Neo4j GraphAcademy launches AI proxy so workshop learners skip OpenAI billing setup
JeremyCMorgan · x · 2026-10-21
Neo4j's GraphAcademy now routes workshop LLM calls through its own OpenAI-compatible proxy, so learners no longer need an OpenAI account or billing to run the GraphRAG workshops.
- Endpoint: graphacademy.neo4j.com/api/llm/v1, supporting POST /chat/completions, /responses (both streaming) and /embeddings; works with any OpenAI SDK, LangChain, Pydantic AI or curl by swapping base URL and key
- Per-course keys starting with ga- enforce course limits; gpt-/o-series go to OpenAI, claude- to Anthropic (chat only, when the course allows)
- The Responses API skips previousresponseid, background mode and built-in tools since responses aren't stored — send the full conversation in input
- The doc doubles as a reference for learners and coding agents debugging failed proxy requests
More from coding & agent
- Research agent Épi sets 120 records, narrows n-queens constant interval 84x — dair_ai · 2026-10-21
- Compaction hooks in practice: keep last n messages verbatim, summarize the rest for full agent continuity — MoonL88537 · 2026-10-21
- The blank prompt box hides real operational burden: context, workflow and supervision fall on users — _AustinCalvert_ · 2026-10-21
- DeepMind paper: self-evolving agents forget as they learn — fastest learner GEPA also breaks old tasks most — rohanpaul_ai · 2026-10-21
- arXiv: Are Self-Evolving Agents Continual Learners? Plasticity comes at the cost of stability — rohanpaul_ai · 2026-10-21
- PM OS vs Team OS vs Company OS: how to layer your AI setup and which to build first — aakashgupta · 2026-10-21