2025-04-02 09:01:55 +02:00

249 lines
9.8 KiB
Python

"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
from .basesdk import BaseSDK
from mistralai import models, utils
from mistralai._hooks import HookContext
from mistralai.types import Nullable, OptionalNullable, UNSET
from mistralai.utils import get_security_from_env
from typing import Any, List, Mapping, Optional, Union
class Ocr(BaseSDK):
r"""OCR API"""
def process(
self,
*,
model: Nullable[str],
document: Union[models.Document, models.DocumentTypedDict],
id: Optional[str] = None,
pages: OptionalNullable[List[int]] = UNSET,
include_image_base64: OptionalNullable[bool] = UNSET,
image_limit: OptionalNullable[int] = UNSET,
image_min_size: OptionalNullable[int] = UNSET,
retries: OptionalNullable[utils.RetryConfig] = UNSET,
server_url: Optional[str] = None,
timeout_ms: Optional[int] = None,
http_headers: Optional[Mapping[str, str]] = None,
) -> models.OCRResponse:
r"""OCR
:param model:
:param document: Document to run OCR on
:param id:
:param pages: Specific pages user wants to process in various formats: single number, range, or list of both. Starts from 0
:param include_image_base64: Include image URLs in response
:param image_limit: Max images to extract
:param image_min_size: Minimum height and width of image to extract
:param retries: Override the default retry configuration for this method
:param server_url: Override the default server URL for this method
:param timeout_ms: Override the default request timeout configuration for this method in milliseconds
:param http_headers: Additional headers to set or replace on requests.
"""
base_url = None
url_variables = None
if timeout_ms is None:
timeout_ms = self.sdk_configuration.timeout_ms
if server_url is not None:
base_url = server_url
else:
base_url = self._get_url(base_url, url_variables)
request = models.OCRRequest(
model=model,
id=id,
document=utils.get_pydantic_model(document, models.Document),
pages=pages,
include_image_base64=include_image_base64,
image_limit=image_limit,
image_min_size=image_min_size,
)
req = self._build_request(
method="POST",
path="/v1/ocr",
base_url=base_url,
url_variables=url_variables,
request=request,
request_body_required=True,
request_has_path_params=False,
request_has_query_params=True,
user_agent_header="user-agent",
accept_header_value="application/json",
http_headers=http_headers,
security=self.sdk_configuration.security,
get_serialized_body=lambda: utils.serialize_request_body(
request, False, False, "json", models.OCRRequest
),
timeout_ms=timeout_ms,
)
if retries == UNSET:
if self.sdk_configuration.retry_config is not UNSET:
retries = self.sdk_configuration.retry_config
retry_config = None
if isinstance(retries, utils.RetryConfig):
retry_config = (retries, ["429", "500", "502", "503", "504"])
http_res = self.do_request(
hook_ctx=HookContext(
base_url=base_url or "",
operation_id="ocr_v1_ocr_post",
oauth2_scopes=[],
security_source=get_security_from_env(
self.sdk_configuration.security, models.Security
),
),
request=req,
error_status_codes=["422", "4XX", "5XX"],
retry_config=retry_config,
)
response_data: Any = None
if utils.match_response(http_res, "200", "application/json"):
return utils.unmarshal_json(http_res.text, models.OCRResponse)
if utils.match_response(http_res, "422", "application/json"):
response_data = utils.unmarshal_json(
http_res.text, models.HTTPValidationErrorData
)
raise models.HTTPValidationError(data=response_data)
if utils.match_response(http_res, "4XX", "*"):
http_res_text = utils.stream_to_text(http_res)
raise models.SDKError(
"API error occurred", http_res.status_code, http_res_text, http_res
)
if utils.match_response(http_res, "5XX", "*"):
http_res_text = utils.stream_to_text(http_res)
raise models.SDKError(
"API error occurred", http_res.status_code, http_res_text, http_res
)
content_type = http_res.headers.get("Content-Type")
http_res_text = utils.stream_to_text(http_res)
raise models.SDKError(
f"Unexpected response received (code: {http_res.status_code}, type: {content_type})",
http_res.status_code,
http_res_text,
http_res,
)
async def process_async(
self,
*,
model: Nullable[str],
document: Union[models.Document, models.DocumentTypedDict],
id: Optional[str] = None,
pages: OptionalNullable[List[int]] = UNSET,
include_image_base64: OptionalNullable[bool] = UNSET,
image_limit: OptionalNullable[int] = UNSET,
image_min_size: OptionalNullable[int] = UNSET,
retries: OptionalNullable[utils.RetryConfig] = UNSET,
server_url: Optional[str] = None,
timeout_ms: Optional[int] = None,
http_headers: Optional[Mapping[str, str]] = None,
) -> models.OCRResponse:
r"""OCR
:param model:
:param document: Document to run OCR on
:param id:
:param pages: Specific pages user wants to process in various formats: single number, range, or list of both. Starts from 0
:param include_image_base64: Include image URLs in response
:param image_limit: Max images to extract
:param image_min_size: Minimum height and width of image to extract
:param retries: Override the default retry configuration for this method
:param server_url: Override the default server URL for this method
:param timeout_ms: Override the default request timeout configuration for this method in milliseconds
:param http_headers: Additional headers to set or replace on requests.
"""
base_url = None
url_variables = None
if timeout_ms is None:
timeout_ms = self.sdk_configuration.timeout_ms
if server_url is not None:
base_url = server_url
else:
base_url = self._get_url(base_url, url_variables)
request = models.OCRRequest(
model=model,
id=id,
document=utils.get_pydantic_model(document, models.Document),
pages=pages,
include_image_base64=include_image_base64,
image_limit=image_limit,
image_min_size=image_min_size,
)
req = self._build_request_async(
method="POST",
path="/v1/ocr",
base_url=base_url,
url_variables=url_variables,
request=request,
request_body_required=True,
request_has_path_params=False,
request_has_query_params=True,
user_agent_header="user-agent",
accept_header_value="application/json",
http_headers=http_headers,
security=self.sdk_configuration.security,
get_serialized_body=lambda: utils.serialize_request_body(
request, False, False, "json", models.OCRRequest
),
timeout_ms=timeout_ms,
)
if retries == UNSET:
if self.sdk_configuration.retry_config is not UNSET:
retries = self.sdk_configuration.retry_config
retry_config = None
if isinstance(retries, utils.RetryConfig):
retry_config = (retries, ["429", "500", "502", "503", "504"])
http_res = await self.do_request_async(
hook_ctx=HookContext(
base_url=base_url or "",
operation_id="ocr_v1_ocr_post",
oauth2_scopes=[],
security_source=get_security_from_env(
self.sdk_configuration.security, models.Security
),
),
request=req,
error_status_codes=["422", "4XX", "5XX"],
retry_config=retry_config,
)
response_data: Any = None
if utils.match_response(http_res, "200", "application/json"):
return utils.unmarshal_json(http_res.text, models.OCRResponse)
if utils.match_response(http_res, "422", "application/json"):
response_data = utils.unmarshal_json(
http_res.text, models.HTTPValidationErrorData
)
raise models.HTTPValidationError(data=response_data)
if utils.match_response(http_res, "4XX", "*"):
http_res_text = await utils.stream_to_text_async(http_res)
raise models.SDKError(
"API error occurred", http_res.status_code, http_res_text, http_res
)
if utils.match_response(http_res, "5XX", "*"):
http_res_text = await utils.stream_to_text_async(http_res)
raise models.SDKError(
"API error occurred", http_res.status_code, http_res_text, http_res
)
content_type = http_res.headers.get("Content-Type")
http_res_text = await utils.stream_to_text_async(http_res)
raise models.SDKError(
f"Unexpected response received (code: {http_res.status_code}, type: {content_type})",
http_res.status_code,
http_res_text,
http_res,
)