Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
Python agent-contextagent-memoryagent-pluginsagentic-ragcontext-databasedsh-pluginknowledge-basememorymemory-managementself-evolvingvector-database
docs(retrieval): align score_propagation_alpha default 0.5→1.0 with #1947 (#1948)
Evo4237d5018f74
diff --git a/docs/en/concepts/07-retrieval.md b/docs/en/concepts/07-retrieval.mdindex 2fcceb3cd..521150a6c 100644--- a/docs/en/concepts/07-retrieval.md+++ b/docs/en/concepts/07-retrieval.md@@ -124,7 +124,7 @@ while dir_queue:| Parameter | Value | Description ||-----------|-------|-------------|-| `retrieval.score_propagation_alpha` | 0.5 | Child-score weight in the propagation blend; `0.5` means 50% child score + 50% parent score |+| `retrieval.score_propagation_alpha` | 1.0 | Child-score weight in the propagation blend; `1.0` uses only the child's own score and ignores the parent score || `MAX_CONVERGENCE_ROUNDS` | 3 | Convergence detection rounds || `GLOBAL_SEARCH_TOPK` | 10 | Global search candidates || `MAX_RELATIONS` | 5 | Max relations per resource |diff --git a/docs/en/guides/01-configuration.md b/docs/en/guides/01-configuration.mdindex d983fb719..8ab43a534 100644--- a/docs/en/guides/01-configuration.md+++ b/docs/en/guides/01-configuration.md@@ -735,7 +735,7 @@ Retrieval ranking configuration for final search scores.{"retrieval": {"hotness_alpha": 0.0,- "score_propagation_alpha": 0.5+ "score_propagation_alpha": 1.0}}```@@ -743,7 +743,7 @@ Retrieval ranking configuration for final search scores.| Parameter | Type | Description | Default ||-----------|------|-------------|---------|| `hotness_alpha` | float | Weight for blending hotness into final retrieval scores. `0.0` disables the hotness boost and keeps scores equal to semantic similarity; `1.0` uses only hotness. Valid range: `0.0` to `1.0`. | `0.0` |-| `score_propagation_alpha` | float | Weight for each child result's own score when blending with its parent score during hierarchical retrieval. `0.5` keeps the existing equal blend; `1.0` ignores the parent score; `0.0` uses only the parent score. Valid range: `0.0` to `1.0`. | `0.5` |+| `score_propagation_alpha` | float | Weight for each child result's own score when blending with its parent score during hierarchical retrieval. `1.0` ignores the parent score (semantic similarity only); `0.5` is an equal blend with the parent score; `0.0` uses only the parent score. Valid range: `0.0` to `1.0`. | `1.0` |Keep `hotness_alpha` at `0.0` when you need scores to reflect pure vector similarity. Set it above `0.0` only when frequently accessed or recently updated contexts should receive a ranking boost.@@ -1207,7 +1207,7 @@ For detailed encryption explanations, see [Data Encryption](../concepts/10-encry},"retrieval": {"hotness_alpha": 0.0,- "score_propagation_alpha": 0.5+ "score_propagation_alpha": 1.0},"encryption": {"enabled": false,diff --git a/docs/zh/concepts/07-retrieval.md b/docs/zh/concepts/07-retrieval.mdindex 28a1fbb70..d6f2b758e 100644--- a/docs/zh/concepts/07-retrieval.md+++ b/docs/zh/concepts/07-retrieval.md@@ -124,7 +124,7 @@ while dir_queue:| 参数 | 值 | 说明 ||------|-----|------|-| `retrieval.score_propagation_alpha` | 0.5 | 分数传播混合中子节点自身分数的权重;`0.5` 表示 50% 子节点分数 + 50% 父节点分数 |+| `retrieval.score_propagation_alpha` | 1.0 | 分数传播混合中子节点自身分数的权重;`1.0` 表示仅使用子节点自身分数,忽略父节点分数 || `MAX_CONVERGENCE_ROUNDS` | 3 | 收敛检测轮数 || `GLOBAL_SEARCH_TOPK` | 10 | 全局搜索候选数 || `MAX_RELATIONS` | 5 | 每资源最大关联数 |diff --git a/docs/zh/guides/01-configuration.md b/docs/zh/guides/01-configuration.mdindex 36f0d849a..b430925d0 100644--- a/docs/zh/guides/01-configuration.md+++ b/docs/zh/guides/01-configuration.md@@ -707,7 +707,7 @@ AST 提取支持:Python、JavaScript/TypeScript、Rust、Go、Java、C/C++。{"retrieval": {"hotness_alpha": 0.0,- "score_propagation_alpha": 0.5+ "score_propagation_alpha": 1.0}}```@@ -715,7 +715,7 @@ AST 提取支持:Python、JavaScript/TypeScript、Rust、Go、Java、C/C++。| 参数 | 类型 | 说明 | 默认值 ||------|------|------|--------|| `hotness_alpha` | float | hotness 分数在最终召回分数中的混合权重。`0.0` 表示关闭 hotness boost,最终分数等于语义相似度;`1.0` 表示只使用 hotness。有效范围:`0.0` 到 `1.0`。 | `0.0` |-| `score_propagation_alpha` | float | 层级检索中,子节点自身分数与父节点传播分数混合时,子节点自身分数的权重。`0.5` 保持当前 50/50 行为;`1.0` 表示忽略父节点分数;`0.0` 表示只使用父节点分数。有效范围:`0.0` 到 `1.0`。 | `0.5` |+| `score_propagation_alpha` | float | 层级检索中,子节点自身分数与父节点传播分数混合时,子节点自身分数的权重。`1.0` 表示忽略父节点分数(仅使用语义相似度);`0.5` 表示与父节点分数等权混合;`0.0` 表示只使用父节点分数。有效范围:`0.0` 到 `1.0`。 | `1.0` |如果需要分数严格反映向量相似度,保持 `hotness_alpha` 为 `0.0`。只有当希望高频访问或最近更新的上下文获得排序提升时,才将它设置为大于 `0.0`。@@ -1181,7 +1181,7 @@ openviking add-resource ./docs --exclude "*.tmp"},"retrieval": {"hotness_alpha": 0.0,- "score_propagation_alpha": 0.5+ "score_propagation_alpha": 1.0},"encryption": {"enabled": false,diff --git a/examples/ov.conf.example b/examples/ov.conf.exampleindex 80ea7f50a..4860cbb07 100644--- a/examples/ov.conf.example+++ b/examples/ov.conf.example@@ -148,7 +148,7 @@"model": "qwen3-rerank","threshold": 0.1,},- "retrieval": {"hotness_alpha": 0.0, "score_propagation_alpha": 0.5},+ "retrieval": {"hotness_alpha": 0.0, "score_propagation_alpha": 1.0},"auto_generate_l0": true,"auto_generate_l1": true,"default_search_mode": "thinking",