forked from phoenix-oss/llama-stack-mirror
feat(api): (1/n) datasets api clean up (#1573)
## PR Stack - https://github.com/meta-llama/llama-stack/pull/1573 - https://github.com/meta-llama/llama-stack/pull/1625 - https://github.com/meta-llama/llama-stack/pull/1656 - https://github.com/meta-llama/llama-stack/pull/1657 - https://github.com/meta-llama/llama-stack/pull/1658 - https://github.com/meta-llama/llama-stack/pull/1659 - https://github.com/meta-llama/llama-stack/pull/1660 **Client SDK** - https://github.com/meta-llama/llama-stack-client-python/pull/203 **CI** -1391130488
<img width="1042" alt="image" src="https://github.com/user-attachments/assets/69636067-376d-436b-9204-896e2dd490ca" /> -- the test_rag_agent_with_attachments is flaky and not related to this PR ## Doc <img width="789" alt="image" src="https://github.com/user-attachments/assets/b88390f3-73d6-4483-b09a-a192064e32d9" /> ## Client Usage ```python client.datasets.register( source={ "type": "uri", "uri": "lsfs://mydata.jsonl", }, schema="jsonl_messages", # optional dataset_id="my_first_train_data" ) # quick prototype debugging client.datasets.register( data_reference={ "type": "rows", "rows": [ "messages": [...], ], }, schema="jsonl_messages", ) ``` ## Test Plan - CI:1387805545
``` LLAMA_STACK_CONFIG=fireworks pytest -v tests/integration/datasets/test_datasets.py ``` ``` LLAMA_STACK_CONFIG=fireworks pytest -v tests/integration/scoring/test_scoring.py ``` ``` pytest -v -s --nbval-lax ./docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb ```
This commit is contained in:
parent
3b35a39b8b
commit
5287b437ae
29 changed files with 2593 additions and 2296 deletions
|
@ -10,18 +10,17 @@ from urllib.parse import unquote
|
|||
|
||||
import pandas
|
||||
|
||||
from llama_stack.apis.common.content_types import URL
|
||||
from llama_stack.providers.utils.memory.vector_store import parse_data_url
|
||||
|
||||
|
||||
def get_dataframe_from_url(url: URL):
|
||||
def get_dataframe_from_uri(uri: str):
|
||||
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)
|
||||
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)
|
||||
|
@ -39,6 +38,6 @@ def get_dataframe_from_url(url: URL):
|
|||
else:
|
||||
df = pandas.read_excel(data_bytes)
|
||||
else:
|
||||
raise ValueError(f"Unsupported file type: {url}")
|
||||
raise ValueError(f"Unsupported file type: {uri}")
|
||||
|
||||
return df
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue