raggrep 0.5.1 → 0.6.0

package/README.md

@@ -78,19 +78,60 @@ This monitors file changes and re-indexes automatically. Useful during active de
 [Watch] language/typescript: 2 indexed, 0 errors
 ```
 
-## CLI Quick Reference
+## CLI Reference
+
+### Commands
 
 ```bash
-# Search (auto-indexes if needed)
-raggrep query "user login"
-raggrep query "error handling" --top 5
-raggrep query "database" --type ts
+raggrep query <query>    # Search the codebase
+raggrep index            # Build/update the index
+raggrep status           # Show index status
+raggrep reset            # Clear the index
+```
 
-# Watch mode
-raggrep index --watch
+### Query Options
+
+```bash
+raggrep query "user login"                    # Basic search
+raggrep query "error handling" --top 5        # Limit results
+raggrep query "database" --min-score 0.2      # Set minimum score threshold
+raggrep query "interface" --type ts           # Filter by file extension
+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                                  |
+
+### Index Options
 
-# Check index status
-raggrep status
+```bash
+raggrep index                        # Index current directory
+raggrep index --watch                # Watch mode - re-index on file changes
+raggrep index --verbose              # Show detailed progress
+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                                       |
+
+### Other Commands
+
+```bash
+raggrep status           # Show index status and statistics
+raggrep reset            # Clear the index completely
+raggrep --version        # Show version
 ```
 
 ## How It Works
@@ -104,9 +145,13 @@ The index is stored in a system temp directory, keeping your project clean.
 
 ## What Gets Indexed
 
-**File types:** `.ts`, `.tsx`, `.js`, `.jsx`, `.py`, `.go`, `.rs`, `.java`, `.md`, `.txt`
+**TypeScript/JavaScript:** `.ts`, `.tsx`, `.js`, `.jsx`, `.mjs`, `.cjs` — AST-parsed for functions, classes, interfaces, types, enums
+
+**Documentation:** `.md`, `.txt` — Section-aware parsing with heading extraction
+
+**Data:** `.json` — Structure-aware with key/value extraction
 
-**Code structures:** Functions, classes, interfaces, types, enums, exports
+**Other languages:** `.py`, `.go`, `.rs`, `.java`, `.yaml`, `.yml`, `.toml`, `.sql` — Symbol extraction and keyword search
 
 **Automatically ignored:** `node_modules`, `dist`, `build`, `.git`, and other common directories
 

package/dist/app/indexer/index.d.ts

@@ -16,7 +16,7 @@ export interface IndexOptions {
     quiet?: boolean;
     /** Logger for progress reporting. If not provided, uses console by default (quiet mode uses silent logger) */
     logger?: Logger;
-    /** Number of files to process in parallel (default: 4) */
+    /** Number of files to process in parallel (default: auto based on CPU cores) */
     concurrency?: number;
 }
 export interface EnsureFreshResult {

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"
   };
 });
 
@@ -4275,6 +4284,7 @@ __export(exports_indexer, {
 import { glob } from "glob";
 import * as fs6 from "fs/promises";
 import * as path15 from "path";
+import * as os3 from "os";
 async function parallelMap(items, processor, concurrency) {
   const results = new Array(items.length);
   let nextIndex = 0;
@@ -4306,6 +4316,11 @@ function formatDuration(ms) {
   const remainingSeconds = seconds % 60;
   return `${minutes}m ${remainingSeconds.toFixed(1)}s`;
 }
+function getOptimalConcurrency() {
+  const cpuCount = os3.cpus().length;
+  const optimal = Math.max(2, Math.min(16, Math.floor(cpuCount * 0.75)));
+  return optimal;
+}
 async function indexDirectory(rootDir, options = {}) {
   const verbose = options.verbose ?? false;
   const quiet = options.quiet ?? false;
@@ -4849,13 +4864,14 @@ async function getIndexStatus(rootDir) {
   }
   return status;
 }
-var INDEX_SCHEMA_VERSION = "1.0.0", DEFAULT_CONCURRENCY = 4;
+var INDEX_SCHEMA_VERSION = "1.1.0", DEFAULT_CONCURRENCY;
 var init_indexer = __esm(() => {
   init_config2();
   init_registry();
   init_introspection2();
   init_logger();
   init_watcher();
+  DEFAULT_CONCURRENCY = getOptimalConcurrency();
 });
 
 // src/types.ts
@@ -5025,7 +5041,7 @@ init_logger();
 // package.json
 var package_default = {
   name: "raggrep",
-  version: "0.5.1",
+  version: "0.6.0",
   description: "Local filesystem-based RAG system for codebases - semantic search using local embeddings",
   type: "module",
   main: "./dist/index.js",
@@ -5201,7 +5217,7 @@ Usage:
 Options:
   -w, --watch              Watch for file changes and re-index automatically
   -m, --model <name>       Embedding model to use (default: all-MiniLM-L6-v2)
-  -c, --concurrency <n>    Number of files to process in parallel (default: 4)
+  -c, --concurrency <n>    Number of files to process in parallel (default: auto)
   -v, --verbose            Show detailed progress
   -h, --help               Show this help message
 
@@ -5486,4 +5502,4 @@ Run 'raggrep <command> --help' for more information.
 }
 main();
 
-//# debugId=E73618F0DDE8326264756E2164756E21
+//# debugId=5883D798B8D780D764756E2164756E21