forked from phoenix-oss/llama-stack-mirror
a568bf3f9d
# What does this PR do? - fix dataset registeration & iterrows > NOTE: the URL endpoint is changed to datasetio due to flaky path routing [//]: # (If resolving an issue, uncomment and update the line below) [//]: # (Closes #[issue-number]) ## Test Plan ``` LLAMA_STACK_CONFIG=fireworks pytest -v tests/integration/datasets/test_datasets.py ``` <img width="854" alt="image" src="https://github.com/user-attachments/assets/0168b352-1c5a-48d1-8e9a-93141d418e54" /> [//]: # (## Documentation)
43 lines
1.2 KiB
Python
43 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_stack.providers.utils.memory.vector_store import parse_data_url
|
|
|
|
|
|
def get_dataframe_from_uri(uri: str):
|
|
df = None
|
|
if uri.endswith(".csv"):
|
|
df = pandas.read_csv(uri)
|
|
elif uri.endswith(".xlsx"):
|
|
df = pandas.read_excel(uri)
|
|
elif uri.startswith("data:"):
|
|
parts = parse_data_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: {uri}")
|
|
|
|
return df
|