autogen.logger.SqliteLogger

SqliteLogger

SqliteLogger(config: dict[str, Any])

Sqlite logger class.
Initialize the SqliteLogger.

Parameters:

Name	Description
config	Type: dict[str, Any]

Class Attributes

schema_version

Instance Methods

get_connection

get_connection(self) -> None | Connection

Get connection.

log_chat_completion

log_chat_completion(
    self,
    invocation_id: UUID,
    client_id: int,
    wrapper_id: int,
    source: str | Agent,
    request: dict[str, float | str | list[dict[str, str]]],
    response: str | ChatCompletion,
    is_cached: int,
    cost: float,
    start_time: str
) -> None

Log chat completion.

Parameters:

Name	Description
invocation_id	Invocation ID. Type: uuid.UUID
client_id	Client ID. Type: int
wrapper_id	Wrapper ID. Type: int
source	Source of the chat completion. Type: str | Agent
request	Request for the chat completion. Type: dict[str, float | str | list[dict[str, str]]]
response	Response for the chat completion. Type: str | ChatCompletion
is_cached	Whether the response is cached. Type: int
cost	Cost of the chat completion. Type: float
start_time	Start time of the chat completion. Type: str

log_event

log_event(
    self,
    source: str | Agent,
    name: str,
    **kwargs: dict[str, Any]
) -> None

Log event.

Parameters:

Name	Description
source	Source of the event. Type: str | Agent
name	Name of the event. Type: str
**kwargs	Additional arguments for the event. Type: dict[str, Any]

log_function_use

log_function_use(
    self,
    source: str | Agent,
    function: F,
    args: dict[str, Any],
    returns: Any
) -> None

Log function use.

Parameters:

Name	Description
source	Source of the function use. Type: str | Agent
function	Function to log. Type: F
args	Arguments of the function. Type: dict[str, Any]
returns	Returns of the function. Type: Any

log_new_agent

log_new_agent(
    self,
    agent: ConversableAgent,
    init_args: dict[str, Any]
) -> None

Log new agent.

Parameters:

Name	Description
agent	Agent to log. Type: ConversableAgent
init_args	Initialization arguments of the agent Type: dict[str, Any]

log_new_client

log_new_client(
    self,
    client: AzureOpenAI | OpenAI | CerebrasClient | GeminiClient | AnthropicClient | MistralAIClient | TogetherClient | GroqClient | CohereClient | OllamaClient | BedrockClient,
    wrapper: OpenAIWrapper,
    init_args: dict[str, Any]
) -> None

Log new client.

Parameters:

Name	Description
client	Client to log. Type: AzureOpenAI | OpenAI | CerebrasClient | GeminiClient | AnthropicClient | MistralAIClient | TogetherClient | GroqClient | CohereClient | OllamaClient | BedrockClient
wrapper	Wrapper of the client. Type: OpenAIWrapper
init_args	Initialization arguments of the client. Type: dict[str, Any]

log_new_wrapper

log_new_wrapper(
    self,
    wrapper: OpenAIWrapper,
    init_args: dict[str, LLMConfig | list[LLMConfig]]
) -> None

Log new wrapper.

Parameters:

Name	Description
wrapper	Wrapper to log. Type: OpenAIWrapper
init_args	Initialization arguments of the wrapper Type: dict[str, LLMConfig | list[LLMConfig]]

start

start(self) -> str

Open a connection to the logging database, and start recording.
Returns:
session_id (str): a unique id for the logging session

Returns:

Type	Description
str	session_id (str): a unique id for the logging session

stop

stop(self) -> None

Stop the logger