Uh oh!
There was an error while loading. Please reload this page.
Document when to use common.ai vs vendor-specific AI providers - #69551
Conversation
df9954b to
feac1fdComparefeac1fd to
36aa507Compare
gopidesupavan
left a comment
There was a problem hiding this comment.
LGTM, thanks for adding..
The common.ai, openai, and anthropic docs landing pages now explain how to choose between the vendor-neutral operators and the native API wrappers — including where the agent loop runs (Airflow worker vs vendor-managed service).
36aa507 to
d07db20CompareUh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
| When to use this provider | ||
| -------------------------- | ||
| ``common.ai`` is the vendor-neutral way to put LLM and agent steps in a Dag. It is built on |
There was a problem hiding this comment.
A reader who already has LangChain or LlamaIndex code may read "built on pydantic-ai" as "not for me" and move on. Since the provider ships a LangChain toolset (the langchain extra), one sentence noting that existing LangChain tools can be called from a common.ai agent would keep that reader engaged, without overstating support.
There was a problem hiding this comment.

I added it to the middle of this paragraph in https://github.com/apache/airflow/pull/69649/changes. let me know if it's better to move it or extend it
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
…docs Reviewer feedback on apache#69551 (merged) asked for a scannable package-choice table linking to the vendor provider pages, a note that existing LangChain tools work via the langchain extra, and a link to the toolsets doc from the agent bullet.
…fy batch tradeoff Reviewer feedback on apache#69551 (merged) noted the comparison section ran before readers knew what the provider was, that OpenAIHook isn't batch-specific, and that the batch bullet didn't explain why one would pick it over a synchronous call.
…d batch cost/turnaround rationale Reviewer feedback on apache#69551 (merged) noted the comparison section ran before readers knew what the provider was, and that the batch bullet didn't explain why one would pick it over a synchronous call. The new clause reuses the cost/turnaround figures already documented in operators/anthropic.rst for consistency.
Why
common.aioperators and each vendor's native API wrappers — readers had to infer it.What
common.ai,openai, andanthropicindex pages now each carry a "When to use this provider" section with the decision rule and a runnable example snippet.common.ai, model stays swappable via connection) vs submitted to a vendor-managed service (native Batch / Responses / Managed Agents endpoints).Was generative AI tooling used to co-author this PR?
Generated-by: [Claude] following the guidelines
{pr_number}.significant.rst, in airflow-core/newsfragments. You can add this file in a follow-up commit after the PR is created so you know the PR number.