llama-cloud 0.1.15__py3-none-any.whl → 0.1.16__py3-none-any.whl

llama_cloud/resources/pipelines/client.py

@@ -14,10 +14,7 @@ from ...types.cloud_document import CloudDocument
 from ...types.cloud_document_create import CloudDocumentCreate
 from ...types.configured_transformation_item import ConfiguredTransformationItem
 from ...types.data_sink_create import DataSinkCreate
-from ...types.eval_dataset_job_record import EvalDatasetJobRecord
 from ...types.eval_execution_params import EvalExecutionParams
-from ...types.eval_execution_params_override import EvalExecutionParamsOverride
-from ...types.eval_question_result import EvalQuestionResult
 from ...types.http_validation_error import HttpValidationError
 from ...types.input_message import InputMessage
 from ...types.llama_parse_parameters import LlamaParseParameters
@@ -423,188 +420,6 @@ class PipelinesClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def get_eval_dataset_executions(self, eval_dataset_id: str, pipeline_id: str) -> typing.List[EvalDatasetJobRecord]:
-        """
-        Get the status of an EvalDatasetExecution.
-
-        Parameters:
-            - eval_dataset_id: str.
-
-            - pipeline_id: str.
-        ---
-        from llama_cloud.client import LlamaCloud
-
-        client = LlamaCloud(
-            token="YOUR_TOKEN",
-        )
-        client.pipelines.get_eval_dataset_executions(
-            eval_dataset_id="string",
-            pipeline_id="string",
-        )
-        """
-        _response = self._client_wrapper.httpx_client.request(
-            "GET",
-            urllib.parse.urljoin(
-                f"{self._client_wrapper.get_base_url()}/",
-                f"api/v1/pipelines/{pipeline_id}/eval-datasets/{eval_dataset_id}/execute",
-            ),
-            headers=self._client_wrapper.get_headers(),
-            timeout=60,
-        )
-        if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(typing.List[EvalDatasetJobRecord], _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 execute_eval_dataset(
-        self,
-        eval_dataset_id: str,
-        pipeline_id: str,
-        *,
-        eval_question_ids: typing.List[str],
-        params: typing.Optional[EvalExecutionParamsOverride] = OMIT,
-    ) -> EvalDatasetJobRecord:
-        """
-        Execute a dataset.
-
-        Parameters:
-            - eval_dataset_id: str.
-
-            - pipeline_id: str.
-
-            - eval_question_ids: typing.List[str].
-
-            - params: typing.Optional[EvalExecutionParamsOverride]. The parameters for the eval execution that will override the ones set in the pipeline.
-        ---
-        from llama_cloud import EvalExecutionParamsOverride, SupportedLlmModelNames
-        from llama_cloud.client import LlamaCloud
-
-        client = LlamaCloud(
-            token="YOUR_TOKEN",
-        )
-        client.pipelines.execute_eval_dataset(
-            eval_dataset_id="string",
-            pipeline_id="string",
-            eval_question_ids=[],
-            params=EvalExecutionParamsOverride(
-                llm_model=SupportedLlmModelNames.GPT_3_5_TURBO,
-            ),
-        )
-        """
-        _request: typing.Dict[str, typing.Any] = {"eval_question_ids": eval_question_ids}
-        if params is not OMIT:
-            _request["params"] = params
-        _response = self._client_wrapper.httpx_client.request(
-            "POST",
-            urllib.parse.urljoin(
-                f"{self._client_wrapper.get_base_url()}/",
-                f"api/v1/pipelines/{pipeline_id}/eval-datasets/{eval_dataset_id}/execute",
-            ),
-            json=jsonable_encoder(_request),
-            headers=self._client_wrapper.get_headers(),
-            timeout=60,
-        )
-        if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(EvalDatasetJobRecord, _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_eval_dataset_execution_result(
-        self, eval_dataset_id: str, pipeline_id: str
-    ) -> typing.List[EvalQuestionResult]:
-        """
-        Get the result of an EvalDatasetExecution.
-        If eval_question_ids is specified, only the results for the specified
-        questions will be returned.
-        If any of the specified questions do not have a result, they will be ignored.
-
-        Parameters:
-            - eval_dataset_id: str.
-
-            - pipeline_id: str.
-        ---
-        from llama_cloud.client import LlamaCloud
-
-        client = LlamaCloud(
-            token="YOUR_TOKEN",
-        )
-        client.pipelines.get_eval_dataset_execution_result(
-            eval_dataset_id="string",
-            pipeline_id="string",
-        )
-        """
-        _response = self._client_wrapper.httpx_client.request(
-            "GET",
-            urllib.parse.urljoin(
-                f"{self._client_wrapper.get_base_url()}/",
-                f"api/v1/pipelines/{pipeline_id}/eval-datasets/{eval_dataset_id}/execute/result",
-            ),
-            headers=self._client_wrapper.get_headers(),
-            timeout=60,
-        )
-        if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(typing.List[EvalQuestionResult], _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_eval_dataset_execution(
-        self, eval_dataset_id: str, eval_dataset_execution_id: str, pipeline_id: str
-    ) -> EvalDatasetJobRecord:
-        """
-        Get the status of an EvalDatasetExecution.
-
-        Parameters:
-            - eval_dataset_id: str.
-
-            - eval_dataset_execution_id: str.
-
-            - pipeline_id: str.
-        ---
-        from llama_cloud.client import LlamaCloud
-
-        client = LlamaCloud(
-            token="YOUR_TOKEN",
-        )
-        client.pipelines.get_eval_dataset_execution(
-            eval_dataset_id="string",
-            eval_dataset_execution_id="string",
-            pipeline_id="string",
-        )
-        """
-        _response = self._client_wrapper.httpx_client.request(
-            "GET",
-            urllib.parse.urljoin(
-                f"{self._client_wrapper.get_base_url()}/",
-                f"api/v1/pipelines/{pipeline_id}/eval-datasets/{eval_dataset_id}/execute/{eval_dataset_execution_id}",
-            ),
-            headers=self._client_wrapper.get_headers(),
-            timeout=60,
-        )
-        if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(EvalDatasetJobRecord, _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_pipeline_files(
         self,
         pipeline_id: str,
@@ -1675,7 +1490,11 @@ class PipelinesClient:
 
