将 GenAI 推理从原型扩展到生产：速度与成本的现实经验.pdf

1、Forward-looking StatementThis presentation has been prepared for informational purposes only.The information set forth herein does not purport to be complete or contain all relevant information.Statements contained herein are made as of the date of this presentation unless stated otherwise.This pres

2、entation and the accompanying oral commentary may contain forward-looking statements.In some cases,forward-looking statements can be identified by terms such as“may”,“will”,“should”,“expects”,“plans”,“anticipates”,“could”,“intends”,“projects”,“believes”,“estimates”,“predicts”,or“continue”,or the neg

3、ative of these words or other similar terms or expressions that concern Databricks expectations,strategy,plans,or intentions.Forward-looking statements are based on information available at the time those statements are made and are inherently subject to risks and uncertainties that could cause actu

4、al results to differ materially from those expressed in or suggested by the forward-looking statements.Forward-looking statements should not be read as a guarantee of future performance or outcomes.Except as required by law,Databricks does not undertake any obligation to publicly update or revise an

5、y forward-looking statement,whether as a result of new information,future developments or otherwise.3Scaling GenAI InferencePrototype to ProductionAnish KumarJune 10,2025Scribd Inc.Scribd,Everand,SlideshareHow it startedThe problemMetadata ExtractionExtract rich structured metadata from Ebooks and A

6、udiobooksThe bigger pictureEnriching documents using GenAI inferenceUnique challenges150,000 audiobooks500,000 ebooksMultiple languagesRealtime Whisper(audio transcription)Evaluate LLMsCostQualityDue to size and type of corpusLLM evaluations10From recent projectsPrompt Engineering and evaluation20 a