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

gllm_inference/lm_invoker/google_lm_invoker.pyi

@@ -6,8 +6,9 @@ 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 google.genai.types import GenerateContentResponse as GenerateContentResponse
 from langchain_core.tools import Tool as LangChainTool
 from typing import Any
 
@@ -15,7 +16,12 @@ SUPPORTED_ATTACHMENTS: Incomplete
 DEFAULT_THINKING_BUDGET: int
 REQUIRE_THINKING_MODEL_PREFIX: Incomplete
 IMAGE_GENERATION_MODELS: Incomplete
-YOUTUBE_URL_PATTERN: Incomplete
+BATCH_STATUS_MAP: Incomplete
+
+class URLPattern:
+    """Defines specific Google related URL patterns."""
+    GOOGLE_FILE: Incomplete
+    YOUTUBE: Incomplete
 
 class GoogleLMInvoker(BaseLMInvoker):
     '''A language model invoker to interact with Google language models.
@@ -31,10 +37,10 @@ class GoogleLMInvoker(BaseLMInvoker):
             structured response as defined by the schema. Supports both Pydantic BaseModel and JSON schema dictionary.
         output_analytics (bool): Whether to output the invocation analytics.
         retry_config (RetryConfig | None): The retry configuration for the language model.
-        generate_image (bool): Whether to generate image. Only allowed for image generation models.
         thinking (bool): Whether to enable thinking. Only allowed for thinking models.
         thinking_budget (int): The tokens allowed for thinking process. Only allowed for thinking models.
             If set to -1, the model will control the budget automatically.
+        image_generation (bool): Whether to generate image. Only allowed for image generation models.
 
     Basic usage:
         The `GoogleLMInvoker` can be used as follows:
@@ -82,10 +88,61 @@ class GoogleLMInvoker(BaseLMInvoker):
         result = await lm_invoker.invoke([text, image])
         ```
 
+    Text output:
+        The `GoogleLMInvoker` generates text outputs by default.
+        Text outputs are stored in the `outputs` attribute of the `LMOutput` object and can be accessed
+        via the `texts` (all text outputs) or `text` (first text output) properties.
+
+        Output example:
+        ```python
+        LMOutput(outputs=[LMOutputItem(type="text", output="Hello, there!")])
+        ```
+
+    Structured output:
+        The `GoogleLMInvoker` can be configured to generate structured outputs.
+        This feature can be enabled by providing a schema to the `response_schema` parameter.
+
+        Structured outputs are stored in the `outputs` attribute of the `LMOutput` object and can be accessed
+        via the `structureds` (all structured outputs) or `structured` (first structured output) properties.
+
+        The schema must either be one of the following:
+        1. A Pydantic BaseModel class
+            The structured output will be a Pydantic model.
+        2. A JSON schema dictionary
+            JSON dictionary schema must be compatible with Pydantic\'s JSON schema, especially for complex schemas.
+            Thus, it is recommended to create the JSON schema using Pydantic\'s `model_json_schema` method.
+            The structured output will be a dictionary.
+
+        Usage example:
+        ```python
+        class Animal(BaseModel):
+            name: str
+            color: str
+
+        json_schema = Animal.model_json_schema()
+
+        lm_invoker = GoogleLMInvoker(..., response_schema=Animal)  # Using Pydantic BaseModel class
+        lm_invoker = GoogleLMInvoker(..., response_schema=json_schema)  # Using JSON schema dictionary
+        ```
+
+        Output example:
+        ```python
+        # Using Pydantic BaseModel class outputs a Pydantic model
+        LMOutput(outputs=[LMOutputItem(type="structured", output=Animal(name="dog", color="white"))])
+
+        # Using JSON schema dictionary outputs a dictionary
+        LMOutput(outputs=[LMOutputItem(type="structured", output={"name": "dog", "color": "white"})])
+        ```
+
+        Structured output is not compatible with tool calling.
+        When structured output is enabled, streaming is disabled.
+
     Image generation:
-        The `GoogleLMInvoker` supports image generation. This can be done by using an image generation model,
-        such as `gemini-2.5-flash-image`. Streaming is disabled for image generation models.
-        The generated image will be stored in the `attachments` attribute in the output.
+        The `GoogleLMInvoker` can be configured to generate images.
+        This feature can be enabled by using an image generation model, such as `gemini-2.5-flash-image`.
+
+        Image outputs are stored in the `outputs` attribute of the `LMOutput` object and can be accessed
+        via the `attachments` property.
 
