llama-cloud 0.1.41__py3-none-any.whl → 0.1.43__py3-none-any.whl

llama_cloud/resources/llama_extract/client.py

@@ -12,19 +12,19 @@ from ...errors.unprocessable_entity_error import UnprocessableEntityError
 from ...types.extract_agent import ExtractAgent
 from ...types.extract_config import ExtractConfig
 from ...types.extract_job import ExtractJob
-from ...types.extract_job_create import ExtractJobCreate
 from ...types.extract_resultset import ExtractResultset
 from ...types.extract_run import ExtractRun
 from ...types.extract_schema_generate_response import ExtractSchemaGenerateResponse
 from ...types.extract_schema_validate_response import ExtractSchemaValidateResponse
 from ...types.file_data import FileData
 from ...types.http_validation_error import HttpValidationError
-from ...types.llama_extract_settings import LlamaExtractSettings
 from ...types.paginated_extract_runs_response import PaginatedExtractRunsResponse
 from ...types.webhook_configuration import WebhookConfiguration
 from .types.extract_agent_create_data_schema import ExtractAgentCreateDataSchema
 from .types.extract_agent_update_data_schema import ExtractAgentUpdateDataSchema
 from .types.extract_job_create_batch_data_schema_override import ExtractJobCreateBatchDataSchemaOverride
+from .types.extract_job_create_data_schema_override import ExtractJobCreateDataSchemaOverride
+from .types.extract_job_create_priority import ExtractJobCreatePriority
 from .types.extract_schema_validate_request_data_schema import ExtractSchemaValidateRequestDataSchema
 from .types.extract_stateless_request_data_schema import ExtractStatelessRequestDataSchema
 
@@ -44,39 +44,29 @@ class LlamaExtractClient:
     def __init__(self, *, client_wrapper: SyncClientWrapper):
         self._client_wrapper = client_wrapper
 
-    def list_extraction_agents(
-        self,
-        *,
-        include_default: typing.Optional[bool] = None,
-        project_id: typing.Optional[str] = None,
-        organization_id: typing.Optional[str] = None,
-    ) -> typing.List[ExtractAgent]:
+    def list_jobs(self, *, extraction_agent_id: str) -> typing.List[ExtractJob]:
         """
         Parameters:
-            - include_default: typing.Optional[bool]. Whether to include default agents in the results
-
-            - project_id: typing.Optional[str].
-
-            - organization_id: typing.Optional[str].
+            - extraction_agent_id: str.
         ---
         from llama_cloud.client import LlamaCloud
 
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.llama_extract.list_extraction_agents()
+        client.llama_extract.list_jobs(
+            extraction_agent_id="string",
+        )
         """
         _response = self._client_wrapper.httpx_client.request(
             "GET",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents"),
-            params=remove_none_from_dict(
-                {"include_default": include_default, "project_id": project_id, "organization_id": organization_id}
-            ),
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs"),
+            params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(typing.List[ExtractAgent], _response.json())  # type: ignore
+            return pydantic.parse_obj_as(typing.List[ExtractJob], _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -85,31 +75,38 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def create_extraction_agent(
+    def run_job(
         self,
         *,
-        project_id: typing.Optional[str] = None,
-        organization_id: typing.Optional[str] = None,
-        name: str,
-        data_schema: ExtractAgentCreateDataSchema,
-        config: ExtractConfig,
-    ) -> ExtractAgent:
+        from_ui: typing.Optional[bool] = None,
+        priority: typing.Optional[ExtractJobCreatePriority] = OMIT,
+        webhook_configurations: typing.Optional[typing.List[WebhookConfiguration]] = OMIT,
+        extraction_agent_id: str,
+        file_id: str,
+        data_schema_override: typing.Optional[ExtractJobCreateDataSchemaOverride] = OMIT,
+        config_override: typing.Optional[ExtractConfig] = OMIT,
+    ) -> ExtractJob:
         """
         Parameters:
-            - project_id: typing.Optional[str].
+            - from_ui: typing.Optional[bool].
 
-            - organization_id: typing.Optional[str].
+            - priority: typing.Optional[ExtractJobCreatePriority].
 
-            - name: str. The name of the extraction schema
+            - webhook_configurations: typing.Optional[typing.List[WebhookConfiguration]].
 
-            - data_schema: ExtractAgentCreateDataSchema. The schema of the data.
+            - extraction_agent_id: str. The id of the extraction agent
 
-            - config: ExtractConfig. The configuration parameters for the extraction agent.
+            - file_id: str. The id of the file
+
+            - data_schema_override: typing.Optional[ExtractJobCreateDataSchemaOverride]. The data schema to override the extraction agent's data schema with
+
+            - config_override: typing.Optional[ExtractConfig].
         ---
         from llama_cloud import (
             DocumentChunkMode,
             ExtractConfig,
             ExtractConfigPriority,
+            ExtractJobCreatePriority,
             ExtractMode,
             ExtractModels,
             ExtractTarget,
@@ -120,9 +117,11 @@ class LlamaExtractClient:
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.llama_extract.create_extraction_agent(
-            name="string",
-            config=ExtractConfig(
+        client.llama_extract.run_job(
+            priority=ExtractJobCreatePriority.LOW,
+            extraction_agent_id="string",
+            file_id="string",
+            config_override=ExtractConfig(
                 priority=ExtractConfigPriority.LOW,
                 extraction_target=ExtractTarget.PER_DOC,
                 extraction_mode=ExtractMode.FAST,
@@ -132,16 +131,25 @@ class LlamaExtractClient:
             ),
         )
         """
+        _request: typing.Dict[str, typing.Any] = {"extraction_agent_id": extraction_agent_id, "file_id": file_id}
+        if priority is not OMIT:
+            _request["priority"] = priority
+        if webhook_configurations is not OMIT:
+            _request["webhook_configurations"] = webhook_configurations
+        if data_schema_override is not OMIT:
+            _request["data_schema_override"] = data_schema_override
+        if config_override is not OMIT:
+            _request["config_override"] = config_override
         _response = self._client_wrapper.httpx_client.request(
             "POST",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents"),
-            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
-            json=jsonable_encoder({"name": name, "data_schema": data_schema, "config": config}),
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs"),
+            params=remove_none_from_dict({"from_ui": from_ui}),
+            json=jsonable_encoder(_request),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(ExtractAgent, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ExtractJob, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -150,34 +158,74 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def validate_extraction_schema(
-        self, *, data_schema: ExtractSchemaValidateRequestDataSchema
-    ) -> ExtractSchemaValidateResponse:
+    def get_job(self, job_id: str) -> ExtractJob:
         """
-        Validates an extraction agent's schema definition.
-        Returns the normalized and validated schema if valid, otherwise raises an HTTP 400.
-
         Parameters:
-            - data_schema: ExtractSchemaValidateRequestDataSchema.
+            - job_id: str.
         ---
         from llama_cloud.client import LlamaCloud
 
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.llama_extract.validate_extraction_schema()
+        client.llama_extract.get_job(
+            job_id="string",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/jobs/{job_id}"),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExtractJob, _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 run_job_on_file(
+        self,
+        *,
+        from_ui: typing.Optional[bool] = None,
+        extraction_agent_id: str,
+        file: typing.IO,
+        data_schema_override: typing.Optional[str] = None,
+        config_override: typing.Optional[str] = None,
+    ) -> ExtractJob:
+        """
+        Parameters:
+            - from_ui: typing.Optional[bool].
+
+            - extraction_agent_id: str.
+
+            - file: typing.IO.
+
+            - data_schema_override: typing.Optional[str].
+
+            - config_override: typing.Optional[str].
         """
         _response = self._client_wrapper.httpx_client.request(
             "POST",
-            urllib.parse.urljoin(
-                f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents/schema/validation"
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs/file"),
+            params=remove_none_from_dict({"from_ui": from_ui}),
+            data=jsonable_encoder(
+                {
+                    "extraction_agent_id": extraction_agent_id,
+                    "data_schema_override": data_schema_override,
+                    "config_override": config_override,
+                }
             ),
-            json=jsonable_encoder({"data_schema": data_schema}),
+            files={"file": file},
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(ExtractSchemaValidateResponse, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ExtractJob, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -186,50 +234,69 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def generate_extraction_schema(
+    def run_batch_jobs(
         self,
         *,
-        project_id: typing.Optional[str] = None,
-        organization_id: typing.Optional[str] = None,
-        prompt: typing.Optional[str] = OMIT,
-        file_id: typing.Optional[str] = OMIT,
-    ) -> ExtractSchemaGenerateResponse:
+        from_ui: typing.Optional[bool] = None,
+        extraction_agent_id: str,
+        file_ids: typing.List[str],
+        data_schema_override: typing.Optional[ExtractJobCreateBatchDataSchemaOverride] = OMIT,
+        config_override: typing.Optional[ExtractConfig] = OMIT,
+    ) -> typing.List[ExtractJob]:
         """
-        Generates an extraction agent's schema definition from a file and/or natural language prompt.
-
         Parameters:
-            - project_id: typing.Optional[str].
+            - from_ui: typing.Optional[bool].
 
