I want to experiment with the summarizer API On Thursday, 10 October 2024 at 09:54:21 UTC-7 Mike Taylor wrote:
> LGTM to experiment from 131 to 136 inclusive. > On 10/9/24 7:58 PM, Domenic Denicola wrote: > > Contact emails > > dom...@chromium.org, fer...@chromium.org, kenji...@chromium.org > > Explainer > > > https://github.com/explainers-by-googlers/writing-assistance-apis/blob/main/README.md > > Specification > > None yet, although we'll be writing one during the experimentation period. > > Summary > > A JavaScript API for producing summaries of input text, backed by an AI > language model. > > Blink component > > Blink>AI>Summarization > <https://bugs.chromium.org/p/chromium/issues/list?q=component:Blink%3EAI%3ESummarization> > > TAG review > > https://github.com/w3ctag/design-reviews/issues/991 > > TAG review status > > Pending > > Risks > Interoperability and Compatibility > > This feature has definite interoperability and compatibility risks, due to > the likelihood that different implementations will use different language > models, prompts, and fine-tunings, and even within a single implementation > such as Chrome, these pieces will likely change over time. Additionally, > not all browsers and operating systems will have a built-in language model > to expose, and not all devices will be powerful enough to run one > effectively. > > We are taking a variety of steps to attempt to mitigate these risks. For > example, the specification is designed to allow the API to be backed by a > cloud-based language model. This approach could extend the functionality to > a wider range of devices and users. The API is designed to abstract away > the specifics of the underlying language model, including prompts and > fine-tuning. This prevents developers from relying on specific outputs, > ensuring they receive a generalized summary rather than structured data > that might vary across implementations. Finally, the API surface is > designed with many clear points of failure, that encourage the developer to > probe for capabilities ahead of time and fall back to other techniques if a > capability is not available. > > Nevertheless, interoperability and compatibility risk remains high for > these sorts of APIs, and we'll be closely monitoring it during the > prototyping period. > > Gecko: No signal ( > https://github.com/mozilla/standards-positions/issues/1067) > > WebKit: No signal ( > https://github.com/WebKit/standards-positions/issues/393) > > Web developers: Mixed signals ( > https://github.com/WICG/proposals/issues/163). Prototyping with partners > behind a flag revealed enthusiasm and many prototypes built, from which we > drew the discussion of potential use cases [1]. Feedback on the WICG thread > was more mixed. Some themes we saw include: asking for more capabilities > (e.g. full prompting of a language model instead of higher-level APIs (our > response at [2]); multi-modal support); desire to make sure the API > actually works robustly in many real-world use cases; removal of any > safety/ethical safeguards; and confusion about client-side vs. cloud APIs. > > [1]: > https://github.com/WICG/writing-assistance-apis/blob/main/README.md#summarizer-api > > [2]: > https://github.com/WICG/writing-assistance-apis/blob/main/README.md#directly-exposing-a-prompt-api) > > <https://github.com/WICG/writing-assistance-apis/blob/main/README.md#directly-exposing-a-prompt-api);> > > Other signals: > > Activation > > This feature would definitely benefit from having polyfills, backed by any > of: cloud services, lazily-loaded client-side models using WebGPU, or the > web developer's own server. We anticipate seeing an ecosystem of such > polyfills grow as more developers experiment with this API. > > > WebView application risks > > Does this intent deprecate or change behavior of existing APIs, such that > it has potentially high risk for Android WebView-based applications? > > None > > > Goals for experimentation > > We're most interested in feedback on whether the summarization quality we > can provide is useful to sites, and whether the options we've defined for > controlling the summarization are useful. Additionally, we want to learn > about the impact of the current API's limitations, e.g. maximum input > length, to determine where we should spend our best effort lifting those > limits. > > The origin trial will be limited to English-language input to start. We > are hoping to add support for more languages over time. Learning how much > of a limitation this is, and which languages ought to be prioritized, will > also be helpful. > > Finally, we're also interested in feedback about the API shape and ease of > use. > > Ongoing technical constraints > > None. > > Debuggability > > It is possible that giving DevTools more insight into the nondeterministic > states of the model, e.g. random seeds, could help with debugging. See > related discussion at > https://github.com/explainers-by-googlers/prompt-api/issues/9. > > Will this feature be supported on all six Blink platforms (Windows, Mac, > Linux, ChromeOS, Android, and Android WebView)? > > No. Not all platforms will come with a language model. In particular, in > the initial stages we are focusing on Windows, Mac, and Linux. > > Is this feature fully tested by web-platform-tests > <https://chromium.googlesource.com/chromium/src/+/main/docs/testing/web_platform_tests.md> > ? > > No. We hope to work on web platform tests for this feature, but how much > we can guarantee as testable beyond the surface API is unclear, given the > nondeterministic nature of the output. The explainer discusses this in > https://github.com/WICG/writing-assistance-apis/blob/main/README.md#specifications-and-tests > . > > Flag name on chrome://flags > > summarization-api-for-gemini-nano > > Finch feature name > > EnableAISummarizationAPI > > Requires code in //chrome? > > True > > Tracking bug > > https://issues.chromium.org/issues/351744634 > > Estimated milestones > > Origin trial desktop first > > 131 > > Origin trial desktop last > > 136 > > DevTrial on desktop > > 129 > > > Link to entry on the Chrome Platform Status > > https://chromestatus.com/feature/5193953788559360?gate=5082928917512192 > > Links to previous Intent discussions > > Intent to Prototype: > https://groups.google.com/a/chromium.org/d/msgid/blink-dev/CAM0wra8iMt24s_jP9Ng9_RKU3cH4wFywAt00kitJCeMJ3CaUAw%40mail.gmail.com > > > This intent message was generated by Chrome Platform Status > <https://chromestatus.com/>. > > -- > You received this message because you are subscribed to the Google Groups > "blink-dev" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to blink-dev+...@chromium.org. > To view this discussion on the web visit > https://groups.google.com/a/chromium.org/d/msgid/blink-dev/CAM0wra8d6bZo%2B9-8Rum0N%3D4oFpwVfquqAzRC7mu1GTyVeDWw5A%40mail.gmail.com > > <https://groups.google.com/a/chromium.org/d/msgid/blink-dev/CAM0wra8d6bZo%2B9-8Rum0N%3D4oFpwVfquqAzRC7mu1GTyVeDWw5A%40mail.gmail.com?utm_medium=email&utm_source=footer> > . > > -- You received this message because you are subscribed to the Google Groups "blink-dev" group. To unsubscribe from this group and stop receiving emails from it, send an email to blink-dev+unsubscr...@chromium.org. To view this discussion visit https://groups.google.com/a/chromium.org/d/msgid/blink-dev/0c704e0b-5577-4759-9c27-d394a9b8ceb6n%40chromium.org.