         Usage example:
         ```python
@@ -97,16 +154,25 @@ class GoogleLMInvoker(BaseLMInvoker):
         Output example:
         ```python
         LMOutput(
-            response="Let me call the tools...",
-            attachments=[Attachment(filename="image.png", mime_type="image/png", data=b"...")],
+            outputs=[
+                LMOutputItem(type="text", output="Creating a picture..."),
+                LMOutputItem(
+                    type="attachment",
+                    output=Attachment(filename="image.png", mime_type="image/png", data=b"..."),
+                ),
+            ],
         )
         ```
 
+        Image generation is not compatible with tool calling and thinking.
+        When image generation is enabled, streaming is disabled.
+
     Tool calling:
-        Tool calling is a feature that allows the language model to call tools to perform tasks.
-        Tools can be passed to the via the `tools` parameter as a list of `Tool` objects.
-        When tools are provided and the model decides to call a tool, the tool calls are stored in the
-        `tool_calls` attribute in the output.
+        The `GoogleLMInvoker` can be configured to call tools to perform certain tasks.
+        This feature can be enabled by providing a list of `Tool` objects to the `tools` parameter.
+
+        Tool calls outputs are stored in the `outputs` attribute of the `LMOutput` object and
+        can be accessed via the `tool_calls` property.
 
         Usage example:
         ```python
@@ -116,67 +182,60 @@ class GoogleLMInvoker(BaseLMInvoker):
         Output example:
         ```python
         LMOutput(
-            response="Let me call the tools...",
-            tool_calls=[
-                ToolCall(id="123", name="tool_1", args={"key": "value"}),
-                ToolCall(id="456", name="tool_2", args={"key": "value"}),
+            outputs=[
+                LMOutputItem(type="text", output="I\'m using tools..."),
+                LMOutputItem(type="tool_call", output=ToolCall(id="123", name="tool_1", args={"key": "value"})),
+                LMOutputItem(type="tool_call", output=ToolCall(id="456", name="tool_2", args={"key": "value"})),
             ]
         )
         ```
 
-    Structured output:
-        Structured output is a feature that allows the language model to output a structured response.
-        This feature can be enabled by providing a schema to the `response_schema` parameter.
-
-        The schema must be either a JSON schema dictionary or a Pydantic BaseModel class.
-        If JSON schema is used, it must be compatible with Pydantic\'s JSON schema, especially for complex schemas.
-        For this reason, it is recommended to create the JSON schema using Pydantic\'s `model_json_schema` method.
-
-        Structured output is not compatible with tool calling. The language model also doesn\'t need to stream
-        anything when structured output is enabled. Thus, standard invocation will be performed regardless of
-        whether the `event_emitter` parameter is provided or not.
+    Thinking:
+        The `GoogleLMInvoker` can be configured to perform step-by-step thinking process before answering.
+        This feature can be enabled by setting the `thinking` parameter to `True`.
 
-        When enabled, the structured output is stored in the `structured_output` attribute in the output.
-        1. If the schema is a JSON schema dictionary, the structured output is a dictionary.
-        2. If the schema is a Pydantic BaseModel class, the structured output is a Pydantic model.
+        Thinking outputs are stored in the `outputs` attribute of the `LMOutput` object
+        and can be accessed via the `thinkings` property.
 
-        # Example 1: Using a JSON schema dictionary
         Usage example:
         ```python
-        schema = {
-            "title": "Animal",
-            "description": "A description of an animal.",
-            "properties": {
-                "color": {"title": "Color", "type": "string"},
-                "name": {"title": "Name", "type": "string"},
-            },
-            "required": ["name", "color"],
-            "type": "object",
-        }
-        lm_invoker = GoogleLMInvoker(..., response_schema=schema)
+        lm_invoker = GoogleLMInvoker(..., thinking=True, thinking_budget=1024)
         ```
+
         Output example:
         ```python
-        LMOutput(structured_output={"name": "Golden retriever", "color": "Golden"})
+        LMOutput(
+            outputs=[
+                LMOutputItem(type="thinking", output=Reasoning(type="thinking", reasoning="I\'m thinking...", ...)),
+                LMOutputItem(type="text", output="Golden retriever is a good dog breed."),
+            ]
+        )
         ```
 
-        # Example 2: Using a Pydantic BaseModel class
-        Usage example:
-        ```python
-        class Animal(BaseModel):
-            name: str
-            color: str
-
-        lm_invoker = GoogleLMInvoker(..., response_schema=Animal)
-        ```
-        Output example:
+        Streaming output example:
         ```python
-        LMOutput(structured_output=Animal(name="Golden retriever", color="Golden"))
+        {"type": "thinking_start", "value": "", ...}
+        {"type": "thinking", "value": "I\'m ", ...}
+        {"type": "thinking", "value": "thinking...", ...}
+        {"type": "thinking_end", "value": "", ...}
+        {"type": "response", "value": "Golden retriever ", ...}
+        {"type": "response", "value": "is a good dog breed.", ...}
         ```
+        Note: By default, the thinking token will be streamed with the legacy `EventType.DATA` event type.
+        To use the new simplified streamed event format, set the `simplify_events` parameter to `True` during
+        LM invoker initialization. The legacy event format support will be removed in v0.6.
+
+        The amount of tokens allocated for the thinking process can be set via the `thinking_budget` parameter.
+        For more information, please refer to the following documentation:
+        https://ai.google.dev/gemini-api/docs/thinking
+
+        Thinking is only available for certain models, starting from Gemini 2.5 series.
+        Thinking is required for Gemini 2.5 Pro models.
 
     Analytics tracking:
-        Analytics tracking is a feature that allows the module to output additional information about the invocation.
+        The `GoogleLMInvoker` can be configured to output additional information about the invocation.
         This feature can be enabled by setting the `output_analytics` parameter to `True`.
+
         When enabled, the following attributes will be stored in the output:
         1. `token_usage`: The token usage.
         2. `duration`: The duration in seconds.
@@ -185,15 +244,10 @@ class GoogleLMInvoker(BaseLMInvoker):
         Output example:
         ```python
         LMOutput(
-            response="Golden retriever is a good dog breed.",
-            token_usage=TokenUsage(
-                input_tokens=1500,
-                output_tokens=200,
-                input_token_details=InputTokenDetails(cached_tokens=1200, uncached_tokens=300),
-                output_token_details=OutputTokenDetails(reasoning_tokens=180, response_tokens=20),
-            ),
+            outputs=[...],
+            token_usage=TokenUsage(input_tokens=100, output_tokens=50),
             duration=0.729,
-            finish_details={"finish_reason": "STOP", "finish_message": None},
+            finish_details={"stop_reason": "end_turn"},
         )
         ```
 
@@ -205,8 +259,6 @@ class GoogleLMInvoker(BaseLMInvoker):
         Retry config examples:
         ```python
         retry_config = RetryConfig(max_retries=0, timeout=None)  # No retry, no timeout
-        retry_config = RetryConfig(max_retries=0, timeout=10.0)  # No retry, 10.0 seconds timeout
-        retry_config = RetryConfig(max_retries=5, timeout=None)  # 5 max retries, no timeout
         retry_config = RetryConfig(max_retries=5, timeout=10.0)  # 5 max retries, 10.0 seconds timeout
         ```
 
@@ -215,63 +267,96 @@ class GoogleLMInvoker(BaseLMInvoker):
         lm_invoker = GoogleLMInvoker(..., retry_config=retry_config)
         ```
 
-    Thinking:
-        Thinking is a feature that allows the language model to have enhanced reasoning capabilities for complex tasks,
-        while also providing transparency into its step-by-step thought process before it delivers its final answer.
-        It can be enabled by setting the `thinking` parameter to `True`.
+    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.
 
-        Thinking is only available for certain models, starting from Gemini 2.5 series, and is required for
-        Gemini 2.5 Pro models. Therefore, `thinking` defaults to `True` for Gemini 2.5 Pro models and `False`
-        for other models. Setting `thinking` to `False` for Gemini 2.5 Pro models will raise a `ValueError`.
-        When enabled, the reasoning is stored in the `reasoning` attribute in the output.
+        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
-        lm_invoker = GoogleLMInvoker(..., thinking=True, thinking_budget=1024)
+        requests = {"1": "What color is the sky?", "2": "What color is the grass?"}
+        results = await lm_invoker.batch.invoke(requests)
         ```
 
         Output example:
         ```python
-        LMOutput(
-            response="Golden retriever is a good dog breed.",
-            reasoning=[Reasoning(reasoning="Let me think about it...")],
-        )
+        {
+            "1": LMOutput(outputs=[LMOutputItem(type="text", output="The sky is blue.")]),
+            "2": LMOutput(finish_details={"type": "error", "message": "..."}),
+        }
         ```
 
-        Streaming output example:
-        ```python
-        {"type": "thinking_start", "value": "", ...}
-        {"type": "thinking", "value": "Let me think "\', ...}
-        {"type": "thinking", "value": "about it...", ...}
-        {"type": "thinking_end", "value": ""}\', ...}
-        {"type": "response", "value": "Golden retriever ", ...}
-        {"type": "response", "value": "is a good dog breed.", ...}
-        ```
-        Note: By default, the thinking token will be streamed with the legacy `EventType.DATA` event type.
-        To use the new simplified streamed event format, set the `simplify_events` parameter to `True` during
-        LM invoker initialization. The legacy event format support will be removed in v0.6.
+        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"},
+            ]
+            ```
 
-        When thinking is enabled, the amount of tokens allocated for the thinking process can be set via the
-        `thinking_budget` parameter. The `thinking_budget`:
-        1. Defaults to -1, in which case the model will control the budget automatically.
-        2. Must be greater than the model\'s minimum thinking budget.
-        For more details, please refer to https://ai.google.dev/gemini-api/docs/thinking
-
-    Output types:
-        The output of the `GoogleLMInvoker` can either be:
-        1. `str`: A text response.
-        2. `LMOutput`: A Pydantic model that may contain the following attributes:
-            2.1. response (str)
-            2.2. attachments (list[Attachment])
-            2.3. tool_calls (list[ToolCall])
-            2.4. structured_output (dict[str, Any] | BaseModel | None)
-            2.5. token_usage (TokenUsage | None)
-            2.6. duration (float | None)
-            2.7. finish_details (dict[str, Any])
-            2.8. reasoning (list[Reasoning])
+        5. Cancel a batch job:
+            ```python
+            await lm_invoker.batch.cancel(batch_id)
+            ```
     '''
     client_params: Incomplete
-    generate_image: Incomplete
+    image_generation: Incomplete
     thinking: Incomplete
     thinking_budget: Incomplete
     def __init__(self, model_name: str, api_key: str | None = None, credentials_path: str | None = None, project_id: str | None = None, location: str = 'us-central1', model_kwargs: dict[str, Any] | None = None, default_hyperparameters: dict[str, Any] | None = None, tools: list[Tool | LangChainTool] | None = None, response_schema: ResponseSchema | None = None, output_analytics: bool = False, retry_config: RetryConfig | None = None, thinking: bool | None = None, thinking_budget: int = ..., simplify_events: bool = False) -> None:

gllm_inference/lm_invoker/langchain_lm_invoker.pyi

@@ -78,81 +78,82 @@ class LangChainLMInvoker(BaseLMInvoker):
         result = await lm_invoker.invoke([text, image])
         ```
 
-    Tool calling:
-        Tool calling is a feature that allows the language model to call tools to perform tasks.
-        Tools can be passed to the via the `tools` parameter as a list of `Tool` objects.
-        When tools are provided and the model decides to call a tool, the tool calls are stored in the
-        `tool_calls` attribute in the output.
-
-        Usage example:
-        ```python
-        lm_invoker = LangChainLMInvoker(..., tools=[tool_1, tool_2])
-        ```
+    Text output:
+        The `LangChainLMInvoker` generates text outputs by default.
+        Text outputs are stored in the `outputs` attribute of the `LMOutput` object and can be accessed
+        via the `texts` (all text outputs) or `text` (first text output) properties.
 
         Output example:
         ```python
-        LMOutput(
-            response="Let me call the tools...",
-            tool_calls=[
-                ToolCall(id="123", name="tool_1", args={"key": "value"}),
-                ToolCall(id="456", name="tool_2", args={"key": "value"}),
-            ]
-        )
+        LMOutput(outputs=[LMOutputItem(type="text", output="Hello, there!")])
         ```
 
     Structured output:
-        Structured output is a feature that allows the language model to output a structured response.
+        The `LangChainLMInvoker` can be configured to generate structured outputs.
         This feature can be enabled by providing a schema to the `response_schema` parameter.
 
-        The schema must be either a JSON schema dictionary or a Pydantic BaseModel class.
-        If JSON schema is used, it must be compatible with Pydantic\'s JSON schema, especially for complex schemas.
-        For this reason, it is recommended to create the JSON schema using Pydantic\'s `model_json_schema` method.
-
-        Structured output is not compatible with tool calling. The language model also doesn\'t need to stream
-        anything when structured output is enabled. Thus, standard invocation will be performed regardless of
-        whether the `event_emitter` parameter is provided or not.
+        Structured outputs are stored in the `outputs` attribute of the `LMOutput` object and can be accessed
+        via the `structureds` (all structured outputs) or `structured` (first structured output) properties.
 
-        When enabled, the structured output is stored in the `structured_output` attribute in the output.
-        1. If the schema is a JSON schema dictionary, the structured output is a dictionary.
-        2. If the schema is a Pydantic BaseModel class, the structured output is a Pydantic model.
+        The schema must either be one of the following:
+        1. A Pydantic BaseModel class
+            The structured output will be a Pydantic model.
+        2. A JSON schema dictionary
+            JSON dictionary schema must be compatible with Pydantic\'s JSON schema, especially for complex schemas.
+            Thus, it is recommended to create the JSON schema using Pydantic\'s `model_json_schema` method.
+            The structured output will be a dictionary.
 
-        # Example 1: Using a JSON schema dictionary
         Usage example:
         ```python
-        schema = {
-            "title": "Animal",
-            "description": "A description of an animal.",
-            "properties": {
-                "color": {"title": "Color", "type": "string"},
-                "name": {"title": "Name", "type": "string"},
-            },
-            "required": ["name", "color"],
-            "type": "object",
-        }
-        lm_invoker = LangChainLMInvoker(..., response_schema=schema)
+        class Animal(BaseModel):
+            name: str
+            color: str
+
+        json_schema = Animal.model_json_schema()
+
+        lm_invoker = LangChainLMInvoker(..., response_schema=Animal)  # Using Pydantic BaseModel class
+        lm_invoker = LangChainLMInvoker(..., response_schema=json_schema)  # Using JSON schema dictionary
         ```
+
         Output example:
         ```python
-        LMOutput(structured_output={"name": "Golden retriever", "color": "Golden"})
+        # Using Pydantic BaseModel class outputs a Pydantic model
+        LMOutput(outputs=[LMOutputItem(type="structured", output=Animal(name="dog", color="white"))])
+
+        # Using JSON schema dictionary outputs a dictionary
+        LMOutput(outputs=[LMOutputItem(type="structured", output={"name": "dog", "color": "white"})])
         ```
 
-        # Example 2: Using a Pydantic BaseModel class
+        Structured output is not compatible with tool calling.
+        When structured output is enabled, streaming is disabled.
+
+    Tool calling:
+        The `LangChainLMInvoker` can be configured to call tools to perform certain tasks.
+        This feature can be enabled by providing a list of `Tool` objects to the `tools` parameter.
+
+        Tool calls outputs are stored in the `outputs` attribute of the `LMOutput` object and
+        can be accessed via the `tool_calls` property.
+
         Usage example:
         ```python
-        class Animal(BaseModel):
-            name: str
-            color: str
-
-        lm_invoker = LangChainLMInvoker(..., response_schema=Animal)
+        lm_invoker = LangChainLMInvoker(..., tools=[tool_1, tool_2])
         ```
+
         Output example:
         ```python
-        LMOutput(structured_output=Animal(name="Golden retriever", color="Golden"))
+        LMOutput(
+            outputs=[
+                LMOutputItem(type="text", output="I\'m using tools..."),
+                LMOutputItem(type="tool_call", output=ToolCall(id="123", name="tool_1", args={"key": "value"})),
+                LMOutputItem(type="tool_call", output=ToolCall(id="456", name="tool_2", args={"key": "value"})),
+            ]
+        )
         ```
 
     Analytics tracking:
-        Analytics tracking is a feature that allows the module to output additional information about the invocation.
+        The `LangChainLMInvoker` can be configured to output additional information about the invocation.
         This feature can be enabled by setting the `output_analytics` parameter to `True`.
+
         When enabled, the following attributes will be stored in the output:
         1. `token_usage`: The token usage.
         2. `duration`: The duration in seconds.
@@ -161,10 +162,10 @@ class LangChainLMInvoker(BaseLMInvoker):
         Output example:
         ```python
         LMOutput(
-            response="Golden retriever is a good dog breed.",
+            outputs=[...],
             token_usage=TokenUsage(input_tokens=100, output_tokens=50),
             duration=0.729,
-            finish_details={"finish_reason": "stop"},
+            finish_details={"stop_reason": "end_turn"},
         )
         ```
 
@@ -176,8 +177,6 @@ class LangChainLMInvoker(BaseLMInvoker):
         Retry config examples:
         ```python
         retry_config = RetryConfig(max_retries=0, timeout=None)  # No retry, no timeout
-        retry_config = RetryConfig(max_retries=0, timeout=10.0)  # No retry, 10.0 seconds timeout
-        retry_config = RetryConfig(max_retries=5, timeout=None)  # 5 max retries, no timeout
         retry_config = RetryConfig(max_retries=5, timeout=10.0)  # 5 max retries, 10.0 seconds timeout
         ```
 
@@ -185,17 +184,6 @@ class LangChainLMInvoker(BaseLMInvoker):
         ```python
         lm_invoker = LangChainLMInvoker(..., retry_config=retry_config)
         ```
-
-    Output types:
-        The output of the `LangChainLMInvoker` can either be:
-        1. `str`: A text response.
-        2. `LMOutput`: A Pydantic model that may contain the following attributes:
-            2.1. response (str)
-            2.2. tool_calls (list[ToolCall])
-            2.3. structured_output (dict[str, Any] | BaseModel | None)
-            2.4. token_usage (TokenUsage | None)
-            2.5. duration (float | None)
-            2.6. finish_details (dict[str, Any])
     '''
     model: Incomplete
     def __init__(self, model: BaseChatModel | None = None, model_class_path: str | None = None, model_name: str | None = None, model_kwargs: dict[str, Any] | None = None, default_hyperparameters: dict[str, Any] | None = None, tools: list[Tool | LangChainTool] | None = None, response_schema: ResponseSchema | None = None, output_analytics: bool = False, retry_config: RetryConfig | None = None) -> None: