llama-cloud 0.1.35__py3-none-any.whl → 0.1.36__py3-none-any.whl

llama_cloud/__init__.py

@@ -38,7 +38,12 @@ from .types import (
     ChatData,
     ChunkMode,
     ClassificationResult,
-    ClassifyResponse,
+    ClassifierRule,
+    ClassifyJob,
+    ClassifyJobResults,
+    ClassifyJobWithStatus,
+    ClassifyParsingConfiguration,
+    CloudAstraDbVectorStore,
     CloudAzStorageBlobDataSource,
     CloudAzureAiSearchVectorStore,
     CloudBoxDataSource,
@@ -132,13 +137,17 @@ from .types import (
     ExtractState,
     ExtractTarget,
     FailPageMode,
+    FailureHandlingConfig,
     File,
+    FileClassification,
     FileCountByStatusResponse,
     FileData,
     FileIdPresignedUrl,
     FileParsePublic,
     FilePermissionInfoValue,
     FileResourceInfoValue,
+    FileStoreInfoResponse,
+    FileStoreInfoResponseStatus,
     FilterCondition,
     FilterOperation,
     FilterOperationEq,
@@ -457,7 +466,12 @@ __all__ = [
     "ChatData",
     "ChunkMode",
     "ClassificationResult",
-    "ClassifyResponse",
+    "ClassifierRule",
+    "ClassifyJob",
+    "ClassifyJobResults",
+    "ClassifyJobWithStatus",
+    "ClassifyParsingConfiguration",
+    "CloudAstraDbVectorStore",
     "CloudAzStorageBlobDataSource",
     "CloudAzureAiSearchVectorStore",
     "CloudBoxDataSource",
@@ -572,7 +586,9 @@ __all__ = [
     "ExtractStatelessRequestDataSchemaZeroValue",
     "ExtractTarget",
     "FailPageMode",
+    "FailureHandlingConfig",
     "File",
+    "FileClassification",
     "FileCountByStatusResponse",
     "FileCreateFromUrlResourceInfoValue",
     "FileCreatePermissionInfoValue",
@@ -582,6 +598,8 @@ __all__ = [
     "FileParsePublic",
     "FilePermissionInfoValue",
     "FileResourceInfoValue",
+    "FileStoreInfoResponse",
+    "FileStoreInfoResponseStatus",
     "FilterCondition",
     "FilterOperation",
     "FilterOperationEq",

llama_cloud/resources/admin/client.py

@@ -8,6 +8,7 @@ from ...core.api_error import ApiError
 from ...core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
 from ...core.remove_none_from_dict import remove_none_from_dict
 from ...errors.unprocessable_entity_error import UnprocessableEntityError
+from ...types.file_store_info_response import FileStoreInfoResponse
 from ...types.http_validation_error import HttpValidationError
 from ...types.license_info_response import LicenseInfoResponse
 
@@ -53,6 +54,31 @@ class AdminClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    def get_file_store_info(self) -> FileStoreInfoResponse:
+        """
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.admin.get_file_store_info()
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/admin/filestores/info"),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(FileStoreInfoResponse, _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 AsyncAdminClient:
     def __init__(self, *, client_wrapper: AsyncClientWrapper):
@@ -86,3 +112,28 @@ class AsyncAdminClient:
         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_file_store_info(self) -> FileStoreInfoResponse:
+        """
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.admin.get_file_store_info()
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/admin/filestores/info"),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(FileStoreInfoResponse, _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/classifier/client.py

@@ -9,7 +9,11 @@ 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.classify_response import ClassifyResponse
+from ...types.classifier_rule import ClassifierRule
+from ...types.classify_job import ClassifyJob
+from ...types.classify_job_results import ClassifyJobResults
+from ...types.classify_job_with_status import ClassifyJobWithStatus
+from ...types.classify_parsing_configuration import ClassifyParsingConfiguration
 from ...types.http_validation_error import HttpValidationError
 
 try:
@@ -28,126 +32,149 @@ class ClassifierClient:
     def __init__(self, *, client_wrapper: SyncClientWrapper):
         self._client_wrapper = client_wrapper
 
-    def classify_documents(
+    def create_classify_job(
         self,
         *,
         project_id: typing.Optional[str] = None,
         organization_id: typing.Optional[str] = None,
-        rules_json: str,
-        files: typing.Optional[typing.List[str]] = OMIT,
-        file_ids: typing.Optional[str] = OMIT,
-        matching_threshold: typing.Optional[float] = OMIT,
-        enable_metadata_heuristic: typing.Optional[bool] = OMIT,
-    ) -> ClassifyResponse:
+        rules: typing.List[ClassifierRule],
+        file_ids: typing.List[str],
+        parsing_configuration: typing.Optional[ClassifyParsingConfiguration] = OMIT,
+    ) -> ClassifyJob:
         """
-        **[BETA]** Classify documents based on provided rules - simplified classification system.
+        Create a classify job.
+        Experimental: This endpoint is not yet ready for production use and is subject to change at any time.
 
