RC-2
release-tag / release-image (push) Has been cancelled

This commit is contained in:
2026-07-28 20:15:43 +02:00
parent a01b53097a
commit 523e597e7a
17 changed files with 211 additions and 61 deletions
+13 -7
View File
@@ -1172,14 +1172,20 @@ func minInt(a, b int) int {
}
func hashDoc(d model.KnowledgeDoc, cfg ScoringConfig) string {
// Only retrieval-relevant fields belong in the embedding fingerprint.
// Formatting-only changes to AnswerHTML must not force re-embedding.
b, _ := json.Marshal(struct {
Doc model.KnowledgeDoc `json:"doc"`
Profile string `json:"profile"`
EmbeddingIdentity string `json:"embedding_identity"`
ChunkWords int `json:"chunk_words"`
ChunkOverlap int `json:"chunk_overlap"`
MaxChunks int `json:"max_chunks"`
}{d, cfg.EmbeddingProfile, cfg.EmbeddingIdentity, cfg.ChunkWords, cfg.ChunkOverlap, cfg.MaxChunksPerDoc})
ID string `json:"id"`
Title string `json:"title"`
Text string `json:"text"`
Categories []int64 `json:"categories"`
Keywords []string `json:"keywords"`
Profile string `json:"profile"`
EmbeddingIdentity string `json:"embedding_identity"`
ChunkWords int `json:"chunk_words"`
ChunkOverlap int `json:"chunk_overlap"`
MaxChunks int `json:"max_chunks"`
}{d.ID, d.Title, d.Text, d.Categories, d.Keywords, cfg.EmbeddingProfile, cfg.EmbeddingIdentity, cfg.ChunkWords, cfg.ChunkOverlap, cfg.MaxChunksPerDoc})
h := sha256.Sum256(b)
return hex.EncodeToString(h[:])
}