LocalAI/core
eureka928 bbb32ac244
feat(endpoints): extract raw JSON schema for structured output
In chat and completion endpoints, when response_format is json_schema,
extract the raw JSON schema and store it on config.JSONSchema alongside
the GBNF grammar. Also set config.ResponseFormat to the format type.

This allows backends that support native structured output (like vLLM)
to use the JSON schema directly instead of the GBNF grammar.

Ref: #6857
Signed-off-by: eureka928 <meobius123@gmail.com>
2026-04-13 13:52:05 +02:00
..
application feat(ux): backend management enhancement (#9325) 2026-04-12 00:35:22 +02:00
backend feat(backend): pass JSONSchema and ResponseFormat through gRPC 2026-04-13 13:52:05 +02:00
cli feat(ux): backend management enhancement (#9325) 2026-04-12 00:35:22 +02:00
clients feat: add distributed mode (#9124) 2026-03-30 00:47:27 +02:00
config feat(vllm): parity with llama.cpp backend (#9328) 2026-04-13 11:00:29 +02:00
dependencies_manager feat(ui): move to React for frontend (#8772) 2026-03-05 21:47:12 +01:00
explorer feat: add distributed mode (#9124) 2026-03-30 00:47:27 +02:00
gallery feat(vllm): parity with llama.cpp backend (#9328) 2026-04-13 11:00:29 +02:00
http feat(endpoints): extract raw JSON schema for structured output 2026-04-13 13:52:05 +02:00
p2p feat: add distributed mode (#9124) 2026-03-30 00:47:27 +02:00
schema feat(vllm): parity with llama.cpp backend (#9328) 2026-04-13 11:00:29 +02:00
services feat: backend versioning, upgrade detection and auto-upgrade (#9315) 2026-04-11 22:31:15 +02:00
startup feat: add distributed mode (#9124) 2026-03-30 00:47:27 +02:00
templates feat: add distributed mode (#9124) 2026-03-30 00:47:27 +02:00
trace feat: add distributed mode (#9124) 2026-03-30 00:47:27 +02:00