llama-cloud 0.1.15__tar.gz → 0.1.17__tar.gz

{llama_cloud-0.1.15 → llama_cloud-0.1.17}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: llama-cloud
-Version: 0.1.15
+Version: 0.1.17
 Summary: 
 License: MIT
 Author: Logan Markewich

{llama_cloud-0.1.15 → llama_cloud-0.1.17}/llama_cloud/__init__.py

@@ -96,15 +96,7 @@ from .types import (
     EmbeddingModelConfigUpdateEmbeddingConfig_HuggingfaceApiEmbedding,
     EmbeddingModelConfigUpdateEmbeddingConfig_OpenaiEmbedding,
     EmbeddingModelConfigUpdateEmbeddingConfig_VertexaiEmbedding,
-    EvalDataset,
-    EvalDatasetJobParams,
-    EvalDatasetJobRecord,
     EvalExecutionParams,
-    EvalExecutionParamsOverride,
-    EvalMetric,
-    EvalQuestion,
-    EvalQuestionCreate,
-    EvalQuestionResult,
     ExtractAgent,
     ExtractAgentCreate,
     ExtractAgentCreateDataSchema,
@@ -169,9 +161,6 @@ from .types import (
     Llm,
     LlmModelData,
     LlmParameters,
-    LocalEval,
-    LocalEvalResults,
-    LocalEvalSets,
     ManagedIngestionStatus,
     ManagedIngestionStatusResponse,
     MarkdownElementNodeParser,
@@ -182,7 +171,6 @@ from .types import (
     MetadataFilterValue,
     MetadataFilters,
     MetadataFiltersFiltersItem,
-    MetricResult,
     NodeParser,
     NodeRelationship,
     NoneChunkingConfig,
@@ -246,6 +234,7 @@ from .types import (
     PipelineFileCustomMetadataValue,
     PipelineFilePermissionInfoValue,
     PipelineFileResourceInfoValue,
+    PipelineFileStatus,
     PipelineTransformConfig,
     PipelineTransformConfig_Advanced,
     PipelineTransformConfig_Auto,
@@ -261,9 +250,9 @@ from .types import (
     Project,
     ProjectCreate,
     PromptConf,
-    PromptMixinPrompts,
-    PromptSpec,
     PydanticProgramMode,
+    ReRankConfig,
+    ReRankerType,
     RecurringCreditGrant,
     RelatedNodeInfo,
     RelatedNodeInfoNodeType,
@@ -307,10 +296,10 @@ from .types import (
     TokenChunkingConfig,
     TokenTextSplitter,
     TransformationCategoryNames,
-    Usage,
-    UsageActiveAlertsItem,
     UsageAndPlan,
     UsageMetricResponse,
+    UsageResponse,
+    UsageResponseActiveAlertsItem,
     UserJobRecord,
     UserOrganization,
     UserOrganizationCreate,
@@ -474,15 +463,7 @@ __all__ = [
     "EmbeddingModelConfigUpdateEmbeddingConfig_HuggingfaceApiEmbedding",
     "EmbeddingModelConfigUpdateEmbeddingConfig_OpenaiEmbedding",
     "EmbeddingModelConfigUpdateEmbeddingConfig_VertexaiEmbedding",
-    "EvalDataset",
-    "EvalDatasetJobParams",
-    "EvalDatasetJobRecord",
     "EvalExecutionParams",
-    "EvalExecutionParamsOverride",
-    "EvalMetric",
-    "EvalQuestion",
-    "EvalQuestionCreate",
-    "EvalQuestionResult",
     "ExtractAgent",
     "ExtractAgentCreate",
     "ExtractAgentCreateDataSchema",
@@ -551,9 +532,6 @@ __all__ = [
     "Llm",
     "LlmModelData",
     "LlmParameters",
-    "LocalEval",
-    "LocalEvalResults",
-    "LocalEvalSets",
     "ManagedIngestionStatus",
     "ManagedIngestionStatusResponse",
     "MarkdownElementNodeParser",
@@ -564,7 +542,6 @@ __all__ = [
     "MetadataFilterValue",
     "MetadataFilters",
     "MetadataFiltersFiltersItem",
-    "MetricResult",
     "NodeParser",
     "NodeRelationship",
     "NoneChunkingConfig",
@@ -628,6 +605,7 @@ __all__ = [
     "PipelineFileCustomMetadataValue",
     "PipelineFilePermissionInfoValue",
     "PipelineFileResourceInfoValue",
+    "PipelineFileStatus",
     "PipelineFileUpdateCustomMetadataValue",
     "PipelineTransformConfig",
     "PipelineTransformConfig_Advanced",
@@ -653,9 +631,9 @@ __all__ = [
     "Project",
     "ProjectCreate",
     "PromptConf",
-    "PromptMixinPrompts",
-    "PromptSpec",
     "PydanticProgramMode",
+    "ReRankConfig",
+    "ReRankerType",
     "RecurringCreditGrant",
     "RelatedNodeInfo",
     "RelatedNodeInfoNodeType",
@@ -701,10 +679,10 @@ __all__ = [
     "TransformationCategoryNames",
     "UnprocessableEntityError",
     "UpdateReportPlanApiV1ReportsReportIdPlanPatchRequestAction",
-    "Usage",
-    "UsageActiveAlertsItem",
     "UsageAndPlan",
     "UsageMetricResponse",
+    "UsageResponse",
+    "UsageResponseActiveAlertsItem",
     "UserJobRecord",
     "UserOrganization",
     "UserOrganizationCreate",

{llama_cloud-0.1.15 → llama_cloud-0.1.17}/llama_cloud/environment.py

@@ -4,4 +4,4 @@ import enum
 
 
 class LlamaCloudEnvironment(enum.Enum):
-    DEFAULT = "https://api.cloud.llamaindex.ai/"
+    DEFAULT = "https://api.cloud.llamaindex.ai"

{llama_cloud-0.1.15 → llama_cloud-0.1.17}/llama_cloud/resources/chat_apps/client.py

@@ -95,6 +95,8 @@ class ChatAppsClient:
             CompositeRetrievalMode,
             LlmParameters,
             PresetCompositeRetrievalParams,
+            ReRankConfig,
+            ReRankerType,
             SupportedLlmModelNames,
         )
         from llama_cloud.client import LlamaCloud
@@ -110,6 +112,9 @@ class ChatAppsClient:
             ),
             retrieval_config=PresetCompositeRetrievalParams(
                 mode=CompositeRetrievalMode.ROUTING,
+                rerank_config=ReRankConfig(
+                    type=ReRankerType.SYSTEM_DEFAULT,
+                ),
             ),
         )
         """
@@ -200,6 +205,8 @@ class ChatAppsClient:
             CompositeRetrievalMode,
             LlmParameters,
             PresetCompositeRetrievalParams,
+            ReRankConfig,
+            ReRankerType,
             SupportedLlmModelNames,
         )
         from llama_cloud.client import LlamaCloud
@@ -214,6 +221,9 @@ class ChatAppsClient:
             ),
             retrieval_config=PresetCompositeRetrievalParams(
                 mode=CompositeRetrievalMode.ROUTING,
+                rerank_config=ReRankConfig(
+                    type=ReRankerType.SYSTEM_DEFAULT,
+                ),
             ),
         )
         """
@@ -378,6 +388,8 @@ class AsyncChatAppsClient:
             CompositeRetrievalMode,
             LlmParameters,
             PresetCompositeRetrievalParams,
+            ReRankConfig,
+            ReRankerType,
             SupportedLlmModelNames,
         )
         from llama_cloud.client import AsyncLlamaCloud
@@ -393,6 +405,9 @@ class AsyncChatAppsClient:
             ),
             retrieval_config=PresetCompositeRetrievalParams(
                 mode=CompositeRetrievalMode.ROUTING,
+                rerank_config=ReRankConfig(
+                    type=ReRankerType.SYSTEM_DEFAULT,
+                ),
             ),
         )
         """
@@ -483,6 +498,8 @@ class AsyncChatAppsClient:
             CompositeRetrievalMode,
             LlmParameters,
             PresetCompositeRetrievalParams,
+            ReRankConfig,
+            ReRankerType,
             SupportedLlmModelNames,
         )
         from llama_cloud.client import AsyncLlamaCloud
@@ -497,6 +514,9 @@ class AsyncChatAppsClient:
             ),
             retrieval_config=PresetCompositeRetrievalParams(
                 mode=CompositeRetrievalMode.ROUTING,
+                rerank_config=ReRankConfig(
+                    type=ReRankerType.SYSTEM_DEFAULT,
+                ),
             ),
         )
         """

llama_cloud-0.1.17/llama_cloud/resources/evals/client.py

@@ -0,0 +1,85 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+import urllib.parse
+from json.decoder import JSONDecodeError
+
+from ...core.api_error import ApiError
+from ...core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
+from ...errors.unprocessable_entity_error import UnprocessableEntityError
+from ...types.http_validation_error import HttpValidationError
+from ...types.supported_llm_model import SupportedLlmModel
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class EvalsClient:
+    def __init__(self, *, client_wrapper: SyncClientWrapper):
+        self._client_wrapper = client_wrapper
+
+    def list_supported_models(self) -> typing.List[SupportedLlmModel]:
+        """
+        List supported models.
+
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.evals.list_supported_models()
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/evals/models"),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(typing.List[SupportedLlmModel], _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+
+class AsyncEvalsClient:
+    def __init__(self, *, client_wrapper: AsyncClientWrapper):
+        self._client_wrapper = client_wrapper
+
+    async def list_supported_models(self) -> typing.List[SupportedLlmModel]:
+        """
+        List supported models.
+
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.evals.list_supported_models()
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/evals/models"),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(typing.List[SupportedLlmModel], _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)

{llama_cloud-0.1.15 → llama_cloud-0.1.17}/llama_cloud/resources/llama_extract/client.py

@@ -336,9 +336,11 @@ 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, *, request: ExtractJobCreate) -> ExtractJob:
+    def run_job(self, *, from_ui: typing.Optional[bool] = None, request: ExtractJobCreate) -> ExtractJob:
         """
         Parameters:
+            - from_ui: typing.Optional[bool].
+
             - request: ExtractJobCreate.
         ---
         from llama_cloud import (
@@ -366,6 +368,7 @@ class LlamaExtractClient:
         _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),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
@@ -411,10 +414,16 @@ class LlamaExtractClient:
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
     def run_job_test_user(
-        self, *, job_create: ExtractJobCreate, extract_settings: typing.Optional[LlamaExtractSettings] = OMIT
+        self,
+        *,
+        from_ui: typing.Optional[bool] = None,
+        job_create: ExtractJobCreate,
+        extract_settings: typing.Optional[LlamaExtractSettings] = OMIT,
     ) -> ExtractJob:
         """
         Parameters:
+            - from_ui: typing.Optional[bool].
+
             - job_create: ExtractJobCreate.
 
             - extract_settings: typing.Optional[LlamaExtractSettings].
@@ -457,6 +466,7 @@ class LlamaExtractClient:
         _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),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
@@ -471,9 +481,13 @@ 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(self, *, request: ExtractJobCreateBatch) -> typing.List[ExtractJob]:
+    def run_batch_jobs(
+        self, *, from_ui: typing.Optional[bool] = None, request: ExtractJobCreateBatch
+    ) -> typing.List[ExtractJob]:
         """
         Parameters:
+            - from_ui: typing.Optional[bool].
+
             - request: ExtractJobCreateBatch.
         ---
         from llama_cloud import (
@@ -501,6 +515,7 @@ class LlamaExtractClient:
         _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}),
             json=jsonable_encoder(request),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
@@ -582,6 +597,37 @@ 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]:
+        """
+        Parameters:
+            - extraction_agent_id: str.
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        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()}/", "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(typing.Optional[ExtractRun], _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
     def get_run_by_job_id(self, job_id: str) -> ExtractRun:
         """
         Parameters:
@@ -976,9 +1022,11 @@ 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(self, *, request: ExtractJobCreate) -> ExtractJob:
+    async def run_job(self, *, from_ui: typing.Optional[bool] = None, request: ExtractJobCreate) -> ExtractJob:
         """
         Parameters:
+            - from_ui: typing.Optional[bool].
+
             - request: ExtractJobCreate.
         ---
         from llama_cloud import (
@@ -1006,6 +1054,7 @@ class AsyncLlamaExtractClient:
         _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,
@@ -1051,10 +1100,16 @@ class AsyncLlamaExtractClient:
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
     async def run_job_test_user(
-        self, *, job_create: ExtractJobCreate, extract_settings: typing.Optional[LlamaExtractSettings] = OMIT
+        self,
+        *,
+        from_ui: typing.Optional[bool] = None,
+        job_create: ExtractJobCreate,
+        extract_settings: typing.Optional[LlamaExtractSettings] = OMIT,
     ) -> ExtractJob:
         """
         Parameters:
+            - from_ui: typing.Optional[bool].
+
             - job_create: ExtractJobCreate.
 
             - extract_settings: typing.Optional[LlamaExtractSettings].
@@ -1097,6 +1152,7 @@ class AsyncLlamaExtractClient:
         _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}),
             json=jsonable_encoder(_request),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
@@ -1111,9 +1167,13 @@ class AsyncLlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    async def run_batch_jobs(self, *, request: ExtractJobCreateBatch) -> typing.List[ExtractJob]:
+    async def run_batch_jobs(
+        self, *, from_ui: typing.Optional[bool] = None, request: ExtractJobCreateBatch
+    ) -> typing.List[ExtractJob]:
         """
         Parameters:
+            - from_ui: typing.Optional[bool].
+
             - request: ExtractJobCreateBatch.
         ---
         from llama_cloud import (
@@ -1141,6 +1201,7 @@ class AsyncLlamaExtractClient:
         _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),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
@@ -1222,6 +1283,37 @@ 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]:
+        """
+        Parameters:
+            - extraction_agent_id: 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",
+        )
+        """
+        _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}),
+            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
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
     async def get_run_by_job_id(self, job_id: str) -> ExtractRun:
         """
         Parameters:

{llama_cloud-0.1.15 → llama_cloud-0.1.17}/llama_cloud/resources/parsing/client.py

@@ -248,6 +248,7 @@ class ParsingClient:
         vendor_multimodal_model_name: str,
         model: str,
         webhook_url: str,
+        preset: str,
         parse_mode: typing.Optional[ParsingMode] = OMIT,
         system_prompt: str,
         system_prompt_append: str,
@@ -385,6 +386,8 @@ class ParsingClient:
 
             - webhook_url: str.
 
+            - preset: str.
+
             - parse_mode: typing.Optional[ParsingMode].
 
             - system_prompt: str.
@@ -484,6 +487,7 @@ class ParsingClient:
             "vendor_multimodal_model_name": vendor_multimodal_model_name,
             "model": model,
             "webhook_url": webhook_url,
+            "preset": preset,
             "system_prompt": system_prompt,
             "system_prompt_append": system_prompt_append,
             "user_prompt": user_prompt,
@@ -1224,6 +1228,7 @@ class AsyncParsingClient:
         vendor_multimodal_model_name: str,
         model: str,
         webhook_url: str,
+        preset: str,
         parse_mode: typing.Optional[ParsingMode] = OMIT,
         system_prompt: str,
         system_prompt_append: str,
@@ -1361,6 +1366,8 @@ class AsyncParsingClient:
 
             - webhook_url: str.
 
+            - preset: str.
+
             - parse_mode: typing.Optional[ParsingMode].
 
             - system_prompt: str.
@@ -1460,6 +1467,7 @@ class AsyncParsingClient:
             "vendor_multimodal_model_name": vendor_multimodal_model_name,
             "model": model,
             "webhook_url": webhook_url,
+            "preset": preset,
             "system_prompt": system_prompt,
             "system_prompt_append": system_prompt_append,
             "user_prompt": user_prompt,