86 lines
4.5 KiB
Go
86 lines
4.5 KiB
Go
package grammar
|
|
|
|
import (
|
|
"encoding/json"
|
|
"fmt"
|
|
|
|
"gitea.maximumdirect.net/eric/audita/internal/core/schema"
|
|
"gitea.maximumdirect.net/eric/audita/internal/framework/contracts"
|
|
)
|
|
|
|
type promptSegment struct {
|
|
ID int `json:"id"`
|
|
Speaker string `json:"speaker"`
|
|
Start float64 `json:"start"`
|
|
End float64 `json:"end"`
|
|
Text string `json:"text"`
|
|
Categories []string `json:"categories,omitempty"`
|
|
}
|
|
|
|
type promptTranscriptSection struct {
|
|
SectionIndex int `json:"section_index"`
|
|
Segments []promptSegment `json:"segments"`
|
|
}
|
|
|
|
// BuildProposalMessages mirrors the Python grammar-module prompt intent:
|
|
// punctuation/capitalization/spacing cleanup only, with strict meaning guards.
|
|
func BuildProposalMessages(transcript *schema.Transcript, glossary *schema.Glossary) ([]contracts.LLMMessage, error) {
|
|
glossaryJSON, err := json.MarshalIndent(glossary, "", " ")
|
|
if err != nil {
|
|
return nil, fmt.Errorf("marshal glossary prompt context: %w", err)
|
|
}
|
|
|
|
sectionPayload := promptTranscriptSection{
|
|
SectionIndex: 0,
|
|
Segments: make([]promptSegment, 0),
|
|
}
|
|
if transcript != nil {
|
|
for _, s := range transcript.Segments {
|
|
sectionPayload.Segments = append(sectionPayload.Segments, promptSegment{
|
|
ID: s.ID,
|
|
Speaker: s.Speaker,
|
|
Start: s.Start,
|
|
End: s.End,
|
|
Text: s.Text,
|
|
Categories: append([]string(nil), s.Categories...),
|
|
})
|
|
}
|
|
}
|
|
|
|
sectionJSON, err := json.MarshalIndent(sectionPayload, "", " ")
|
|
if err != nil {
|
|
return nil, fmt.Errorf("marshal transcript prompt context: %w", err)
|
|
}
|
|
|
|
system := "You are Audita, a conservative grammar cleanup assistant. Identify only punctuation, capitalization, and spacing cleanup that preserves the same underlying words. Do not change content, substitute words, or rewrite the speaker's phrasing."
|
|
user := "Review this transcript section and return only grammar cleanup corrections that should be applied.\n\n" +
|
|
"Rules:\n" +
|
|
"- Allowed changes are punctuation, capitalization, spacing, and article cleanup only.\n" +
|
|
"- You may add, remove, or adjust commas, periods, quotation marks, apostrophes, dashes, ellipses, spacing, and capitalization when the underlying words stay the same.\n" +
|
|
"- You may change the whole-word article \"a\" to \"an\" or \"an\" to \"a\" when the surrounding text otherwise stays the same.\n" +
|
|
"- Homophone, spoken-form, and mistranscription corrections are handled during a later review stage; do not propose them here.\n" +
|
|
"- Do not make word substitutions, spelling fixes, homophone fixes, filler cleanup, repetition cleanup, paraphrases, or other semantic rewrites.\n" +
|
|
"- Do not change one written word into a different written word, except for capitalization changes to the same letters.\n" +
|
|
"- If a possible correction depends on changing a content word into a different word, omit it here rather than bundling it together with formatting cleanup.\n" +
|
|
"- Treat glossary names and aliases as protected spellings and context.\n" +
|
|
"- Do not replace, Anglicize, normalize, lowercase, or otherwise alter protected glossary names or aliases away from their glossary spelling.\n" +
|
|
"- Preserve canonical glossary capitalization for protected names and aliases, even if they look unusual.\n" +
|
|
"- If a segment includes categories, treat them as additional transcript context.\n" +
|
|
"- Use the exact id from the input segment.\n" +
|
|
"- For returned corrections, original_text must be only the exact text span that needs replacement, not the full segment text unless the whole segment is the replacement span.\n" +
|
|
"- Choose an original_text span that appears exactly once in the current segment text.\n" +
|
|
"- corrected_text must be only the replacement text for that span, not the full corrected segment text unless the whole segment is the replacement span.\n" +
|
|
"- Each returned correction must contain only id, original_text, corrected_text, and confidence.\n" +
|
|
"- Do not return corrections where original_text and corrected_text are identical.\n" +
|
|
"- Do not return speaker, start, or end fields.\n" +
|
|
"- Return only changed segments; do not return entries for unchanged segments.\n" +
|
|
"- confidence must be between 0.0 and 1.0.\n" +
|
|
"- If no corrections are needed, return an empty corrections list.\n\n" +
|
|
fmt.Sprintf("Protected glossary/context:\n%s\n\nTranscript section:\n%s", string(glossaryJSON), string(sectionJSON))
|
|
|
|
return []contracts.LLMMessage{
|
|
{Role: "system", Content: system},
|
|
{Role: "user", Content: user},
|
|
}, nil
|
|
}
|