-        **This is a Beta feature** - API may change based on user feedback.
-
-        This endpoint supports:
-
-        - Classifying new uploaded files
-        - Classifying existing files by ID
-        - Both new files and existing file IDs in one request
-
-        ## v0 Features:
-
-        - **Simplified Rules**: Only `type` and `description` fields needed
-        - **Matching Threshold**: Confidence-based classification with configurable threshold
-        - **Smart Classification**: Filename heuristics + LLM content analysis
-        - **Document Type Filtering**: Automatically filters out non-document file types
-        - **Fast Processing**: Uses LlamaParse fast mode + GPT-4.1-nano
-        - **Optimized Performance**: Parses each file only once for all rules
-
-        ## Simplified Scoring Logic:
-
-        1. **Evaluate All Rules**: Compare document against all classification rules
-        2. **Best Match Selection**: Return the highest scoring rule above matching_threshold
-        3. **Unknown Classification**: Return as "unknown" if no rules score above threshold
-
-        This ensures optimal classification by:
-
-        - Finding the best possible match among all rules
-        - Avoiding false positives with confidence thresholds
-        - Maximizing performance with single-pass file parsing
+        Parameters:
+            - project_id: typing.Optional[str].
 
-        ## Rule Format:
+            - organization_id: typing.Optional[str].
 
-        ```json
-        [
-          {
-            "type": "invoice",
-            "description": "contains invoice number, line items, and total amount"
-          },
-          {
-            "type": "receipt",
-            "description": "purchase receipt with transaction details and payment info"
-          }
-        ]
-        ```
+            - rules: typing.List[ClassifierRule]. The rules to classify the files
 
-        ## Classification Process:
+            - file_ids: typing.List[str]. The IDs of the files to classify
 
-        1. **Metadata Heuristics** (configurable via API):
-           - **Document Type Filter**: Only process document file types (PDF, DOC, DOCX, RTF, TXT, ODT, Pages, HTML, XML, Markdown)
-           - **Filename Heuristics**: Check if rule type appears in filename
-           - **Content Analysis**: Parse document content once and use LLM for semantic matching against all rules
-        2. **Result**: Returns type, confidence score, and matched rule information
+            - parsing_configuration: typing.Optional[ClassifyParsingConfiguration]. The configuration for the parsing job
+        ---
+        from llama_cloud import ClassifyParsingConfiguration, ParserLanguages
+        from llama_cloud.client import LlamaCloud
 
-        ## API Parameters:
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.classifier.create_classify_job(
+            rules=[],
+            file_ids=[],
+            parsing_configuration=ClassifyParsingConfiguration(
+                lang=ParserLanguages.AF,
+            ),
+        )
+        """
+        _request: typing.Dict[str, typing.Any] = {"rules": rules, "file_ids": file_ids}
+        if parsing_configuration is not OMIT:
+            _request["parsing_configuration"] = parsing_configuration
+        _response = self._client_wrapper.httpx_client.request(
+            "POST",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/classifier/jobs"),
+            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(ClassifyJob, _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)
 
-        - `matching_threshold` (0.1-0.99, default: 0.6): Minimum confidence threshold for acceptable matches
-        - `enable_metadata_heuristic` (boolean, default: true): Enable metadata-based features
+    def get_classify_job(
+        self,
+        classify_job_id: str,
+        *,
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
+    ) -> ClassifyJobWithStatus:
+        """
+        Get a classify job.
+        Experimental: This endpoint is not yet ready for production use and is subject to change at any time.
 
-        ## Supported Document Types:
+        Parameters:
+            - classify_job_id: str.
 
-        **Text Documents**: pdf, doc, docx, rtf, txt, odt, pages
-        **Web Documents**: html, htm, xml
-        **Markup**: md, markdown
+            - project_id: typing.Optional[str].
 
-        ## Limits (Beta):
+            - organization_id: typing.Optional[str].
+        ---
+        from llama_cloud.client import LlamaCloud
 
-        - Maximum 100 files per request
-        - Maximum 10 rules per request
-        - Rule descriptions: 10-500 characters
-        - Document types: 1-50 characters (alphanumeric, hyphens, underscores)
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.classifier.get_classify_job(
+            classify_job_id="string",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/classifier/jobs/{classify_job_id}"
+            ),
+            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ClassifyJobWithStatus, _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)
 
-        **Beta Notice**: This API is subject to change. Please provide feedback!
+    def get_classification_job_results(
+        self,
+        classify_job_id: str,
+        *,
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
+    ) -> ClassifyJobResults:
+        """
+        Get the results of a classify job.
+        Experimental: This endpoint is not yet ready for production use and is subject to change at any time.
 
         Parameters:
+            - classify_job_id: str.
+
             - project_id: typing.Optional[str].
 
             - organization_id: typing.Optional[str].
+        ---
+        from llama_cloud.client import LlamaCloud
 
-            - rules_json: str. JSON string containing classifier rules
-
-            - files: typing.Optional[typing.List[str]].
-
-            - file_ids: typing.Optional[str].
-
-            - matching_threshold: typing.Optional[float].
-
-            - enable_metadata_heuristic: typing.Optional[bool].
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.classifier.get_classification_job_results(
+            classify_job_id="string",
+        )
         """
-        _request: typing.Dict[str, typing.Any] = {"rules_json": rules_json}
-        if files is not OMIT:
-            _request["files"] = files
-        if file_ids is not OMIT:
-            _request["file_ids"] = file_ids
-        if matching_threshold is not OMIT:
-            _request["matching_threshold"] = matching_threshold
-        if enable_metadata_heuristic is not OMIT:
-            _request["enable_metadata_heuristic"] = enable_metadata_heuristic
         _response = self._client_wrapper.httpx_client.request(
-            "POST",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/classifier/classify"),
+            "GET",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/classifier/jobs/{classify_job_id}/results"
+            ),
             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(ClassifyResponse, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ClassifyJobResults, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -161,126 +188,149 @@ class AsyncClassifierClient:
     def __init__(self, *, client_wrapper: AsyncClientWrapper):
         self._client_wrapper = client_wrapper
 
-    async def classify_documents(
+    async def create_classify_job(
         self,
         *,
         project_id: typing.Optional[str] = None,
         organization_id: typing.Optional[str] = None,
-        rules_json: str,
-        files: typing.Optional[typing.List[str]] = OMIT,
-        file_ids: typing.Optional[str] = OMIT,
-        matching_threshold: typing.Optional[float] = OMIT,
-        enable_metadata_heuristic: typing.Optional[bool] = OMIT,
-    ) -> ClassifyResponse:
+        rules: typing.List[ClassifierRule],
+        file_ids: typing.List[str],
+        parsing_configuration: typing.Optional[ClassifyParsingConfiguration] = OMIT,
+    ) -> ClassifyJob:
         """
-        **[BETA]** Classify documents based on provided rules - simplified classification system.
+        Create a classify job.
+        Experimental: This endpoint is not yet ready for production use and is subject to change at any time.
 
-        **This is a Beta feature** - API may change based on user feedback.
-
-        This endpoint supports:
-
-        - Classifying new uploaded files
-        - Classifying existing files by ID
-        - Both new files and existing file IDs in one request
-
-        ## v0 Features:
-
-        - **Simplified Rules**: Only `type` and `description` fields needed
-        - **Matching Threshold**: Confidence-based classification with configurable threshold
-        - **Smart Classification**: Filename heuristics + LLM content analysis
-        - **Document Type Filtering**: Automatically filters out non-document file types
-        - **Fast Processing**: Uses LlamaParse fast mode + GPT-4.1-nano
-        - **Optimized Performance**: Parses each file only once for all rules
-
-        ## Simplified Scoring Logic:
-
-        1. **Evaluate All Rules**: Compare document against all classification rules
-        2. **Best Match Selection**: Return the highest scoring rule above matching_threshold
-        3. **Unknown Classification**: Return as "unknown" if no rules score above threshold
-
-        This ensures optimal classification by:
-
-        - Finding the best possible match among all rules
-        - Avoiding false positives with confidence thresholds
-        - Maximizing performance with single-pass file parsing
+        Parameters:
+            - project_id: typing.Optional[str].
 
-        ## Rule Format:
+            - organization_id: typing.Optional[str].
 
-        ```json
-        [
-          {
-            "type": "invoice",
-            "description": "contains invoice number, line items, and total amount"
-          },
-          {
-            "type": "receipt",
-            "description": "purchase receipt with transaction details and payment info"
-          }
-        ]
-        ```
+            - rules: typing.List[ClassifierRule]. The rules to classify the files
 
-        ## Classification Process:
+            - file_ids: typing.List[str]. The IDs of the files to classify
 