-            - organization_id: typing.Optional[str].
+            - extraction_agent_id: str. The id of the extraction agent
 
-            - prompt: typing.Optional[str].
+            - file_ids: typing.List[str]. The ids of the files
 
-            - file_id: typing.Optional[str].
+            - data_schema_override: typing.Optional[ExtractJobCreateBatchDataSchemaOverride]. The data schema to override the extraction agent's data schema with
+
+            - config_override: typing.Optional[ExtractConfig].
         ---
+        from llama_cloud import (
+            DocumentChunkMode,
+            ExtractConfig,
+            ExtractConfigPriority,
+            ExtractMode,
+            ExtractModels,
+            ExtractTarget,
+            PublicModelName,
+        )
         from llama_cloud.client import LlamaCloud
 
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.llama_extract.generate_extraction_schema()
+        client.llama_extract.run_batch_jobs(
+            extraction_agent_id="string",
+            file_ids=[],
+            config_override=ExtractConfig(
+                priority=ExtractConfigPriority.LOW,
+                extraction_target=ExtractTarget.PER_DOC,
+                extraction_mode=ExtractMode.FAST,
+                parse_model=PublicModelName.OPENAI_GPT_4_O,
+                extract_model=ExtractModels.OPENAI_GPT_4_1,
+                chunk_mode=DocumentChunkMode.PAGE,
+            ),
+        )
         """
-        _request: typing.Dict[str, typing.Any] = {}
-        if prompt is not OMIT:
-            _request["prompt"] = prompt
-        if file_id is not OMIT:
-            _request["file_id"] = file_id
+        _request: typing.Dict[str, typing.Any] = {"extraction_agent_id": extraction_agent_id, "file_ids": file_ids}
+        if data_schema_override is not OMIT:
+            _request["data_schema_override"] = data_schema_override
+        if config_override is not OMIT:
+            _request["config_override"] = config_override
         _response = self._client_wrapper.httpx_client.request(
             "POST",
-            urllib.parse.urljoin(
-                f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents/schema/generate"
-            ),
-            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs/batch"),
+            params=remove_none_from_dict({"from_ui": from_ui}),
             json=jsonable_encoder(_request),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(ExtractSchemaGenerateResponse, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(typing.List[ExtractJob], _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -238,12 +305,12 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def get_extraction_agent_by_name(
-        self, name: str, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
-    ) -> ExtractAgent:
+    def get_job_result(
+        self, job_id: str, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
+    ) -> ExtractResultset:
         """
         Parameters:
-            - name: str.
+            - job_id: str.
 
             - project_id: typing.Optional[str].
 
@@ -254,21 +321,19 @@ class LlamaExtractClient:
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.llama_extract.get_extraction_agent_by_name(
-            name="string",
+        client.llama_extract.get_job_result(
+            job_id="string",
         )
         """
         _response = self._client_wrapper.httpx_client.request(
             "GET",
-            urllib.parse.urljoin(
-                f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/by-name/{name}"
-            ),
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/jobs/{job_id}/result"),
             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(ExtractAgent, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ExtractResultset, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -277,36 +342,35 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def get_or_create_default_extraction_agent(
-        self, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
-    ) -> ExtractAgent:
+    def list_extract_runs(
+        self, *, extraction_agent_id: str, skip: typing.Optional[int] = None, limit: typing.Optional[int] = None
+    ) -> PaginatedExtractRunsResponse:
         """
-        Get or create a default extraction agent for the current project.
-        The default agent has an empty schema and default configuration.
-
         Parameters:
-            - project_id: typing.Optional[str].
+            - extraction_agent_id: str.
 
-            - organization_id: typing.Optional[str].
+            - skip: typing.Optional[int].
+
+            - limit: typing.Optional[int].
         ---
         from llama_cloud.client import LlamaCloud
 
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.llama_extract.get_or_create_default_extraction_agent()
+        client.llama_extract.list_extract_runs(
+            extraction_agent_id="string",
+        )
         """
         _response = self._client_wrapper.httpx_client.request(
             "GET",
-            urllib.parse.urljoin(
-                f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents/default"
-            ),
-            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/runs"),
+            params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id, "skip": skip, "limit": limit}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(ExtractAgent, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(PaginatedExtractRunsResponse, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -315,7 +379,7 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def get_extraction_agent(self, extraction_agent_id: str) -> ExtractAgent:
+    def get_latest_run_from_ui(self, *, extraction_agent_id: str) -> typing.Optional[ExtractRun]:
         """
         Parameters:
             - extraction_agent_id: str.
@@ -325,20 +389,19 @@ class LlamaExtractClient:
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.llama_extract.get_extraction_agent(
+        client.llama_extract.get_latest_run_from_ui(
             extraction_agent_id="string",
         )
         """
         _response = self._client_wrapper.httpx_client.request(
             "GET",
-            urllib.parse.urljoin(
-                f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/{extraction_agent_id}"
-            ),
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/runs/latest-from-ui"),
+            params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(ExtractAgent, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(typing.Optional[ExtractRun], _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -347,54 +410,35 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def update_extraction_agent(
-        self, extraction_agent_id: str, *, data_schema: ExtractAgentUpdateDataSchema, config: ExtractConfig
-    ) -> ExtractAgent:
+    def get_run_by_job_id(
+        self, job_id: str, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
+    ) -> ExtractRun:
         """
         Parameters:
-            - extraction_agent_id: str.
+            - job_id: str.
 
-            - data_schema: ExtractAgentUpdateDataSchema. The schema of the data
+            - project_id: typing.Optional[str].
 
-            - config: ExtractConfig. The configuration parameters for the extraction agent.
+            - organization_id: typing.Optional[str].
         ---
-        from llama_cloud import (
-            DocumentChunkMode,
-            ExtractConfig,
-            ExtractConfigPriority,
-            ExtractMode,
-            ExtractModels,
-            ExtractTarget,
-            PublicModelName,
-        )
         from llama_cloud.client import LlamaCloud
 
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.llama_extract.update_extraction_agent(
-            extraction_agent_id="string",
-            config=ExtractConfig(
-                priority=ExtractConfigPriority.LOW,
-                extraction_target=ExtractTarget.PER_DOC,
-                extraction_mode=ExtractMode.FAST,
-                parse_model=PublicModelName.OPENAI_GPT_4_O,
-                extract_model=ExtractModels.OPENAI_GPT_4_1,
-                chunk_mode=DocumentChunkMode.PAGE,
-            ),
+        client.llama_extract.get_run_by_job_id(
+            job_id="string",
         )
         """
         _response = self._client_wrapper.httpx_client.request(
-            "PUT",
-            urllib.parse.urljoin(
-                f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/{extraction_agent_id}"
-            ),
-            json=jsonable_encoder({"data_schema": data_schema, "config": config}),
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/runs/by-job/{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(ExtractAgent, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ExtractRun, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -403,30 +447,35 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def delete_extraction_agent(self, extraction_agent_id: str) -> typing.Any:
+    def get_run(
+        self, run_id: str, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
+    ) -> ExtractRun:
         """
         Parameters:
-            - extraction_agent_id: str.
+            - run_id: str.
+
+            - project_id: typing.Optional[str].
+
+            - organization_id: typing.Optional[str].
         ---
         from llama_cloud.client import LlamaCloud
 
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.llama_extract.delete_extraction_agent(
-            extraction_agent_id="string",
+        client.llama_extract.get_run(
+            run_id="string",
         )
         """
         _response = self._client_wrapper.httpx_client.request(
-            "DELETE",
-            urllib.parse.urljoin(
-                f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/{extraction_agent_id}"
-            ),
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/runs/{run_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(typing.Any, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ExtractRun, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -435,29 +484,35 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def list_jobs(self, *, extraction_agent_id: str) -> typing.List[ExtractJob]:
+    def delete_extraction_run(
+        self, run_id: str, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
+    ) -> typing.Any:
         """
         Parameters:
-            - extraction_agent_id: str.
+            - run_id: str.
+
+            - project_id: typing.Optional[str].
+
+            - organization_id: typing.Optional[str].
         ---
         from llama_cloud.client import LlamaCloud
 
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.llama_extract.list_jobs(
-            extraction_agent_id="string",
+        client.llama_extract.delete_extraction_run(
+            run_id="string",
         )
         """
         _response = self._client_wrapper.httpx_client.request(
-            "GET",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs"),
-            params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id}),
+            "DELETE",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/runs/{run_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(typing.List[ExtractJob], _response.json())  # type: ignore
+            return pydantic.parse_obj_as(typing.Any, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -466,22 +521,47 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def run_job(self, *, from_ui: typing.Optional[bool] = None, request: ExtractJobCreate) -> ExtractJob:
+    def extract_stateless(
+        self,
+        *,
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
+        webhook_configurations: typing.Optional[typing.List[WebhookConfiguration]] = OMIT,
+        data_schema: ExtractStatelessRequestDataSchema,
+        config: ExtractConfig,
+        file_id: typing.Optional[str] = OMIT,
+        text: typing.Optional[str] = OMIT,
+        file: typing.Optional[FileData] = OMIT,
+    ) -> ExtractJob:
         """
+        Stateless extraction endpoint that uses a default extraction agent in the user's default project.
+        Requires data_schema, config, and either file_id, text, or base64 encoded file data.
+
         Parameters:
-            - from_ui: typing.Optional[bool].
+            - project_id: typing.Optional[str].
+
+            - organization_id: typing.Optional[str].
+
+            - webhook_configurations: typing.Optional[typing.List[WebhookConfiguration]].
+
+            - data_schema: ExtractStatelessRequestDataSchema. The schema of the data to extract
+
+            - config: ExtractConfig. The configuration parameters for the extraction
 
