dataleon 0.1.0a8__py3-none-any.whl

dataleon/types/individuals/document_response.py

@@ -0,0 +1,41 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import List, Optional
+
+from ..._models import BaseModel
+
+__all__ = ["DocumentResponse", "Document"]
+
+
+class Document(BaseModel):
+    id: Optional[str] = None
+    """Unique identifier of the document."""
+
+    document_type: Optional[str] = None
+    """Functional type of the document (e.g., identity document, invoice)."""
+
+    filename: Optional[str] = None
+    """Original filename of the uploaded document."""
+
+    name: Optional[str] = None
+    """Human-readable name of the document."""
+
+    signed_url: Optional[str] = None
+    """Secure URL to access the document."""
+
+    state: Optional[str] = None
+    """Processing state of the document (e.g., WAITING, STARTED, RUNNING, PROCESSED)."""
+
+    status: Optional[str] = None
+    """Validation status of the document (e.g., need_review, approved, rejected)."""
+
+    workspace_id: Optional[str] = None
+    """Identifier of the workspace to which the document belongs."""
+
+
+class DocumentResponse(BaseModel):
+    documents: Optional[List[Document]] = None
+    """List of documents associated with the response."""
+
+    total_document: Optional[int] = None
+    """Total number of documents available in the response."""

dataleon/types/individuals/document_upload_params.py

@@ -0,0 +1,56 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing_extensions import Literal, Required, TypedDict
+
+from ..._types import FileTypes
+
+__all__ = ["DocumentUploadParams"]
+
+
+class DocumentUploadParams(TypedDict, total=False):
+    document_type: Required[
+        Literal[
+            "liasse_fiscale",
+            "amortised_loan_schedule",
+            "invoice",
+            "receipt",
+            "company_statuts",
+            "registration_company_certificate",
+            "kbis",
+            "rib",
+            "livret_famille",
+            "birth_certificate",
+            "payslip",
+            "social_security_card",
+            "vehicle_registration_certificate",
+            "carte_grise",
+            "criminal_record_extract",
+            "proof_of_address",
+            "identity_card_front",
+            "identity_card_back",
+            "driver_license_front",
+            "driver_license_back",
+            "identity_document",
+            "driver_license",
+            "passport",
+            "tax",
+            "certificate_of_incorporation",
+            "certificate_of_good_standing",
+            "lcb_ft_lab_aml_policies",
+            "niu_entreprise",
+            "financial_statements",
+            "rccm",
+            "proof_of_source_funds",
+            "organizational_chart",
+            "risk_policies",
+        ]
+    ]
+    """Filter by document type for upload (must be one of the allowed values)"""
+
+    file: FileTypes
+    """File to upload (required)"""
+
+    url: str
+    """URL of the file to upload (either `file` or `url` is required)"""

dataleon/types/individuals/generic_document.py

@@ -0,0 +1,57 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import List, Optional
+from datetime import datetime
+
+from ..._models import BaseModel
+from ..shared.check import Check
+
+__all__ = ["GenericDocument", "Table", "Value"]
+
+
+class Table(BaseModel):
+    operation: Optional[List[object]] = None
+    """List of operations or actions associated with the table."""
+
+
+class Value(BaseModel):
+    confidence: Optional[float] = None
+    """Confidence score (between 0 and 1) for the extracted value."""
+
+    name: Optional[str] = None
+    """Name or label of the extracted field."""
+
+    value: Optional[List[int]] = None
+    """List of integer values related to the field (e.g., bounding box coordinates)."""
+
+
+class GenericDocument(BaseModel):
+    id: Optional[str] = None
+    """Unique identifier of the document."""
+
+    checks: Optional[List[Check]] = None
+    """List of verification checks performed on the document."""
+
+    created_at: Optional[datetime] = None
+    """Timestamp when the document was created or uploaded."""
+
+    document_type: Optional[str] = None
+    """Type/category of the document."""
+
+    name: Optional[str] = None
+    """Name or label for the document."""
+
+    signed_url: Optional[str] = None
+    """Signed URL for accessing the document file."""
+
+    state: Optional[str] = None
+    """Current processing state of the document (e.g., WAITING, PROCESSED)."""
+
+    status: Optional[str] = None
+    """Status of the document reception or approval."""
+
+    tables: Optional[List[Table]] = None
+    """List of tables extracted from the document, each containing operations."""
+
+    values: Optional[List[Value]] = None
+    """Extracted key-value pairs from the document, including confidence scores."""

dataleon/types/shared/__init__.py

@@ -0,0 +1,3 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from .check import Check as Check

dataleon/types/shared/check.py

@@ -0,0 +1,26 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Optional
+
+from pydantic import Field as FieldInfo
+
+from ..._models import BaseModel
+
+__all__ = ["Check"]
+
+
+class Check(BaseModel):
+    masked: Optional[bool] = None
+    """Indicates whether the result or data is masked/hidden."""
+
+    message: Optional[str] = None
+    """Additional message or explanation about the check result."""
+
+    name: Optional[str] = None
+    """Name or type of the check performed."""
+
+    validate_: Optional[bool] = FieldInfo(alias="validate", default=None)
+    """Result of the check, true if passed."""
+
+    weight: Optional[int] = None
+    """Importance or weight of the check, often used in scoring."""

dataleon-0.1.0a8.dist-info/METADATA

@@ -0,0 +1,448 @@
+Metadata-Version: 2.3
+Name: dataleon
+Version: 0.1.0a8
+Summary: The official Python library for the dataleon API
+Project-URL: Homepage, https://github.com/dataleonlabs/dataleon-python
+Project-URL: Repository, https://github.com/dataleonlabs/dataleon-python
+Author-email: Dataleon <support@dataleon.ai>
+License: Apache-2.0
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: MacOS
+Classifier: Operating System :: Microsoft :: Windows
+Classifier: Operating System :: OS Independent
+Classifier: Operating System :: POSIX
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Typing :: Typed
+Requires-Python: >=3.9
+Requires-Dist: anyio<5,>=3.5.0
+Requires-Dist: distro<2,>=1.7.0
+Requires-Dist: httpx<1,>=0.23.0
+Requires-Dist: pydantic<3,>=1.9.0
+Requires-Dist: sniffio
+Requires-Dist: typing-extensions<5,>=4.10
+Provides-Extra: aiohttp
+Requires-Dist: aiohttp; extra == 'aiohttp'
+Requires-Dist: httpx-aiohttp>=0.1.9; extra == 'aiohttp'
+Description-Content-Type: text/markdown
+
+# Dataleon Python API library
+
+<!-- prettier-ignore -->
+[![PyPI version](https://img.shields.io/pypi/v/dataleon.svg?label=pypi%20(stable))](https://pypi.org/project/dataleon/)
+
+The Dataleon Python library provides convenient access to the Dataleon REST API from any Python 3.9+
+application. The library includes type definitions for all request params and response fields,
+and offers both synchronous and asynchronous clients powered by [httpx](https://github.com/encode/httpx).
+
+It is generated with [Stainless](https://www.stainless.com/).
+
+## Documentation
+
+The REST API documentation can be found on [docs.dataleon.ai](https://docs.dataleon.ai). The full API of this library can be found in [api.md](https://github.com/dataleonlabs/dataleon-python/tree/main/api.md).
+
+## Installation
+
+```sh
+# install from PyPI
+pip install --pre dataleon
+```
+
+## Usage
+
+The full API of this library can be found in [api.md](https://github.com/dataleonlabs/dataleon-python/tree/main/api.md).
+
+```python
+import os
+from dataleon import Dataleon
+
+client = Dataleon(
+    api_key=os.environ.get("DATALEON_API_KEY"),  # This is the default and can be omitted
+)
+
+individual = client.individuals.create(
+    workspace_id="wk_123",
+)
+print(individual.id)
+```
+
+While you can provide an `api_key` keyword argument,
+we recommend using [python-dotenv](https://pypi.org/project/python-dotenv/)
+to add `DATALEON_API_KEY="My API Key"` to your `.env` file
+so that your API Key is not stored in source control.
+
+## Async usage
+
+Simply import `AsyncDataleon` instead of `Dataleon` and use `await` with each API call:
+
+```python
+import os
+import asyncio
+from dataleon import AsyncDataleon
+
+client = AsyncDataleon(
+    api_key=os.environ.get("DATALEON_API_KEY"),  # This is the default and can be omitted
+)
+
+
+async def main() -> None:
+    individual = await client.individuals.create(
+        workspace_id="wk_123",
+    )
+    print(individual.id)
+
