Data schemas and type definitions used throughout the LangSmith SDK.
Run schema when loading from the DB.
Base Run schema.
A Run is a span representing a single unit of work or operation within your LLM app. This could be a single call to an LLM or chain, to a prompt formatting call, to a runnable lambda
Example model.
Example upload with attachments.
Example update with attachments.
Dataset ORM model.
Dataset base model.
Enum for dataset data types.
Class representing a dataset version.
Schema for getting feedback.
Schema used for creating feedback.
Feedback schema.
Feedback source type.
TracerSession schema for the API.
Sessions are also referred to as "Projects" in the UI.
A project, hydrated with additional information.
Sessions are also referred to as "Projects" in the UI.
Represents a Prompt with metadata.
Represents a Prompt with a manifest.
Results container for experiment data with stats and examples.
Breaking change in v0.4.32: The 'stats' field has been split into 'feedback_stats' and 'run_stats'.
Annotated type that will be stored as an attachment if used.
Info for an attachment.
Operations to perform on attachments.
Usage metadata for a message, such as token counts.
This is a standard representation of token usage that is consistent across models.
Information about the LangSmith server.
