llama-cloud 0.1.4__py3-none-any.whl → 0.1.6__py3-none-any.whl

llama_cloud/resources/embedding_model_configs/client.py

@@ -0,0 +1,416 @@
+# 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.embedding_model_config import EmbeddingModelConfig
+from ...types.embedding_model_config_update import EmbeddingModelConfigUpdate
+from ...types.http_validation_error import HttpValidationError
+from .types.embedding_model_config_create_embedding_config import EmbeddingModelConfigCreateEmbeddingConfig
+
+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 EmbeddingModelConfigsClient:
+    def __init__(self, *, client_wrapper: SyncClientWrapper):
+        self._client_wrapper = client_wrapper
+
+    def list_embedding_model_configs(self, *, project_id: str) -> typing.List[EmbeddingModelConfig]:
+        """
+        Parameters:
+            - project_id: str.
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/embedding-model-configs"),
+            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[EmbeddingModelConfig], _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_embedding_model_config(
+        self, *, project_id: str, name: str, embedding_config: EmbeddingModelConfigCreateEmbeddingConfig
+    ) -> EmbeddingModelConfig:
+        """
+        Create a new embedding model configuration within a specified project.
+
+        Parameters:
+            - project_id: str.
+
+            - name: str. The name of the embedding model config.
+
+            - embedding_config: EmbeddingModelConfigCreateEmbeddingConfig. The embedding configuration for the embedding model config.
+        ---
+        from llama_cloud import (
+            EmbeddingModelConfigCreateEmbeddingConfig_VertexaiEmbedding,
+        )
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.embedding_model_configs.create_embedding_model_config(
+            project_id="project_id",
+            name="name",
+            embedding_config=EmbeddingModelConfigCreateEmbeddingConfig_VertexaiEmbedding(
+                type="VERTEXAI_EMBEDDING",
+            ),
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "POST",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/embedding-model-configs"),
+            params=remove_none_from_dict({"project_id": project_id}),
+            json=jsonable_encoder({"name": name, "embedding_config": embedding_config}),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(EmbeddingModelConfig, _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 upsert_embedding_model_config(
+        self,
+        *,
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
+        request: EmbeddingModelConfigUpdate,
+    ) -> EmbeddingModelConfig:
+        """
+        Upserts an embedding model config.
+        Updates if an embedding model config with the same name and project_id already exists. Otherwise, creates a new embedding model config.
+
+        Parameters:
+            - project_id: typing.Optional[str].
+
+            - organization_id: typing.Optional[str].
+
+            - request: EmbeddingModelConfigUpdate.
+        ---
+        from llama_cloud import EmbeddingModelConfigUpdate
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.embedding_model_configs.upsert_embedding_model_config(
+            request=EmbeddingModelConfigUpdate(),
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "PUT",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/embedding-model-configs"),
+            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
+            json=jsonable_encoder(request),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(EmbeddingModelConfig, _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_embedding_model_config(
+        self, embedding_model_config_id: str, *, request: EmbeddingModelConfigUpdate
+    ) -> EmbeddingModelConfig:
+        """
+        Update an embedding model config by ID.
+
+        Parameters:
+            - embedding_model_config_id: str.
+
+            - request: EmbeddingModelConfigUpdate.
+        ---
+        from llama_cloud import EmbeddingModelConfigUpdate
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.embedding_model_configs.update_embedding_model_config(
+            embedding_model_config_id="embedding_model_config_id",
+            request=EmbeddingModelConfigUpdate(),
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "PUT",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/embedding-model-configs/{embedding_model_config_id}"
+            ),
+            json=jsonable_encoder(request),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(EmbeddingModelConfig, _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_embedding_model_config(self, embedding_model_config_id: str) -> None:
+        """
+        Delete an embedding model config by ID.
+
+        Parameters:
+            - embedding_model_config_id: str.
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.embedding_model_configs.delete_embedding_model_config(
+            embedding_model_config_id="embedding_model_config_id",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "DELETE",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/embedding-model-configs/{embedding_model_config_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)
+
+
+class AsyncEmbeddingModelConfigsClient:
+    def __init__(self, *, client_wrapper: AsyncClientWrapper):
+        self._client_wrapper = client_wrapper
+
+    async def list_embedding_model_configs(self, *, project_id: str) -> typing.List[EmbeddingModelConfig]:
+        """
+        Parameters:
+            - project_id: str.
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/embedding-model-configs"),
+            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[EmbeddingModelConfig], _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_embedding_model_config(
+        self, *, project_id: str, name: str, embedding_config: EmbeddingModelConfigCreateEmbeddingConfig
+    ) -> EmbeddingModelConfig:
+        """
+        Create a new embedding model configuration within a specified project.
+
+        Parameters:
+            - project_id: str.
+
+            - name: str. The name of the embedding model config.
+
+            - embedding_config: EmbeddingModelConfigCreateEmbeddingConfig. The embedding configuration for the embedding model config.
+        ---
+        from llama_cloud import (
+            EmbeddingModelConfigCreateEmbeddingConfig_VertexaiEmbedding,
+        )
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.embedding_model_configs.create_embedding_model_config(
+            project_id="project_id",
+            name="name",
+            embedding_config=EmbeddingModelConfigCreateEmbeddingConfig_VertexaiEmbedding(
+                type="VERTEXAI_EMBEDDING",
+            ),
+        )
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "POST",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/embedding-model-configs"),
+            params=remove_none_from_dict({"project_id": project_id}),
+            json=jsonable_encoder({"name": name, "embedding_config": embedding_config}),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(EmbeddingModelConfig, _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 upsert_embedding_model_config(
+        self,
+        *,
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
+        request: EmbeddingModelConfigUpdate,
+    ) -> EmbeddingModelConfig:
+        """
+        Upserts an embedding model config.
+        Updates if an embedding model config with the same name and project_id already exists. Otherwise, creates a new embedding model config.
+
+        Parameters:
+            - project_id: typing.Optional[str].
+
+            - organization_id: typing.Optional[str].
+
+            - request: EmbeddingModelConfigUpdate.
+        ---
+        from llama_cloud import EmbeddingModelConfigUpdate
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.embedding_model_configs.upsert_embedding_model_config(
+            request=EmbeddingModelConfigUpdate(),
+        )
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "PUT",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/embedding-model-configs"),
+            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
+            json=jsonable_encoder(request),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(EmbeddingModelConfig, _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_embedding_model_config(
+        self, embedding_model_config_id: str, *, request: EmbeddingModelConfigUpdate
+    ) -> EmbeddingModelConfig:
+        """
+        Update an embedding model config by ID.
+
+        Parameters:
+            - embedding_model_config_id: str.
+
+            - request: EmbeddingModelConfigUpdate.
+        ---
+        from llama_cloud import EmbeddingModelConfigUpdate
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.embedding_model_configs.update_embedding_model_config(
+            embedding_model_config_id="embedding_model_config_id",
+            request=EmbeddingModelConfigUpdate(),
+        )
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "PUT",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/embedding-model-configs/{embedding_model_config_id}"
+            ),
+            json=jsonable_encoder(request),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(EmbeddingModelConfig, _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_embedding_model_config(self, embedding_model_config_id: str) -> None:
+        """
+        Delete an embedding model config by ID.
+
+        Parameters:
+            - embedding_model_config_id: str.
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.embedding_model_configs.delete_embedding_model_config(
+            embedding_model_config_id="embedding_model_config_id",
+        )
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "DELETE",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/embedding-model-configs/{embedding_model_config_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)

