cleanup gbnf grammars

This commit is contained in:
Aaron Po
2026-06-23 00:38:53 -04:00
parent ac701d661a
commit 22b3f2b3f9
4 changed files with 49 additions and 27 deletions

View File

@@ -0,0 +1,44 @@
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_JSON_GRAMMARS_H_
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_JSON_GRAMMARS_H_
/**
* @file data_generation/json_grammars.h
* @brief GBNF grammars constraining structured JSON output from
* LlamaGenerator inference calls.
*/
#include <string_view>
// GBNF grammar for structured user JSON output.
inline constexpr std::string_view kUserJsonGrammar = R"json_user(
root ::= thought-block "{" ws
"\"username\"" ws ":" ws string ws "," ws
"\"bio\"" ws ":" ws string ws "," ws
"\"activity_weight\"" ws ":" ws number ws
"}" ws
thought-block ::= [^{]*
ws ::= [ \t\n\r]*
string ::= "\"" char+ "\""
char ::= [^"\\\x7F\x00-\x1F] | [\\] escape
escape ::= ["\\/bfnrt] | "u" hex hex hex hex
hex ::= [0-9a-fA-F]
number ::= "-"? ("0" | [1-9] [0-9]*) ("." [0-9]+)?
)json_user";
// GBNF grammar for structured brewery JSON output.
inline constexpr std::string_view kBreweryJsonGrammar = R"json_brewery(
root ::= thought-block "{" ws
"\"name_en\"" ws ":" ws string ws "," ws
"\"description_en\"" ws ":" ws string ws "," ws
"\"name_local\"" ws ":" ws string ws "," ws
"\"description_local\"" ws ":" ws string ws
"}" ws
thought-block ::= [^{]*
ws ::= [ \t\n\r]*
string ::= "\"" char+ "\""
char ::= [^"\\\x7F\x00-\x1F] | [\\] escape
escape ::= ["\\/bfnrt] | "u" hex hex hex hex
hex ::= [0-9a-fA-F]
)json_brewery";
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_JSON_GRAMMARS_H_