AI, SQL, and GraphQL Walk into a Fertility Clinic… LLM-based Medical feature development
summary
Compares three concrete implementations—LLM+SQL, LLM+RestAPI, and LLM+GraphQL—and demonstrates why the team selects GraphQL: a single endpoint with GraphQL resolver checks that enforce role-based access, combine multiple databases via patient IDs, and return exactly the fields requested. Shows Python LLM chains that generate GraphQL queries from free‑form doctor questions, validate query syntax, run safely through resolvers, and then ask the LLM for a final answer paired with the raw DB results. Notes extra development cost but reports a working prototype with improved security and precision, plus NLP checks and AI-labeled answers.
AI-written summary · about
chapters (8)
- 0:00Introduction to the challenge
- 1:55Medical data query problem
- 3:42Doctors' tool requirements
- 6:34LLMs for medical queries
- 8:43SQL vs GraphQL debate
- 15:58GraphQL advantages explained
- 20:35Flow with LM and GraphQL
- 27:37Key takeaways and conclusion
related talks
27mAI, SQL, and GraphQL Walk into a Fertility Clinic
31mWhy AI needs GraphQL
30mLLM Query Benchmarks: Cypher vs SQL
15mTraining and Using Generative AI Models with GraphQL
18mInteracting with LLMs via GraphQL
15mFrom Words to Data: Using LLMs to Turn Questions into SQL
40mLLMs & Data Warehouses: Reliable AI Agents for Business (Keynote)
41mEnhancing LLMs with Graph Technology