gllm-inference-binary 0.5.40__cp311-cp311-win_amd64.whl → 0.5.66__cp311-cp311-win_amd64.whl

gllm_inference/schema/lm_output.pyi

@@ -1,6 +1,8 @@
-from gllm_core.schema import Chunk as Chunk
+from _typeshed import Incomplete
+from gllm_core.schema import Chunk
 from gllm_inference.schema.attachment import Attachment as Attachment
 from gllm_inference.schema.code_exec_result import CodeExecResult as CodeExecResult
+from gllm_inference.schema.enums import LMOutputType as LMOutputType
 from gllm_inference.schema.mcp import MCPCall as MCPCall
 from gllm_inference.schema.reasoning import Reasoning as Reasoning
 from gllm_inference.schema.token_usage import TokenUsage as TokenUsage
@@ -8,37 +10,257 @@ from gllm_inference.schema.tool_call import ToolCall as ToolCall
 from pydantic import BaseModel
 from typing import Any
 
+LMOutputData = str | dict[str, Any] | BaseModel | Attachment | ToolCall | Reasoning | Chunk | CodeExecResult | MCPCall
+logger: Incomplete
+
+class LMOutputItem(BaseModel):
+    """Defines the output item of a language model.
+
+    Attributes:
+        type (str): The type of the output item.
+        output (LMOutputData): The output data of the output item.
+    """
+    type: str
+    output: LMOutputData
+
 class LMOutput(BaseModel):
     """Defines the output of a language model.
 