     def delete_pipeline_document(self, document_id: str, pipeline_id: str) -> None:
         """
-        Delete a document for a pipeline.
+        Delete a document from a pipeline.
+        Initiates an async job that will:
+
+        1. Delete vectors from the vector store
+        2. Delete the document from MongoDB after vectors are successfully deleted
 
         Parameters:
             - document_id: str.
@@ -2156,190 +1975,6 @@ class AsyncPipelinesClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    async def get_eval_dataset_executions(
-        self, eval_dataset_id: str, pipeline_id: str
-    ) -> typing.List[EvalDatasetJobRecord]:
-        """
-        Get the status of an EvalDatasetExecution.
-
-        Parameters:
-            - eval_dataset_id: str.
-
-            - pipeline_id: str.
-        ---
-        from llama_cloud.client import AsyncLlamaCloud
-
-        client = AsyncLlamaCloud(
-            token="YOUR_TOKEN",
-        )
-        await client.pipelines.get_eval_dataset_executions(
-            eval_dataset_id="string",
-            pipeline_id="string",
-        )
-        """
-        _response = await self._client_wrapper.httpx_client.request(
-            "GET",
-            urllib.parse.urljoin(
-                f"{self._client_wrapper.get_base_url()}/",
-                f"api/v1/pipelines/{pipeline_id}/eval-datasets/{eval_dataset_id}/execute",
-            ),
-            headers=self._client_wrapper.get_headers(),
-            timeout=60,
-        )
-        if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(typing.List[EvalDatasetJobRecord], _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 execute_eval_dataset(
-        self,
-        eval_dataset_id: str,
-        pipeline_id: str,
-        *,
-        eval_question_ids: typing.List[str],
-        params: typing.Optional[EvalExecutionParamsOverride] = OMIT,
-    ) -> EvalDatasetJobRecord:
-        """
-        Execute a dataset.
-
-        Parameters:
-            - eval_dataset_id: str.
-
-            - pipeline_id: str.
-
-            - eval_question_ids: typing.List[str].
-
-            - params: typing.Optional[EvalExecutionParamsOverride]. The parameters for the eval execution that will override the ones set in the pipeline.
-        ---
-        from llama_cloud import EvalExecutionParamsOverride, SupportedLlmModelNames
-        from llama_cloud.client import AsyncLlamaCloud
-
-        client = AsyncLlamaCloud(
-            token="YOUR_TOKEN",
-        )
-        await client.pipelines.execute_eval_dataset(
-            eval_dataset_id="string",
-            pipeline_id="string",
-            eval_question_ids=[],
-            params=EvalExecutionParamsOverride(
-                llm_model=SupportedLlmModelNames.GPT_3_5_TURBO,
-            ),
-        )
-        """
-        _request: typing.Dict[str, typing.Any] = {"eval_question_ids": eval_question_ids}
-        if params is not OMIT:
-            _request["params"] = params
-        _response = await self._client_wrapper.httpx_client.request(
-            "POST",
-            urllib.parse.urljoin(
-                f"{self._client_wrapper.get_base_url()}/",
-                f"api/v1/pipelines/{pipeline_id}/eval-datasets/{eval_dataset_id}/execute",
-            ),
-            json=jsonable_encoder(_request),