-            - request: ExtractJobCreate.
+            - file_id: typing.Optional[str].
+
+            - text: typing.Optional[str].
+
+            - file: typing.Optional[FileData].
         ---
         from llama_cloud import (
             DocumentChunkMode,
             ExtractConfig,
             ExtractConfigPriority,
-            ExtractJobCreate,
-            ExtractJobCreatePriority,
             ExtractMode,
             ExtractModels,
             ExtractTarget,
+            FileData,
             PublicModelName,
         )
         from llama_cloud.client import LlamaCloud
@@ -489,27 +569,35 @@ class LlamaExtractClient:
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.llama_extract.run_job(
-            request=ExtractJobCreate(
-                priority=ExtractJobCreatePriority.LOW,
-                extraction_agent_id="string",
-                file_id="string",
-                config_override=ExtractConfig(
-                    priority=ExtractConfigPriority.LOW,
-                    extraction_target=ExtractTarget.PER_DOC,
-                    extraction_mode=ExtractMode.FAST,
-                    parse_model=PublicModelName.OPENAI_GPT_4_O,
-                    extract_model=ExtractModels.OPENAI_GPT_4_1,
-                    chunk_mode=DocumentChunkMode.PAGE,
-                ),
+        client.llama_extract.extract_stateless(
+            config=ExtractConfig(
+                priority=ExtractConfigPriority.LOW,
+                extraction_target=ExtractTarget.PER_DOC,
+                extraction_mode=ExtractMode.FAST,
+                parse_model=PublicModelName.OPENAI_GPT_4_O,
+                extract_model=ExtractModels.OPENAI_GPT_4_1,
+                chunk_mode=DocumentChunkMode.PAGE,
+            ),
+            file=FileData(
+                data="string",
+                mime_type="string",
             ),
         )
         """
+        _request: typing.Dict[str, typing.Any] = {"data_schema": data_schema, "config": config}
+        if webhook_configurations is not OMIT:
+            _request["webhook_configurations"] = webhook_configurations
+        if file_id is not OMIT:
+            _request["file_id"] = file_id
+        if text is not OMIT:
+            _request["text"] = text
+        if file is not OMIT:
+            _request["file"] = file
         _response = self._client_wrapper.httpx_client.request(
             "POST",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs"),
-            params=remove_none_from_dict({"from_ui": from_ui}),
-            json=jsonable_encoder(request),
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/run"),
+            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,
         )
@@ -523,28 +611,39 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def get_job(self, job_id: str) -> ExtractJob:
+    def list_extraction_agents(
+        self,
+        *,
+        include_default: typing.Optional[bool] = None,
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
+    ) -> typing.List[ExtractAgent]:
         """
         Parameters:
-            - job_id: str.
+            - include_default: typing.Optional[bool]. Whether to include default agents in the results
+
+            - project_id: typing.Optional[str].
+
+            - organization_id: typing.Optional[str].
         ---
         from llama_cloud.client import LlamaCloud
 
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.llama_extract.get_job(
-            job_id="string",
-        )
+        client.llama_extract.list_extraction_agents()
         """
         _response = self._client_wrapper.httpx_client.request(
             "GET",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/jobs/{job_id}"),
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents"),
+            params=remove_none_from_dict(
+                {"include_default": include_default, "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(ExtractJob, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(typing.List[ExtractAgent], _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -553,37 +652,34 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def run_job_test_user(
+    def create_extraction_agent(
         self,
         *,
-        from_ui: typing.Optional[bool] = None,
-        job_create: ExtractJobCreate,
-        extract_settings: typing.Optional[LlamaExtractSettings] = OMIT,
-    ) -> ExtractJob:
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
+        name: str,
+        data_schema: ExtractAgentCreateDataSchema,
+        config: ExtractConfig,
+    ) -> ExtractAgent:
         """
         Parameters:
-            - from_ui: typing.Optional[bool].
+            - project_id: typing.Optional[str].
+
+            - organization_id: typing.Optional[str].
 
-            - job_create: ExtractJobCreate.
+            - name: str. The name of the extraction schema
+
+            - data_schema: ExtractAgentCreateDataSchema. The schema of the data.
 
-            - extract_settings: typing.Optional[LlamaExtractSettings].
+            - config: ExtractConfig. The configuration parameters for the extraction agent.
         ---
         from llama_cloud import (
-            ChunkMode,
             DocumentChunkMode,
             ExtractConfig,
             ExtractConfigPriority,
-            ExtractJobCreate,
-            ExtractJobCreatePriority,
             ExtractMode,
             ExtractModels,
             ExtractTarget,
-            FailPageMode,
-            LlamaExtractSettings,
-            LlamaParseParameters,
-            LlamaParseParametersPriority,
-            MultimodalParseResolution,
-            ParsingMode,
             PublicModelName,
         )
         from llama_cloud.client import LlamaCloud
@@ -591,44 +687,28 @@ class LlamaExtractClient:
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.llama_extract.run_job_test_user(
-            job_create=ExtractJobCreate(
-                priority=ExtractJobCreatePriority.LOW,
-                extraction_agent_id="string",
-                file_id="string",
-                config_override=ExtractConfig(
-                    priority=ExtractConfigPriority.LOW,
-                    extraction_target=ExtractTarget.PER_DOC,
-                    extraction_mode=ExtractMode.FAST,
-                    parse_model=PublicModelName.OPENAI_GPT_4_O,
-                    extract_model=ExtractModels.OPENAI_GPT_4_1,
-                    chunk_mode=DocumentChunkMode.PAGE,
-                ),
-            ),
-            extract_settings=LlamaExtractSettings(
-                chunk_mode=ChunkMode.PAGE,
-                llama_parse_params=LlamaParseParameters(
-                    priority=LlamaParseParametersPriority.LOW,
-                    parse_mode=ParsingMode.PARSE_PAGE_WITHOUT_LLM,
-                    replace_failed_page_mode=FailPageMode.RAW_TEXT,
-                ),
-                multimodal_parse_resolution=MultimodalParseResolution.MEDIUM,
+        client.llama_extract.create_extraction_agent(
+            name="string",
+            config=ExtractConfig(
+                priority=ExtractConfigPriority.LOW,
+                extraction_target=ExtractTarget.PER_DOC,
+                extraction_mode=ExtractMode.FAST,
+                parse_model=PublicModelName.OPENAI_GPT_4_O,
+                extract_model=ExtractModels.OPENAI_GPT_4_1,
+                chunk_mode=DocumentChunkMode.PAGE,
             ),
         )
         """
-        _request: typing.Dict[str, typing.Any] = {"job_create": job_create}
-        if extract_settings is not OMIT:
-            _request["extract_settings"] = extract_settings
         _response = self._client_wrapper.httpx_client.request(
             "POST",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs/test"),
-            params=remove_none_from_dict({"from_ui": from_ui}),
-            json=jsonable_encoder(_request),
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents"),
+            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
+            json=jsonable_encoder({"name": name, "data_schema": data_schema, "config": config}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(ExtractJob, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ExtractAgent, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -637,44 +717,34 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def run_job_on_file(
-        self,
-        *,
-        from_ui: typing.Optional[bool] = None,
-        extraction_agent_id: str,
-        file: typing.IO,
-        data_schema_override: typing.Optional[str] = None,
-        config_override: typing.Optional[str] = None,
-    ) -> ExtractJob:
+    def validate_extraction_schema(
+        self, *, data_schema: ExtractSchemaValidateRequestDataSchema
+    ) -> ExtractSchemaValidateResponse:
         """
-        Parameters:
-            - from_ui: typing.Optional[bool].
-
-            - extraction_agent_id: str.
-
-            - file: typing.IO.
+        Validates an extraction agent's schema definition.
+        Returns the normalized and validated schema if valid, otherwise raises an HTTP 400.
 
-            - data_schema_override: typing.Optional[str].
+        Parameters:
+            - data_schema: ExtractSchemaValidateRequestDataSchema.
+        ---
+        from llama_cloud.client import LlamaCloud
 
-            - config_override: typing.Optional[str].
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.llama_extract.validate_extraction_schema()
         """
         _response = self._client_wrapper.httpx_client.request(
             "POST",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs/file"),
-            params=remove_none_from_dict({"from_ui": from_ui}),
-            data=jsonable_encoder(
-                {
-                    "extraction_agent_id": extraction_agent_id,
-                    "data_schema_override": data_schema_override,
-                    "config_override": config_override,
-                }
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents/schema/validation"
             ),
-            files={"file": file},
+            json=jsonable_encoder({"data_schema": data_schema}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(ExtractJob, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ExtractSchemaValidateResponse, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -683,69 +753,50 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def run_batch_jobs(
+    def generate_extraction_schema(
         self,
         *,
-        from_ui: typing.Optional[bool] = None,
-        extraction_agent_id: str,
-        file_ids: typing.List[str],
-        data_schema_override: typing.Optional[ExtractJobCreateBatchDataSchemaOverride] = OMIT,
-        config_override: typing.Optional[ExtractConfig] = OMIT,
-    ) -> typing.List[ExtractJob]:
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
+        prompt: typing.Optional[str] = OMIT,
+        file_id: typing.Optional[str] = OMIT,
+    ) -> ExtractSchemaGenerateResponse:
         """
-        Parameters:
-            - from_ui: typing.Optional[bool].
+        Generates an extraction agent's schema definition from a file and/or natural language prompt.
 
-            - extraction_agent_id: str. The id of the extraction agent
+        Parameters:
+            - project_id: typing.Optional[str].
 
-            - file_ids: typing.List[str]. The ids of the files
+            - organization_id: typing.Optional[str].
 
-            - data_schema_override: typing.Optional[ExtractJobCreateBatchDataSchemaOverride]. The data schema to override the extraction agent's data schema with
+            - prompt: typing.Optional[str].
 
-            - config_override: typing.Optional[ExtractConfig].
+            - file_id: typing.Optional[str].
         ---
-        from llama_cloud import (
-            DocumentChunkMode,
-            ExtractConfig,
-            ExtractConfigPriority,
-            ExtractMode,
-            ExtractModels,
-            ExtractTarget,
-            PublicModelName,
-        )
         from llama_cloud.client import LlamaCloud
 
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.llama_extract.run_batch_jobs(
-            extraction_agent_id="string",
-            file_ids=[],
-            config_override=ExtractConfig(
-                priority=ExtractConfigPriority.LOW,
-                extraction_target=ExtractTarget.PER_DOC,
-                extraction_mode=ExtractMode.FAST,
-                parse_model=PublicModelName.OPENAI_GPT_4_O,
-                extract_model=ExtractModels.OPENAI_GPT_4_1,
-                chunk_mode=DocumentChunkMode.PAGE,
-            ),
-        )
+        client.llama_extract.generate_extraction_schema()
         """
-        _request: typing.Dict[str, typing.Any] = {"extraction_agent_id": extraction_agent_id, "file_ids": file_ids}
-        if data_schema_override is not OMIT:
-            _request["data_schema_override"] = data_schema_override
-        if config_override is not OMIT:
-            _request["config_override"] = config_override
+        _request: typing.Dict[str, typing.Any] = {}
+        if prompt is not OMIT:
+            _request["prompt"] = prompt
+        if file_id is not OMIT:
+            _request["file_id"] = file_id
         _response = self._client_wrapper.httpx_client.request(
             "POST",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs/batch"),
-            params=remove_none_from_dict({"from_ui": from_ui}),
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents/schema/generate"
+            ),
+            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(typing.List[ExtractJob], _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ExtractSchemaGenerateResponse, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -754,12 +805,12 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def get_job_result(
-        self, job_id: str, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
-    ) -> ExtractResultset:
+    def get_extraction_agent_by_name(
+        self, name: str, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
+    ) -> ExtractAgent:
         """
         Parameters:
-            - job_id: str.
+            - name: str.
 
             - project_id: typing.Optional[str].
 
@@ -770,19 +821,21 @@ class LlamaExtractClient:
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.llama_extract.get_job_result(
-            job_id="string",
+        client.llama_extract.get_extraction_agent_by_name(
+            name="string",
         )
         """
         _response = self._client_wrapper.httpx_client.request(
             "GET",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/jobs/{job_id}/result"),
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/by-name/{name}"
+            ),
             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(ExtractResultset, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ExtractAgent, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -791,35 +844,36 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def list_extract_runs(
-        self, *, extraction_agent_id: str, skip: typing.Optional[int] = None, limit: typing.Optional[int] = None
-    ) -> PaginatedExtractRunsResponse:
+    def get_or_create_default_extraction_agent(
+        self, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
+    ) -> ExtractAgent:
         """
-        Parameters:
-            - extraction_agent_id: str.
+        Get or create a default extraction agent for the current project.
+        The default agent has an empty schema and default configuration.
 
-            - skip: typing.Optional[int].
+        Parameters:
+            - project_id: typing.Optional[str].
 
-            - limit: typing.Optional[int].
+            - organization_id: typing.Optional[str].
         ---
         from llama_cloud.client import LlamaCloud
 
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.llama_extract.list_extract_runs(
-            extraction_agent_id="string",
-        )
+        client.llama_extract.get_or_create_default_extraction_agent()
         """
         _response = self._client_wrapper.httpx_client.request(
             "GET",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/runs"),
-            params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id, "skip": skip, "limit": limit}),
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents/default"
+            ),
+            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(PaginatedExtractRunsResponse, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ExtractAgent, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -828,7 +882,7 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def get_latest_run_from_ui(self, *, extraction_agent_id: str) -> typing.Optional[ExtractRun]:
+    def get_extraction_agent(self, extraction_agent_id: str) -> ExtractAgent:
         """
         Parameters:
             - extraction_agent_id: str.
@@ -838,19 +892,20 @@ class LlamaExtractClient:
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.llama_extract.get_latest_run_from_ui(
+        client.llama_extract.get_extraction_agent(
             extraction_agent_id="string",
         )
         """
         _response = self._client_wrapper.httpx_client.request(
             "GET",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/runs/latest-from-ui"),
-            params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id}),
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/{extraction_agent_id}"
+            ),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(typing.Optional[ExtractRun], _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ExtractAgent, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -859,35 +914,54 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def get_run_by_job_id(
-        self, job_id: str, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
-    ) -> ExtractRun:
+    def update_extraction_agent(
+        self, extraction_agent_id: str, *, data_schema: ExtractAgentUpdateDataSchema, config: ExtractConfig
+    ) -> ExtractAgent:
         """
         Parameters:
-            - job_id: str.
+            - extraction_agent_id: str.
 
-            - project_id: typing.Optional[str].
+            - data_schema: ExtractAgentUpdateDataSchema. The schema of the data
 
-            - organization_id: typing.Optional[str].
+            - config: ExtractConfig. The configuration parameters for the extraction agent.
         ---
+        from llama_cloud import (
+            DocumentChunkMode,
+            ExtractConfig,
+            ExtractConfigPriority,
+            ExtractMode,
+            ExtractModels,
+            ExtractTarget,
+            PublicModelName,
+        )
         from llama_cloud.client import LlamaCloud
 
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.llama_extract.get_run_by_job_id(
-            job_id="string",
+        client.llama_extract.update_extraction_agent(
+            extraction_agent_id="string",
+            config=ExtractConfig(
+                priority=ExtractConfigPriority.LOW,
+                extraction_target=ExtractTarget.PER_DOC,
+                extraction_mode=ExtractMode.FAST,
+                parse_model=PublicModelName.OPENAI_GPT_4_O,
+                extract_model=ExtractModels.OPENAI_GPT_4_1,
+                chunk_mode=DocumentChunkMode.PAGE,
+            ),
         )
         """
         _response = self._client_wrapper.httpx_client.request(
-            "GET",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/runs/by-job/{job_id}"),
-            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
+            "PUT",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/{extraction_agent_id}"
+            ),
+            json=jsonable_encoder({"data_schema": data_schema, "config": config}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(ExtractRun, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ExtractAgent, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -896,35 +970,30 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def get_run(
-        self, run_id: str, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
-    ) -> ExtractRun:
+    def delete_extraction_agent(self, extraction_agent_id: str) -> typing.Any:
         """
         Parameters:
-            - run_id: str.
-
-            - project_id: typing.Optional[str].
-
-            - organization_id: typing.Optional[str].
+            - extraction_agent_id: str.
         ---
         from llama_cloud.client import LlamaCloud
 
         client = LlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.llama_extract.get_run(
-            run_id="string",
+        client.llama_extract.delete_extraction_agent(
+            extraction_agent_id="string",
         )
         """
         _response = self._client_wrapper.httpx_client.request(
-            "GET",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/runs/{run_id}"),
-            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
+            "DELETE",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/{extraction_agent_id}"
+            ),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(ExtractRun, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(typing.Any, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -933,35 +1002,34 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def delete_extraction_run(
-        self, run_id: str, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
-    ) -> typing.Any:
-        """
-        Parameters:
-            - run_id: str.
 
-            - project_id: typing.Optional[str].
+class AsyncLlamaExtractClient:
+    def __init__(self, *, client_wrapper: AsyncClientWrapper):
+        self._client_wrapper = client_wrapper
 
-            - organization_id: typing.Optional[str].
+    async def list_jobs(self, *, extraction_agent_id: str) -> typing.List[ExtractJob]:
+        """
+        Parameters:
+            - extraction_agent_id: str.
         ---
-        from llama_cloud.client import LlamaCloud
+        from llama_cloud.client import AsyncLlamaCloud
 
-        client = LlamaCloud(
+        client = AsyncLlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.llama_extract.delete_extraction_run(
-            run_id="string",
+        await client.llama_extract.list_jobs(
+            extraction_agent_id="string",
         )
         """
-        _response = self._client_wrapper.httpx_client.request(
-            "DELETE",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/runs/{run_id}"),
-            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
+        _response = await self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs"),
+            params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(typing.Any, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(typing.List[ExtractJob], _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -970,56 +1038,53 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def extract_stateless(
+    async def run_job(
         self,
         *,
-        project_id: typing.Optional[str] = None,
-        organization_id: typing.Optional[str] = None,
+        from_ui: typing.Optional[bool] = None,
+        priority: typing.Optional[ExtractJobCreatePriority] = OMIT,
         webhook_configurations: typing.Optional[typing.List[WebhookConfiguration]] = OMIT,
-        data_schema: ExtractStatelessRequestDataSchema,
-        config: ExtractConfig,
-        file_id: typing.Optional[str] = OMIT,
-        text: typing.Optional[str] = OMIT,
-        file: typing.Optional[FileData] = OMIT,
+        extraction_agent_id: str,
+        file_id: str,
+        data_schema_override: typing.Optional[ExtractJobCreateDataSchemaOverride] = OMIT,
+        config_override: typing.Optional[ExtractConfig] = OMIT,
     ) -> ExtractJob:
         """
-        Stateless extraction endpoint that uses a default extraction agent in the user's default project.
-        Requires data_schema, config, and either file_id, text, or base64 encoded file data.
-
         Parameters:
-            - project_id: typing.Optional[str].
+            - from_ui: typing.Optional[bool].
 
-            - organization_id: typing.Optional[str].
+            - priority: typing.Optional[ExtractJobCreatePriority].
 
             - webhook_configurations: typing.Optional[typing.List[WebhookConfiguration]].
 
