llama-cloud 0.0.10__tar.gz → 0.0.11__tar.gz

{llama_cloud-0.0.10 → llama_cloud-0.0.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: llama-cloud
-Version: 0.0.10
+Version: 0.0.11
 Summary: 
 Author: Logan Markewich
 Author-email: logan@runllama.ai

{llama_cloud-0.0.10 → llama_cloud-0.0.11}/llama_cloud/__init__.py

@@ -1,6 +1,7 @@
 # This file was auto-generated by Fern from our API Definition.
 
 from .types import (
+    AutoTransformConfig,
     AzureOpenAiEmbedding,
     Base,
     BasePromptTemplate,
@@ -48,6 +49,9 @@ from .types import (
     DataSourceCreateCustomMetadataValue,
     DataSourceCustomMetadataValue,
     DataSourceDefinition,
+    EmbeddingConfig,
+    EmbeddingConfigComponent,
+    EmbeddingConfigType,
     EvalDataset,
     EvalDatasetJobParams,
     EvalDatasetJobRecord,
@@ -134,6 +138,8 @@ from .types import (
     TextNodeRelationshipsValue,
     TextNodeWithScore,
     TokenTextSplitter,
+    TransformConfig,
+    TransformConfigMode,
     TransformationCategoryNames,
     UserOrganization,
     UserOrganizationCreate,
@@ -148,6 +154,7 @@ from .resources import (
     DataSourceUpdateComponent,
     DataSourceUpdateComponentOne,
     DataSourceUpdateCustomMetadataValue,
+    ExtractionSchemaCreateDataSchemaValue,
     ExtractionSchemaUpdateDataSchemaValue,
     FileCreateResourceInfoValue,
     PipelineFileUpdateCustomMetadataValue,
@@ -165,6 +172,7 @@ from .resources import (
 from .environment import LlamaCloudEnvironment
 
 __all__ = [
+    "AutoTransformConfig",
     "AzureOpenAiEmbedding",
     "Base",
     "BasePromptTemplate",
@@ -217,6 +225,9 @@ __all__ = [
     "DataSourceUpdateComponent",
     "DataSourceUpdateComponentOne",
     "DataSourceUpdateCustomMetadataValue",
+    "EmbeddingConfig",
+    "EmbeddingConfigComponent",
+    "EmbeddingConfigType",
     "EvalDataset",
     "EvalDatasetJobParams",
     "EvalDatasetJobRecord",
@@ -230,6 +241,7 @@ __all__ = [
     "ExtractionResult",
     "ExtractionResultDataValue",
     "ExtractionSchema",
+    "ExtractionSchemaCreateDataSchemaValue",
     "ExtractionSchemaDataSchemaValue",
     "ExtractionSchemaUpdateDataSchemaValue",
     "File",
@@ -307,6 +319,8 @@ __all__ = [
     "TextNodeRelationshipsValue",
     "TextNodeWithScore",
     "TokenTextSplitter",
+    "TransformConfig",
+    "TransformConfigMode",
     "TransformationCategoryNames",
     "UnprocessableEntityError",
     "UserOrganization",

{llama_cloud-0.0.10 → llama_cloud-0.0.11}/llama_cloud/resources/__init__.py

@@ -14,7 +14,7 @@ from . import (
 )
 from .data_sinks import DataSinkUpdateComponent, DataSinkUpdateComponentOne
 from .data_sources import DataSourceUpdateComponent, DataSourceUpdateComponentOne, DataSourceUpdateCustomMetadataValue
-from .extraction import ExtractionSchemaUpdateDataSchemaValue
+from .extraction import ExtractionSchemaCreateDataSchemaValue, ExtractionSchemaUpdateDataSchemaValue
 from .files import FileCreateResourceInfoValue
 from .pipelines import PipelineFileUpdateCustomMetadataValue
 
@@ -24,6 +24,7 @@ __all__ = [
     "DataSourceUpdateComponent",
     "DataSourceUpdateComponentOne",
     "DataSourceUpdateCustomMetadataValue",
+    "ExtractionSchemaCreateDataSchemaValue",
     "ExtractionSchemaUpdateDataSchemaValue",
     "FileCreateResourceInfoValue",
     "PipelineFileUpdateCustomMetadataValue",

llama_cloud-0.0.11/llama_cloud/resources/extraction/__init__.py

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

{llama_cloud-0.0.10 → llama_cloud-0.0.11}/llama_cloud/resources/extraction/client.py

@@ -13,6 +13,7 @@ from ...types.extraction_job import ExtractionJob
 from ...types.extraction_result import ExtractionResult
 from ...types.extraction_schema import ExtractionSchema
 from ...types.http_validation_error import HttpValidationError
+from .types.extraction_schema_create_data_schema_value import ExtractionSchemaCreateDataSchemaValue
 from .types.extraction_schema_update_data_schema_value import ExtractionSchemaUpdateDataSchemaValue
 
 try:
@@ -31,47 +32,66 @@ class ExtractionClient:
     def __init__(self, *, client_wrapper: SyncClientWrapper):
         self._client_wrapper = client_wrapper
 
-    def infer_schema(
+    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 create_schema(
         self,
         *,
-        schema_id: typing.Optional[str] = OMIT,
         name: str,
         project_id: typing.Optional[str] = OMIT,
-        file_ids: typing.List[str],
-        stream: typing.Optional[bool] = OMIT,
+        data_schema: typing.Dict[str, ExtractionSchemaCreateDataSchemaValue],
     ) -> ExtractionSchema:
         """
         Parameters:
-            - schema_id: typing.Optional[str]. The ID of a schema to update with the new schema
-
             - 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
-
-            - stream: typing.Optional[bool]. Whether to stream the results of the extraction schema
+            - data_schema: typing.Dict[str, ExtractionSchemaCreateDataSchemaValue]. The schema of the data
         ---
         from llama_cloud.client import LlamaCloud
 
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.extraction.infer_schema(
+        client.extraction.create_schema(
             name="string",
-            file_ids=[],
+            data_schema={},
         )
         """
-        _request: typing.Dict[str, typing.Any] = {"name": name, "file_ids": file_ids}
-        if schema_id is not OMIT:
-            _request["schema_id"] = schema_id
+        _request: typing.Dict[str, typing.Any] = {"name": name, "data_schema": data_schema}
         if project_id is not OMIT:
             _request["project_id"] = project_id
-        if stream is not OMIT:
-            _request["stream"] = stream
         _response = self._client_wrapper.httpx_client.request(
             "POST",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/schemas/infer"),
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/schemas"),
             json=jsonable_encoder(_request),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
@@ -86,27 +106,53 @@ class ExtractionClient:
             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]:
+    def infer_schema(
+        self,
+        *,
+        schema_id: typing.Optional[str] = OMIT,
+        name: str,
+        project_id: typing.Optional[str] = OMIT,
+        file_ids: typing.List[str],
+        stream: typing.Optional[bool] = OMIT,
+    ) -> ExtractionSchema:
         """
         Parameters:
-            - project_id: typing.Optional[str].
+            - schema_id: typing.Optional[str]. The ID of a schema to update with the new schema
+
+            - 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
+
+            - stream: typing.Optional[bool]. Whether to stream the results of the extraction schema
         ---
         from llama_cloud.client import LlamaCloud
 
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.extraction.list_schemas()
+        client.extraction.infer_schema(
+            name="string",
+            file_ids=[],
+        )
         """
+        _request: typing.Dict[str, typing.Any] = {"name": name, "file_ids": file_ids}
+        if schema_id is not OMIT:
+            _request["schema_id"] = schema_id
+        if project_id is not OMIT:
+            _request["project_id"] = project_id
+        if stream is not OMIT:
+            _request["stream"] = stream
         _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}),
+            "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(typing.List[ExtractionSchema], _response.json())  # type: ignore
+            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:
@@ -350,47 +396,66 @@ class AsyncExtractionClient:
     def __init__(self, *, client_wrapper: AsyncClientWrapper):
         self._client_wrapper = client_wrapper
 