     Attributes:
-        response (str): The text response. Defaults to an empty string.
-        attachments (list[Attachment]): The attachments, if the language model decides to output attachments.
-            Defaults to an empty list.
-        tool_calls (list[ToolCall]): The tool calls, if the language model decides to invoke tools.
-            Defaults to an empty list.
-        structured_output (dict[str, Any] | BaseModel | None): The structured output, if a response schema is defined
-            for the language model. Defaults to None.
+        outputs (list[LMOutputItem]): The outputs of the language model in sequential order. Defaults to an empty list.
         token_usage (TokenUsage | None): The token usage analytics, if requested. Defaults to None.
         duration (float | None): The duration of the invocation in seconds, if requested. Defaults to None.
         finish_details (dict[str, Any]): The details about how the generation finished, if requested.
             Defaults to an empty dictionary.
-        reasoning (list[Reasoning]): The reasoning, if the language model is configured to output reasoning.
-            Defaults to an empty list.
-        citations (list[Chunk]): The citations, if the language model outputs citations. Defaults to an empty list.
-        code_exec_results (list[CodeExecResult]): The code execution results, if the language model decides to
-            execute code. Defaults to an empty list.
-        mcp_calls (list[MCPCall]): The MCP calls, if the language model decides to invoke MCP tools.
-            Defaults to an empty list.
+
+        text (str): The first text response.
+        structured_output (dict[str, Any] | BaseModel | None): The first structured output.
+
+        texts (list[str]): The texts from the outputs.
+        structured_outputs (list[dict[str, Any] | BaseModel]): The structured outputs from the outputs.
+        attachments (list[Attachment]): The attachments from the outputs.
+        tool_calls (list[ToolCall]): The tool calls from the outputs.
+        thinkings (list[Reasoning]): The thinkings from the outputs.
+        citations (list[Chunk]): The citations from the outputs.
+        code_exec_results (list[CodeExecResult]): The code exec results from the outputs.
+        mcp_calls (list[MCPCall]): The MCP calls from the outputs.
+
+        response (str): Deprecated. Replaced by `text`.
+        reasoning (list[Reasoning]): Deprecated. Replaced by `thinkings`.
     """
-    response: str
-    attachments: list[Attachment]
-    tool_calls: list[ToolCall]
-    structured_output: dict[str, Any] | BaseModel | None
+    outputs: list[LMOutputItem]
     token_usage: TokenUsage | None
     duration: float | None
     finish_details: dict[str, Any]
-    reasoning: list[Reasoning]
-    citations: list[Chunk]
-    code_exec_results: list[CodeExecResult]
-    mcp_calls: list[MCPCall]
+    def __init__(self, *, outputs: list[LMOutputItem] | None = None, token_usage: TokenUsage | None = None, duration: float | None = None, finish_details: dict[str, Any] | None = None, response: str = '', structured_output: dict[str, Any] | BaseModel | None = None, tool_calls: list[ToolCall] | None = None, reasoning: list[Reasoning] | None = None, attachments: list[Attachment] | None = None, citations: list[Chunk] | None = None, code_exec_results: list[CodeExecResult] | None = None, mcp_calls: list[MCPCall] | None = None) -> None:
+        """Initialize the LMOutput.
+
+        This constructor is created for backward compatibility with the legacy method to initialize the LMOutput.
+        This constructor will be removed in v0.6.
+
+        Args:
+            outputs (list[LMOutputItem] | None, optional): The output items. Defaults to an empty list.
+            token_usage (TokenUsage | None, optional): The token usage analytics. Defaults to None.
+            duration (float | None, optional): The duration of the invocation in seconds. Defaults to None.
+            finish_details (dict[str, Any] | None, optional): The details about how the generation finished.
+                Defaults to an empty dictionary.
+            response (str, optional): The first text response. Defaults to an empty string.
+            structured_output (dict[str, Any] | BaseModel | None, optional): The first structured output.
+                Defaults to None.
+            tool_calls (list[ToolCall] | None, optional): The tool calls. Defaults to None.
+            reasoning (list[Reasoning] | None, optional): The thinkings. Defaults to None.
+            attachments (list[Attachment] | None, optional): The attachments. Defaults to None.
+            citations (list[Chunk] | None, optional): The citations. Defaults to None.
+            code_exec_results (list[CodeExecResult] | None, optional): The code exec results. Defaults to None.
+            mcp_calls (list[MCPCall] | None, optional): The MCP calls. Defaults to None.
+        """
+    @property
+    def response(self) -> str:
+        """Deprecated property to get the first text response from the LMOutput.
+
+        Returns:
+            str: The first text response from the LMOutput.
+        """
+    @response.setter
+    def response(self, value: str) -> None:
+        """Deprecated setter to set the first text response to the LMOutput.
+
+        Args:
+            value (str): The first text response to set.
+        """
+    @property
+    def text(self) -> str:
+        """Get the first text from the LMOutput.
+
+        Returns:
+            str: The first text from the LMOutput.
+        """
+    @property
+    def structured_output(self) -> dict[str, Any] | BaseModel | None:
+        """Deprecated property to get the first structured output from the LMOutput.
+
+        Returns:
+            dict[str, Any] | BaseModel | None: The first structured output from the LMOutput.
+        """
+    @structured_output.setter
+    def structured_output(self, value: dict[str, Any] | BaseModel) -> None:
