Skip to content

feat: GenAI SDK client(multimodal) - Return the assembled table as a DataFrame from datasets.assemble.#6905

Open
copybara-service[bot] wants to merge 1 commit into
mainfrom
copybara_934391455
Open

feat: GenAI SDK client(multimodal) - Return the assembled table as a DataFrame from datasets.assemble.#6905
copybara-service[bot] wants to merge 1 commit into
mainfrom
copybara_934391455

Conversation

@copybara-service

@copybara-service copybara-service Bot commented Jun 19, 2026

Copy link
Copy Markdown
Contributor

feat: GenAI SDK client(multimodal) - Return the assembled table as a DataFrame from datasets.assemble.

BREAKING CHANGE: datasets.assemble now returns tuple[str, Optional[bigframes.pandas.DataFrame]] (the BigQuery table id without the bq:// prefix, and the assembled table as a BigFrames DataFrame) instead of the BigQuery URI str. By default no DataFrame is loaded (load_dataframe=False): the second element is None, no BigQuery read is performed, and bigframes is not required. Pass load_dataframe=True to load the assembled table.

Before:

uri = client.datasets.assemble(name=..., gemini_request_read_config=...)

After:

# Returns a (table_id, dataframe) tuple; no DataFrame is loaded by default.
table_id, _ = client.datasets.assemble(name=..., gemini_request_read_config=...)

# Pass load_dataframe=True to also get the assembled table as a BigFrames DataFrame.
table_id, df = client.datasets.assemble(
    name=..., gemini_request_read_config=..., load_dataframe=True
)

@copybara-service copybara-service Bot requested a review from a team as a code owner June 19, 2026 14:38
@product-auto-label product-auto-label Bot added size: m Pull request size is medium. api: vertex-ai Issues related to the googleapis/python-aiplatform API. labels Jun 19, 2026
@copybara-service copybara-service Bot force-pushed the copybara_934391455 branch from 37550e2 to 6f18240 Compare June 19, 2026 15:15
…DataFrame from `datasets.assemble`.

BREAKING CHANGE: `datasets.assemble` now returns `tuple[str, Optional[bigframes.pandas.DataFrame]]` (the BigQuery table id without the `bq://` prefix, and the assembled table as a BigFrames DataFrame) instead of the BigQuery URI `str`. By default no DataFrame is loaded (`load_dataframe=False`): the second element is `None`, no BigQuery read is performed, and `bigframes` is not required. Pass `load_dataframe=True` to load the assembled table.

Before:

```
uri = client.datasets.assemble(name=..., gemini_request_read_config=...)
```

After:

```
# Returns a (table_id, dataframe) tuple; no DataFrame is loaded by default.
table_id, _ = client.datasets.assemble(name=..., gemini_request_read_config=...)

# Pass load_dataframe=True to also get the assembled table as a BigFrames DataFrame.
table_id, df = client.datasets.assemble(
    name=..., gemini_request_read_config=..., load_dataframe=True
)
```

PiperOrigin-RevId: 934391455
@copybara-service copybara-service Bot force-pushed the copybara_934391455 branch from 6f18240 to 5ce1828 Compare June 24, 2026 08:45
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

api: vertex-ai Issues related to the googleapis/python-aiplatform API. google-contributor size: m Pull request size is medium.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant