feat: allow injecting prefixes and suffixes into prompts

This commit is contained in:
Philipp Emanuel Weidmann
2025-12-31 12:00:44 +05:30
parent 02a5237a02
commit c4b2ea0c42
2 changed files with 19 additions and 1 deletions
+10
View File
@@ -27,6 +27,16 @@ class DatasetSpecification(BaseModel):
column: str = Field(description="Column in the dataset that contains the prompts.")
prefix: str = Field(
default="",
description="Text to prepend to each prompt.",
)
suffix: str = Field(
default="",
description="Text to append to each prompt.",
)
residual_plot_label: str | None = Field(
default=None,
description="Label to use for the dataset in plots of residual vectors.",
+9 -1
View File
@@ -171,7 +171,15 @@ def load_prompts(specification: DatasetSpecification) -> list[str]:
# Probably a repository path; let load_dataset figure it out.
dataset = load_dataset(path, split=split_str)
return list(dataset[specification.column])
prompts = list(dataset[specification.column])
if specification.prefix:
prompts = [f"{specification.prefix} {prompt}" for prompt in prompts]
if specification.suffix:
prompts = [f"{prompt} {specification.suffix}" for prompt in prompts]
return prompts
T = TypeVar("T")