feat(server): wire EmbeddingRelevanceScorer into context builder, default level 4
Move embedder construction ahead of the engines so the context pack builder ranks freeform turns by query relevance (query-conditioned selection). Default compression_level 4 (format + static cache + token pruning + age-tiering) for a 12b on a 16k window.
This commit is contained in:
@@ -624,7 +624,7 @@ object ConfigLoader {
|
||||
asInt(orchestrationSection["journal_compaction_token_threshold"], 2_000),
|
||||
resumeAbandonedMaxAgeMinutes =
|
||||
asLong(orchestrationSection["resume_abandoned_max_age_minutes"], 1_440),
|
||||
compressionLevel = asInt(orchestrationSection["compression_level"], 2),
|
||||
compressionLevel = asInt(orchestrationSection["compression_level"], 4),
|
||||
tokenPrunerUrl =
|
||||
asString(orchestrationSection["token_pruner_url"], "http://127.0.0.1:8199"),
|
||||
)
|
||||
|
||||
@@ -64,9 +64,10 @@ data class OrchestrationKnobs(
|
||||
/**
|
||||
* Context compression pipeline level (docs/plans/correx-compression-pipeline.md §5), additive
|
||||
* 1..9. Default 2 = free format-compress + static cache. Raise toward the 16k wall; ≥3 needs
|
||||
* the LLMLingua-2 sidecar at [tokenPrunerUrl] (fails open if absent).
|
||||
* the LLMLingua-2 sidecar at [tokenPrunerUrl] (fails open if absent). Default 4 = format +
|
||||
* static cache + token pruning + age-tiering, sized for a 12b on a 16k window.
|
||||
*/
|
||||
val compressionLevel: Int = 2,
|
||||
val compressionLevel: Int = 4,
|
||||
val tokenPrunerUrl: String = "http://127.0.0.1:8199",
|
||||
)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user