+        """Deprecated setter to set the first structured output to the LMOutput.
+
+        Args:
+            value (dict[str, Any] | BaseModel): The first structured output to set.
+        """
+    @property
+    def texts(self) -> list[str]:
+        """Get the texts from the LMOutput.
+
+        Returns:
+            list[str]: The texts from the LMOutput.
+        """
+    @property
+    def structured_outputs(self) -> list[dict[str, Any] | BaseModel]:
+        """Get the structured outputs from the LMOutput.
+
+        Returns:
+            list[dict[str, Any] | BaseModel]: The structured outputs from the LMOutput.
+        """
+    @property
+    def attachments(self) -> list[Attachment]:
+        """Get the attachments from the LMOutput.
+
+        Returns:
+            list[Attachment]: The attachments from the LMOutput.
+        """
+    @attachments.setter
+    def attachments(self, value: list[Attachment]) -> None:
+        """Deprecated setter to set the attachments to the LMOutput.
+
+        Args:
+            value (list[Attachment]): The attachments to set.
+        """
+    @property
+    def tool_calls(self) -> list[ToolCall]:
+        """Get the tool calls from the LMOutput.
+
+        Returns:
+            list[ToolCall]: The tool calls from the LMOutput.
+        """
+    @tool_calls.setter
+    def tool_calls(self, value: list[ToolCall]) -> None:
+        """Deprecated setter to set the tool calls to the LMOutput.
+
+        Args:
+            value (list[ToolCall]): The tool calls to set.
+        """
+    @property
+    def reasoning(self) -> list[Reasoning]:
+        """Deprecated property to get the thinkings from the LMOutput.
+
+        Returns:
+            list[Reasoning]: The thinkings from the LMOutput.
+        """
+    @reasoning.setter
+    def reasoning(self, value: list[Reasoning]) -> None:
+        """Deprecated setter to set the thinkings to the LMOutput.
+
+        Args:
+            value (list[Reasoning]): The thinkings to set.
+        """
+    @property
+    def thinkings(self) -> list[Reasoning]:
+        """Get the thinkings from the LMOutput.
+
+        Returns:
+            list[Reasoning]: The thinkings from the LMOutput.
+        """
+    @property
+    def citations(self) -> list[Chunk]:
+        """Get the citations from the LMOutput.
+
+        Returns:
+            list[Chunk]: The citations from the LMOutput.
+        """
+    @citations.setter
+    def citations(self, value: list[Chunk]) -> None:
+        """Deprecated setter to set the citations to the LMOutput.
+
+        Args:
+            value (list[Chunk]): The citations to set.
+        """
+    @property
+    def code_exec_results(self) -> list[CodeExecResult]:
+        """Get the code exec results from the LMOutput.
+
+        Returns:
+            list[CodeExecResult]: The code exec results from the LMOutput.
+        """
+    @code_exec_results.setter
+    def code_exec_results(self, value: list[CodeExecResult]) -> None:
+        """Deprecated setter to set the code exec results to the LMOutput.
+
+        Args:
+            value (list[CodeExecResult]): The code exec results to set.
+        """
+    @property
+    def mcp_calls(self) -> list[MCPCall]:
+        """Get the MCP calls from the LMOutput.
+
+        Returns:
+            list[MCPCall]: The MCP calls from the LMOutput.
+        """
+    @mcp_calls.setter
+    def mcp_calls(self, value: list[MCPCall]) -> None:
+        """Deprecated setter to set the MCP calls to the LMOutput.
+
+        Args:
+            value (list[MCPCall]): The MCP calls to set.
+        """
+    def add_text(self, text: str | list[str]) -> None:
+        """Add an output or a list of outputs to the LMOutput.
+
+        Args:
+            text (str | list[str]): The text or a list of texts to add.
+        """
+    def add_attachment(self, attachment: Attachment | list[Attachment]) -> None:
+        """Add an attachment or a list of attachments to the LMOutput.
+
+        Args:
+            attachment (Attachment | list[Attachment]): The attachment or a list of attachments to add.
+        """
+    def add_tool_call(self, tool_call: ToolCall | list[ToolCall]) -> None:
+        """Add a tool call or a list of tool calls to the LMOutput.
+
+        Args:
+            tool_call (ToolCall | list[ToolCall]): The tool call or a list of tool calls to add.
+        """
+    def add_structured(self, structured: dict[str, Any] | BaseModel | list[dict[str, Any] | BaseModel]) -> None:
+        """Add a structured output or a list of structured outputs to the LMOutput.
+
+        Args:
+            structured (dict[str, Any] | BaseModel | list[dict[str, Any] | BaseModel]): The structured output
+                or a list of structured outputs to add.
+        """
+    def add_thinking(self, thinking: Reasoning | list[Reasoning]) -> None:
+        """Add a thinking or a list of thoughts to the LMOutput.
+
+        Args:
+            thinking (Reasoning | list[Reasoning]): The thinking or a list of thoughts to add.
+        """
+    def add_citation(self, citation: Chunk | list[Chunk]) -> None:
+        """Add a citation or a list of citations to the LMOutput.
+
+        Args:
+            citation (Chunk | list[Chunk]): The citation or a list of citations to add.
+        """
+    def add_code_exec_result(self, code_exec_result: CodeExecResult | list[CodeExecResult]) -> None:
+        """Add a code exec result or a list of code exec results to the LMOutput.
+
+        Args:
+            code_exec_result (CodeExecResult | list[CodeExecResult]): The code exec result or a list of code exec
+                results to add.
+        """
+    def add_mcp_call(self, mcp_call: MCPCall | list[MCPCall]) -> None:
+        """Add an MCP call or a list of MCP calls to the LMOutput.
+
+        Args:
+            mcp_call (MCPCall | list[MCPCall]): The MCP call or a list of MCP calls to add.
+        """