-            headers=self._client_wrapper.get_headers(),
-            timeout=60,
-        )
-        if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(EvalDatasetJobRecord, _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_eval_dataset_execution_result(
-        self, eval_dataset_id: str, pipeline_id: str
-    ) -> typing.List[EvalQuestionResult]:
-        """
-        Get the result of an EvalDatasetExecution.
-        If eval_question_ids is specified, only the results for the specified
-        questions will be returned.
-        If any of the specified questions do not have a result, they will be ignored.
-
-        Parameters:
-            - eval_dataset_id: str.
-
-            - pipeline_id: str.
-        ---
-        from llama_cloud.client import AsyncLlamaCloud
-
-        client = AsyncLlamaCloud(
-            token="YOUR_TOKEN",
-        )
-        await client.pipelines.get_eval_dataset_execution_result(
-            eval_dataset_id="string",
-            pipeline_id="string",
-        )
-        """
-        _response = await self._client_wrapper.httpx_client.request(
-            "GET",
-            urllib.parse.urljoin(
-                f"{self._client_wrapper.get_base_url()}/",
-                f"api/v1/pipelines/{pipeline_id}/eval-datasets/{eval_dataset_id}/execute/result",
-            ),
-            headers=self._client_wrapper.get_headers(),
-            timeout=60,
-        )
-        if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(typing.List[EvalQuestionResult], _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_eval_dataset_execution(
-        self, eval_dataset_id: str, eval_dataset_execution_id: str, pipeline_id: str
-    ) -> EvalDatasetJobRecord:
-        """
-        Get the status of an EvalDatasetExecution.
-
-        Parameters:
-            - eval_dataset_id: str.
-
-            - eval_dataset_execution_id: str.
-
-            - pipeline_id: str.
-        ---
-        from llama_cloud.client import AsyncLlamaCloud
-
-        client = AsyncLlamaCloud(
-            token="YOUR_TOKEN",
-        )
-        await client.pipelines.get_eval_dataset_execution(
-            eval_dataset_id="string",
-            eval_dataset_execution_id="string",
-            pipeline_id="string",
-        )
-        """
-        _response = await self._client_wrapper.httpx_client.request(
-            "GET",
-            urllib.parse.urljoin(
-                f"{self._client_wrapper.get_base_url()}/",
-                f"api/v1/pipelines/{pipeline_id}/eval-datasets/{eval_dataset_id}/execute/{eval_dataset_execution_id}",
-            ),
-            headers=self._client_wrapper.get_headers(),
-            timeout=60,
-        )
-        if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(EvalDatasetJobRecord, _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_pipeline_files(
         self,
         pipeline_id: str,
@@ -3412,7 +3047,11 @@ class AsyncPipelinesClient:
 
     async def delete_pipeline_document(self, document_id: str, pipeline_id: str) -> None:
         """
-        Delete a document for a pipeline.
+        Delete a document from a pipeline.
+        Initiates an async job that will:
+
+        1. Delete vectors from the vector store
+        2. Delete the document from MongoDB after vectors are successfully deleted
 
         Parameters:
             - document_id: str.