-        1. **Metadata Heuristics** (configurable via API):
-           - **Document Type Filter**: Only process document file types (PDF, DOC, DOCX, RTF, TXT, ODT, Pages, HTML, XML, Markdown)
-           - **Filename Heuristics**: Check if rule type appears in filename
-           - **Content Analysis**: Parse document content once and use LLM for semantic matching against all rules
-        2. **Result**: Returns type, confidence score, and matched rule information
+            - parsing_configuration: typing.Optional[ClassifyParsingConfiguration]. The configuration for the parsing job
+        ---
+        from llama_cloud import ClassifyParsingConfiguration, ParserLanguages
+        from llama_cloud.client import AsyncLlamaCloud
 
-        ## API Parameters:
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.classifier.create_classify_job(
+            rules=[],
+            file_ids=[],
+            parsing_configuration=ClassifyParsingConfiguration(
+                lang=ParserLanguages.AF,
+            ),
+        )
+        """
+        _request: typing.Dict[str, typing.Any] = {"rules": rules, "file_ids": file_ids}
+        if parsing_configuration is not OMIT:
+            _request["parsing_configuration"] = parsing_configuration
+        _response = await self._client_wrapper.httpx_client.request(
+            "POST",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/classifier/jobs"),
+            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(ClassifyJob, _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)
 
-        - `matching_threshold` (0.1-0.99, default: 0.6): Minimum confidence threshold for acceptable matches
-        - `enable_metadata_heuristic` (boolean, default: true): Enable metadata-based features
+    async def get_classify_job(
+        self,
+        classify_job_id: str,
+        *,
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
+    ) -> ClassifyJobWithStatus:
+        """
+        Get a classify job.
+        Experimental: This endpoint is not yet ready for production use and is subject to change at any time.
 
-        ## Supported Document Types:
+        Parameters:
+            - classify_job_id: str.
 
-        **Text Documents**: pdf, doc, docx, rtf, txt, odt, pages
-        **Web Documents**: html, htm, xml
-        **Markup**: md, markdown
+            - project_id: typing.Optional[str].
 
-        ## Limits (Beta):
+            - organization_id: typing.Optional[str].
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
 
-        - Maximum 100 files per request
-        - Maximum 10 rules per request
-        - Rule descriptions: 10-500 characters
-        - Document types: 1-50 characters (alphanumeric, hyphens, underscores)
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.classifier.get_classify_job(
+            classify_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/classifier/jobs/{classify_job_id}"
+            ),
+            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ClassifyJobWithStatus, _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)
 
-        **Beta Notice**: This API is subject to change. Please provide feedback!
+    async def get_classification_job_results(
+        self,
+        classify_job_id: str,
+        *,
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
+    ) -> ClassifyJobResults:
+        """
+        Get the results of a classify job.
+        Experimental: This endpoint is not yet ready for production use and is subject to change at any time.
 
         Parameters:
+            - classify_job_id: str.
+
             - project_id: typing.Optional[str].
 
             - organization_id: typing.Optional[str].
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
 
-            - rules_json: str. JSON string containing classifier rules
-
-            - files: typing.Optional[typing.List[str]].
-
-            - file_ids: typing.Optional[str].
-
-            - matching_threshold: typing.Optional[float].
-
-            - enable_metadata_heuristic: typing.Optional[bool].
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.classifier.get_classification_job_results(
+            classify_job_id="string",
+        )
         """
-        _request: typing.Dict[str, typing.Any] = {"rules_json": rules_json}
-        if files is not OMIT:
-            _request["files"] = files
-        if file_ids is not OMIT:
-            _request["file_ids"] = file_ids
-        if matching_threshold is not OMIT:
-            _request["matching_threshold"] = matching_threshold
-        if enable_metadata_heuristic is not OMIT:
-            _request["enable_metadata_heuristic"] = enable_metadata_heuristic
         _response = await self._client_wrapper.httpx_client.request(
-            "POST",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/classifier/classify"),
+            "GET",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/classifier/jobs/{classify_job_id}/results"
+            ),
             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(ClassifyResponse, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ClassifyJobResults, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:

llama_cloud/resources/data_sinks/types/data_sink_update_component.py

@@ -2,6 +2,7 @@
 
 import typing
 
+from ....types.cloud_astra_db_vector_store import CloudAstraDbVectorStore
 from ....types.cloud_azure_ai_search_vector_store import CloudAzureAiSearchVectorStore
 from ....types.cloud_milvus_vector_store import CloudMilvusVectorStore
 from ....types.cloud_mongo_db_atlas_vector_search import CloudMongoDbAtlasVectorSearch
@@ -17,4 +18,5 @@ DataSinkUpdateComponent = typing.Union[
     CloudAzureAiSearchVectorStore,
     CloudMongoDbAtlasVectorSearch,
     CloudMilvusVectorStore,
+    CloudAstraDbVectorStore,
 ]