gllm-inference-binary 0.5.59__cp312-cp312-win_amd64.whl → 0.5.60__cp312-cp312-win_amd64.whl

gllm_inference/lm_invoker/batch/batch_operations.pyi

@@ -104,11 +104,12 @@ class BatchOperations:
         Returns:
             BatchStatus: The status of the batch job.
         """
-    async def retrieve(self, batch_id: str) -> dict[str, LMOutput]:
+    async def retrieve(self, batch_id: str, **kwargs: Any) -> dict[str, LMOutput]:
         """Retrieves the results of a batch job.
 
         Args:
             batch_id (str): The ID of the batch job to get the results of.
+            **kwargs (Any): Additional keyword arguments.
 
         Returns:
             dict[str, LMOutput]: The results of the batch job.

gllm_inference/lm_invoker/google_lm_invoker.pyi

@@ -6,8 +6,8 @@ from gllm_inference.constants import GOOGLE_SCOPES as GOOGLE_SCOPES, SECONDS_TO_
 from gllm_inference.exceptions import BaseInvokerError as BaseInvokerError, convert_http_status_to_base_invoker_error as convert_http_status_to_base_invoker_error
 from gllm_inference.exceptions.provider_error_map import GOOGLE_ERROR_MAPPING as GOOGLE_ERROR_MAPPING
 from gllm_inference.lm_invoker.lm_invoker import BaseLMInvoker as BaseLMInvoker
-from gllm_inference.lm_invoker.schema.google import InputType as InputType, Key as Key
-from gllm_inference.schema import Attachment as Attachment, AttachmentType as AttachmentType, LMOutput as LMOutput, Message as Message, MessageRole as MessageRole, ModelId as ModelId, ModelProvider as ModelProvider, Reasoning as Reasoning, ResponseSchema as ResponseSchema, ThinkingEvent as ThinkingEvent, TokenUsage as TokenUsage, ToolCall as ToolCall, ToolResult as ToolResult
+from gllm_inference.lm_invoker.schema.google import InputType as InputType, JobState as JobState, Key as Key
+from gllm_inference.schema import Attachment as Attachment, AttachmentType as AttachmentType, BatchStatus as BatchStatus, LMInput as LMInput, LMOutput as LMOutput, Message as Message, MessageRole as MessageRole, ModelId as ModelId, ModelProvider as ModelProvider, Reasoning as Reasoning, ResponseSchema as ResponseSchema, ThinkingEvent as ThinkingEvent, TokenUsage as TokenUsage, ToolCall as ToolCall, ToolResult as ToolResult
 from langchain_core.tools import Tool as LangChainTool
 from typing import Any
 
@@ -16,6 +16,7 @@ DEFAULT_THINKING_BUDGET: int
 REQUIRE_THINKING_MODEL_PREFIX: Incomplete
 IMAGE_GENERATION_MODELS: Incomplete
 YOUTUBE_URL_PATTERN: Incomplete
+BATCH_STATUS_MAP: Incomplete
 GOOGLE_FILE_URL_PATTERN: Incomplete
 
