llama-stack-mirror/llama_stack/providers/utils/datasetio/url_utils.py
Ashwin Bharambe 7f834339ba
Some checks failed
Integration Tests (Replay) / discover-tests (push) Successful in 3s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 9s
Python Package Build Test / build (3.12) (push) Failing after 4s
Vector IO Integration Tests / test-matrix (3.12, inline::milvus) (push) Failing after 12s
Test Llama Stack Build / generate-matrix (push) Successful in 11s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 12s
Vector IO Integration Tests / test-matrix (3.12, inline::faiss) (push) Failing after 14s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 22s
Test External API and Providers / test-external (venv) (push) Failing after 14s
Integration Tests (Replay) / Integration Tests (, , , client=, vision=) (push) Failing after 12s
Vector IO Integration Tests / test-matrix (3.12, remote::pgvector) (push) Failing after 15s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 22s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 14s
Unit Tests / unit-tests (3.13) (push) Failing after 14s
Test Llama Stack Build / build-single-provider (push) Failing after 13s
Vector IO Integration Tests / test-matrix (3.12, remote::chromadb) (push) Failing after 18s
Unit Tests / unit-tests (3.12) (push) Failing after 16s
Vector IO Integration Tests / test-matrix (3.12, remote::qdrant) (push) Failing after 18s
Vector IO Integration Tests / test-matrix (3.13, remote::weaviate) (push) Failing after 10s
Vector IO Integration Tests / test-matrix (3.13, inline::faiss) (push) Failing after 11s
Vector IO Integration Tests / test-matrix (3.12, remote::weaviate) (push) Failing after 16s
Vector IO Integration Tests / test-matrix (3.13, remote::qdrant) (push) Failing after 18s
Test Llama Stack Build / build (push) Failing after 12s
Vector IO Integration Tests / test-matrix (3.13, remote::chromadb) (push) Failing after 18s
Vector IO Integration Tests / test-matrix (3.13, remote::pgvector) (push) Failing after 20s
Vector IO Integration Tests / test-matrix (3.13, inline::sqlite-vec) (push) Failing after 16s
Python Package Build Test / build (3.13) (push) Failing after 53s
Vector IO Integration Tests / test-matrix (3.13, inline::milvus) (push) Failing after 59s
Vector IO Integration Tests / test-matrix (3.12, inline::sqlite-vec) (push) Failing after 1m1s
Update ReadTheDocs / update-readthedocs (push) Failing after 1m6s
Pre-commit / pre-commit (push) Successful in 1m53s
chore(misc): make tests and starter faster (#3042)
A bunch of miscellaneous cleanup focusing on tests, but ended up
speeding up starter distro substantially.

- Pulled llama stack client init for tests into `pytest_sessionstart` so
it does not clobber output
- Profiling of that told me where we were doing lots of heavy imports
for starter, so lazied them
- starter now starts 20seconds+ faster on my Mac
- A few other smallish refactors for `compat_client`
2025-08-05 14:55:05 -07:00

47 lines
1.4 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 asyncio
import base64
import io
from urllib.parse import unquote
from llama_stack.providers.utils.memory.vector_store import parse_data_url
async def get_dataframe_from_uri(uri: str):
import pandas
df = None
if uri.endswith(".csv"):
# Moving to its own thread to avoid io from blocking the eventloop
# This isn't ideal as it moves more then just the IO to a new thread
# but it is as close as we can easly get
df = await asyncio.to_thread(pandas.read_csv, uri)
elif uri.endswith(".xlsx"):
df = await asyncio.to_thread(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