raggrep 0.5.2 → 0.6.1

package/README.md

@@ -100,13 +100,13 @@ raggrep query "auth" --filter src/auth        # Filter by path
 raggrep query "api" -f src/api -f src/routes  # Multiple path filters
 ```
 
-| Flag | Short | Description |
-|------|-------|-------------|
-| `--top <n>` | `-k` | Number of results to return (default: 10) |
-| `--min-score <n>` | `-s` | Minimum similarity score 0-1 (default: 0.15) |
-| `--type <ext>` | `-t` | Filter by file extension (e.g., ts, tsx, js) |
-| `--filter <path>` | `-f` | Filter by path prefix (can be used multiple times) |
-| `--help` | `-h` | Show help message |
+| Flag              | Short | Description                                        |
+| ----------------- | ----- | -------------------------------------------------- |
+| `--top <n>`       | `-k`  | Number of results to return (default: 10)          |
+| `--min-score <n>` | `-s`  | Minimum similarity score 0-1 (default: 0.15)       |
+| `--type <ext>`    | `-t`  | Filter by file extension (e.g., ts, tsx, js)       |
+| `--filter <path>` | `-f`  | Filter by path prefix (can be used multiple times) |
+| `--help`          | `-h`  | Show help message                                  |
 
 ### Index Options
 
@@ -118,13 +118,13 @@ raggrep index --concurrency 8        # Set parallel workers (default: auto)
 raggrep index --model bge-small-en-v1.5  # Use specific embedding model
 ```
 
-| Flag | Short | Description |
-|------|-------|-------------|
-| `--watch` | `-w` | Watch for file changes and re-index automatically |
-| `--verbose` | `-v` | Show detailed progress |
-| `--concurrency <n>` | `-c` | Number of parallel workers (default: auto based on CPU) |
-| `--model <name>` | `-m` | Embedding model to use |
-| `--help` | `-h` | Show help message |
+| Flag                | Short | Description                                             |
+| ------------------- | ----- | ------------------------------------------------------- |
+| `--watch`           | `-w`  | Watch for file changes and re-index automatically       |
+| `--verbose`         | `-v`  | Show detailed progress                                  |
+| `--concurrency <n>` | `-c`  | Number of parallel workers (default: auto based on CPU) |
+| `--model <name>`    | `-m`  | Embedding model to use                                  |
+| `--help`            | `-h`  | Show help message                                       |
 
 ### Other Commands
 

package/dist/cli/main.js

@@ -43,7 +43,7 @@ class TransformersEmbeddingProvider {
   initPromise = null;
   constructor(config) {
     this.config = {
-      model: config?.model ?? "all-MiniLM-L6-v2",
+      model: config?.model ?? "bge-small-en-v1.5",
       showProgress: config?.showProgress ?? false,
       logger: config?.logger
     };
@@ -157,7 +157,7 @@ class TransformersEmbeddingProvider {
     return results;
   }
   getDimension() {
-    return EMBEDDING_DIMENSION;
+    return EMBEDDING_DIMENSIONS[this.config.model];
   }
   getModelName() {
     return this.config.model;
@@ -206,7 +206,7 @@ async function getEmbeddings(texts) {
   const provider = await ensureGlobalProvider();
   return provider.getEmbeddings(texts);
 }
-var CACHE_DIR, EMBEDDING_MODELS, EMBEDDING_DIMENSION = 384, BATCH_SIZE = 32, globalProvider = null, globalConfig;
+var CACHE_DIR, EMBEDDING_MODELS, EMBEDDING_DIMENSIONS, BATCH_SIZE = 32, globalProvider = null, globalConfig;
 var init_transformersEmbedding = __esm(() => {
   CACHE_DIR = path.join(os.homedir(), ".cache", "raggrep", "models");
   env.cacheDir = CACHE_DIR;
@@ -215,10 +215,18 @@ var init_transformersEmbedding = __esm(() => {
     "all-MiniLM-L6-v2": "Xenova/all-MiniLM-L6-v2",
     "all-MiniLM-L12-v2": "Xenova/all-MiniLM-L12-v2",
     "bge-small-en-v1.5": "Xenova/bge-small-en-v1.5",
-    "paraphrase-MiniLM-L3-v2": "Xenova/paraphrase-MiniLM-L3-v2"
+    "paraphrase-MiniLM-L3-v2": "Xenova/paraphrase-MiniLM-L3-v2",
+    "nomic-embed-text-v1.5": "nomic-ai/nomic-embed-text-v1.5"
+  };
+  EMBEDDING_DIMENSIONS = {
+    "all-MiniLM-L6-v2": 384,
+    "all-MiniLM-L12-v2": 384,
+    "bge-small-en-v1.5": 384,
+    "paraphrase-MiniLM-L3-v2": 384,
+    "nomic-embed-text-v1.5": 768
   };
   globalConfig = {
-    model: "all-MiniLM-L6-v2",
+    model: "bge-small-en-v1.5",
     showProgress: false,
     logger: undefined
   };
@@ -481,10 +489,10 @@ function getModuleConfig(config, moduleId) {
 }
 function getEmbeddingConfigFromModule(moduleConfig) {
   const options = moduleConfig.options || {};
-  const modelName = options.embeddingModel || "all-MiniLM-L6-v2";
+  const modelName = options.embeddingModel || "bge-small-en-v1.5";
   if (!(modelName in EMBEDDING_MODELS2)) {
-    console.warn(`Unknown embedding model: ${modelName}, falling back to all-MiniLM-L6-v2`);
-    return { model: "all-MiniLM-L6-v2" };
+    console.warn(`Unknown embedding model: ${modelName}, falling back to bge-small-en-v1.5`);
+    return { model: "bge-small-en-v1.5" };
   }
   return {
     model: modelName,
@@ -500,7 +508,8 @@ var init_configLoader = __esm(() => {
     "all-MiniLM-L6-v2": "Xenova/all-MiniLM-L6-v2",
     "all-MiniLM-L12-v2": "Xenova/all-MiniLM-L12-v2",
     "bge-small-en-v1.5": "Xenova/bge-small-en-v1.5",
-    "paraphrase-MiniLM-L3-v2": "Xenova/paraphrase-MiniLM-L3-v2"
+    "paraphrase-MiniLM-L3-v2": "Xenova/paraphrase-MiniLM-L3-v2",
+    "nomic-embed-text-v1.5": "nomic-ai/nomic-embed-text-v1.5"
   };
 });
 
@@ -4855,7 +4864,7 @@ async function getIndexStatus(rootDir) {
   }
   return status;
 }
-var INDEX_SCHEMA_VERSION = "1.0.0", DEFAULT_CONCURRENCY;
+var INDEX_SCHEMA_VERSION = "1.1.0", DEFAULT_CONCURRENCY;
 var init_indexer = __esm(() => {
   init_config2();
   init_registry();
@@ -5032,7 +5041,7 @@ init_logger();
 // package.json
 var package_default = {
   name: "raggrep",
-  version: "0.5.2",
+  version: "0.6.1",
   description: "Local filesystem-based RAG system for codebases - semantic search using local embeddings",
   type: "module",
   main: "./dist/index.js",
@@ -5207,7 +5216,7 @@ Usage:
 
 Options:
   -w, --watch              Watch for file changes and re-index automatically
-  -m, --model <name>       Embedding model to use (default: all-MiniLM-L6-v2)
+  -m, --model <name>       Embedding model to use (default: bge-small-en-v1.5)
   -c, --concurrency <n>    Number of files to process in parallel (default: auto)
   -v, --verbose            Show detailed progress
   -h, --help               Show this help message
@@ -5493,4 +5502,4 @@ Run 'raggrep <command> --help' for more information.
 }
 main();
 
-//# debugId=3B601F4F22C997A464756E2164756E21
+//# debugId=8FCF189E9FBCBFE264756E2164756E21