 class GoogleLMInvoker(BaseLMInvoker):
@@ -261,6 +262,94 @@ class GoogleLMInvoker(BaseLMInvoker):
         ```python
         lm_invoker = GoogleLMInvoker(..., retry_config=retry_config)
         ```
+
+    Batch processing:
+        The `GoogleLMInvoker` supports batch processing, which allows the language model to process multiple
+        requests in a single call. Batch processing is supported through the `batch` attribute.
+
+        Due to Google SDK limitations with batch processing:
+        1. Only inline requests are currently supported (not file-based or BigQuery sources).
+        2. The total size of all requests must be under 20MB.
+        3. Original request indices are not preserved in the results. The results are keyed by request index in the
+        format \'1\', \'2\', etc, in which order are preserved based on the original request order. If you want to use
+        custom request IDs, you can pass them as a list of strings to the `custom_request_ids` keyword argument
+
+        Usage example:
+        ```python
+        requests = {"1": "What color is the sky?", "2": "What color is the grass?"}
+        results = await lm_invoker.batch.invoke(requests)
+        ```
+
+        Output example:
+        ```python
+        {
+            "1": LMOutput(outputs=[LMOutputItem(type="text", output="The sky is blue.")]),
+            "2": LMOutput(finish_details={"type": "error", "message": "..."}),
+        }
+        ```
+
+        The `GoogleLMInvoker` also supports the following standalone batch processing operations:
+
+        1. Create a batch job:
+            ```python
+            requests = {"1": "What color is the sky?", "2": "What color is the grass?"}
+            batch_id = await lm_invoker.batch.create(requests)
+            ```
+
+        2. Get the status of a batch job:
+            ```python
+            status = await lm_invoker.batch.status(batch_id)
+            ```
+
+        3. Retrieve the results of a batch job:
+
+            In default, the results will be keyed by request index in the format \'1\', \'2\', etc,
+            in which order are preserved based on the original request order.
+
+
+            ```python
+            results = await lm_invoker.batch.retrieve(batch_id)
+            ```
+
+            Output example:
+            ```python
+            {
+                "1": LMOutput(outputs=[LMOutputItem(type="text", output="The sky is blue.")]),
+                "2": LMOutput(finish_details={"type": "error", "error": {"message": "...", ...}, ...}),
+            }
+            ```
+
+            If you pass custom_request_ids to the create method, the results will be keyed by the custom_request_ids.
+            ```python
+            results = await lm_invoker.batch.retrieve(batch_id, custom_request_ids=["request_1", "request_2"])
+            ```
+
+            Output example:
+            ```python
+            {
+                "request_1": LMOutput(outputs=[LMOutputItem(type="text", output="The sky is blue.")]),
+                "request_2": LMOutput(finish_details={"type": "error", "error": {"message": "...", ...}, ...}),
+            }
+            ```
+
+        4. List the batch jobs:
+            ```python
+            batch_jobs = await lm_invoker.batch.list()
+            ```
+
+            Output example:
+            ```python
+            [
+                {"id": "batch_123", "status": "finished"},
+                {"id": "batch_456", "status": "in_progress"},
+                {"id": "batch_789", "status": "canceling"},
+            ]
+            ```
+
+        5. Cancel a batch job:
+            ```python
+            await lm_invoker.batch.cancel(batch_id)
+            ```
     '''
     client_params: Incomplete
     image_generation: Incomplete

gllm_inference/lm_invoker/schema/google.pyi

@@ -7,8 +7,10 @@ class Key:
     FUNCTION: str
     FUNCTION_CALL: str
     HTTP_OPTIONS: str
+    ID: str
     NAME: str
     RETRY_OPTIONS: str
+    STATUS: str
     SYSTEM_INSTRUCTION: str
     THINKING_CONFIG: str
     TIMEOUT: str
@@ -16,9 +18,19 @@ class Key:
     RESPONSE_SCHEMA: str
     RESPONSE_MIME_TYPE: str
     VERTEXAI: str
+    CUSTOM_REQUEST_IDS: str
 
 class InputType:
     """Defines valid input types in Google."""
     APPLICATION_JSON: str
     MODEL: str
     USER: str
+
+class JobState:
+    """Defines valid output types in Google."""
+    JOB_STATE_CANCELLED: str
+    JOB_STATE_EXPIRED: str
+    JOB_STATE_FAILED: str
+    JOB_STATE_PENDING: str
+    JOB_STATE_RUNNING: str
+    JOB_STATE_SUCCEEDED: str

gllm_inference/schema/enums.pyi

@@ -9,9 +9,11 @@ class AttachmentType(StrEnum):
 
 class BatchStatus(StrEnum):
     """Defines the status of a batch job."""
-    CANCELING = 'canceling'
     IN_PROGRESS = 'in_progress'
     FINISHED = 'finished'
+    FAILED = 'failed'
+    CANCELING = 'canceling'
+    EXPIRED = 'expired'
     UNKNOWN = 'unknown'
 
 class LMEventType(StrEnum):

{gllm_inference_binary-0.5.59.dist-info → gllm_inference_binary-0.5.60.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: gllm-inference-binary
-Version: 0.5.59
+Version: 0.5.60
 Summary: A library containing components related to model inferences in Gen AI applications.
 Author-email: Henry Wicaksono <henry.wicaksono@gdplabs.id>, Resti Febrina <resti.febrina@gdplabs.id>
 Requires-Python: <3.14,>=3.11

{gllm_inference_binary-0.5.59.dist-info → gllm_inference_binary-0.5.60.dist-info}/RECORD

