Add files via upload

web/static/i18n/en-US.json

@@ -1299,10 +1299,36 @@
     "similarityThreshold": "Similarity threshold",
     "similarityPlaceholder": "0.7",
     "similarityHint": "Results below this value are filtered (0-1)",
-    "hybridWeight": "Hybrid weight",
-    "hybridPlaceholder": "0.7",
-    "hybridHint": "Vector weight (0-1); 1.0 = vector only, 0.0 = keyword only",
+    "subIndexFilter": "Sub-index filter (optional)",
+    "subIndexFilterPlaceholder": "e.g. prod, must match an indexing sub_indexes tag",
+    "subIndexFilterHint": "Empty = no filter. When set, only rows whose sub_indexes contain this tag (legacy rows with empty sub_indexes still match).",
+    "postRetrieveHeader": "Post-retrieval (dedupe / budget)",
+    "postRetrieveDedupeAuto": "Results are always deduped by normalized text (whitespace-collapsed bodies). No setting required.",
+    "prefetchTopK": "Prefetch candidates (vector stage)",
+    "prefetchTopKPlaceholder": "0",
+    "prefetchTopKHint": "0 = same as Top-K; larger values fetch more vector hits before dedupe/truncate (max 200).",
+    "maxContextChars": "Max returned characters (Unicode)",
+    "maxContextCharsPlaceholder": "0",
+    "maxContextCharsHint": "0 = unlimited; keeps whole chunks in rank order until the budget is exceeded.",
+    "maxContextTokens": "Max returned tokens",
+    "maxContextTokensPlaceholder": "0",
+    "maxContextTokensHint": "0 = unlimited; tiktoken estimate (embedding model name, fallback cl100k_base).",
     "indexConfig": "Index config",
+    "chunkStrategy": "Chunking strategy",
+    "chunkStrategyMarkdownRecursive": "Markdown headers, then recursive (recommended)",
+    "chunkStrategyRecursive": "Recursive only",
+    "chunkStrategyHint": "Matches Eino-style pipelines: Markdown headers + recursive for docs; plain text can use recursive only.",
+    "requestTimeoutSeconds": "Embedding HTTP timeout (seconds)",
+    "requestTimeoutPlaceholder": "120",
+    "requestTimeoutHint": "0 uses the default 120s embedding HTTP client timeout.",
+    "batchSize": "Embedding batch size",
+    "batchSizePlaceholder": "64",
+    "batchSizeHint": "Max texts per embedding request (SQLite indexer batches writes accordingly).",
+    "preferSourceFile": "Prefer on-disk source file when indexing (Eino FileLoader)",
+    "preferSourceFileHint": "When enabled, content comes from file_path; falls back to DB content if load fails.",
+    "subIndexes": "Eino sub-indexes (comma-separated)",
+    "subIndexesPlaceholder": "e.g. prod, knowledge",
+    "subIndexesHint": "Passed to indexer.WithSubIndexes; stored in the sub_indexes column.",
     "chunkSize": "Chunk size",
     "chunkSizePlaceholder": "512",
     "chunkSizeHint": "Max tokens per chunk (default 512)",

web/static/i18n/zh-CN.json

@@ -1299,10 +1299,36 @@
     "similarityThreshold": "相似度阈值",
     "similarityPlaceholder": "0.7",
     "similarityHint": "相似度阈值（0-1），低于此值的结果将被过滤",
-    "hybridWeight": "混合检索权重",
-    "hybridPlaceholder": "0.7",
-    "hybridHint": "向量检索的权重（0-1），1.0表示纯向量检索，0.0表示纯关键词检索",
+    "subIndexFilter": "子索引过滤（可选）",
+    "subIndexFilterPlaceholder": "如 prod，与索引 sub_indexes 一致",
+    "subIndexFilterHint": "留空不过滤；填写后仅检索向量行 sub_indexes 中含该标签的结果（未打标旧行仍保留）。",
+    "postRetrieveHeader": "检索后处理（去重 / 预算）",
+    "postRetrieveDedupeAuto": "检索结果会自动按正文规范化去重（合并仅空白不同的重复片段），无需配置。",
+    "prefetchTopK": "预取候选数（向量阶段）",
+    "prefetchTopKPlaceholder": "0",
+    "prefetchTopKHint": "0 表示与 Top-K 相同；大于 Top-K 时先多取候选再经去重/截断回到 Top-K（上限 200）。",
+    "maxContextChars": "返回内容最大字符数（Unicode）",
+    "maxContextCharsPlaceholder": "0",
+    "maxContextCharsHint": "0 表示不限制；按检索顺序整段保留 chunk，超出则丢弃后续。",
+    "maxContextTokens": "返回内容最大 Token 数",
+    "maxContextTokensPlaceholder": "0",
+    "maxContextTokensHint": "0 表示不限制；tiktoken 估算（与嵌入模型名一致，失败则用 cl100k_base）。",
     "indexConfig": "索引配置",
+    "chunkStrategy": "分块策略",
+    "chunkStrategyMarkdownRecursive": "Markdown 标题切分后递归（推荐）",
+    "chunkStrategyRecursive": "仅递归切分",
+    "chunkStrategyHint": "与 Eino 索引链一致：技术文档建议 Markdown 标题 + 递归；纯文本可仅用递归。",
+    "requestTimeoutSeconds": "嵌入 HTTP 超时（秒）",
+    "requestTimeoutPlaceholder": "120",
+    "requestTimeoutHint": "0 表示使用默认 120 秒，与嵌入 HTTP 客户端一致。",
+    "batchSize": "嵌入批大小",
+    "batchSizePlaceholder": "64",
+    "batchSizeHint": "单次嵌入请求的文本条数上限（SQLite 写入按此分批）。",
+    "preferSourceFile": "索引时优先从磁盘源文件读取（Eino FileLoader）",
+    "preferSourceFileHint": "开启后以 file_path 为准；读取失败时回退数据库中的 content。",
+    "subIndexes": "Eino 子索引（逗号分隔）",
+    "subIndexesPlaceholder": "例如: prod, knowledge",
+    "subIndexesHint": "对应 indexer.WithSubIndexes，持久化到向量表 sub_indexes 字段。",
     "chunkSize": "分块大小（Chunk Size）",
     "chunkSizePlaceholder": "512",
     "chunkSizeHint": "每个块的最大 token 数（默认 512），长文本会被分割成多个块",