Openai lm invoker

Defines a module to interact with OpenAI language models.

Authors

Henry Wicaksono (henry.wicaksono@gdplabs.id)

References

[1] https://platform.openai.com/docs/api-reference/responses

`OpenAILMInvoker(model_name, api_key=None, model_kwargs=None, default_hyperparameters=None, tools=None, response_schema=None, output_analytics=False, retry_config=None, reasoning_effort=None, reasoning_summary=None, code_interpreter=False, web_search=False, bind_tools_params=None, with_structured_output_params=None)`

Bases: BaseLMInvoker

A language model invoker to interact with OpenAI language models.

Attributes:

Name	Type	Description
`model_id`	`str`	The model ID of the language model.
`model_provider`	`str`	The provider of the language model.
`model_name`	`str`	The name of the language model.
`client`	`AsyncOpenAI`	The OpenAI client instance.
`default_hyperparameters`	`dict[str, Any]`	Default hyperparameters for invoking the model.
`tools`	`list[Any]`	The list of tools provided to the model to enable tool calling.
`response_schema`	`ResponseSchema \| None`	The schema of the response. If provided, the model will output a 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`	The retry configuration for the language model.
`reasoning_effort`	`ReasoningEffort \| None`	The reasoning effort for reasoning models. Not allowed for non-reasoning models. If None, the model will perform medium reasoning effort.
`reasoning_summary`	`ReasoningSummary \| None`	The reasoning summary level for reasoning models. Not allowed for non-reasoning models. If None, no summary will be generated.
`code_interpreter`	`bool`	Whether to enable the code interpreter.
`web_search`	`bool`	Whether to enable the web search.

Basic usage

The OpenAILMInvoker can be used as follows:

lm_invoker = OpenAILMInvoker(model_name="gpt-4.1-nano")
result = await lm_invoker.invoke("Hi there!")

Input types

Text.
Document: ".pdf".
Image: ".jpg", ".jpeg", ".png", ".gif", and ".webp". Non-text inputs must be of valid file extensions and can be passed as an Attachment object.

Non-text inputs can only be passed with the user role.

Usage example:

text = "What animal is in this image?"
image = Attachment.from_path("path/to/local/image.png")

prompt = [(PromptRole.USER, [text, image])]
result = await lm_invoker.invoke(prompt)

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 LangChain's 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:

lm_invoker = OpenAILMInvoker(..., tools=[tool_1, tool_2])

Output example:

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"}),
    ]
)

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.

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.

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.

Example 1: Using a JSON schema dictionary

Usage example:

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 = OpenAILMInvoker(..., response_schema=schema)

Output example:

LMOutput(structured_output={"name": "Golden retriever", "color": "Golden"})

Example 2: Using a Pydantic BaseModel class

Usage example:

class Animal(BaseModel):
    name: str
    color: str

lm_invoker = OpenAILMInvoker(..., response_schema=Animal)

Output example:

LMOutput(structured_output=Animal(name="Golden retriever", color="Golden"))

Analytics tracking

Analytics tracking is a feature that allows the module 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. 3. finish_details: The details about how the generation finished.

Output example:

LMOutput(
    response="Golden retriever is a good dog breed.",
    token_usage=TokenUsage(input_tokens=100, output_tokens=50),
    duration=0.729,
    finish_details={"status": "completed", "incomplete_details": {"reason": None}},
)

Retry and timeout

The OpenAILMInvoker supports retry and timeout configuration. By default, the max retries is set to 0 and the timeout is set to 30.0 seconds. They can be customized by providing a custom RetryConfig object to the retry_config parameter.

Retry config examples:

retry_config = RetryConfig(max_retries=0, timeout=0.0)  # 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=0.0)  # 5 max retries, no timeout
retry_config = RetryConfig(max_retries=5, timeout=10.0)  # 5 max retries, 10.0 seconds timeout

Usage example:

lm_invoker = OpenAILMInvoker(..., retry_config=retry_config)

Reasoning

OpenAI's o-series models are classified as reasoning models. Reasoning models think before they answer, producing a long internal chain of thought before responding to the user. Reasoning models excel in complex problem solving, coding, scientific reasoning, and multi-step planning for agentic workflows.

The reasoning effort of reasoning models can be set via the reasoning_effort parameter. This parameter will guide the models on how many reasoning tokens it should generate before creating a response to the prompt. Available options include: 1. "low": Favors speed and economical token usage. 2. "medium": Favors a balance between speed and reasoning accuracy. 3. "high": Favors more complete reasoning at the cost of more tokens generated and slower responses. When not set, the reasoning effort will be equivalent to medium by default.

OpenAI doesn't expose the raw reasoning tokens. However, the summary of the reasoning tokens can still be generated. The summary level can be set via the reasoning_summary parameter. Available options include: 1. "auto": The model decides the summary level automatically. 2. "detailed": The model will generate a detailed summary of the reasoning tokens. Reasoning summary is not compatible with tool calling. When enabled, the reasoning summary will be stored in the reasoning attribute in the output.

Output example:

LMOutput(
    response="Golden retriever is a good dog breed.",
    reasoning=[Reasoning(id="x", reasoning="Let me think about it...")],
)

When streaming is enabled along with reasoning summary, the reasoning summary token will be streamed with the EventType.DATA event type.

Streaming output example:

{"type": "data", "value": '{"data_type": "thinking_start", "data_value": ""}', ...}
{"type": "data", "value": '{"data_type": "thinking", "data_value": "Let me think "}', ...}
{"type": "data", "value": '{"data_type": "thinking", "data_value": "about it..."}', ...}
{"type": "data", "value": '{"data_type": "thinking_end", "data_value": ""}', ...}
{"type": "response", "value": "Golden retriever ", ...}
{"type": "response", "value": "is a good dog breed.", ...}

Setting reasoning-related parameters for non-reasoning models will raise an error.

Code interpreter

The code interpreter is a feature that allows the language model to write and run Python code in a sandboxed environment to solve complex problems in domains like data analysis, coding, and math. This feature can be enabled by setting the code_interpreter parameter to True.

Usage example:

lm_invoker = OpenAILMInvoker(..., code_interpreter=True)

When code interpreter is enabled, it is highly recommended to instruct the model to use the "python tool" in the system message, as "python tool" is the term recognized by the model to refer to the code interpreter.

Prompt example:

prompt = [
    ("system", ["You are a data analyst. Use the python tool to generate a file."]),
    ("user", ["Show an histogram of the following data: [1, 2, 1, 4, 1, 2, 4, 2, 3, 1]"]),
]

When code interpreter is enabled, the code execution results are stored in the code_exec_results attribute in the output.

Output example:

LMOutput(
    response="The histogram is attached.",
    code_exec_results=[
        CodeExecResult(
            id="123",
            code="import matplotlib.pyplot as plt...",
            output=[Attachment(data=b"...", mime_type="image/png")],
        ),
    ],
)

When streaming is enabled, the executed code will be streamed with the EventType.DATA event type. Streaming output example:

{"type": "data", "value": '{"data_type": "code_start", "data_value": ""}', ...}
{"type": "data", "value": '{"data_type": "code", "data_value": "import matplotlib"}', ...}
{"type": "data", "value": '{"data_type": "code", "data_value": ".pyplot as plt..."}', ...}
{"type": "data", "value": '{"data_type": "code_end", "data_value": ""}', ...}
{"type": "response", "value": "The histogram ", ...}
{"type": "response", "value": "is attached.", ...}

Web search

The web search is a feature that allows the language model to search the web for relevant information. This feature can be enabled by setting the web_search parameter to True.

Usage example:

lm_invoker = OpenAILMInvoker(..., web_search=True)

When web search is enabled, the language model will search the web for relevant information and may cite the relevant sources. The citations will be stored as Chunk objects in the citations attribute in the output. The content of the Chunk object is the type of the citation, e.g. "url_citation".

Output example:

LMOutput(
    response="The winner of the match is team A ([Example title](https://www.example.com)).",
    citations=[
        Chunk(
            id="123",
            content="url_citation",
            metadata={
                "start_index": 164,
                "end_index": 275,
                "title": "Example title",
                "url": "https://www.example.com",
                "type": "url_citation",
            },
        ),
    ],
)

When streaming is enabled, the web search activities will be streamed with the EventType.DATA event type. Streaming output example:

{"type": "data", "value": '{"data_type": "activity", "data_value": "{\"query\": \"search query\"}", ...}', ...}
{"type": "response", "value": "The winner of the match ", ...}
{"type": "response", "value": "is team A ([Example title](https://www.example.com)).", ...}

Output types

The output of the OpenAILMInvoker is of type MultimodalOutput, which is a type alias that can represent: 1. str: The text response if no additional output is needed. 2. LMOutput: A Pydantic model with the following attributes if any additional output is needed: 2.1. response (str): The text response. 2.2. tool_calls (list[ToolCall]): The tool calls, if the tools parameter is defined and the language model decides to invoke tools. Defaults to an empty list. 2.3. structured_output (dict[str, Any] | BaseModel | None): The structured output, if the response_schema parameter is defined. Defaults to None. 2.4. token_usage (TokenUsage | None): The token usage analytics, if the output_analytics parameter is set to True. Defaults to None. 2.5. duration (float | None): The duration of the invocation in seconds, if the output_analytics parameter is set to True. Defaults to None. 2.6. finish_details (dict[str, Any] | None): The details about how the generation finished, if the output_analytics parameter is set to True. Defaults to None. 2.7. reasoning (list[Reasoning]): The reasoning objects, if the reasoning_summary parameter is provided for reasoning models. Defaults to an empty list. 2.8. citations (list[Chunk]): The citations, if the web_search is enabled and the language model decides to cite the relevant sources. Defaults to an empty list. 2.9. code_exec_results (list[CodeExecResult]): The code execution results, if the code interpreter is enabled and the language model decides to execute any codes. Defaults to an empty list.

Initializes a new instance of the OpenAILMInvoker class.

Parameters:

Name	Type	Description	Default
`model_name`	`str`	The name of the OpenAI model.	required
`api_key`	`str \| None`	The API key for authenticating with OpenAI. Defaults to None, in which case the `OPENAI_API_KEY` environment variable will be used.	`None`
`model_kwargs`	`dict[str, Any] \| None`	Additional model parameters. Defaults to None.	`None`
`default_hyperparameters`	`dict[str, Any] \| None`	Default hyperparameters for invoking the model. Defaults to None.	`None`
`tools`	`list[Tool] \| None`	Tools provided to the language model to enable tool calling. Defaults to None.	`None`
`response_schema`	`ResponseSchema \| None`	The schema of the response. If provided, the model will output a structured response as defined by the schema. Supports both Pydantic BaseModel and JSON schema dictionary. Defaults to None.	`None`
`output_analytics`	`bool`	Whether to output the invocation analytics. Defaults to False.	`False`
`retry_config`	`RetryConfig \| None`	The retry configuration for the language model. Defaults to None, in which case a default config with no retry and 30.0 seconds timeout is used.	`None`
`reasoning_effort`	`ReasoningEffort \| None`	The reasoning effort for reasoning models. Not allowed for non-reasoning models. If None, the model will perform medium reasoning effort. Defaults to None.	`None`
`reasoning_summary`	`ReasoningSummary \| None`	The reasoning summary level for reasoning models. Not allowed for non-reasoning models. If None, no summary will be generated. Defaults to None.	`None`
`code_interpreter`	`bool`	Whether to enable the code interpreter. Defaults to False.	`False`
`web_search`	`bool`	Whether to enable the web search. Defaults to False.	`False`
`bind_tools_params`	`dict[str, Any] \| None`	Deprecated parameter to add tool calling capability. If provided, must at least include the `tools` key that is equivalent to the `tools` parameter. Retained for backward compatibility. Defaults to None.	`None`
`with_structured_output_params`	`dict[str, Any] \| None`	Deprecated parameter to instruct the model to produce output with a certain schema. If provided, must at least include the `schema` key that is equivalent to the `response_schema` parameter. Retained for backward compatibility. Defaults to None.	`None`

Raises:

Type	Description
`ValueError`

`set_response_schema(response_schema)`

Sets the response schema for the OpenAI language model.

This method sets the response schema for the OpenAI language model. Any existing response schema will be replaced.

Parameters:

Name	Type	Description	Default
`response_schema`	`ResponseSchema \| None`	The response schema to be used.	required