[
https://issues.apache.org/jira/browse/FLINK-41001?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
ASF GitHub Bot updated FLINK-41001:
-----------------------------------
Labels: pull-request-available (was: )
> OpenAI model provider rejects compatible string input types
> -----------------------------------------------------------
>
> Key: FLINK-41001
> URL: https://issues.apache.org/jira/browse/FLINK-41001
> Project: Flink
> Issue Type: Bug
> Components: Library / Machine Learning
> Affects Versions: 2.1.0, 2.2.0, 2.3.0, 2.4.0
> Reporter: Liu Liu
> Priority: Major
> Labels: pull-request-available
>
> The OpenAI model provider validates its model input schema against an exact
> nullable, unbounded {{STRING}} type. Consequently, models declaring
> {{{}CHAR{}}}, bounded {{{}VARCHAR{}}}, or {{STRING NOT NULL}} inputs fail
> during prediction planning, although the provider supports their string
> representation.
> For example,
>
> {code:java}
> CREATE MODEL chat_model
> INPUT (prompt CHAR(5) NOT NULL)
> OUTPUT (answer STRING)
> WITH (
> 'provider' = 'openai',
> 'endpoint' = 'https://example.test/chat/completions',
> 'api-key' = 'dummy',
> 'model' = 'example'
> );
> CREATE TEMPORARY VIEW prompts AS
> SELECT 'hello' AS prompt;
> EXPLAIN PLAN FOR
> SELECT * FROM TABLE(
> ML_PREDICT(TABLE prompts, MODEL chat_model, DESCRIPTOR(prompt))
> ); {code}
>
> Planning fails with
> {code:java}
> input column prompt should be STRING, but is a CHAR(5) NOT NULL. {code}
> The shared validation affects OpenAI models through SQL and Table API.
> Input validation should accept CHAR and VARCHAR regardless of their length or
> nullability, while retaining the existing output schema, column count, and
> metadata constraints.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