-    async def infer_schema(
+    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 create_schema(
         self,
         *,
-        schema_id: typing.Optional[str] = OMIT,
         name: str,
         project_id: typing.Optional[str] = OMIT,
-        file_ids: typing.List[str],
-        stream: typing.Optional[bool] = OMIT,
+        data_schema: typing.Dict[str, ExtractionSchemaCreateDataSchemaValue],
     ) -> ExtractionSchema:
         """
         Parameters:
-            - schema_id: typing.Optional[str]. The ID of a schema to update with the new schema
-
             - 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
-
-            - stream: typing.Optional[bool]. Whether to stream the results of the extraction schema
+            - data_schema: typing.Dict[str, ExtractionSchemaCreateDataSchemaValue]. The schema of the data
         ---
         from llama_cloud.client import AsyncLlamaCloud
 
         client = AsyncLlamaCloud(
             token="YOUR_TOKEN",
         )
-        await client.extraction.infer_schema(
+        await client.extraction.create_schema(
             name="string",
-            file_ids=[],
+            data_schema={},
         )
         """
-        _request: typing.Dict[str, typing.Any] = {"name": name, "file_ids": file_ids}
-        if schema_id is not OMIT:
-            _request["schema_id"] = schema_id
+        _request: typing.Dict[str, typing.Any] = {"name": name, "data_schema": data_schema}
         if project_id is not OMIT:
             _request["project_id"] = project_id
-        if stream is not OMIT:
-            _request["stream"] = stream
         _response = await self._client_wrapper.httpx_client.request(
             "POST",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/schemas/infer"),
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/schemas"),
             json=jsonable_encoder(_request),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
@@ -405,27 +470,53 @@ class AsyncExtractionClient:
             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]:
+    async def infer_schema(
+        self,
+        *,
+        schema_id: typing.Optional[str] = OMIT,
+        name: str,
+        project_id: typing.Optional[str] = OMIT,
+        file_ids: typing.List[str],
+        stream: typing.Optional[bool] = OMIT,
+    ) -> ExtractionSchema:
         """
         Parameters:
-            - project_id: typing.Optional[str].
+            - schema_id: typing.Optional[str]. The ID of a schema to update with the new schema
+
+            - 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
+
+            - stream: typing.Optional[bool]. Whether to stream the results of the extraction schema
         ---
         from llama_cloud.client import AsyncLlamaCloud
 
         client = AsyncLlamaCloud(
             token="YOUR_TOKEN",
         )
-        await client.extraction.list_schemas()
+        await client.extraction.infer_schema(
+            name="string",
+            file_ids=[],
+        )
         """
+        _request: typing.Dict[str, typing.Any] = {"name": name, "file_ids": file_ids}
+        if schema_id is not OMIT:
+            _request["schema_id"] = schema_id
+        if project_id is not OMIT:
+            _request["project_id"] = project_id
+        if stream is not OMIT:
+            _request["stream"] = stream
         _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}),
+            "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(typing.List[ExtractionSchema], _response.json())  # type: ignore
+            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:

llama_cloud-0.0.11/llama_cloud/resources/extraction/types/__init__.py

@@ -0,0 +1,6 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from .extraction_schema_create_data_schema_value import ExtractionSchemaCreateDataSchemaValue
+from .extraction_schema_update_data_schema_value import ExtractionSchemaUpdateDataSchemaValue
+
+__all__ = ["ExtractionSchemaCreateDataSchemaValue", "ExtractionSchemaUpdateDataSchemaValue"]

llama_cloud-0.0.11/llama_cloud/resources/extraction/types/extraction_schema_create_data_schema_value.py

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