gllm_inference/schema/model_id.pyi

@@ -1,6 +1,5 @@
 from _typeshed import Incomplete
 from enum import StrEnum
-from gllm_inference.utils import validate_string_enum as validate_string_enum
 from pydantic import BaseModel
 
 PROVIDER_SEPARATOR: str
@@ -12,19 +11,23 @@ class ModelProvider(StrEnum):
     ANTHROPIC = 'anthropic'
     AZURE_OPENAI = 'azure-openai'
     BEDROCK = 'bedrock'
+    COHERE = 'cohere'
     DATASAUR = 'datasaur'
     GOOGLE = 'google'
+    JINA = 'jina'
     LANGCHAIN = 'langchain'
     LITELLM = 'litellm'
     OPENAI = 'openai'
+    PORTKEY = 'portkey'
     OPENAI_CHAT_COMPLETIONS = 'openai-chat-completions'
     OPENAI_COMPATIBLE = 'openai-compatible'
+    SEA_LION = 'sea-lion'
     TWELVELABS = 'twelvelabs'
     VOYAGE = 'voyage'
     XAI = 'xai'
 
-OPTIONAL_PATH_PROVIDERS: Incomplete
-PATH_SUPPORTING_PROVIDERS: Incomplete
+PROVIDERS_OPTIONAL_PATH: Incomplete
+PROVIDERS_SUPPORT_PATH: Incomplete
 
 class ModelId(BaseModel):
     '''Defines a representation of a valid model id.
@@ -45,6 +48,16 @@ class ModelId(BaseModel):
         model_id = ModelId.from_string("bedrock/us.anthropic.claude-sonnet-4-20250514-v1:0")
         ```
 
+        # Using Cohere
+        ```python
+        model_id = ModelId.from_string("cohere/embed-english-v3.0")
+        ```
+
+        # Using Cohere with custom endpoint
+        ```python
+        model_id = ModelId.from_string("cohere/https://my-cohere-url:8000/v1:my-model-name")
+        ```
+
         # Using Datasaur
         ```python
         model_id = ModelId.from_string("datasaur/https://deployment.datasaur.ai/api/deployment/teamId/deploymentId/")
@@ -55,6 +68,16 @@ class ModelId(BaseModel):
         model_id = ModelId.from_string("google/gemini-2.5-flash-lite")
         ```
 
+        # Using Jina
+        ```python
+        model_id = ModelId.from_string("jina/jina-embeddings-v2-large")
+        ```
+
+        # Using Jina with custom endpoint
+        ```python
+        model_id = ModelId.from_string("jina/https://my-jina-url:8000/v1:my-model-name")
+        ```
+
         # Using OpenAI
         ```python
         model_id = ModelId.from_string("openai/gpt-5-nano")
@@ -94,6 +117,7 @@ class ModelId(BaseModel):
         ```python
         model_id = ModelId.from_string("langchain/langchain_openai.ChatOpenAI:gpt-4o-mini")
         ```
+
         For the list of supported providers, please refer to the following table:
         https://python.langchain.com/docs/integrations/chat/#featured-providers
 

gllm_inference/utils/validation.pyi

@@ -1,5 +1,8 @@
+from _typeshed import Incomplete
 from enum import StrEnum
 
+logger: Incomplete
+
 def validate_string_enum(enum_type: type[StrEnum], value: str) -> None:
     """Validates that the provided value is a valid string enum value.
 