llama_cloud/resources/embedding_model_configs/types/__init__.py

@@ -0,0 +1,23 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from .embedding_model_config_create_embedding_config import (
+    EmbeddingModelConfigCreateEmbeddingConfig,
+    EmbeddingModelConfigCreateEmbeddingConfig_AzureEmbedding,
+    EmbeddingModelConfigCreateEmbeddingConfig_BedrockEmbedding,
+    EmbeddingModelConfigCreateEmbeddingConfig_CohereEmbedding,
+    EmbeddingModelConfigCreateEmbeddingConfig_GeminiEmbedding,
+    EmbeddingModelConfigCreateEmbeddingConfig_HuggingfaceApiEmbedding,
+    EmbeddingModelConfigCreateEmbeddingConfig_OpenaiEmbedding,
+    EmbeddingModelConfigCreateEmbeddingConfig_VertexaiEmbedding,
+)
+
+__all__ = [
+    "EmbeddingModelConfigCreateEmbeddingConfig",
+    "EmbeddingModelConfigCreateEmbeddingConfig_AzureEmbedding",
+    "EmbeddingModelConfigCreateEmbeddingConfig_BedrockEmbedding",
+    "EmbeddingModelConfigCreateEmbeddingConfig_CohereEmbedding",
+    "EmbeddingModelConfigCreateEmbeddingConfig_GeminiEmbedding",
+    "EmbeddingModelConfigCreateEmbeddingConfig_HuggingfaceApiEmbedding",
+    "EmbeddingModelConfigCreateEmbeddingConfig_OpenaiEmbedding",
+    "EmbeddingModelConfigCreateEmbeddingConfig_VertexaiEmbedding",
+]

llama_cloud/resources/embedding_model_configs/types/embedding_model_config_create_embedding_config.py

@@ -0,0 +1,89 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from __future__ import annotations
+
+import typing
+
+import typing_extensions
+
+from ....types.azure_open_ai_embedding_config import AzureOpenAiEmbeddingConfig
+from ....types.bedrock_embedding_config import BedrockEmbeddingConfig
+from ....types.cohere_embedding_config import CohereEmbeddingConfig
+from ....types.gemini_embedding_config import GeminiEmbeddingConfig
+from ....types.hugging_face_inference_api_embedding_config import HuggingFaceInferenceApiEmbeddingConfig
+from ....types.open_ai_embedding_config import OpenAiEmbeddingConfig
+from ....types.vertex_ai_embedding_config import VertexAiEmbeddingConfig
+
+
+class EmbeddingModelConfigCreateEmbeddingConfig_AzureEmbedding(AzureOpenAiEmbeddingConfig):
+    type: typing_extensions.Literal["AZURE_EMBEDDING"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class EmbeddingModelConfigCreateEmbeddingConfig_BedrockEmbedding(BedrockEmbeddingConfig):
+    type: typing_extensions.Literal["BEDROCK_EMBEDDING"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class EmbeddingModelConfigCreateEmbeddingConfig_CohereEmbedding(CohereEmbeddingConfig):
+    type: typing_extensions.Literal["COHERE_EMBEDDING"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class EmbeddingModelConfigCreateEmbeddingConfig_GeminiEmbedding(GeminiEmbeddingConfig):
+    type: typing_extensions.Literal["GEMINI_EMBEDDING"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class EmbeddingModelConfigCreateEmbeddingConfig_HuggingfaceApiEmbedding(HuggingFaceInferenceApiEmbeddingConfig):
+    type: typing_extensions.Literal["HUGGINGFACE_API_EMBEDDING"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class EmbeddingModelConfigCreateEmbeddingConfig_OpenaiEmbedding(OpenAiEmbeddingConfig):
+    type: typing_extensions.Literal["OPENAI_EMBEDDING"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class EmbeddingModelConfigCreateEmbeddingConfig_VertexaiEmbedding(VertexAiEmbeddingConfig):
+    type: typing_extensions.Literal["VERTEXAI_EMBEDDING"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+EmbeddingModelConfigCreateEmbeddingConfig = typing.Union[
+    EmbeddingModelConfigCreateEmbeddingConfig_AzureEmbedding,
+    EmbeddingModelConfigCreateEmbeddingConfig_BedrockEmbedding,
+    EmbeddingModelConfigCreateEmbeddingConfig_CohereEmbedding,
+    EmbeddingModelConfigCreateEmbeddingConfig_GeminiEmbedding,
+    EmbeddingModelConfigCreateEmbeddingConfig_HuggingfaceApiEmbedding,
+    EmbeddingModelConfigCreateEmbeddingConfig_OpenaiEmbedding,
+    EmbeddingModelConfigCreateEmbeddingConfig_VertexaiEmbedding,
+]