Upload a dataframe as individual examples to the LangSmith API.
upload_dataframe(
self,
df: pd.DataFrame,
name: str,
input_keys: Sequence[str],
output_keys: Sequence[str],
*,
description: Optional[str] = None,
data_type: Optional[ls_schemas.DataType] = ls_schemas.DataType.kv
) -> ls_schemas.DatasetExample:
from langsmith import Client
import os
import pandas as pd
client = Client()
df = pd.read_parquet("path/to/your/myfile.parquet")
input_keys = ["column1", "column2"] # replace with your input column names
output_keys = ["output1", "output2"] # replace with your output column names
dataset = client.upload_dataframe(
df=df,
input_keys=input_keys,
output_keys=output_keys,
name="My Parquet Dataset",
description="Dataset created from a parquet file",
data_type="kv", # The default
)| Name | Type | Description |
|---|---|---|
df* | pd.DataFrame | The dataframe to upload. |
name* | str | The name of the dataset. |
input_keys* | Sequence[str] | The input keys. |
output_keys* | Sequence[str] | The output keys. |
description | Optional[str] | Default: NoneThe description of the dataset. |
data_type | Optional[ls_schemas.DataType] | Default: ls_schemas.DataType.kvThe data type of the dataset. |