2075 - 在 AWS 上使用 IBM Watsonx.data 和 IBM Data Gate 在 RAG 应用程序中使用大型机数据.pdf

1、Orlando,FLOctober 69IBM TechXchange 2025Session code 2075Anson KokkatIBM,Product Manager,watsonx.dataEduardo Monich FronzaAWS,Senior Partner Solutions ArchitectUsing Your Mainframe Data in RAG Applications on AWS with IBM watsonx.data and IBM Data GateAgenda01020304050607Value of enterprise dataIntr

2、oduction to watsonx.dataUnlock mainframe data for AI and analytics Modernize your Data LakeBuild generative AI applications with your data watsonx.data SaaS on AWSQ&AIBM TechXchange|2025 IBM CorporationOrlando,FLOctober 69IBM TechXchange 2025Value of enterprise data3Your enterprise data enterprise d

3、ata is key to differentiated gen AIGrowing unstructured Growing unstructured datadata adds complexity90%1%of enterprise data is currently being leveraged for gen AI 2Gen AI has amplified the need for AIAI-ready dataready data60%of AI projects that arent supported by an AIAI-ready data ready data pra

4、ctice practice will fail through 2026 1IBM TechXchange|2025 IBM Corporation4of enterprise-generated data is unstructured unstructured 3Data is the best tool for building accurate AImore accurate AI than conventional RAG with watsonx.data*Based on internal testing comparing the answer correctness of

5、AI model outputs using watsonx.data Premium Edition retrieval layer to vector-only RAG on three common use cases with IBM proprietary datasets using the same set of selected opensource commodity inferencing,judging and embedding models and additional variables.Results can vary.IBM TechXchange|2025 I

6、BM Corporation5Unprecedented data challenges to scale AIEmerging challenges of unstructured dataAI is only as good as your dataMore data volume and complexityIn more locationsIn more formatsWith less quality Exploding data growth But less than 1/3 of tech leaders strongly agree that their enterprise