-            - data_schema: ExtractStatelessRequestDataSchema. The schema of the data to extract
-
-            - config: ExtractConfig. The configuration parameters for the extraction
+            - extraction_agent_id: str. The id of the extraction agent
 
-            - file_id: typing.Optional[str].
+            - file_id: str. The id of the file
 
-            - text: typing.Optional[str].
+            - data_schema_override: typing.Optional[ExtractJobCreateDataSchemaOverride]. The data schema to override the extraction agent's data schema with
 
-            - file: typing.Optional[FileData].
+            - config_override: typing.Optional[ExtractConfig].
         ---
         from llama_cloud import (
             DocumentChunkMode,
             ExtractConfig,
             ExtractConfigPriority,
+            ExtractJobCreatePriority,
             ExtractMode,
             ExtractModels,
             ExtractTarget,
-            FileData,
             PublicModelName,
         )
-        from llama_cloud.client import LlamaCloud
+        from llama_cloud.client import AsyncLlamaCloud
 
-        client = LlamaCloud(
+        client = AsyncLlamaCloud(
             token="YOUR_TOKEN",
         )
-        client.llama_extract.extract_stateless(
-            config=ExtractConfig(
+        await client.llama_extract.run_job(
+            priority=ExtractJobCreatePriority.LOW,
+            extraction_agent_id="string",
+            file_id="string",
+            config_override=ExtractConfig(
                 priority=ExtractConfigPriority.LOW,
                 extraction_target=ExtractTarget.PER_DOC,
                 extraction_mode=ExtractMode.FAST,
@@ -1027,25 +1092,21 @@ class LlamaExtractClient:
                 extract_model=ExtractModels.OPENAI_GPT_4_1,
                 chunk_mode=DocumentChunkMode.PAGE,
             ),
-            file=FileData(
-                data="string",
-                mime_type="string",
-            ),
         )
         """
-        _request: typing.Dict[str, typing.Any] = {"data_schema": data_schema, "config": config}
+        _request: typing.Dict[str, typing.Any] = {"extraction_agent_id": extraction_agent_id, "file_id": file_id}
+        if priority is not OMIT:
+            _request["priority"] = priority
         if webhook_configurations is not OMIT:
             _request["webhook_configurations"] = webhook_configurations
-        if file_id is not OMIT:
-            _request["file_id"] = file_id
-        if text is not OMIT:
-            _request["text"] = text
-        if file is not OMIT:
-            _request["file"] = file
-        _response = self._client_wrapper.httpx_client.request(
+        if data_schema_override is not OMIT:
+            _request["data_schema_override"] = data_schema_override
+        if config_override is not OMIT:
+            _request["config_override"] = config_override
+        _response = await self._client_wrapper.httpx_client.request(
             "POST",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/run"),
-            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs"),
+            params=remove_none_from_dict({"from_ui": from_ui}),
             json=jsonable_encoder(_request),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
@@ -1060,44 +1121,74 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-
-class AsyncLlamaExtractClient:
-    def __init__(self, *, client_wrapper: AsyncClientWrapper):
-        self._client_wrapper = client_wrapper
-
-    async def list_extraction_agents(
-        self,
-        *,
-        include_default: typing.Optional[bool] = None,
-        project_id: typing.Optional[str] = None,
-        organization_id: typing.Optional[str] = None,
-    ) -> typing.List[ExtractAgent]:
+    async def get_job(self, job_id: str) -> ExtractJob:
         """
         Parameters:
-            - include_default: typing.Optional[bool]. Whether to include default agents in the results
-
-            - project_id: typing.Optional[str].
-
-            - organization_id: typing.Optional[str].
+            - job_id: str.
         ---
         from llama_cloud.client import AsyncLlamaCloud
 
         client = AsyncLlamaCloud(
             token="YOUR_TOKEN",
         )
-        await client.llama_extract.list_extraction_agents()
+        await client.llama_extract.get_job(
+            job_id="string",
+        )
         """
         _response = await self._client_wrapper.httpx_client.request(
             "GET",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents"),
-            params=remove_none_from_dict(
-                {"include_default": include_default, "project_id": project_id, "organization_id": organization_id}
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/jobs/{job_id}"),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExtractJob, _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 run_job_on_file(
+        self,
+        *,
+        from_ui: typing.Optional[bool] = None,
+        extraction_agent_id: str,
+        file: typing.IO,
+        data_schema_override: typing.Optional[str] = None,
+        config_override: typing.Optional[str] = None,
+    ) -> ExtractJob:
+        """
+        Parameters:
+            - from_ui: typing.Optional[bool].
+
+            - extraction_agent_id: str.
+
+            - file: typing.IO.
+
+            - data_schema_override: typing.Optional[str].
+
+            - config_override: typing.Optional[str].
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "POST",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs/file"),
+            params=remove_none_from_dict({"from_ui": from_ui}),
+            data=jsonable_encoder(
+                {
+                    "extraction_agent_id": extraction_agent_id,
+                    "data_schema_override": data_schema_override,
+                    "config_override": config_override,
+                }
             ),
+            files={"file": file},
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(typing.List[ExtractAgent], _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ExtractJob, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -1106,26 +1197,26 @@ class AsyncLlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    async def create_extraction_agent(
+    async def run_batch_jobs(
         self,
         *,
-        project_id: typing.Optional[str] = None,
-        organization_id: typing.Optional[str] = None,
-        name: str,
-        data_schema: ExtractAgentCreateDataSchema,
-        config: ExtractConfig,
-    ) -> ExtractAgent:
+        from_ui: typing.Optional[bool] = None,
+        extraction_agent_id: str,
+        file_ids: typing.List[str],
+        data_schema_override: typing.Optional[ExtractJobCreateBatchDataSchemaOverride] = OMIT,
+        config_override: typing.Optional[ExtractConfig] = OMIT,
+    ) -> typing.List[ExtractJob]:
         """
         Parameters:
-            - project_id: typing.Optional[str].
+            - from_ui: typing.Optional[bool].
 
-            - organization_id: typing.Optional[str].
+            - extraction_agent_id: str. The id of the extraction agent
 
-            - name: str. The name of the extraction schema
+            - file_ids: typing.List[str]. The ids of the files
 
-            - data_schema: ExtractAgentCreateDataSchema. The schema of the data.
+            - data_schema_override: typing.Optional[ExtractJobCreateBatchDataSchemaOverride]. The data schema to override the extraction agent's data schema with
 
-            - config: ExtractConfig. The configuration parameters for the extraction agent.
+            - config_override: typing.Optional[ExtractConfig].
         ---
         from llama_cloud import (
             DocumentChunkMode,
@@ -1141,9 +1232,10 @@ class AsyncLlamaExtractClient:
         client = AsyncLlamaCloud(
             token="YOUR_TOKEN",
         )
-        await client.llama_extract.create_extraction_agent(
-            name="string",
-            config=ExtractConfig(
+        await client.llama_extract.run_batch_jobs(
+            extraction_agent_id="string",
+            file_ids=[],
+            config_override=ExtractConfig(
                 priority=ExtractConfigPriority.LOW,
                 extraction_target=ExtractTarget.PER_DOC,
                 extraction_mode=ExtractMode.FAST,
@@ -1153,16 +1245,21 @@ class AsyncLlamaExtractClient:
             ),
         )
         """
+        _request: typing.Dict[str, typing.Any] = {"extraction_agent_id": extraction_agent_id, "file_ids": file_ids}
+        if data_schema_override is not OMIT:
+            _request["data_schema_override"] = data_schema_override
+        if config_override is not OMIT:
+            _request["config_override"] = config_override
         _response = await self._client_wrapper.httpx_client.request(
             "POST",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents"),
-            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
-            json=jsonable_encoder({"name": name, "data_schema": data_schema, "config": config}),
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs/batch"),
+            params=remove_none_from_dict({"from_ui": from_ui}),
+            json=jsonable_encoder(_request),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(ExtractAgent, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(typing.List[ExtractJob], _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -1171,34 +1268,35 @@ class AsyncLlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    async def validate_extraction_schema(
-        self, *, data_schema: ExtractSchemaValidateRequestDataSchema
-    ) -> ExtractSchemaValidateResponse:
+    async def get_job_result(
+        self, job_id: str, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
+    ) -> ExtractResultset:
         """
-        Validates an extraction agent's schema definition.
-        Returns the normalized and validated schema if valid, otherwise raises an HTTP 400.
-
         Parameters:
-            - data_schema: ExtractSchemaValidateRequestDataSchema.
+            - job_id: str.
+
+            - project_id: typing.Optional[str].
+
+            - organization_id: typing.Optional[str].
         ---
         from llama_cloud.client import AsyncLlamaCloud
 
         client = AsyncLlamaCloud(
             token="YOUR_TOKEN",
         )
-        await client.llama_extract.validate_extraction_schema()
+        await client.llama_extract.get_job_result(
+            job_id="string",
+        )
         """
         _response = await self._client_wrapper.httpx_client.request(
-            "POST",
-            urllib.parse.urljoin(
-                f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents/schema/validation"
-            ),
-            json=jsonable_encoder({"data_schema": data_schema}),
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/jobs/{job_id}/result"),
+            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(ExtractSchemaValidateResponse, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ExtractResultset, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -1207,50 +1305,35 @@ class AsyncLlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    async def generate_extraction_schema(
-        self,
-        *,
-        project_id: typing.Optional[str] = None,
-        organization_id: typing.Optional[str] = None,
-        prompt: typing.Optional[str] = OMIT,
-        file_id: typing.Optional[str] = OMIT,
-    ) -> ExtractSchemaGenerateResponse:
+    async def list_extract_runs(
+        self, *, extraction_agent_id: str, skip: typing.Optional[int] = None, limit: typing.Optional[int] = None
+    ) -> PaginatedExtractRunsResponse:
         """
-        Generates an extraction agent's schema definition from a file and/or natural language prompt.
-
         Parameters:
-            - project_id: typing.Optional[str].
-
-            - organization_id: typing.Optional[str].
+            - extraction_agent_id: str.
 
-            - prompt: typing.Optional[str].
+            - skip: typing.Optional[int].
 
-            - file_id: typing.Optional[str].
+            - limit: typing.Optional[int].
         ---
         from llama_cloud.client import AsyncLlamaCloud
 
         client = AsyncLlamaCloud(
             token="YOUR_TOKEN",
         )
-        await client.llama_extract.generate_extraction_schema()
+        await client.llama_extract.list_extract_runs(
+            extraction_agent_id="string",
+        )
         """
-        _request: typing.Dict[str, typing.Any] = {}
-        if prompt is not OMIT:
-            _request["prompt"] = prompt
-        if file_id is not OMIT:
-            _request["file_id"] = file_id
         _response = await self._client_wrapper.httpx_client.request(
-            "POST",
-            urllib.parse.urljoin(
-                f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents/schema/generate"
-            ),
-            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
-            json=jsonable_encoder(_request),
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/runs"),
+            params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id, "skip": skip, "limit": limit}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(ExtractSchemaGenerateResponse, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(PaginatedExtractRunsResponse, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -1259,37 +1342,29 @@ class AsyncLlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    async def get_extraction_agent_by_name(
-        self, name: str, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
-    ) -> ExtractAgent:
+    async def get_latest_run_from_ui(self, *, extraction_agent_id: str) -> typing.Optional[ExtractRun]:
         """
         Parameters:
-            - name: str.
-
-            - project_id: typing.Optional[str].
-
-            - organization_id: typing.Optional[str].
+            - extraction_agent_id: str.
         ---
         from llama_cloud.client import AsyncLlamaCloud
 
         client = AsyncLlamaCloud(
             token="YOUR_TOKEN",
         )
-        await client.llama_extract.get_extraction_agent_by_name(
-            name="string",
+        await client.llama_extract.get_latest_run_from_ui(
+            extraction_agent_id="string",
         )
         """
         _response = await self._client_wrapper.httpx_client.request(
             "GET",
-            urllib.parse.urljoin(
-                f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/by-name/{name}"
-            ),
-            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/runs/latest-from-ui"),
+            params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(ExtractAgent, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(typing.Optional[ExtractRun], _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -1298,14 +1373,13 @@ class AsyncLlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    async def get_or_create_default_extraction_agent(
-        self, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
-    ) -> ExtractAgent:
+    async def get_run_by_job_id(
+        self, job_id: str, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
+    ) -> ExtractRun:
         """
-        Get or create a default extraction agent for the current project.
-        The default agent has an empty schema and default configuration.
-
         Parameters:
+            - job_id: str.
+
             - project_id: typing.Optional[str].
 
             - organization_id: typing.Optional[str].
@@ -1315,19 +1389,19 @@ class AsyncLlamaExtractClient:
         client = AsyncLlamaCloud(
             token="YOUR_TOKEN",
         )
-        await client.llama_extract.get_or_create_default_extraction_agent()
+        await client.llama_extract.get_run_by_job_id(
+            job_id="string",
+        )
         """
         _response = await self._client_wrapper.httpx_client.request(
             "GET",
-            urllib.parse.urljoin(
-                f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents/default"
-            ),
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/runs/by-job/{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(ExtractAgent, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ExtractRun, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -1336,30 +1410,35 @@ class AsyncLlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    async def get_extraction_agent(self, extraction_agent_id: str) -> ExtractAgent:
+    async def get_run(
+        self, run_id: str, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
+    ) -> ExtractRun:
         """
         Parameters:
-            - extraction_agent_id: str.
+            - run_id: str.
+
+            - project_id: typing.Optional[str].
+
+            - organization_id: typing.Optional[str].
         ---
         from llama_cloud.client import AsyncLlamaCloud
 
         client = AsyncLlamaCloud(
             token="YOUR_TOKEN",
         )
-        await client.llama_extract.get_extraction_agent(
-            extraction_agent_id="string",
+        await client.llama_extract.get_run(
+            run_id="string",
         )
         """
         _response = await self._client_wrapper.httpx_client.request(
             "GET",
-            urllib.parse.urljoin(
-                f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/{extraction_agent_id}"
-            ),
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/runs/{run_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(ExtractAgent, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ExtractRun, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -1368,81 +1447,30 @@ class AsyncLlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    async def update_extraction_agent(
-        self, extraction_agent_id: str, *, data_schema: ExtractAgentUpdateDataSchema, config: ExtractConfig
-    ) -> ExtractAgent:
+    async def delete_extraction_run(
+        self, run_id: str, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
+    ) -> typing.Any:
         """
         Parameters:
-            - extraction_agent_id: str.
-
-            - data_schema: ExtractAgentUpdateDataSchema. The schema of the data
-
-            - config: ExtractConfig. The configuration parameters for the extraction agent.
-        ---
-        from llama_cloud import (
-            DocumentChunkMode,
-            ExtractConfig,
-            ExtractConfigPriority,
-            ExtractMode,
-            ExtractModels,
-            ExtractTarget,
-            PublicModelName,
-        )
-        from llama_cloud.client import AsyncLlamaCloud
+            - run_id: str.
 
-        client = AsyncLlamaCloud(
-            token="YOUR_TOKEN",
-        )
-        await client.llama_extract.update_extraction_agent(
-            extraction_agent_id="string",
-            config=ExtractConfig(
-                priority=ExtractConfigPriority.LOW,
-                extraction_target=ExtractTarget.PER_DOC,
-                extraction_mode=ExtractMode.FAST,
-                parse_model=PublicModelName.OPENAI_GPT_4_O,
-                extract_model=ExtractModels.OPENAI_GPT_4_1,
-                chunk_mode=DocumentChunkMode.PAGE,
-            ),
-        )
-        """
-        _response = await self._client_wrapper.httpx_client.request(
-            "PUT",
-            urllib.parse.urljoin(
-                f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/{extraction_agent_id}"
-            ),
-            json=jsonable_encoder({"data_schema": data_schema, "config": config}),
-            headers=self._client_wrapper.get_headers(),
-            timeout=60,
-        )
-        if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(ExtractAgent, _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)
+            - project_id: typing.Optional[str].
 
-    async def delete_extraction_agent(self, extraction_agent_id: str) -> typing.Any:
-        """
-        Parameters:
-            - extraction_agent_id: str.
+            - organization_id: typing.Optional[str].
         ---
         from llama_cloud.client import AsyncLlamaCloud
 
         client = AsyncLlamaCloud(
             token="YOUR_TOKEN",
         )
-        await client.llama_extract.delete_extraction_agent(
-            extraction_agent_id="string",
+        await client.llama_extract.delete_extraction_run(
+            run_id="string",
         )
         """
         _response = await self._client_wrapper.httpx_client.request(
             "DELETE",
-            urllib.parse.urljoin(
-                f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/{extraction_agent_id}"
-            ),
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/runs/{run_id}"),
+            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
@@ -1456,155 +1484,47 @@ class AsyncLlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    async def list_jobs(self, *, extraction_agent_id: str) -> typing.List[ExtractJob]:
-        """
-        Parameters:
-            - extraction_agent_id: str.
-        ---
-        from llama_cloud.client import AsyncLlamaCloud
-
-        client = AsyncLlamaCloud(
-            token="YOUR_TOKEN",
-        )
-        await client.llama_extract.list_jobs(
-            extraction_agent_id="string",
-        )
+    async def extract_stateless(
+        self,
+        *,
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
+        webhook_configurations: typing.Optional[typing.List[WebhookConfiguration]] = OMIT,
+        data_schema: ExtractStatelessRequestDataSchema,
+        config: ExtractConfig,
+        file_id: typing.Optional[str] = OMIT,
+        text: typing.Optional[str] = OMIT,
+        file: typing.Optional[FileData] = OMIT,
+    ) -> ExtractJob:
         """
-        _response = await self._client_wrapper.httpx_client.request(
-            "GET",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs"),
-            params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id}),
-            headers=self._client_wrapper.get_headers(),
-            timeout=60,
-        )
-        if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(typing.List[ExtractJob], _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)
+        Stateless extraction endpoint that uses a default extraction agent in the user's default project.
+        Requires data_schema, config, and either file_id, text, or base64 encoded file data.
 
-    async def run_job(self, *, from_ui: typing.Optional[bool] = None, request: ExtractJobCreate) -> ExtractJob:
-        """
         Parameters:
-            - from_ui: typing.Optional[bool].
+            - project_id: typing.Optional[str].
 
-            - request: ExtractJobCreate.
-        ---
-        from llama_cloud import (
-            DocumentChunkMode,
-            ExtractConfig,
-            ExtractConfigPriority,
-            ExtractJobCreate,
-            ExtractJobCreatePriority,
-            ExtractMode,
-            ExtractModels,
-            ExtractTarget,
-            PublicModelName,
-        )
-        from llama_cloud.client import AsyncLlamaCloud
+            - organization_id: typing.Optional[str].
 
-        client = AsyncLlamaCloud(
-            token="YOUR_TOKEN",
-        )
-        await client.llama_extract.run_job(
-            request=ExtractJobCreate(
-                priority=ExtractJobCreatePriority.LOW,
-                extraction_agent_id="string",
-                file_id="string",
-                config_override=ExtractConfig(
-                    priority=ExtractConfigPriority.LOW,
-                    extraction_target=ExtractTarget.PER_DOC,
-                    extraction_mode=ExtractMode.FAST,
-                    parse_model=PublicModelName.OPENAI_GPT_4_O,
-                    extract_model=ExtractModels.OPENAI_GPT_4_1,
-                    chunk_mode=DocumentChunkMode.PAGE,
-                ),
-            ),
-        )
-        """
-        _response = await self._client_wrapper.httpx_client.request(
-            "POST",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs"),
-            params=remove_none_from_dict({"from_ui": from_ui}),
-            json=jsonable_encoder(request),
-            headers=self._client_wrapper.get_headers(),
-            timeout=60,
-        )
-        if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(ExtractJob, _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)
+            - webhook_configurations: typing.Optional[typing.List[WebhookConfiguration]].
 