@@ -1,4 +1,4 @@
-gllm_inference.cp312-win_amd64.pyd,sha256=N0oHEnIhVKT1VotWdJthKu7g6O5hPcCoH4ChSlSPz9Q,3976192
+gllm_inference.cp312-win_amd64.pyd,sha256=yWHLDowySBzJo8GNdY3_KZzwO8LNXHCIdwJseQXqYYI,4029952
 gllm_inference.pyi,sha256=t6lCcDjutByvoSK439LdRhQ9i7dq9tmp0Vwr5aAuv4Y,5077
 gllm_inference/__init__.pyi,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 gllm_inference/constants.pyi,sha256=8jIYOyxJYVWUYXSXF3vag9HhHwjq1iU9tzPiosRHkWk,328
@@ -45,7 +45,7 @@ gllm_inference/lm_invoker/anthropic_lm_invoker.pyi,sha256=_Dst_88LOpC-FN01hApihx
 gllm_inference/lm_invoker/azure_openai_lm_invoker.pyi,sha256=uV98H2nJsElCTsxAuInZ9KSk1jOTq6SROAGQRPR-_r0,13173
 gllm_inference/lm_invoker/bedrock_lm_invoker.pyi,sha256=qXmFK6zsOM3nPfueEhY5pAfG24bZytA1jqemPa63vLY,10951
 gllm_inference/lm_invoker/datasaur_lm_invoker.pyi,sha256=FnpayOW_Zi0pWFSawLX8XahEnknbnpsRWrkhKZe8Y3U,8035
-gllm_inference/lm_invoker/google_lm_invoker.pyi,sha256=LFX9c7dQviIP3lRUmAlJPU50utTW3kF5rQRMLE7iFdU,16727
+gllm_inference/lm_invoker/google_lm_invoker.pyi,sha256=XFQigZlicGnpm9_p8Hso-CB8xoi5ENbJwJvE8TubKus,20339
 gllm_inference/lm_invoker/langchain_lm_invoker.pyi,sha256=ull3cX-iUT4hYMbixcxqfrNUxR8ZoR4Vt9ACVILQWSM,12126
 gllm_inference/lm_invoker/litellm_lm_invoker.pyi,sha256=qG8pPTiDJZR2e7wr5Q2VyceC227tz3QybX3UPihT5ng,11400
 gllm_inference/lm_invoker/lm_invoker.pyi,sha256=L_PHRCeHo0dNs6BjnB8H29irGib-qhxKYf7F7pZlU0E,8652
@@ -55,12 +55,12 @@ gllm_inference/lm_invoker/openai_lm_invoker.pyi,sha256=ReU37hrmYZFbLfCD_c14ryRgn
 gllm_inference/lm_invoker/portkey_lm_invoker.pyi,sha256=FYOp4BaDfOtompWIRhDqzMVVSK-TiFyw7JA4TznANQE,15236
 gllm_inference/lm_invoker/xai_lm_invoker.pyi,sha256=6beZsQjGUTo7TdzWBWksRzVGT58XyipErpGfiRq6NH0,13017
 gllm_inference/lm_invoker/batch/__init__.pyi,sha256=vJOTHRJ83oq8Bq0UsMdID9_HW5JAxr06gUs4aPRZfEE,130
-gllm_inference/lm_invoker/batch/batch_operations.pyi,sha256=o2U17M41RKVFW6j_oxy-SxU1JqUtVt75pKRxrqXzorE,5499
+gllm_inference/lm_invoker/batch/batch_operations.pyi,sha256=EKwINY8DQFOXquGGrUTr_Yg24ZrSyiiAo2hX8If9vyQ,5573
 gllm_inference/lm_invoker/schema/__init__.pyi,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 gllm_inference/lm_invoker/schema/anthropic.pyi,sha256=Ol_IqeBPgrmG5iaY3NV6AD-alC2HmUvljp0vI8GApWo,1154
 gllm_inference/lm_invoker/schema/bedrock.pyi,sha256=rB1AWfER2BBKZ5I219211YE2EUFPF25bhzysqjdPgiY,1080
 gllm_inference/lm_invoker/schema/datasaur.pyi,sha256=8lmb1PRbkqBsF_l7iOffxW0K5Xxpi69GW9Z7KxyxHTE,279
