LocalAI/pkg/functions/grammars/bnf_rules.go
Ettore Di Giacinto 2169c3497d
feat(grammar): add llama3.1 schema (#3015)
* wip

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* get rid of panics

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* expose it properly from the config

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Simplify

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* forgot to commit

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Remove focus on test

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Small fixups

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-26 20:11:29 +02:00

59 lines
1.3 KiB
Go

package grammars
import (
"encoding/json"
"regexp"
)
var (
PRIMITIVE_RULES = map[string]string{
"boolean": `("true" | "false") space`,
"number": `("-"? ([0-9] | [1-9] [0-9]*)) ("." [0-9]+)? ([eE] [-+]? [0-9]+)? space`,
"integer": `("-"? ([0-9] | [1-9] [0-9]*)) space`,
"string": `"\"" (
[^"\\] |
"\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
)* "\"" space`,
// TODO: we shouldn't forbid \" and \\ or all unicode and have this branch here,
// however, if we don't have it, the grammar will be ambiguous and
// empirically results are way worse.
"freestring": `(
[^\x00] |
"\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
)* space`,
"null": `"null" space`,
}
INVALID_RULE_CHARS_RE = regexp.MustCompile(`[^a-zA-Z0-9-]+`)
GRAMMAR_LITERAL_ESCAPE_RE = regexp.MustCompile(`[\r\n"]`)
GRAMMAR_LITERAL_ESCAPES = map[string]string{
"\r": `\r`,
"\n": `\n`,
`"`: `\"`,
}
)
const (
SPACE_RULE = `" "?`
arrayNewLines = `arr ::=
"[\n" (
realvalue
(",\n" realvalue)*
)? "]"`
array = `arr ::=
"[" (
realvalue
("," realvalue)*
)? "]"`
)
func jsonString(v interface{}) (string, error) {
b, err := json.Marshal(v)
if err != nil {
return "", err
}
return string(b), nil
}