AI Case studies - Experiences and lessons learnt (How would you integrate AI in your business).pdf
0 likes234 views
The document discusses the integration of AI in business, highlighting experiences and lessons learned by a senior enterprise java developer. It explores various generative AI models and tools, their applications in fields like healthcare, and the importance of adaptive learning and data privacy. Additionally, it mentions the role of non-profit organizations like Devoxx4Kids in promoting programming and robotics among children.
AI Case studies - Experiences and lessons learnt (How would you integrate AI in your business).pdf
- 1. AI CASE STUDY – EXPERIENCES & LESSON LEARNED How would you integrate with AI in your business?
- 2. ● Senior Full Stack Enterprise Java Developer, Engineer and Consultant, Sindi Technologies (Pty) Ltd ○ 18+ years of enterprise software development experience. ● Tech speaker / Blogger ● Devoxx4Kids South Africa (Non- Profit Organisation) founder and event organiser About Me
- 3. Where to find me? https://linktr.ee/theEliteGentleman buhake@gmail.com @EliteGentleman www.sindi.co.za www.devoxx4kids.org.za
- 4. Agenda IBFP 2024 Case study 02 Solution 04 Glossary 01 Problems and Concerns 03 Finally 05 Q&A 06
- 5. GLOSSARY 01
- 6. • An AI research organization, started in December 2015. • Mission: To develop “safe and beneficial” artificial generative intelligence. • First GPT was introduced in 2018 • Introduced ChatGPT, a chatbot and virtual assistant, in November 2022 • Today, ChatGPT-4o, released in May 2024 • It powers Microsoft Copilot, Apple Intelligence • ChatGPT is credited for starting the AI boom, catalyzing the widespread interest of generative AI. https://openai.com/
- 7. ● Use of prompts to generate various data using generative models. ● Chat Prompts ○ ChatGPT by OpenAI, Gemini by Google, LLaMA by Meta AI, Mistral, Claude by Anthropic, Qwen by Alibaba, ERNIE by Baidu ● Text-to-Image models ○ DALL-E by OpenAI, Imagen by Google, Firefly by Apple, Midjourney by Midjourney, Stable Diffusion by Stability AI, RunwayML by Runway AI ● Text-to-Video models ○ Sora by OpenAI, VideoPoet by Google, Runway by Runway AI GenerativeAI
- 8. ● Using the combination of Gen AI and Retrieval-Augmented Generation (RAG) ○ RAG: a technique for enhancing the accuracy and reliability of generative AI models with facts fetched from external sources. ● Human-like conversational skills ○ Fully understand customer intents, contexts and provide tailor services around their exact need ● Enterprise knowledge. ○ Pre-train your GenAI with factual enterprise knowledge for superior query resolution, ● Adaptive learning ○ Improve your GenAI with new knowledge acquired from customer interactions to provide better service skills. AI Agents for your business
- 10. ● Problem space: ○ Healthcare professionals doing consultations may have too many patient visits: ■ Medical records needs to accurately captured and filed. ■ Usually captured by an assistant for filing ● Problem: initial training to get up to speed with doctor speak. ● Problem: difficulty reading doctor’s handwriting. ■ Time consuming: Doctor may have to go for surgeries. ● Problem: peer review of captured record may happen late. ● Problem: remembering the conversation that is in the past. ● Solution: ○ Tool must: ■ Transcribe audio recording ● Multi-language support (English, Afrikaans and other supported native languages) ● Able to identify multiple speakers from audio. ■ Text summarization and document generation from transcribed text ● GPTs to the rescue. MEDICAL CONSULT TRANSCRIBING
- 12. Varieties of AI companies to choose from
- 13. ● IBM: ○ Watsonx ● Microsoft: ○ Various models available on Azure AI services ■ OpenAI, Mistral AI, Phi-3, Meta AI, Stability AI, Core42 (Arabic LLM), Nixtla, and more. ● Google: ○ Vertex AI, includes PaLM2 ○ Generative AI, includes Gemini ● Amazon Bedrock ○ AWS ○ Fully managed services that offer choices of high-performing foundational models (FM) from leading AI companies ■ AL 21 Labs, Anthropic, Cohere, Meta, Mistral AI, Stability AI, Amazon ● Oracle ○ Oracle Cloud Infrastructure (OCI) Generative AI Top tech cloud providers – For enterprise customers.
- 14. ● China’s investment into AI ○ Alibaba: ■ Alibaba ■ Qwen (own Gen AI) ○ Baidu: ■ Baidu AI Cloud ■ ERNIE (own Gen AI) Top tech cloud providers – For enterprise customers.
- 15. ● Audio to text services are few: ○ Speaker diarization support (identify multiple speakers from audio conversations). ○ Multiple languages support (some don’t support local languages). ● Integration to their AI services: ○ Closed and proprietary, free and public (REST API), Cloud services ● Accuracy of the responses ○ Is text summarization accurate enough and does it understand context accordingly? ○ Do we have to refine the chat prompt assistant script to make the response accurate? ● Data Privacy ○ Hide client personal information at all cost. ○ What data info can be shared to AI services? ○ Governance – US laws vs. SA laws ● Cost. ○ Network Bandwidth ○ Cost of using AI service (in USD). ○ Credit card is required to access AI upfront. KEY PROBLEMS - CASE STUDY
- 16. Most have REST APIs INTEGRATION WITH AI
- 17. ● Input and Output price, per million tokens COST
- 18. ● Measured by tokens per second OUTPUT SPEED
- 19. ● Feeding the GenAI with facts. ○ Removing bias ○ Data cleanliness ○ Information overload ○ Context loss after consolidation ● Cost (too expensive) ○ LLM API ○ Embedding Model API ○ Vector database BUILDING YOUR AI AGENT
- 20. SOLUTION. 04
- 21. ● Transcribe with speaker diarization ○ Google Cloud Speech. ○ Converts speech-to-text. ○ Text returned, tagged orderly by speakers identified ● Text summarization: ○ Google Gemini ○ Prompt designed to understand transcribed text and generate document close to medical records. ● APIs are open (REST) ○ Simple to integrate (written in Java). ● Not too cheap, not too expensive either. CLOUD
- 22. ● Not all AI APIs are the same. ● Joined the Eclipse Foundation to standardize AI APIs -> AI Framework for Java ○ Eclipse Microprofile for AI ○ One simple framework for developers to access any AI models from various providers with ease. Standardization of AI APIs.
- 23. FINALLY. 05
- 24. ● A Non-profit Organisation that introduces kids to programming & robotics in a fun way. ● Started in 2016, hosted various events countrywide. ● Won numerous awards: ○ 2020 – Dzone Community Award ○ 2023 – JCP Award (Java in Community). Awarded by Oracle US. ● Future plans ○ Host future event workshops ○ Provide full online courses online that schools, parents can use to teach kids at home. ● Funding is always welcome! DEVOXX4KIDS SOUTH AFRICA https://www.devoxx4kids.org.za/
- 25. Thank you!
- 26. Questions?
- 27. Where to find me? https://linktr.ee/theEliteGentleman buhake@gmail.com @EliteGentleman www.sindi.co.za www.devoxx4kids.org.za https://jakartaee-ambassadors.io/