXY_URL.read(config_file))
+        return PlatformConfig(**kwargs)
+
+    @classmethod
+    def for_endpoint(cls, endpoint: str, insecure: bool = False) -> "PlatformConfig":
+        return PlatformConfig(endpoint=endpoint, insecure=insecure)
+
+
+@dataclass(init=True, repr=True, eq=True, frozen=True)
+class TaskConfig(object):
+    org: str | None = None
+    project: str | None = None
+    domain: str | None = None
+
+    @classmethod
+    def auto(cls, config_file: typing.Optional[typing.Union[str, ConfigFile]] = None) -> "TaskConfig":
+        """
+        Reads from a config file, and overrides from Environment variables. Refer to ConfigEntry for details
+        :param config_file:
+        :return:
+        """
+        from flyte._initialize import set_if_exists
+
+        config_file = get_config_file(config_file)
+        kwargs: typing.Dict[str, typing.Any] = {}
+        kwargs = set_if_exists(kwargs, "org", _internal.Task.ORG.read(config_file))
+        kwargs = set_if_exists(kwargs, "project", _internal.Task.PROJECT.read(config_file))
+        kwargs = set_if_exists(kwargs, "domain", _internal.Task.DOMAIN.read(config_file))
+        return TaskConfig(**kwargs)
+
+
+@dataclass(init=True, repr=True, eq=True, frozen=True)
+class Config(object):
+    """
+    This the parent configuration object and holds all the underlying configuration object types. An instance of
+    this object holds all the config necessary to
+
+    1. Interactive session with Flyte backend
+    2. Some parts are required for Serialization, for example Platform Config is not required
+    3. Runtime of a task
+    """
+
+    platform: PlatformConfig = field(default=PlatformConfig())
+    task: TaskConfig = field(default=TaskConfig())
+
+    def with_params(
+        self,
+        platform: PlatformConfig | None = None,
+        task: TaskConfig | None = None,
+    ) -> "Config":
+        return Config(
+            platform=platform or self.platform,
+            task=task or self.task,
+        )
+
+    @classmethod
+    def auto(cls, config_file: typing.Union[str, ConfigFile, None] = None) -> "Config":
+        """
+        Automatically constructs the Config Object. The order of precedence is as follows
+          1. first try to find any env vars that match the config vars specified in the FLYTE_CONFIG format.
+          2. If not found in environment then values ar read from the config file
+          3. If not found in the file, then the default values are used.
+
+        :param config_file: file path to read the config from, if not specified default locations are searched
+        :return: Config
+        """
+        config_file = get_config_file(config_file)
+        return Config(platform=PlatformConfig.auto(config_file), task=TaskConfig.auto(config_file))

flyte/config/_config.py

@@ -0,0 +1,196 @@
+import os
+import pathlib
+import typing
+from dataclasses import dataclass
+from functools import lru_cache
+from os import getenv
+from pathlib import Path
+
+import yaml
+
+from flyte._logging import logger
+
+# This is the default config file name for flyte
+FLYTECTL_CONFIG_ENV_VAR = "FLYTECTL_CONFIG"
+UCTL_CONFIG_ENV_VAR = "UCTL_CONFIG"
+
+
+@dataclass
+class YamlConfigEntry(object):
+    """
+    Creates a record for the config entry.
+    Args:
+        switch: dot-delimited string that should match flytectl args. Leaving it as dot-delimited instead of a list
+          of strings because it's easier to maintain alignment with flytectl.
+        config_value_type: Expected type of the value
+    """
+
+    switch: str
+    config_value_type: typing.Type = str
+
+    def get_env_name(self) -> str:
+        var_name = self.switch.upper().replace(".", "_")
+        return f"FLYTE_{var_name}"
+
+    def read_from_env(self, transform: typing.Optional[typing.Callable] = None) -> typing.Optional[typing.Any]:
+        """
+        Reads the config entry from environment variable, the structure of the env var is current
+        ``FLYTE_{SECTION}_{OPTION}`` all upper cased. We will change this in the future.
+        :return:
+        """
+        env = self.get_env_name()
+        v = os.environ.get(env, None)
+        if v is None:
+            return None
+        return transform(v) if transform else v
+
+    def read_from_file(
+        self, cfg: "ConfigFile", transform: typing.Optional[typing.Callable] = None
+    ) -> typing.Optional[typing.Any]:
+        if not cfg:
+            return None
+        try:
+            v = cfg.get(self)
+            if isinstance(v, bool) or bool(v is not None and v):
+                return transform(v) if transform else v
+        except Exception:
+            ...
+
+        return None
+
+
+@dataclass
+class ConfigEntry(object):
+    """
+    A top level Config entry holder, that holds multiple different representations of the config.
+    Legacy means the INI style config files. YAML support is for the flytectl config file, which is there by default
+    when flytectl starts a sandbox
+    """
+
+    yaml_entry: YamlConfigEntry
+    transform: typing.Optional[typing.Callable[[str], typing.Any]] = None
+
+    def read(self, cfg: typing.Optional["ConfigFile"] = None) -> typing.Optional[typing.Any]:
+        """
+        Reads the config Entry from the various sources in the following order,
+        #. First try to read from the relevant environment variable,
+        #. If missing, then try to read from the legacy config file, if one was parsed.
+        #. If missing, then try to read from the yaml file.
+
+        The constructor for ConfigFile currently does not allow specification of both the ini and yaml style formats.
+
+        :param cfg:
+        :return:
+        """
+        from_env = self.yaml_entry.read_from_env(self.transform)
+        if from_env is not None:
+            return from_env
+        if cfg and cfg.yaml_config and self.yaml_entry:
+            return self.yaml_entry.read_from_file(cfg, self.transform)
+
+        return None
+
+
+class ConfigFile(object):
+    def __init__(self, location: str):
+        """
+        Load the config from this location
+        """
+        self._location = location
+        self._yaml_config = self._read_yaml_config(location)
+
+    @staticmethod
+    def _read_yaml_config(location: str) -> typing.Optional[typing.Dict[str, typing.Any]]:
+        with open(location, "r") as fh:
+            try:
+                yaml_contents = yaml.safe_load(fh)
+                return yaml_contents
+            except yaml.YAMLError as exc:
+                logger.warning(f"Error {exc} reading yaml config file at {location}, ignoring...")
+                return None
+
+    def _get_from_yaml(self, c: YamlConfigEntry) -> typing.Any:
+        keys = c.switch.split(".")  # flytectl switches are dot delimited
+        d = typing.cast(typing.Dict[str, typing.Any], self.yaml_config)
+        try:
+            for k in keys:
+                d = d[k]
+            return d
+        except KeyError:
+            return None
+
+    def get(self, c: YamlConfigEntry) -> typing.Any:
+        return self._get_from_yaml(c)
+
+    @property
+    def yaml_config(self) -> typing.Dict[str, typing.Any] | None:
+        return self._yaml_config
+
+
+def resolve_config_path() -> pathlib.Path | None:
+    """
+    Config is read from the following locations in order of precedence:
+    1. `UCTL_CONFIG` environment variable
+    2. `FLYTECTL_CONFIG` environment variable
+    3. ~/.union/config.yaml if it exists
+    4. ~/.flyte/config.yaml if it exists
+    5. ./config.yaml if it exists
+    """
+    uctl_path_from_env = getenv(UCTL_CONFIG_ENV_VAR, None)
+    if uctl_path_from_env:
+        return pathlib.Path(uctl_path_from_env)
+    logger.debug("No UCTL_CONFIG environment variable found, checking FLYTECTL_CONFIG")
+
+    flytectl_path_from_env = getenv(FLYTECTL_CONFIG_ENV_VAR, None)
+    if flytectl_path_from_env:
+        return pathlib.Path(flytectl_path_from_env)
+    logger.debug("No FLYTECTL_CONFIG environment variable found, checking default locations")
+
+    home_dir_union_config = Path(Path.home(), ".union", "config.yaml")
+    if home_dir_union_config.exists():
+        return home_dir_union_config
+    logger.debug("No ~/.union/config.yaml found, checking current directory")
+
+    home_dir_flytectl_config = Path(Path.home(), ".flyte", "config.yaml")
+    if home_dir_flytectl_config.exists():
+        return home_dir_flytectl_config
+    logger.debug("No ~/.flyte/config.yaml found, checking current directory")
+
+    current_location_config = Path("config.yaml")
+    if current_location_config.exists():
+        return current_location_config
+    logger.debug("No ./config.yaml found, returning None")
+    return None
+
+
+@lru_cache
+def get_config_file(c: typing.Union[str, ConfigFile, None]) -> ConfigFile | None:
+    """
+    Checks if the given argument is a file or a configFile and returns a loaded configFile else returns None
+    """
+    if "PYTEST_VERSION" in os.environ:
+        # Use default local config in the pytest environment
+        return None
+    if isinstance(c, str):
+        logger.debug(f"Using specified config file at {c}")
+        return ConfigFile(c)
+    config_path = resolve_config_path()
+    if config_path:
+        return ConfigFile(str(config_path))
+    return None
+
+
+def read_file_if_exists(filename: typing.Optional[str], encoding=None) -> typing.Optional[str]:
+    """
+    Reads the contents of the file if passed a path. Otherwise, returns None.
+
+    :param filename: The file path to load
+    :param encoding: The encoding to use when reading the file.
+    :return: The contents of the file as a string or None.
+    """
+    if not filename:
+        return None
+
+    file = pathlib.Path(filename)
+    logger.debug(f"Reading file contents from [{file}] with current directory [{os.getcwd()}].")
+    return file.read_text(encoding=encoding)

flyte/config/_internal.py

@@ -0,0 +1,64 @@
+from flyte.config._config import ConfigEntry, YamlConfigEntry
+
+
+class Platform(object):
+    URL = ConfigEntry(YamlConfigEntry("admin.endpoint"))
+    INSECURE = ConfigEntry(YamlConfigEntry("admin.insecure", bool))
+    INSECURE_SKIP_VERIFY = ConfigEntry(YamlConfigEntry("admin.insecureSkipVerify", bool))
+    CONSOLE_ENDPOINT = ConfigEntry(YamlConfigEntry("console.endpoint"))
+    CA_CERT_FILE_PATH = ConfigEntry(YamlConfigEntry("admin.caCertFilePath"))
+    HTTP_PROXY_URL = ConfigEntry(YamlConfigEntry("admin.httpProxyURL"))
+
+
+class Credentials(object):
+    SECTION = "credentials"
+    COMMAND = ConfigEntry(YamlConfigEntry("admin.command", list))
+    """
+    This command is executed to return a token using an external process.
+    """
+
+    PROXY_COMMAND = ConfigEntry(YamlConfigEntry("admin.proxyCommand", list))
+    """
+    This command is executed to return a token for authorization with a proxy
+     in front of Flyte using an external process.
+    """
+
+    CLIENT_ID = ConfigEntry(YamlConfigEntry("admin.clientId"))
+    """
+    This is the public identifier for the app which handles authorization for a Flyte deployment.
+    More details here: https://www.oauth.com/oauth2-servers/client-registration/client-id-secret/.
+    """
+
+    CLIENT_CREDENTIALS_SECRET_LOCATION = ConfigEntry(YamlConfigEntry("admin.clientSecretLocation"))
+    """
+    Used for basic auth, which is automatically called during pyflyte. This will allow the Flyte engine to read the
+    password from a mounted file.
+    """
+
+    CLIENT_CREDENTIALS_SECRET_ENV_VAR = ConfigEntry(YamlConfigEntry("admin.clientSecretEnvVar"))
+    """
+    Used for basic auth, which is automatically called during pyflyte. This will allow the Flyte engine to read the
+    password from a mounted environment variable.
+    """
+
+    SCOPES = ConfigEntry(YamlConfigEntry("admin.scopes", list))
+    """
+    This setting can be used to manually pass in scopes into authenticator flows - eg.) for Auth0 compatibility
+    """
+
+    AUTH_MODE = ConfigEntry(YamlConfigEntry("admin.authType"))
+    """
+    The auth mode defines the behavior used to request and refresh credentials. The currently supported modes include:
+    - 'standard' or 'Pkce': This uses the pkce-enhanced authorization code flow by opening a browser window to initiate
+            credentials access.
+    - "DeviceFlow": This uses the Device Authorization Flow
+    - 'basic', 'client_credentials' or 'clientSecret': This uses symmetric key auth in which the end user enters a
+            client id and a client secret and public key encryption is used to facilitate authentication.
+    - None: No auth will be attempted.
+    """
+
+
+class Task(object):
+    ORG = ConfigEntry(YamlConfigEntry("task.org"))
+    PROJECT = ConfigEntry(YamlConfigEntry("task.project"))
+    DOMAIN = ConfigEntry(YamlConfigEntry("task.domain"))

flyte/errors.py

@@ -0,0 +1,143 @@
+"""
+Exceptions raised by Union.
+
+These errors are raised when the underlying task execution fails, either because of a user error, system error or an
+unknown error.
+"""
+
+from typing import Literal
+
+ErrorKind = Literal["system", "unknown", "user"]
+
+
+class BaseRuntimeError(RuntimeError):
+    """
+    Base class for all Union runtime errors. These errors are raised when the underlying task execution fails, either
+    because of a user error, system error or an unknown error.
+    """
+
+    def __init__(self, code: str, kind: ErrorKind, root_cause_message: str, worker: str | None = None):
+        super().__init__(root_cause_message)
+        self.code = code
+        self.kind = kind
+        self.worker = worker
+
+
+class InitializationError(BaseRuntimeError):
+    """
+    This error is raised when the Union system is tried to access without being initialized.
+    """
+
+
+class RuntimeSystemError(BaseRuntimeError):
+    """
+    This error is raised when the underlying task execution fails because of a system error. This could be a bug in the
+    Union system or a bug in the user's code.
+    """
+
+    def __init__(self, code: str, message: str, worker: str | None = None):
+        super().__init__(code, "system", message, worker)
+
+
+class UnionRpcError(RuntimeSystemError):
+    """
+    This error is raised when communication with the Union server fails.
+    """
+
+
+class RuntimeUserError(BaseRuntimeError):
+    """
+    This error is raised when the underlying task execution fails because of an error in the user's code.
+    """
+
+    def __init__(self, code: str, message: str, worker: str | None = None):
+        super().__init__(code, "user", message, worker)
+
+
+class RuntimeUnknownError(BaseRuntimeError):
+    """
+    This error is raised when the underlying task execution fails because of an unknown error.
+    """
+
+    def __init__(self, code: str, message: str, worker: str | None = None):
+        super().__init__(code, "unknown", message, worker)
+
+
+class OOMError(RuntimeUserError):
+    """
+    This error is raised when the underlying task execution fails because of an out-of-memory error.
+    """
+
+
+class TaskInterruptedError(RuntimeUserError):
+    """
+    This error is raised when the underlying task execution is interrupted.
+    """
+
+
+class PrimaryContainerNotFoundError(RuntimeUserError):
+    """
+    This error is raised when the primary container is not found.
+    """
+
+
+class TaskTimeoutError(RuntimeUserError):
+    """
+    This error is raised when the underlying task execution runs for longer than the specified timeout.
+    """
+
+
+class RetriesExhaustedError(RuntimeUserError):
+    """
+    This error is raised when the underlying task execution fails after all retries have been exhausted.
+    """
+
+
+class InvalidImageNameError(RuntimeUserError):
+    """
+    This error is raised when the image name is invalid.
+    """
+
+
+class ImagePullBackOffError(RuntimeUserError):
+    """
+    This error is raised when the image cannot be pulled.
+    """
+
+
+class CustomError(RuntimeUserError):
+    """
+    This error is raised when the user raises a custom error.
+    """
+
+    def __init__(self, code: str, message: str):
+        super().__init__(code, message, "user")
+
+    @classmethod
+    def from_exception(cls, e: Exception):
+        """
+        Create a CustomError from an exception. The exception's class name is used as the error code and the exception
+        message is used as the error message.
+        """
+        return cls(e.__class__.__name__, str(e))
+
+
+class NotInTaskContextError(RuntimeUserError):
+    """
+    This error is raised when the user tries to access the task context outside of a task.
+    """
+
+
+class ActionNotFoundError(RuntimeError):
+    """
+    This error is raised when the user tries to access an action that does not exist.
+    """
+
+
+class ReferenceTaskError(RuntimeUserError):
+    """
+    This error is raised when the user tries to access a task that does not exist.
+    """
+
+    def __init__(self, message: str):
+        super().__init__("ReferenceTaskUsageError", message, "user")

flyte/extras/__init__.py

@@ -0,0 +1,5 @@
+from ._container import ContainerTask
+
+__all__ = [
+    "ContainerTask",
+]