forked from phoenix-oss/llama-stack-mirror
2b7d70ba86
* wip * scoring fn api * eval api * eval task * evaluate api update * pre commit * unwrap context -> config * config field doc * typo * naming fix * separate benchmark / app eval * api name * rename * wip tests * wip * datasetio test * delete unused * fixture * scoring resolve * fix scoring register * scoring test pass * score batch * scoring fix * fix eval * test eval works * huggingface provider * datasetdef files * mmlu scoring fn * test wip * remove type ignore * api refactor * add default task_eval_id for routing * add eval_id for jobs * remove type ignore * huggingface provider * wip huggingface register * only keep 1 run_eval * fix optional * register task required * register task required * delete old tests * fix * mmlu loose * refactor * msg * fix tests * move benchmark task def to file * msg * gen openapi * openapi gen * move dataset to hf llamastack repo * remove todo * refactor * add register model to unit test * rename * register to client * delete preregistered dataset/eval task * comments * huggingface -> remote adapter * openapi gen
45 lines
1.2 KiB
Python
45 lines
1.2 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
import base64
|
|
import io
|
|
from urllib.parse import unquote
|
|
|
|
import pandas
|
|
|
|
from llama_models.llama3.api.datatypes import URL
|
|
|
|
from llama_stack.providers.utils.memory.vector_store import parse_data_url
|
|
|
|
|
|
def get_dataframe_from_url(url: URL):
|
|
df = None
|
|
if url.uri.endswith(".csv"):
|
|
df = pandas.read_csv(url.uri)
|
|
elif url.uri.endswith(".xlsx"):
|
|
df = pandas.read_excel(url.uri)
|
|
elif url.uri.startswith("data:"):
|
|
parts = parse_data_url(url.uri)
|
|
data = parts["data"]
|
|
if parts["is_base64"]:
|
|
data = base64.b64decode(data)
|
|
else:
|
|
data = unquote(data)
|
|
encoding = parts["encoding"] or "utf-8"
|
|
data = data.encode(encoding)
|
|
|
|
mime_type = parts["mimetype"]
|
|
mime_category = mime_type.split("/")[0]
|
|
data_bytes = io.BytesIO(data)
|
|
|
|
if mime_category == "text":
|
|
df = pandas.read_csv(data_bytes)
|
|
else:
|
|
df = pandas.read_excel(data_bytes)
|
|
else:
|
|
raise ValueError(f"Unsupported file type: {url}")
|
|
|
|
return df
|