gllm_inference.pyi

@@ -14,7 +14,9 @@ import gllm_core
 import gllm_core.utils
 import gllm_inference.em_invoker.AzureOpenAIEMInvoker
 import gllm_inference.em_invoker.BedrockEMInvoker
+import gllm_inference.em_invoker.CohereEMInvoker
 import gllm_inference.em_invoker.GoogleEMInvoker
+import gllm_inference.em_invoker.JinaEMInvoker
 import gllm_inference.em_invoker.LangChainEMInvoker
 import gllm_inference.em_invoker.OpenAICompatibleEMInvoker
 import gllm_inference.em_invoker.OpenAIEMInvoker
@@ -30,6 +32,8 @@ import gllm_inference.lm_invoker.LiteLLMLMInvoker
 import gllm_inference.lm_invoker.OpenAIChatCompletionsLMInvoker
 import gllm_inference.lm_invoker.OpenAICompatibleLMInvoker
 import gllm_inference.lm_invoker.OpenAILMInvoker
+import gllm_inference.lm_invoker.PortkeyLMInvoker
+import gllm_inference.lm_invoker.SeaLionLMInvoker
 import gllm_inference.lm_invoker.XAILMInvoker
 import gllm_inference.prompt_builder.PromptBuilder
 import gllm_inference.output_parser.JSONOutputParser
@@ -45,24 +49,26 @@ import gllm_inference.schema.ModelId
 import gllm_inference.schema.ModelProvider
 import gllm_inference.schema.TruncationConfig
 import asyncio
+import base64
 import enum
 import gllm_inference.exceptions.BaseInvokerError
 import gllm_inference.exceptions.convert_http_status_to_base_invoker_error
+import gllm_inference.schema.Attachment
+import gllm_inference.schema.AttachmentType
+import gllm_inference.schema.EMContent
 import gllm_inference.schema.Vector
 import aioboto3
+import cohere
 import asyncio.CancelledError
 import gllm_inference.exceptions.convert_to_base_invoker_error
-import gllm_inference.schema.Attachment
-import gllm_inference.schema.AttachmentType
-import gllm_inference.schema.EMContent
 import gllm_inference.schema.TruncateSide
 import google
 import google.auth
 import google.genai
 import google.genai.types
-import concurrent
-import concurrent.futures
-import concurrent.futures.ThreadPoolExecutor
+import httpx
+import gllm_inference.exceptions.ProviderInternalError
+import gllm_core.utils.concurrency
 import langchain_core
 import langchain_core.embeddings
 import gllm_inference.exceptions.InvokerRuntimeError
@@ -71,14 +77,14 @@ import gllm_inference.utils.load_langchain_model
 import gllm_inference.utils.parse_model_data
 import openai
 import io
-import httpx
 import twelvelabs
-import base64
 import sys
 import voyageai
 import voyageai.client_async
 import http
 import http.HTTPStatus
+import __future__
+import uuid
 import gllm_core.constants
 import gllm_core.event
 import gllm_core.schema
@@ -108,10 +114,7 @@ import inspect
 import time
 import jsonschema
 import gllm_inference.lm_invoker.batch.BatchOperations
-import gllm_inference.schema.Activity
 import gllm_inference.schema.MessageContent
-import gllm_inference.utils.validate_string_enum
-import __future__
 import gllm_inference.schema.ActivityEvent
 import gllm_inference.schema.CodeEvent
 import gllm_inference.schema.CodeExecResult
@@ -120,26 +123,33 @@ import gllm_inference.schema.MCPCallActivity
 import gllm_inference.schema.MCPListToolsActivity
 import gllm_inference.schema.MCPServer
 import gllm_inference.schema.WebSearchActivity
+import logging
+import portkey_ai
 import xai_sdk
 import xai_sdk.chat
 import xai_sdk.search
 import xai_sdk.proto
 import xai_sdk.proto.v5
 import xai_sdk.proto.v5.chat_pb2
+import jinja2
+import jinja2.sandbox
+import gllm_inference.schema.JinjaEnvType
+import gllm_inference.prompt_builder.format_strategy.JinjaFormatStrategy
+import gllm_inference.prompt_builder.format_strategy.StringFormatStrategy
+import gllm_inference.schema.HistoryFormatter
 import transformers
 import gllm_inference.prompt_formatter.HuggingFacePromptFormatter
-import logging
 import traceback
 import gllm_inference.realtime_chat.input_streamer.KeyboardInputStreamer
 import gllm_inference.realtime_chat.output_streamer.ConsoleOutputStreamer
 import google.genai.live
 import gllm_core.utils.logger_manager
 import mimetypes
-import uuid
 import pathlib
 import filetype
 import magic
 import requests
+import gllm_core.schema.chunk
 import binascii
 import fnmatch
 import importlib

{gllm_inference_binary-0.5.40.dist-info → gllm_inference_binary-0.5.66.dist-info}/METADATA

@@ -1,12 +1,12 @@
 Metadata-Version: 2.2
 Name: gllm-inference-binary
-Version: 0.5.40
+Version: 0.5.66
 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>
+Author-email: Henry Wicaksono <henry.wicaksono@gdplabs.id>, "Delfia N. A. Putri" <delfia.n.a.putri@gdplabs.id>
 Requires-Python: <3.14,>=3.11
 Description-Content-Type: text/markdown
 Requires-Dist: poetry<3.0.0,>=2.1.3
-Requires-Dist: gllm-core-binary<0.4.0,>=0.3.0
+Requires-Dist: gllm-core-binary<0.4.0,>=0.3.23
 Requires-Dist: aiohttp<4.0.0,>=3.12.14
 Requires-Dist: filetype<2.0.0,>=1.2.0
 Requires-Dist: httpx<0.29.0,>=0.28.0
@@ -30,17 +30,21 @@ Provides-Extra: anthropic
 Requires-Dist: anthropic<0.61.0,>=0.60.0; extra == "anthropic"
 Provides-Extra: bedrock
 Requires-Dist: aioboto3<16.0.0,>=15.0.0; extra == "bedrock"
+Provides-Extra: cohere
+Requires-Dist: cohere<6.0.0,>=5.18.0; extra == "cohere"
 Provides-Extra: datasaur
-Requires-Dist: openai<2.0.0,>=1.98.0; extra == "datasaur"
+Requires-Dist: openai<3.0.0,>=2.7.0; extra == "datasaur"
 Provides-Extra: google
 Requires-Dist: google-genai<=1.36,>=1.23; extra == "google"
 Provides-Extra: huggingface
 Requires-Dist: huggingface-hub<0.31.0,>=0.30.0; extra == "huggingface"
 Requires-Dist: transformers<5.0.0,>=4.52.0; extra == "huggingface"
-Provides-Extra: openai
-Requires-Dist: openai<2.0.0,>=1.98.0; extra == "openai"
 Provides-Extra: litellm
 Requires-Dist: litellm<2.0.0,>=1.69.2; extra == "litellm"
+Provides-Extra: openai
+Requires-Dist: openai<3.0.0,>=2.7.0; extra == "openai"
+Provides-Extra: portkey-ai
+Requires-Dist: portkey-ai<2.0.0,>=1.14.4; extra == "portkey-ai"
 Provides-Extra: twelvelabs
 Requires-Dist: twelvelabs<0.5.0,>=0.4.4; extra == "twelvelabs"
 Provides-Extra: voyage