+
+asyncio.run(main())
+```
+
+Functionality between the synchronous and asynchronous clients is otherwise identical.
+
+### With aiohttp
+
+By default, the async client uses `httpx` for HTTP requests. However, for improved concurrency performance you may also use `aiohttp` as the HTTP backend.
+
+You can enable this by installing `aiohttp`:
+
+```sh
+# install from PyPI
+pip install --pre dataleon[aiohttp]
+```
+
+Then you can enable it by instantiating the client with `http_client=DefaultAioHttpClient()`:
+
+```python
+import asyncio
+from dataleon import DefaultAioHttpClient
+from dataleon import AsyncDataleon
+
+
+async def main() -> None:
+    async with AsyncDataleon(
+        api_key="My API Key",
+        http_client=DefaultAioHttpClient(),
+    ) as client:
+        individual = await client.individuals.create(
+            workspace_id="wk_123",
+        )
+        print(individual.id)
+
+
+asyncio.run(main())
+```
+
+## Using types
+
+Nested request parameters are [TypedDicts](https://docs.python.org/3/library/typing.html#typing.TypedDict). Responses are [Pydantic models](https://docs.pydantic.dev) which also provide helper methods for things like:
+
+- Serializing back into JSON, `model.to_json()`
+- Converting to a dictionary, `model.to_dict()`
+
+Typed requests and responses provide autocomplete and documentation within your editor. If you would like to see type errors in VS Code to help catch bugs earlier, set `python.analysis.typeCheckingMode` to `basic`.
+
+## Nested params
+
+Nested parameters are dictionaries, typed using `TypedDict`, for example:
+
+```python
+from dataleon import Dataleon
+
+client = Dataleon()
+
+individual = client.individuals.create(
+    workspace_id="wk_123",
+    person={},
+)
+print(individual.person)
+```
+
+## File uploads
+
+Request parameters that correspond to file uploads can be passed as `bytes`, or a [`PathLike`](https://docs.python.org/3/library/os.html#os.PathLike) instance or a tuple of `(filename, contents, media type)`.
+
+```python
+from pathlib import Path
+from dataleon import Dataleon
+
+client = Dataleon()
+
+client.individuals.documents.upload(
+    individual_id="individual_id",
+    document_type="liasse_fiscale",
+    file=Path("/path/to/file"),
+)
+```
+
+The async client uses the exact same interface. If you pass a [`PathLike`](https://docs.python.org/3/library/os.html#os.PathLike) instance, the file contents will be read asynchronously automatically.
+
+## Handling errors
+
+When the library is unable to connect to the API (for example, due to network connection problems or a timeout), a subclass of `dataleon.APIConnectionError` is raised.
+
+When the API returns a non-success status code (that is, 4xx or 5xx
+response), a subclass of `dataleon.APIStatusError` is raised, containing `status_code` and `response` properties.
+
+All errors inherit from `dataleon.APIError`.
+
+```python
+import dataleon
+from dataleon import Dataleon
+
+client = Dataleon()
+
+try:
+    client.individuals.create(
+        workspace_id="wk_123",
+    )
+except dataleon.APIConnectionError as e:
+    print("The server could not be reached")
+    print(e.__cause__)  # an underlying Exception, likely raised within httpx.
+except dataleon.RateLimitError as e:
+    print("A 429 status code was received; we should back off a bit.")
+except dataleon.APIStatusError as e:
+    print("Another non-200-range status code was received")
+    print(e.status_code)
+    print(e.response)
+```
+
+Error codes are as follows:
+
+| Status Code | Error Type                 |
+| ----------- | -------------------------- |
+| 400         | `BadRequestError`          |
+| 401         | `AuthenticationError`      |
+| 403         | `PermissionDeniedError`    |
+| 404         | `NotFoundError`            |
+| 422         | `UnprocessableEntityError` |
+| 429         | `RateLimitError`           |
+| >=500       | `InternalServerError`      |
+| N/A         | `APIConnectionError`       |
+
+### Retries
+
+Certain errors are automatically retried 2 times by default, with a short exponential backoff.
+Connection errors (for example, due to a network connectivity problem), 408 Request Timeout, 409 Conflict,
+429 Rate Limit, and >=500 Internal errors are all retried by default.
+
+You can use the `max_retries` option to configure or disable retry settings:
+
+```python
+from dataleon import Dataleon
+
+# Configure the default for all requests:
+client = Dataleon(
+    # default is 2
+    max_retries=0,
+)
+
+# Or, configure per-request:
+client.with_options(max_retries=5).individuals.create(
+    workspace_id="wk_123",
+)
+```
+
+### Timeouts
+
+By default requests time out after 1 minute. You can configure this with a `timeout` option,
+which accepts a float or an [`httpx.Timeout`](https://www.python-httpx.org/advanced/timeouts/#fine-tuning-the-configuration) object:
+
+```python
+from dataleon import Dataleon
+
+# Configure the default for all requests:
+client = Dataleon(
+    # 20 seconds (default is 1 minute)
+    timeout=20.0,
+)
+
+# More granular control:
+client = Dataleon(
+    timeout=httpx.Timeout(60.0, read=5.0, write=10.0, connect=2.0),
+)
+
+# Override per-request:
+client.with_options(timeout=5.0).individuals.create(
+    workspace_id="wk_123",
+)
+```
+
+On timeout, an `APITimeoutError` is thrown.
+
+Note that requests that time out are [retried twice by default](https://github.com/dataleonlabs/dataleon-python/tree/main/#retries).
+
+## Advanced
+
+### Logging
+
+We use the standard library [`logging`](https://docs.python.org/3/library/logging.html) module.
+
+You can enable logging by setting the environment variable `DATALEON_LOG` to `info`.
+
+```shell
+$ export DATALEON_LOG=info
+```
+
+Or to `debug` for more verbose logging.
+
+### How to tell whether `None` means `null` or missing
+
+In an API response, a field may be explicitly `null`, or missing entirely; in either case, its value is `None` in this library. You can differentiate the two cases with `.model_fields_set`:
+
+```py
+if response.my_field is None:
+  if 'my_field' not in response.model_fields_set:
+    print('Got json like {}, without a "my_field" key present at all.')
+  else:
+    print('Got json like {"my_field": null}.')
+```
+
+### Accessing raw response data (e.g. headers)
+
+The "raw" Response object can be accessed by prefixing `.with_raw_response.` to any HTTP method call, e.g.,
+
+```py
+from dataleon import Dataleon
+
+client = Dataleon()
+response = client.individuals.with_raw_response.create(
+    workspace_id="wk_123",
+)
+print(response.headers.get('X-My-Header'))
+
+individual = response.parse()  # get the object that `individuals.create()` would have returned
+print(individual.id)
+```
+
+These methods return an [`APIResponse`](https://github.com/dataleonlabs/dataleon-python/tree/main/src/dataleon/_response.py) object.
+
+The async client returns an [`AsyncAPIResponse`](https://github.com/dataleonlabs/dataleon-python/tree/main/src/dataleon/_response.py) with the same structure, the only difference being `await`able methods for reading the response content.
+
+#### `.with_streaming_response`
+
+The above interface eagerly reads the full response body when you make the request, which may not always be what you want.
+
+To stream the response body, use `.with_streaming_response` instead, which requires a context manager and only reads the response body once you call `.read()`, `.text()`, `.json()`, `.iter_bytes()`, `.iter_text()`, `.iter_lines()` or `.parse()`. In the async client, these are async methods.
+
+```python
+with client.individuals.with_streaming_response.create(
+    workspace_id="wk_123",
+) as response:
+    print(response.headers.get("X-My-Header"))
+
+    for line in response.iter_lines():
+        print(line)
+```
+
+The context manager is required so that the response will reliably be closed.
+
+### Making custom/undocumented requests
+
+This library is typed for convenient access to the documented API.
+
+If you need to access undocumented endpoints, params, or response properties, the library can still be used.
+
+#### Undocumented endpoints
+
+To make requests to undocumented endpoints, you can make requests using `client.get`, `client.post`, and other
+http verbs. Options on the client will be respected (such as retries) when making this request.
+
+```py
+import httpx
+
+response = client.post(
+    "/foo",
+    cast_to=httpx.Response,
+    body={"my_param": True},
+)
+
+print(response.headers.get("x-foo"))
+```
+
+#### Undocumented request params
+
+If you want to explicitly send an extra param, you can do so with the `extra_query`, `extra_body`, and `extra_headers` request
+options.
+
+#### Undocumented response properties
+
+To access undocumented response properties, you can access the extra fields like `response.unknown_prop`. You
+can also get all the extra fields on the Pydantic model as a dict with
+[`response.model_extra`](https://docs.pydantic.dev/latest/api/base_model/#pydantic.BaseModel.model_extra).
+
+### Configuring the HTTP client
+
+You can directly override the [httpx client](https://www.python-httpx.org/api/#client) to customize it for your use case, including:
+
+- Support for [proxies](https://www.python-httpx.org/advanced/proxies/)
+- Custom [transports](https://www.python-httpx.org/advanced/transports/)
+- Additional [advanced](https://www.python-httpx.org/advanced/clients/) functionality
+
+```python
+import httpx
+from dataleon import Dataleon, DefaultHttpxClient
+
+client = Dataleon(
+    # Or use the `DATALEON_BASE_URL` env var
+    base_url="http://my.test.server.example.com:8083",
+    http_client=DefaultHttpxClient(
+        proxy="http://my.test.proxy.example.com",
+        transport=httpx.HTTPTransport(local_address="0.0.0.0"),
+    ),
+)
+```
+
+You can also customize the client on a per-request basis by using `with_options()`:
+
+```python
+client.with_options(http_client=DefaultHttpxClient(...))
+```
+
+### Managing HTTP resources
+
+By default the library closes underlying HTTP connections whenever the client is [garbage collected](https://docs.python.org/3/reference/datamodel.html#object.__del__). You can manually close the client using the `.close()` method if desired, or with a context manager that closes when exiting.
+
+```py
+from dataleon import Dataleon
+
+with Dataleon() as client:
+  # make requests here
+  ...
+
+# HTTP client is now closed
+```
+
+## Versioning
+
+This package generally follows [SemVer](https://semver.org/spec/v2.0.0.html) conventions, though certain backwards-incompatible changes may be released as minor versions:
+
+1. Changes that only affect static types, without breaking runtime behavior.
+2. Changes to library internals which are technically public but not intended or documented for external use. _(Please open a GitHub issue to let us know if you are relying on such internals.)_
+3. Changes that we do not expect to impact the vast majority of users in practice.
+
+We take backwards-compatibility seriously and work hard to ensure you can rely on a smooth upgrade experience.
+
+We are keen for your feedback; please open an [issue](https://www.github.com/dataleonlabs/dataleon-python/issues) with questions, bugs, or suggestions.
+
+### Determining the installed version
+
+If you've upgraded to the latest version but aren't seeing any new features you were expecting then your python environment is likely still using an older version.
+
+You can determine the version that is being used at runtime with:
+
+```py
+import dataleon
+print(dataleon.__version__)
+```
+
+## Requirements
+
+Python 3.9 or higher.
+
+## Contributing
+
+See [the contributing documentation](https://github.com/dataleonlabs/dataleon-python/tree/main/./CONTRIBUTING.md).