https://prod-files-secure.s3.us-west-2.amazonaws.com/e3525cb2-7056-4726-bb14-939e8bc8ef1c/5f610690-1381-4dfc-aaa1-5cd9a1bd0f12/241201_02_dr_katz_4k_h264.mp4
🏔 Challenge: Help Those Who Help Others
Dr. Katz is an online platform that centralizes mental-wellness expertise for patients and caregivers alike. Seeking to improve creative engagement, the startup enlisted Loka to build in generative AI services that will facilitate collaboration and professional development, simplify video production and sharing and automate routine clinical tasks. All system architecture must comply with HIPAA privacy regulations.
💡 Approach: Make it Easy, Make it Shareable
Loka is integrating a Large Language Model (LLM) on AWS Sagemaker, with a primary goal of identifying potential vulnerabilities. Loka’s AWS-certified team of expert ML engineers is developing a refined pipeline using a limited number of content samples. This approach will leverage LangChain for efficient prompt creation and deploy a self-hosted Llama 2 for the LLM.
Ever mindful of budget, Loka has configured AWS cost controls such as budget alerts and infrastructure pausing during inactivity. To create a scalable system, they’ve built a workflow responsible for fetching transcriptions from an S3 bucket and providing LLM-based suggestions. This workflow is handled by a Lambda function, which is triggered when a transcription file is uploaded to an S3 bucket. Subsequently, it sends requests to the Sagemaker endpoint hosting the LLM, which in turn, provides suggestions for titles, descriptions and tags.
🎯 Impact
✅ Key Takeaways