-gllm_inference/lm_invoker/schema/google.pyi,sha256=elXHrUMS46pbTsulk7hBXVVFcT022iD-_U_I590xeV8,529
+gllm_inference/lm_invoker/schema/google.pyi,sha256=LQ14PJyDOe3K5TYvE-gzE1fjpZCSAy-0Sy9Lmw6fICY,827
 gllm_inference/lm_invoker/schema/langchain.pyi,sha256=2OJOUQPlGdlUbIOTDOyiWDBOMm3MoVX-kU2nK0zQsF0,452
 gllm_inference/lm_invoker/schema/openai.pyi,sha256=GIrqEtUPinn8VD-w-38gOw0qiIYuVzM9cj5dRYuGIoQ,2387
 gllm_inference/lm_invoker/schema/openai_chat_completions.pyi,sha256=nNPb7ETC9IrJwkV5wfbGf6Co3-qdq4lhcXz0l_qYCE4,1261
@@ -114,7 +114,7 @@ gllm_inference/schema/activity.pyi,sha256=atrU4OwLesA9FEt1H7K3gsUWYNdOqpI5i2VdWk
 gllm_inference/schema/attachment.pyi,sha256=myJ_cI_h5mwUdvmMrWpSQIwj3nIxe8SD7HxO37o_3D4,4611
 gllm_inference/schema/code_exec_result.pyi,sha256=WQ-ARoGM9r6nyRX-A0Ro1XKiqrc9R3jRYXZpu_xo5S4,573
 gllm_inference/schema/config.pyi,sha256=NVmjQK6HipIE0dKSfx12hgIC0O-S1HEcAc-TWlXAF5A,689
-gllm_inference/schema/enums.pyi,sha256=aJjmCCUV4ASDM8VTiSJlxPxdapKkxXjS4_NqRplyUnE,2145
+gllm_inference/schema/enums.pyi,sha256=U-lADk7xNjA5rByem0fo0xDAy9T3GsekY8B5szTlWPQ,2193
 gllm_inference/schema/events.pyi,sha256=_CKuGNzb3j2Y1dOB2yssFkT_9FQz1AY4J_ApCwKNizU,4743
 gllm_inference/schema/lm_input.pyi,sha256=HxQiZgY7zcXh_Dw8nK8LSeBTZEHMPZVwmPmnfgSsAbs,197
 gllm_inference/schema/lm_output.pyi,sha256=N75CIF_2kZRdXKy2jvu9hhqzk5DrCbsHXTrhKqQ-7vo,11667
@@ -131,7 +131,7 @@ gllm_inference/utils/io_utils.pyi,sha256=Eg7dvHWdXslTKdjh1j3dG50i7r35XG2zTmJ9XXv
 gllm_inference/utils/langchain.pyi,sha256=4AwFiVAO0ZpdgmqeC4Pb5NJwBt8vVr0MSUqLeCdTscc,1194
 gllm_inference/utils/validation.pyi,sha256=OWRZxeVGIuuvNU0LqLGB-9gNmypvbH-LcSJx91rnH1k,453
 gllm_inference.build/.gitignore,sha256=aEiIwOuxfzdCmLZe4oB1JsBmCUxwG8x-u-HBCV9JT8E,1
-gllm_inference_binary-0.5.59.dist-info/METADATA,sha256=zgTWioKaUScz7TQm2RllQ_jv1d1l8CApNKZ1Bjo_kQ4,5945
-gllm_inference_binary-0.5.59.dist-info/WHEEL,sha256=x5rgv--I0NI0IT1Lh9tN1VG2cI637p3deednwYLKnxc,96
-gllm_inference_binary-0.5.59.dist-info/top_level.txt,sha256=FpOjtN80F-qVNgbScXSEyqa0w09FYn6301iq6qt69IQ,15
-gllm_inference_binary-0.5.59.dist-info/RECORD,,
+gllm_inference_binary-0.5.60.dist-info/METADATA,sha256=jFQ1DplA4e1zYc2YKbuvcnha_DNN3seGwOAm8YZG2u8,5945
+gllm_inference_binary-0.5.60.dist-info/WHEEL,sha256=x5rgv--I0NI0IT1Lh9tN1VG2cI637p3deednwYLKnxc,96
+gllm_inference_binary-0.5.60.dist-info/top_level.txt,sha256=FpOjtN80F-qVNgbScXSEyqa0w09FYn6301iq6qt69IQ,15
+gllm_inference_binary-0.5.60.dist-info/RECORD,,