llama-cloud 0.0.6__py3-none-any.whl → 0.0.8__py3-none-any.whl

llama_cloud/resources/extraction/client.py

@@ -0,0 +1,648 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+import urllib.parse
+from json.decoder import JSONDecodeError
+
+from ...core.api_error import ApiError
+from ...core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
+from ...core.jsonable_encoder import jsonable_encoder
+from ...core.remove_none_from_dict import remove_none_from_dict
+from ...errors.unprocessable_entity_error import UnprocessableEntityError
+from ...types.extraction_result import ExtractionResult
+from ...types.extraction_schema import ExtractionSchema
+from ...types.http_validation_error import HttpValidationError
+from .types.extraction_schema_update_data_schema_value import ExtractionSchemaUpdateDataSchemaValue
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+# this is used as the default value for optional parameters
+OMIT = typing.cast(typing.Any, ...)
+
+
+class ExtractionClient:
+    def __init__(self, *, client_wrapper: SyncClientWrapper):
+        self._client_wrapper = client_wrapper
+
+    def infer_schema(
+        self, *, name: str, project_id: typing.Optional[str] = OMIT, file_ids: typing.List[str], openai_api_key: str
+    ) -> ExtractionSchema:
+        """
+        Parameters:
+            - name: str. The name of the extraction schema
+
+            - project_id: typing.Optional[str]. The ID of the project that the extraction schema belongs to
+
+            - file_ids: typing.List[str]. The IDs of the files that the extraction schema contains
+
+            - openai_api_key: str. The API key for the OpenAI API
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.extraction.infer_schema(
+            name="string",
+            file_ids=[],
+            openai_api_key="string",
+        )
+        """
+        _request: typing.Dict[str, typing.Any] = {"name": name, "file_ids": file_ids, "openai_api_key": openai_api_key}
+        if project_id is not OMIT:
+            _request["project_id"] = project_id
+        _response = self._client_wrapper.httpx_client.request(
+            "POST",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/schemas/infer"),
+            json=jsonable_encoder(_request),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExtractionSchema, _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    def list_schemas(self, *, project_id: typing.Optional[str] = None) -> typing.List[ExtractionSchema]:
+        """
+        Parameters:
+            - project_id: typing.Optional[str].
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.extraction.list_schemas()
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/schemas"),
+            params=remove_none_from_dict({"project_id": project_id}),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(typing.List[ExtractionSchema], _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    def get_schema(self, schema_id: str) -> ExtractionSchema:
+        """
+        Parameters:
+            - schema_id: str.
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.extraction.get_schema(
+            schema_id="string",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/schemas/{schema_id}"),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExtractionSchema, _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    def update_schema(
+        self,
+        schema_id: str,
+        *,
+        data_schema: typing.Optional[typing.Dict[str, ExtractionSchemaUpdateDataSchemaValue]] = OMIT,
+        openai_api_key: typing.Optional[str] = OMIT,
+    ) -> ExtractionSchema:
+        """
+        Parameters:
+            - schema_id: str.
+
+            - data_schema: typing.Optional[typing.Dict[str, ExtractionSchemaUpdateDataSchemaValue]]. The schema of the data
+
+            - openai_api_key: typing.Optional[str]. The API key for the OpenAI API
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.extraction.update_schema(
+            schema_id="string",
+        )
+        """
+        _request: typing.Dict[str, typing.Any] = {}
+        if data_schema is not OMIT:
+            _request["data_schema"] = data_schema
+        if openai_api_key is not OMIT:
+            _request["openai_api_key"] = openai_api_key
+        _response = self._client_wrapper.httpx_client.request(
+            "PUT",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/schemas/{schema_id}"),
+            json=jsonable_encoder(_request),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExtractionSchema, _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    def list_jobs(self, *, schema_id: typing.Optional[str] = None) -> typing.List[ExtractionResult]:
+        """
+        Parameters:
+            - schema_id: typing.Optional[str].
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.extraction.list_jobs()
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs"),
+            params=remove_none_from_dict({"schema_id": schema_id}),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(typing.List[ExtractionResult], _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    def run_job(self, *, schema_id: str, file_id: str) -> ExtractionResult:
+        """
+        Parameters:
+            - schema_id: str. The id of the schema
+
+            - file_id: str. The id of the file
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.extraction.run_job(
+            schema_id="string",
+            file_id="string",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "POST",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs"),
+            json=jsonable_encoder({"schema_id": schema_id, "file_id": file_id}),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExtractionResult, _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    def get_job(self, job_id: str) -> ExtractionResult:
+        """
+        Parameters:
+            - job_id: str.
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.extraction.get_job(
+            job_id="string",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/jobs/{job_id}"),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExtractionResult, _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    def run_jobs_in_batch(self, *, schema_id: str, file_ids: typing.List[str]) -> typing.List[ExtractionResult]:
+        """
+        Parameters:
+            - schema_id: str. The id of the schema
+
+            - file_ids: typing.List[str]. The ids of the files
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.extraction.run_jobs_in_batch(
+            schema_id="string",
+            file_ids=[],
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "POST",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs/batch"),
+            json=jsonable_encoder({"schema_id": schema_id, "file_ids": file_ids}),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(typing.List[ExtractionResult], _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    def get_job_result(self, job_id: str) -> ExtractionResult:
+        """
+        Parameters:
+            - job_id: str.
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.extraction.get_job_result(
+            job_id="string",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/jobs/{job_id}/result"),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExtractionResult, _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+
+class AsyncExtractionClient:
+    def __init__(self, *, client_wrapper: AsyncClientWrapper):
+        self._client_wrapper = client_wrapper
+
+    async def infer_schema(
+        self, *, name: str, project_id: typing.Optional[str] = OMIT, file_ids: typing.List[str], openai_api_key: str
+    ) -> ExtractionSchema:
+        """
+        Parameters:
+            - name: str. The name of the extraction schema
+
+            - project_id: typing.Optional[str]. The ID of the project that the extraction schema belongs to
+
+            - file_ids: typing.List[str]. The IDs of the files that the extraction schema contains
+
+            - openai_api_key: str. The API key for the OpenAI API
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.extraction.infer_schema(
+            name="string",
+            file_ids=[],
+            openai_api_key="string",
+        )
+        """
+        _request: typing.Dict[str, typing.Any] = {"name": name, "file_ids": file_ids, "openai_api_key": openai_api_key}
+        if project_id is not OMIT:
+            _request["project_id"] = project_id
+        _response = await self._client_wrapper.httpx_client.request(
+            "POST",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/schemas/infer"),
+            json=jsonable_encoder(_request),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExtractionSchema, _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    async def list_schemas(self, *, project_id: typing.Optional[str] = None) -> typing.List[ExtractionSchema]:
+        """
+        Parameters:
+            - project_id: typing.Optional[str].
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.extraction.list_schemas()
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/schemas"),
+            params=remove_none_from_dict({"project_id": project_id}),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(typing.List[ExtractionSchema], _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    async def get_schema(self, schema_id: str) -> ExtractionSchema:
+        """
+        Parameters:
+            - schema_id: str.
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.extraction.get_schema(
+            schema_id="string",
+        )
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/schemas/{schema_id}"),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExtractionSchema, _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    async def update_schema(
+        self,
+        schema_id: str,
+        *,
+        data_schema: typing.Optional[typing.Dict[str, ExtractionSchemaUpdateDataSchemaValue]] = OMIT,
+        openai_api_key: typing.Optional[str] = OMIT,
+    ) -> ExtractionSchema:
+        """
+        Parameters:
+            - schema_id: str.
+
+            - data_schema: typing.Optional[typing.Dict[str, ExtractionSchemaUpdateDataSchemaValue]]. The schema of the data
+
+            - openai_api_key: typing.Optional[str]. The API key for the OpenAI API
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.extraction.update_schema(
+            schema_id="string",
+        )
+        """
+        _request: typing.Dict[str, typing.Any] = {}
+        if data_schema is not OMIT:
+            _request["data_schema"] = data_schema
+        if openai_api_key is not OMIT:
+            _request["openai_api_key"] = openai_api_key
+        _response = await self._client_wrapper.httpx_client.request(
+            "PUT",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/schemas/{schema_id}"),
+            json=jsonable_encoder(_request),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExtractionSchema, _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    async def list_jobs(self, *, schema_id: typing.Optional[str] = None) -> typing.List[ExtractionResult]:
+        """
+        Parameters:
+            - schema_id: typing.Optional[str].
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.extraction.list_jobs()
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs"),
+            params=remove_none_from_dict({"schema_id": schema_id}),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(typing.List[ExtractionResult], _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    async def run_job(self, *, schema_id: str, file_id: str) -> ExtractionResult:
+        """
+        Parameters:
+            - schema_id: str. The id of the schema
+
+            - file_id: str. The id of the file
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.extraction.run_job(
+            schema_id="string",
+            file_id="string",
+        )
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "POST",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs"),
+            json=jsonable_encoder({"schema_id": schema_id, "file_id": file_id}),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExtractionResult, _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    async def get_job(self, job_id: str) -> ExtractionResult:
+        """
+        Parameters:
+            - job_id: str.
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.extraction.get_job(
+            job_id="string",
+        )
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/jobs/{job_id}"),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExtractionResult, _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    async def run_jobs_in_batch(self, *, schema_id: str, file_ids: typing.List[str]) -> typing.List[ExtractionResult]:
+        """
+        Parameters:
+            - schema_id: str. The id of the schema
+
+            - file_ids: typing.List[str]. The ids of the files
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.extraction.run_jobs_in_batch(
+            schema_id="string",
+            file_ids=[],
+        )
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "POST",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs/batch"),
+            json=jsonable_encoder({"schema_id": schema_id, "file_ids": file_ids}),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(typing.List[ExtractionResult], _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    async def get_job_result(self, job_id: str) -> ExtractionResult:
+        """
+        Parameters:
+            - job_id: str.
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.extraction.get_job_result(
+            job_id="string",
+        )
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/jobs/{job_id}/result"),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExtractionResult, _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)

llama_cloud/resources/extraction/types/__init__.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from .extraction_schema_update_data_schema_value import ExtractionSchemaUpdateDataSchemaValue
+
+__all__ = ["ExtractionSchemaUpdateDataSchemaValue"]

llama_cloud/resources/extraction/types/extraction_schema_update_data_schema_value.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+ExtractionSchemaUpdateDataSchemaValue = typing.Union[
+    typing.Dict[str, typing.Any], typing.List[typing.Any], str, int, float, bool
+]