-    async def get_job(self, job_id: str) -> ExtractJob:
-        """
-        Parameters:
-            - job_id: str.
-        ---
-        from llama_cloud.client import AsyncLlamaCloud
+            - data_schema: ExtractStatelessRequestDataSchema. The schema of the data to extract
 
-        client = AsyncLlamaCloud(
-            token="YOUR_TOKEN",
-        )
-        await client.llama_extract.get_job(
-            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/extraction/jobs/{job_id}"),
-            headers=self._client_wrapper.get_headers(),
-            timeout=60,
-        )
-        if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(ExtractJob, _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)
+            - config: ExtractConfig. The configuration parameters for the extraction
 
-    async def run_job_test_user(
-        self,
-        *,
-        from_ui: typing.Optional[bool] = None,
-        job_create: ExtractJobCreate,
-        extract_settings: typing.Optional[LlamaExtractSettings] = OMIT,
-    ) -> ExtractJob:
-        """
-        Parameters:
-            - from_ui: typing.Optional[bool].
+            - file_id: typing.Optional[str].
 
-            - job_create: ExtractJobCreate.
+            - text: typing.Optional[str].
 
-            - extract_settings: typing.Optional[LlamaExtractSettings].
+            - file: typing.Optional[FileData].
         ---
         from llama_cloud import (
-            ChunkMode,
             DocumentChunkMode,
             ExtractConfig,
             ExtractConfigPriority,
-            ExtractJobCreate,
-            ExtractJobCreatePriority,
             ExtractMode,
             ExtractModels,
             ExtractTarget,
-            FailPageMode,
-            LlamaExtractSettings,
-            LlamaParseParameters,
-            LlamaParseParametersPriority,
-            MultimodalParseResolution,
-            ParsingMode,
+            FileData,
             PublicModelName,
         )
         from llama_cloud.client import AsyncLlamaCloud
@@ -1612,38 +1532,34 @@ class AsyncLlamaExtractClient:
         client = AsyncLlamaCloud(
             token="YOUR_TOKEN",
         )
-        await client.llama_extract.run_job_test_user(
-            job_create=ExtractJobCreate(
-                priority=ExtractJobCreatePriority.LOW,
-                extraction_agent_id="string",
-                file_id="string",
-                config_override=ExtractConfig(
-                    priority=ExtractConfigPriority.LOW,
-                    extraction_target=ExtractTarget.PER_DOC,
-                    extraction_mode=ExtractMode.FAST,
-                    parse_model=PublicModelName.OPENAI_GPT_4_O,
-                    extract_model=ExtractModels.OPENAI_GPT_4_1,
-                    chunk_mode=DocumentChunkMode.PAGE,
-                ),
+        await client.llama_extract.extract_stateless(
+            config=ExtractConfig(
+                priority=ExtractConfigPriority.LOW,
+                extraction_target=ExtractTarget.PER_DOC,
+                extraction_mode=ExtractMode.FAST,
+                parse_model=PublicModelName.OPENAI_GPT_4_O,
+                extract_model=ExtractModels.OPENAI_GPT_4_1,
+                chunk_mode=DocumentChunkMode.PAGE,
             ),
-            extract_settings=LlamaExtractSettings(
-                chunk_mode=ChunkMode.PAGE,
-                llama_parse_params=LlamaParseParameters(
-                    priority=LlamaParseParametersPriority.LOW,
-                    parse_mode=ParsingMode.PARSE_PAGE_WITHOUT_LLM,
-                    replace_failed_page_mode=FailPageMode.RAW_TEXT,
-                ),
-                multimodal_parse_resolution=MultimodalParseResolution.MEDIUM,
+            file=FileData(
+                data="string",
+                mime_type="string",
             ),
         )
         """
-        _request: typing.Dict[str, typing.Any] = {"job_create": job_create}
-        if extract_settings is not OMIT:
-            _request["extract_settings"] = extract_settings
+        _request: typing.Dict[str, typing.Any] = {"data_schema": data_schema, "config": config}
+        if webhook_configurations is not OMIT:
+            _request["webhook_configurations"] = webhook_configurations
+        if file_id is not OMIT:
+            _request["file_id"] = file_id
+        if text is not OMIT:
+            _request["text"] = text
+        if file is not OMIT:
+            _request["file"] = file
         _response = await self._client_wrapper.httpx_client.request(
             "POST",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs/test"),
-            params=remove_none_from_dict({"from_ui": from_ui}),
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/run"),
+            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,
@@ -1658,115 +1574,39 @@ class AsyncLlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    async def run_job_on_file(
-        self,
-        *,
-        from_ui: typing.Optional[bool] = None,
-        extraction_agent_id: str,
-        file: typing.IO,
-        data_schema_override: typing.Optional[str] = None,
-        config_override: typing.Optional[str] = None,
-    ) -> ExtractJob:
-        """
-        Parameters:
-            - from_ui: typing.Optional[bool].
-
-            - extraction_agent_id: str.
-
-            - file: typing.IO.
-
-            - data_schema_override: typing.Optional[str].
-
-            - config_override: typing.Optional[str].
-        """
-        _response = await self._client_wrapper.httpx_client.request(
-            "POST",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs/file"),
-            params=remove_none_from_dict({"from_ui": from_ui}),
-            data=jsonable_encoder(
-                {
-                    "extraction_agent_id": extraction_agent_id,
-                    "data_schema_override": data_schema_override,
-                    "config_override": config_override,
-                }
-            ),
-            files={"file": file},
-            headers=self._client_wrapper.get_headers(),
-            timeout=60,
-        )
-        if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(ExtractJob, _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 run_batch_jobs(
+    async def list_extraction_agents(
         self,
         *,
-        from_ui: typing.Optional[bool] = None,
-        extraction_agent_id: str,
-        file_ids: typing.List[str],
-        data_schema_override: typing.Optional[ExtractJobCreateBatchDataSchemaOverride] = OMIT,
-        config_override: typing.Optional[ExtractConfig] = OMIT,
-    ) -> typing.List[ExtractJob]:
+        include_default: typing.Optional[bool] = None,
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
+    ) -> typing.List[ExtractAgent]:
         """
         Parameters:
-            - from_ui: typing.Optional[bool].
-
-            - extraction_agent_id: str. The id of the extraction agent
-
-            - file_ids: typing.List[str]. The ids of the files
+            - include_default: typing.Optional[bool]. Whether to include default agents in the results
 
-            - data_schema_override: typing.Optional[ExtractJobCreateBatchDataSchemaOverride]. The data schema to override the extraction agent's data schema with
+            - project_id: typing.Optional[str].
 
-            - config_override: typing.Optional[ExtractConfig].
+            - organization_id: typing.Optional[str].
         ---
-        from llama_cloud import (
-            DocumentChunkMode,
-            ExtractConfig,
-            ExtractConfigPriority,
-            ExtractMode,
-            ExtractModels,
-            ExtractTarget,
-            PublicModelName,
-        )
         from llama_cloud.client import AsyncLlamaCloud
 
         client = AsyncLlamaCloud(
             token="YOUR_TOKEN",
         )
-        await client.llama_extract.run_batch_jobs(
-            extraction_agent_id="string",
-            file_ids=[],
-            config_override=ExtractConfig(
-                priority=ExtractConfigPriority.LOW,
-                extraction_target=ExtractTarget.PER_DOC,
-                extraction_mode=ExtractMode.FAST,
-                parse_model=PublicModelName.OPENAI_GPT_4_O,
-                extract_model=ExtractModels.OPENAI_GPT_4_1,
-                chunk_mode=DocumentChunkMode.PAGE,
-            ),
-        )
+        await client.llama_extract.list_extraction_agents()
         """
-        _request: typing.Dict[str, typing.Any] = {"extraction_agent_id": extraction_agent_id, "file_ids": file_ids}
-        if data_schema_override is not OMIT:
-            _request["data_schema_override"] = data_schema_override
-        if config_override is not OMIT:
-            _request["config_override"] = config_override
         _response = await self._client_wrapper.httpx_client.request(
-            "POST",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs/batch"),
-            params=remove_none_from_dict({"from_ui": from_ui}),
-            json=jsonable_encoder(_request),
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents"),
+            params=remove_none_from_dict(
+                {"include_default": include_default, "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(typing.List[ExtractJob], _response.json())  # type: ignore
+            return pydantic.parse_obj_as(typing.List[ExtractAgent], _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -1775,35 +1615,63 @@ class AsyncLlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    async def get_job_result(
-        self, job_id: str, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
-    ) -> ExtractResultset:
+    async def create_extraction_agent(
+        self,
+        *,
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
+        name: str,
+        data_schema: ExtractAgentCreateDataSchema,
+        config: ExtractConfig,
+    ) -> ExtractAgent:
         """
         Parameters:
-            - job_id: str.
-
             - project_id: typing.Optional[str].
 
             - organization_id: typing.Optional[str].
+
+            - name: str. The name of the extraction schema
+
+            - data_schema: ExtractAgentCreateDataSchema. The schema of the data.
+
+            - config: ExtractConfig. The configuration parameters for the extraction agent.
         ---
+        from llama_cloud import (
+            DocumentChunkMode,
+            ExtractConfig,
+            ExtractConfigPriority,
+            ExtractMode,
+            ExtractModels,
+            ExtractTarget,
+            PublicModelName,
+        )
         from llama_cloud.client import AsyncLlamaCloud
 
         client = AsyncLlamaCloud(
             token="YOUR_TOKEN",
         )
-        await client.llama_extract.get_job_result(
-            job_id="string",
+        await client.llama_extract.create_extraction_agent(
+            name="string",
+            config=ExtractConfig(
+                priority=ExtractConfigPriority.LOW,
+                extraction_target=ExtractTarget.PER_DOC,
+                extraction_mode=ExtractMode.FAST,
+                parse_model=PublicModelName.OPENAI_GPT_4_O,
+                extract_model=ExtractModels.OPENAI_GPT_4_1,
+                chunk_mode=DocumentChunkMode.PAGE,
+            ),
         )
         """
         _response = await self._client_wrapper.httpx_client.request(
-            "GET",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/jobs/{job_id}/result"),
+            "POST",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents"),
             params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
+            json=jsonable_encoder({"name": name, "data_schema": data_schema, "config": config}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(ExtractResultset, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ExtractAgent, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -1812,35 +1680,34 @@ class AsyncLlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    async def list_extract_runs(
-        self, *, extraction_agent_id: str, skip: typing.Optional[int] = None, limit: typing.Optional[int] = None
-    ) -> PaginatedExtractRunsResponse:
+    async def validate_extraction_schema(
+        self, *, data_schema: ExtractSchemaValidateRequestDataSchema
+    ) -> ExtractSchemaValidateResponse:
         """
-        Parameters:
-            - extraction_agent_id: str.
-
-            - skip: typing.Optional[int].
+        Validates an extraction agent's schema definition.
+        Returns the normalized and validated schema if valid, otherwise raises an HTTP 400.
 
-            - limit: typing.Optional[int].
+        Parameters:
+            - data_schema: ExtractSchemaValidateRequestDataSchema.
         ---
         from llama_cloud.client import AsyncLlamaCloud
 
         client = AsyncLlamaCloud(
             token="YOUR_TOKEN",
         )
-        await client.llama_extract.list_extract_runs(
-            extraction_agent_id="string",
-        )
+        await client.llama_extract.validate_extraction_schema()
         """
         _response = await self._client_wrapper.httpx_client.request(
-            "GET",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/runs"),
-            params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id, "skip": skip, "limit": limit}),
+            "POST",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents/schema/validation"
+            ),
+            json=jsonable_encoder({"data_schema": data_schema}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(PaginatedExtractRunsResponse, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ExtractSchemaValidateResponse, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -1849,29 +1716,50 @@ class AsyncLlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    async def get_latest_run_from_ui(self, *, extraction_agent_id: str) -> typing.Optional[ExtractRun]:
+    async def generate_extraction_schema(
+        self,
+        *,
+        project_id: typing.Optional[str] = None,
+        organization_id: typing.Optional[str] = None,
+        prompt: typing.Optional[str] = OMIT,
+        file_id: typing.Optional[str] = OMIT,
+    ) -> ExtractSchemaGenerateResponse:
         """
+        Generates an extraction agent's schema definition from a file and/or natural language prompt.
+
         Parameters:
-            - extraction_agent_id: str.
+            - project_id: typing.Optional[str].
+
+            - organization_id: typing.Optional[str].
+
+            - prompt: typing.Optional[str].
+
+            - file_id: typing.Optional[str].
         ---
         from llama_cloud.client import AsyncLlamaCloud
 
         client = AsyncLlamaCloud(
             token="YOUR_TOKEN",
         )
-        await client.llama_extract.get_latest_run_from_ui(
-            extraction_agent_id="string",
-        )
+        await client.llama_extract.generate_extraction_schema()
         """
+        _request: typing.Dict[str, typing.Any] = {}
+        if prompt is not OMIT:
+            _request["prompt"] = prompt
+        if file_id is not OMIT:
+            _request["file_id"] = file_id
         _response = await self._client_wrapper.httpx_client.request(
-            "GET",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/runs/latest-from-ui"),
-            params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id}),
+            "POST",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents/schema/generate"
+            ),
+            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(typing.Optional[ExtractRun], _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ExtractSchemaGenerateResponse, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -1880,12 +1768,12 @@ class AsyncLlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    async def get_run_by_job_id(
-        self, job_id: str, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
-    ) -> ExtractRun:
+    async def get_extraction_agent_by_name(
+        self, name: str, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
+    ) -> ExtractAgent:
         """
         Parameters:
-            - job_id: str.
+            - name: str.
 
             - project_id: typing.Optional[str].
 
@@ -1896,19 +1784,21 @@ class AsyncLlamaExtractClient:
         client = AsyncLlamaCloud(
             token="YOUR_TOKEN",
         )
-        await client.llama_extract.get_run_by_job_id(
-            job_id="string",
+        await client.llama_extract.get_extraction_agent_by_name(
+            name="string",
         )
         """
         _response = await self._client_wrapper.httpx_client.request(
             "GET",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/runs/by-job/{job_id}"),
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/by-name/{name}"
+            ),
             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(ExtractRun, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ExtractAgent, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -1917,13 +1807,14 @@ class AsyncLlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    async def get_run(
-        self, run_id: str, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
-    ) -> ExtractRun:
+    async def get_or_create_default_extraction_agent(
+        self, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
+    ) -> ExtractAgent:
         """
-        Parameters:
-            - run_id: str.
+        Get or create a default extraction agent for the current project.
+        The default agent has an empty schema and default configuration.
 
+        Parameters:
             - project_id: typing.Optional[str].
 
             - organization_id: typing.Optional[str].
@@ -1933,19 +1824,19 @@ class AsyncLlamaExtractClient:
         client = AsyncLlamaCloud(
             token="YOUR_TOKEN",
         )
-        await client.llama_extract.get_run(
-            run_id="string",
-        )
+        await client.llama_extract.get_or_create_default_extraction_agent()
         """
         _response = await self._client_wrapper.httpx_client.request(
             "GET",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/runs/{run_id}"),
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents/default"
+            ),
             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(ExtractRun, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ExtractAgent, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -1954,35 +1845,30 @@ class AsyncLlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    async def delete_extraction_run(
-        self, run_id: str, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None
-    ) -> typing.Any:
+    async def get_extraction_agent(self, extraction_agent_id: str) -> ExtractAgent:
         """
         Parameters:
-            - run_id: str.
-
-            - project_id: typing.Optional[str].
-
-            - organization_id: typing.Optional[str].
+            - extraction_agent_id: str.
         ---
         from llama_cloud.client import AsyncLlamaCloud
 
         client = AsyncLlamaCloud(
             token="YOUR_TOKEN",
         )
-        await client.llama_extract.delete_extraction_run(
-            run_id="string",
+        await client.llama_extract.get_extraction_agent(
+            extraction_agent_id="string",
         )
         """
         _response = await self._client_wrapper.httpx_client.request(
-            "DELETE",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/runs/{run_id}"),
-            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
+            "GET",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/{extraction_agent_id}"
+            ),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(typing.Any, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(ExtractAgent, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -1991,38 +1877,16 @@ class AsyncLlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    async def extract_stateless(
-        self,
-        *,
-        project_id: typing.Optional[str] = None,
-        organization_id: typing.Optional[str] = None,
-        webhook_configurations: typing.Optional[typing.List[WebhookConfiguration]] = OMIT,
-        data_schema: ExtractStatelessRequestDataSchema,
-        config: ExtractConfig,
-        file_id: typing.Optional[str] = OMIT,
-        text: typing.Optional[str] = OMIT,
-        file: typing.Optional[FileData] = OMIT,
-    ) -> ExtractJob:
+    async def update_extraction_agent(
+        self, extraction_agent_id: str, *, data_schema: ExtractAgentUpdateDataSchema, config: ExtractConfig
+    ) -> ExtractAgent:
         """
-        Stateless extraction endpoint that uses a default extraction agent in the user's default project.
-        Requires data_schema, config, and either file_id, text, or base64 encoded file data.
-
         Parameters:
-            - project_id: typing.Optional[str].
-
-            - organization_id: typing.Optional[str].
-
-            - webhook_configurations: typing.Optional[typing.List[WebhookConfiguration]].
-
-            - data_schema: ExtractStatelessRequestDataSchema. The schema of the data to extract
-
-            - config: ExtractConfig. The configuration parameters for the extraction
-
-            - file_id: typing.Optional[str].
+            - extraction_agent_id: str.
 
-            - text: typing.Optional[str].
+            - data_schema: ExtractAgentUpdateDataSchema. The schema of the data
 
-            - file: typing.Optional[FileData].
+            - config: ExtractConfig. The configuration parameters for the extraction agent.
         ---
         from llama_cloud import (
             DocumentChunkMode,
@@ -2031,7 +1895,6 @@ class AsyncLlamaExtractClient:
             ExtractMode,
             ExtractModels,
             ExtractTarget,
-            FileData,
             PublicModelName,
         )
         from llama_cloud.client import AsyncLlamaCloud
@@ -2039,7 +1902,8 @@ class AsyncLlamaExtractClient:
         client = AsyncLlamaCloud(
             token="YOUR_TOKEN",
         )
-        await client.llama_extract.extract_stateless(
+        await client.llama_extract.update_extraction_agent(
+            extraction_agent_id="string",
             config=ExtractConfig(
                 priority=ExtractConfigPriority.LOW,
                 extraction_target=ExtractTarget.PER_DOC,
@@ -2048,31 +1912,51 @@ class AsyncLlamaExtractClient:
                 extract_model=ExtractModels.OPENAI_GPT_4_1,
                 chunk_mode=DocumentChunkMode.PAGE,
             ),
-            file=FileData(
-                data="string",
-                mime_type="string",
+        )
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "PUT",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/{extraction_agent_id}"
             ),
+            json=jsonable_encoder({"data_schema": data_schema, "config": config}),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExtractAgent, _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_extraction_agent(self, extraction_agent_id: str) -> typing.Any:
+        """
+        Parameters:
+            - extraction_agent_id: str.
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.llama_extract.delete_extraction_agent(
+            extraction_agent_id="string",
         )
         """
-        _request: typing.Dict[str, typing.Any] = {"data_schema": data_schema, "config": config}
-        if webhook_configurations is not OMIT:
-            _request["webhook_configurations"] = webhook_configurations
-        if file_id is not OMIT:
-            _request["file_id"] = file_id
-        if text is not OMIT:
-            _request["text"] = text
-        if file is not OMIT:
-            _request["file"] = file
         _response = await self._client_wrapper.httpx_client.request(
-            "POST",
-            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/run"),
-            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
-            json=jsonable_encoder(_request),
+            "DELETE",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/{extraction_agent_id}"
+            ),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(ExtractJob, _response.json())  # type: ignore
+            return pydantic.parse_obj_as(typing.Any, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try: