# 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 ...errors.unprocessable_entity_error import UnprocessableEntityError
from ...types.eval_dataset import EvalDataset
from ...types.eval_question import EvalQuestion
from ...types.eval_question_create import EvalQuestionCreate
from ...types.http_validation_error import HttpValidationError
from ...types.supported_llm_model import SupportedLlmModel

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 EvalsClient:
    def __init__(self, *, client_wrapper: SyncClientWrapper):
        self._client_wrapper = client_wrapper

    def get_dataset(self, dataset_id: str) -> EvalDataset:
        """
        Get a dataset by ID.

        Parameters:
            - dataset_id: str.
        ---
        from llama_cloud.client import LlamaCloud

        client = LlamaCloud(
            token="YOUR_TOKEN",
        )
        client.evals.get_dataset(
            dataset_id="string",
        )
        """
        _response = self._client_wrapper.httpx_client.request(
            "GET",
            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/evals/datasets/{dataset_id}"),
            headers=self._client_wrapper.get_headers(),
            timeout=60,
        )
        if 200 <= _response.status_code < 300:
            return pydantic.parse_obj_as(EvalDataset, _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_dataset(self, dataset_id: str, *, name: str) -> EvalDataset:
        """
        Update a dataset.

        Parameters:
            - dataset_id: str.

            - name: str. The name of the EvalDataset.
        ---
        from llama_cloud.client import LlamaCloud

        client = LlamaCloud(
            token="YOUR_TOKEN",
        )
        client.evals.update_dataset(
            dataset_id="string",
            name="string",
        )
        """
        _response = self._client_wrapper.httpx_client.request(
            "PUT",
            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/evals/datasets/{dataset_id}"),
            json=jsonable_encoder({"name": name}),
            headers=self._client_wrapper.get_headers(),
            timeout=60,
        )
        if 200 <= _response.status_code < 300:
            return pydantic.parse_obj_as(EvalDataset, _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 delete_dataset(self, dataset_id: str) -> None:
        """
        Delete a dataset.

        Parameters:
            - dataset_id: str.
        ---
        from llama_cloud.client import LlamaCloud

        client = LlamaCloud(
            token="YOUR_TOKEN",
        )
        client.evals.delete_dataset(
            dataset_id="string",
        )
        """
        _response = self._client_wrapper.httpx_client.request(
            "DELETE",
            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/evals/datasets/{dataset_id}"),
            headers=self._client_wrapper.get_headers(),
            timeout=60,
        )
        if 200 <= _response.status_code < 300:
            return
        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_questions(self, dataset_id: str) -> typing.List[EvalQuestion]:
        """
        List questions for a dataset.

        Parameters:
            - dataset_id: str.
        ---
        from llama_cloud.client import LlamaCloud

        client = LlamaCloud(
            token="YOUR_TOKEN",
        )
        client.evals.list_questions(
            dataset_id="string",
        )
        """
        _response = self._client_wrapper.httpx_client.request(
            "GET",
            urllib.parse.urljoin(
                f"{self._client_wrapper.get_base_url()}/", f"api/v1/evals/datasets/{dataset_id}/question"
            ),
            headers=self._client_wrapper.get_headers(),
            timeout=60,
        )
        if 200 <= _response.status_code < 300:
            return pydantic.parse_obj_as(typing.List[EvalQuestion], _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 create_question(self, dataset_id: str, *, request: EvalQuestionCreate) -> EvalQuestion:
        """
        Create a new question.

        Parameters:
            - dataset_id: str.

            - request: EvalQuestionCreate.
        ---
        from llama_cloud import EvalQuestionCreate
        from llama_cloud.client import LlamaCloud

        client = LlamaCloud(
            token="YOUR_TOKEN",
        )
        client.evals.create_question(
            dataset_id="string",
            request=EvalQuestionCreate(
                content="string",
            ),
        )
        """
        _response = self._client_wrapper.httpx_client.request(
            "POST",
            urllib.parse.urljoin(
                f"{self._client_wrapper.get_base_url()}/", f"api/v1/evals/datasets/{dataset_id}/question"
            ),
            json=jsonable_encoder(request),
            headers=self._client_wrapper.get_headers(),
            timeout=60,
        )
        if 200 <= _response.status_code < 300:
            return pydantic.parse_obj_as(EvalQuestion, _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 create_questions(
        self, dataset_id: str, *, request: typing.List[EvalQuestionCreate]
    ) -> typing.List[EvalQuestion]:
        """
        Create a new question.

        Parameters:
            - dataset_id: str.

            - request: typing.List[EvalQuestionCreate].
        ---
        from llama_cloud.client import LlamaCloud

        client = LlamaCloud(
            token="YOUR_TOKEN",
        )
        client.evals.create_questions(
            dataset_id="string",
            request=[],
        )
        """
        _response = self._client_wrapper.httpx_client.request(
            "POST",
            urllib.parse.urljoin(
                f"{self._client_wrapper.get_base_url()}/", f"api/v1/evals/datasets/{dataset_id}/questions"
            ),
            json=jsonable_encoder(request),
            headers=self._client_wrapper.get_headers(),
            timeout=60,
        )
        if 200 <= _response.status_code < 300:
            return pydantic.parse_obj_as(typing.List[EvalQuestion], _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_question(self, question_id: str) -> EvalQuestion:
        """
        Get a question by ID.

        Parameters:
            - question_id: str.
        ---
        from llama_cloud.client import LlamaCloud

        client = LlamaCloud(
            token="YOUR_TOKEN",
        )
        client.evals.get_question(
            question_id="string",
        )
        """
        _response = self._client_wrapper.httpx_client.request(
            "GET",
            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/evals/questions/{question_id}"),
            headers=self._client_wrapper.get_headers(),
            timeout=60,
        )
        if 200 <= _response.status_code < 300:
            return pydantic.parse_obj_as(EvalQuestion, _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 replace_question(self, question_id: str, *, request: EvalQuestionCreate) -> EvalQuestion:
        """
        Replace a question.

        Parameters:
            - question_id: str.

            - request: EvalQuestionCreate.
        ---
        from llama_cloud import EvalQuestionCreate
        from llama_cloud.client import LlamaCloud

        client = LlamaCloud(
            token="YOUR_TOKEN",
        )
        client.evals.replace_question(
            question_id="string",
            request=EvalQuestionCreate(
                content="string",
            ),
        )
        """
        _response = self._client_wrapper.httpx_client.request(
            "PUT",
            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/evals/questions/{question_id}"),
            json=jsonable_encoder(request),
            headers=self._client_wrapper.get_headers(),
            timeout=60,
        )
        if 200 <= _response.status_code < 300:
            return pydantic.parse_obj_as(EvalQuestion, _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 delete_question(self, question_id: str) -> None:
        """
        Delete a question.

        Parameters:
            - question_id: str.
        ---
        from llama_cloud.client import LlamaCloud

        client = LlamaCloud(
            token="YOUR_TOKEN",
        )
        client.evals.delete_question(
            question_id="string",
        )
        """
        _response = self._client_wrapper.httpx_client.request(
            "DELETE",
            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/evals/questions/{question_id}"),
            headers=self._client_wrapper.get_headers(),
            timeout=60,
        )
        if 200 <= _response.status_code < 300:
            return
        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_supported_models(self) -> typing.List[SupportedLlmModel]:
        """
        List supported models.

        ---
        from llama_cloud.client import LlamaCloud

        client = LlamaCloud(
            token="YOUR_TOKEN",
        )
        client.evals.list_supported_models()
        """
        _response = self._client_wrapper.httpx_client.request(
            "GET",
            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/evals/models"),
            headers=self._client_wrapper.get_headers(),
            timeout=60,
        )
        if 200 <= _response.status_code < 300:
            return pydantic.parse_obj_as(typing.List[SupportedLlmModel], _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 AsyncEvalsClient:
    def __init__(self, *, client_wrapper: AsyncClientWrapper):
        self._client_wrapper = client_wrapper

    async def get_dataset(self, dataset_id: str) -> EvalDataset:
        """
        Get a dataset by ID.

        Parameters:
            - dataset_id: str.
        ---
        from llama_cloud.client import AsyncLlamaCloud

        client = AsyncLlamaCloud(
            token="YOUR_TOKEN",
        )
        await client.evals.get_dataset(
            dataset_id="string",
        )
        """
        _response = await self._client_wrapper.httpx_client.request(
            "GET",
            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/evals/datasets/{dataset_id}"),
            headers=self._client_wrapper.get_headers(),
            timeout=60,
        )
        if 200 <= _response.status_code < 300:
            return pydantic.parse_obj_as(EvalDataset, _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_dataset(self, dataset_id: str, *, name: str) -> EvalDataset:
        """
        Update a dataset.

        Parameters:
            - dataset_id: str.

            - name: str. The name of the EvalDataset.
        ---
        from llama_cloud.client import AsyncLlamaCloud

        client = AsyncLlamaCloud(
            token="YOUR_TOKEN",
        )
        await client.evals.update_dataset(
            dataset_id="string",
            name="string",
        )
        """
        _response = await self._client_wrapper.httpx_client.request(
            "PUT",
            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/evals/datasets/{dataset_id}"),
            json=jsonable_encoder({"name": name}),
            headers=self._client_wrapper.get_headers(),
            timeout=60,
        )
        if 200 <= _response.status_code < 300:
            return pydantic.parse_obj_as(EvalDataset, _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 delete_dataset(self, dataset_id: str) -> None:
        """
        Delete a dataset.

        Parameters:
            - dataset_id: str.
        ---
        from llama_cloud.client import AsyncLlamaCloud

        client = AsyncLlamaCloud(
            token="YOUR_TOKEN",
        )
        await client.evals.delete_dataset(
            dataset_id="string",
        )
        """
        _response = await self._client_wrapper.httpx_client.request(
            "DELETE",
            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/evals/datasets/{dataset_id}"),
            headers=self._client_wrapper.get_headers(),
            timeout=60,
        )
        if 200 <= _response.status_code < 300:
            return
        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_questions(self, dataset_id: str) -> typing.List[EvalQuestion]:
        """
        List questions for a dataset.

        Parameters:
            - dataset_id: str.
        ---
        from llama_cloud.client import AsyncLlamaCloud

        client = AsyncLlamaCloud(
            token="YOUR_TOKEN",
        )
        await client.evals.list_questions(
            dataset_id="string",
        )
        """
        _response = await self._client_wrapper.httpx_client.request(
            "GET",
            urllib.parse.urljoin(
                f"{self._client_wrapper.get_base_url()}/", f"api/v1/evals/datasets/{dataset_id}/question"
            ),
            headers=self._client_wrapper.get_headers(),
            timeout=60,
        )
        if 200 <= _response.status_code < 300:
            return pydantic.parse_obj_as(typing.List[EvalQuestion], _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 create_question(self, dataset_id: str, *, request: EvalQuestionCreate) -> EvalQuestion:
        """
        Create a new question.

        Parameters:
            - dataset_id: str.

            - request: EvalQuestionCreate.
        ---
        from llama_cloud import EvalQuestionCreate
        from llama_cloud.client import AsyncLlamaCloud

        client = AsyncLlamaCloud(
            token="YOUR_TOKEN",
        )
        await client.evals.create_question(
            dataset_id="string",
            request=EvalQuestionCreate(
                content="string",
            ),
        )
        """
        _response = await self._client_wrapper.httpx_client.request(
            "POST",
            urllib.parse.urljoin(
                f"{self._client_wrapper.get_base_url()}/", f"api/v1/evals/datasets/{dataset_id}/question"
            ),
            json=jsonable_encoder(request),
            headers=self._client_wrapper.get_headers(),
            timeout=60,
        )
        if 200 <= _response.status_code < 300:
            return pydantic.parse_obj_as(EvalQuestion, _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 create_questions(
        self, dataset_id: str, *, request: typing.List[EvalQuestionCreate]
    ) -> typing.List[EvalQuestion]:
        """
        Create a new question.

        Parameters:
            - dataset_id: str.

            - request: typing.List[EvalQuestionCreate].
        ---
        from llama_cloud.client import AsyncLlamaCloud

        client = AsyncLlamaCloud(
            token="YOUR_TOKEN",
        )
        await client.evals.create_questions(
            dataset_id="string",
            request=[],
        )
        """
        _response = await self._client_wrapper.httpx_client.request(
            "POST",
            urllib.parse.urljoin(
                f"{self._client_wrapper.get_base_url()}/", f"api/v1/evals/datasets/{dataset_id}/questions"
            ),
            json=jsonable_encoder(request),
            headers=self._client_wrapper.get_headers(),
            timeout=60,
        )
        if 200 <= _response.status_code < 300:
            return pydantic.parse_obj_as(typing.List[EvalQuestion], _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_question(self, question_id: str) -> EvalQuestion:
        """
        Get a question by ID.

        Parameters:
            - question_id: str.
        ---
        from llama_cloud.client import AsyncLlamaCloud

        client = AsyncLlamaCloud(
            token="YOUR_TOKEN",
        )
        await client.evals.get_question(
            question_id="string",
        )
        """
        _response = await self._client_wrapper.httpx_client.request(
            "GET",
            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/evals/questions/{question_id}"),
            headers=self._client_wrapper.get_headers(),
            timeout=60,
        )
        if 200 <= _response.status_code < 300:
            return pydantic.parse_obj_as(EvalQuestion, _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 replace_question(self, question_id: str, *, request: EvalQuestionCreate) -> EvalQuestion:
        """
        Replace a question.

        Parameters:
            - question_id: str.

            - request: EvalQuestionCreate.
        ---
        from llama_cloud import EvalQuestionCreate
        from llama_cloud.client import AsyncLlamaCloud

        client = AsyncLlamaCloud(
            token="YOUR_TOKEN",
        )
        await client.evals.replace_question(
            question_id="string",
            request=EvalQuestionCreate(
                content="string",
            ),
        )
        """
        _response = await self._client_wrapper.httpx_client.request(
            "PUT",
            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/evals/questions/{question_id}"),
            json=jsonable_encoder(request),
            headers=self._client_wrapper.get_headers(),
            timeout=60,
        )
        if 200 <= _response.status_code < 300:
            return pydantic.parse_obj_as(EvalQuestion, _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 delete_question(self, question_id: str) -> None:
        """
        Delete a question.

        Parameters:
            - question_id: str.
        ---
        from llama_cloud.client import AsyncLlamaCloud

        client = AsyncLlamaCloud(
            token="YOUR_TOKEN",
        )
        await client.evals.delete_question(
            question_id="string",
        )
        """
        _response = await self._client_wrapper.httpx_client.request(
            "DELETE",
            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/evals/questions/{question_id}"),
            headers=self._client_wrapper.get_headers(),
            timeout=60,
        )
        if 200 <= _response.status_code < 300:
            return
        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_supported_models(self) -> typing.List[SupportedLlmModel]:
        """
        List supported models.

        ---
        from llama_cloud.client import AsyncLlamaCloud

        client = AsyncLlamaCloud(
            token="YOUR_TOKEN",
        )
        await client.evals.list_supported_models()
        """
        _response = await self._client_wrapper.httpx_client.request(
            "GET",
            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/evals/models"),
            headers=self._client_wrapper.get_headers(),
            timeout=60,
        )
        if 200 <= _response.status_code < 300:
            return pydantic.parse_obj_as(typing.List[SupportedLlmModel], _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)