mcp-local-rag 0.8.2 → 0.10.0

package/README.md

@@ -119,6 +119,25 @@ HTML is automatically cleaned—you get the article content, not the boilerplate
 
 > **Note:** The RAG server itself doesn't fetch web content—your AI assistant retrieves it and passes the HTML to `ingest_data`. This keeps the server fully local while letting you index any content your assistant can access. Please respect website terms of service and copyright when ingesting external content.
 
+### CLI Commands
+
+All MCP tools are also available as CLI commands — no MCP server needed:
+
+```bash
+npx mcp-local-rag ingest ./docs/               # Bulk ingest files
+npx mcp-local-rag query "authentication API"    # Search documents
+npx mcp-local-rag list                          # Show ingestion status
+npx mcp-local-rag status                        # Database stats
+npx mcp-local-rag delete ./docs/old.pdf         # Remove content
+npx mcp-local-rag delete --source "https://..."  # Remove by source URL
+```
+
+Global options (`--db-path`, `--cache-dir`, `--model-name`) go before the subcommand. Run `npx mcp-local-rag --help` for details.
+
+`query`, `list`, `status`, and `delete` output JSON to stdout for piping (e.g., `| jq`). `ingest` outputs progress to stderr.
+
+> ⚠️ **CLI options must match your MCP server config.** Especially `--model-name` — using a different embedding model against an existing database produces incompatible vectors, silently degrading search quality.
+
 ### Searching Documents
 
 ```
@@ -407,6 +426,7 @@ pnpm run check:all     # Full quality check
 src/
   index.ts      # Entry point
   server/       # MCP tool handlers
+  cli/          # CLI subcommands (ingest)
   parser/       # PDF, DOCX, TXT, MD parsing
   chunker/      # Text splitting
   embedder/     # Transformers.js embeddings

package/dist/cli/common.d.ts

@@ -0,0 +1,14 @@
+import { Embedder } from '../embedder/index.js';
+import { VectorStore } from '../vectordb/index.js';
+import type { ResolvedGlobalConfig } from './options.js';
+/**
+ * Create an uninitialized VectorStore from resolved global config.
+ * Callers are responsible for calling initialize() before use.
+ */
+export declare function createVectorStore(config: ResolvedGlobalConfig): VectorStore;
+/**
+ * Create an uninitialized Embedder from resolved global config.
+ * Callers are responsible for managing the Embedder lifecycle.
+ */
+export declare function createEmbedder(config: ResolvedGlobalConfig): Embedder;
+//# sourceMappingURL=common.d.ts.map

package/dist/cli/common.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"common.d.ts","sourceRoot":"","sources":["../../src/cli/common.ts"],"names":[],"mappings":"AAEA,OAAO,EAAE,QAAQ,EAAE,MAAM,sBAAsB,CAAA;AAC/C,OAAO,EAAE,WAAW,EAAE,MAAM,sBAAsB,CAAA;AAClD,OAAO,KAAK,EAAE,oBAAoB,EAAE,MAAM,cAAc,CAAA;AAExD;;;GAGG;AACH,wBAAgB,iBAAiB,CAAC,MAAM,EAAE,oBAAoB,GAAG,WAAW,CAK3E;AAED;;;GAGG;AACH,wBAAgB,cAAc,CAAC,MAAM,EAAE,oBAAoB,GAAG,QAAQ,CAMrE"}

package/dist/cli/common.js

@@ -0,0 +1,25 @@
+// Shared CLI component helpers — factory functions for VectorStore and Embedder
+import { Embedder } from '../embedder/index.js';
+import { VectorStore } from '../vectordb/index.js';
+/**
+ * Create an uninitialized VectorStore from resolved global config.
+ * Callers are responsible for calling initialize() before use.
+ */
+export function createVectorStore(config) {
+    return new VectorStore({
+        dbPath: config.dbPath,
+        tableName: 'chunks',
+    });
+}
+/**
+ * Create an uninitialized Embedder from resolved global config.
+ * Callers are responsible for managing the Embedder lifecycle.
+ */
+export function createEmbedder(config) {
+    return new Embedder({
+        modelPath: config.modelName,
+        batchSize: 16,
+        cacheDir: config.cacheDir,
+    });
+}
+//# sourceMappingURL=common.js.map

package/dist/cli/common.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"common.js","sourceRoot":"","sources":["../../src/cli/common.ts"],"names":[],"mappings":"AAAA,gFAAgF;AAEhF,OAAO,EAAE,QAAQ,EAAE,MAAM,sBAAsB,CAAA;AAC/C,OAAO,EAAE,WAAW,EAAE,MAAM,sBAAsB,CAAA;AAGlD;;;GAGG;AACH,MAAM,UAAU,iBAAiB,CAAC,MAA4B;IAC5D,OAAO,IAAI,WAAW,CAAC;QACrB,MAAM,EAAE,MAAM,CAAC,MAAM;QACrB,SAAS,EAAE,QAAQ;KACpB,CAAC,CAAA;AACJ,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,cAAc,CAAC,MAA4B;IACzD,OAAO,IAAI,QAAQ,CAAC;QAClB,SAAS,EAAE,MAAM,CAAC,SAAS;QAC3B,SAAS,EAAE,EAAE;QACb,QAAQ,EAAE,MAAM,CAAC,QAAQ;KAC1B,CAAC,CAAA;AACJ,CAAC"}

package/dist/cli/delete.d.ts

@@ -0,0 +1,8 @@
+import type { GlobalOptions } from './options.js';
+/**
+ * Run the delete CLI subcommand.
+ * @param args - Arguments after "delete"
+ * @param globalOptions - Global options parsed before the subcommand
+ */
+export declare function runDelete(args: string[], globalOptions?: GlobalOptions): Promise<void>;
+//# sourceMappingURL=delete.d.ts.map

package/dist/cli/delete.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"delete.d.ts","sourceRoot":"","sources":["../../src/cli/delete.ts"],"names":[],"mappings":"AAUA,OAAO,KAAK,EAAE,aAAa,EAAE,MAAM,cAAc,CAAA;AAkFjD;;;;GAIG;AACH,wBAAsB,SAAS,CAAC,IAAI,EAAE,MAAM,EAAE,EAAE,aAAa,GAAE,aAAkB,GAAG,OAAO,CAAC,IAAI,CAAC,CAiGhG"}

package/dist/cli/delete.js

@@ -0,0 +1,164 @@
+// CLI delete subcommand — delete ingested content by file path or source URL
+import { unlink } from 'node:fs/promises';
+import { resolve } from 'node:path';
+import { generateMetaJsonPath, generateRawDataPath, isRawDataPath, } from '../utils/raw-data-utils.js';
+import { createVectorStore } from './common.js';
+import { resolveGlobalConfig, validatePath } from './options.js';
+// ============================================
+// Help
+// ============================================
+const HELP_TEXT = `Usage: mcp-local-rag [global-options] delete [--source <url>] [<file-path>]
+
+Delete ingested content by file path or source URL.
+
+Either <file-path> or --source is required (not both).
+
+Arguments:
+  <file-path>            File path of ingested content to delete
+
+Options:
+  --source <url>         Delete by source URL (for content ingested via ingest_data)
+  -h, --help             Show this help
+
+Global options (must appear before "delete"):
+  --db-path <path>       LanceDB database path
+  --cache-dir <path>     Model cache directory
+  --model-name <name>    Embedding model`;
+/**
+ * Parse delete-specific CLI arguments.
+ * Accepts a positional <file-path>, --source <url>, and -h/--help.
+ * Unknown flags or conflicting args cause exit(1).
+ */
+function parseArgs(args) {
+    let help = false;
+    let source;
+    let filePath;
+    let i = 0;
+    while (i < args.length) {
+        const arg = args[i];
+        if (arg === '-h' || arg === '--help') {
+            help = true;
+            i++;
+        }
+        else if (arg === '--source') {
+            const value = args[++i];
+            if (value === undefined || value.startsWith('-')) {
+                console.error('Missing value for --source');
+                console.error(HELP_TEXT);
+                process.exit(1);
+            }
+            source = value;
+            i++;
+        }
+        else if (arg.startsWith('-')) {
+            console.error(`Unknown option: ${arg}`);
+            console.error(HELP_TEXT);
+            process.exit(1);
+        }
+        else {
+            // Positional argument: file-path
+            filePath = arg;
+            i++;
+        }
+    }
+    const result = { help };
+    if (source !== undefined)
+        result.source = source;
+    if (filePath !== undefined)
+        result.filePath = filePath;
+    return result;
+}
+// ============================================
+// Main Entry Point
+// ============================================
+/**
+ * Run the delete CLI subcommand.
+ * @param args - Arguments after "delete"
+ * @param globalOptions - Global options parsed before the subcommand
+ */
+export async function runDelete(args, globalOptions = {}) {
+    // Parse CLI options
+    const parsed = parseArgs(args);
+    // Handle --help
+    if (parsed.help) {
+        console.error(HELP_TEXT);
+        process.exit(0);
+    }
+    // Validate: either file-path or --source required, not both
+    if (!parsed.filePath && !parsed.source) {
+        console.error('Either <file-path> or --source is required');
+        console.error(HELP_TEXT);
+        process.exit(1);
+    }
+    if (parsed.filePath && parsed.source) {
+        console.error('Cannot specify both <file-path> and --source');
+        console.error(HELP_TEXT);
+        process.exit(1);
+    }
+    // Resolve global config
+    const globalConfig = resolveGlobalConfig(globalOptions);
+    try {
+        // Create and initialize VectorStore (no Embedder needed for delete)
+        const vectorStore = createVectorStore(globalConfig);
+        await vectorStore.initialize();
+        // Determine target file path
+        let targetPath;
+        if (parsed.source) {
+            // Generate raw-data path from source URL
+            targetPath = generateRawDataPath(globalConfig.dbPath, parsed.source, 'markdown');
+        }
+        else {
+            // Use provided file path, resolve to absolute
+            targetPath = resolve(parsed.filePath);
+            // Validate path (reject sensitive system directories)
+            const pathError = validatePath(targetPath, '<file-path>');
+            if (pathError) {
+                console.error(pathError);
+                process.exitCode = 1;
+                return;
+            }
+        }
+        // Delete chunks from VectorStore
+        await vectorStore.deleteChunks(targetPath);
+        // Clean up physical raw-data files if applicable
+        if (isRawDataPath(targetPath)) {
+            try {
+                await unlink(targetPath);
+            }
+            catch (error) {
+                // Ignore ENOENT (file already deleted / never existed)
+                if (!(error instanceof Error) ||
+                    !('code' in error) ||
+                    error.code !== 'ENOENT') {
+                    throw error;
+                }
+            }
+            try {
+                await unlink(generateMetaJsonPath(targetPath));
+            }
+            catch (error) {
+                // Ignore ENOENT
+                if (!(error instanceof Error) ||
+                    !('code' in error) ||
+                    error.code !== 'ENOENT') {
+                    throw error;
+                }
+            }
+        }
+        // Optimize VectorStore after deletion
+        await vectorStore.optimize();
+        // Output result JSON to stdout
+        const result = {
+            filePath: targetPath,
+            deleted: true,
+            timestamp: new Date().toISOString(),
+        };
+        process.stdout.write(JSON.stringify(result));
+    }
+    catch (error) {
+        const reason = error instanceof Error ? error.message : String(error);
+        console.error(`Error: ${reason}`);
+        process.exit(1);
+    }
+}
+//# sourceMappingURL=delete.js.map

package/dist/cli/delete.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"delete.js","sourceRoot":"","sources":["../../src/cli/delete.ts"],"names":[],"mappings":"AAAA,6EAA6E;AAE7E,OAAO,EAAE,MAAM,EAAE,MAAM,kBAAkB,CAAA;AACzC,OAAO,EAAE,OAAO,EAAE,MAAM,WAAW,CAAA;AACnC,OAAO,EACL,oBAAoB,EACpB,mBAAmB,EACnB,aAAa,GACd,MAAM,4BAA4B,CAAA;AACnC,OAAO,EAAE,iBAAiB,EAAE,MAAM,aAAa,CAAA;AAE/C,OAAO,EAAE,mBAAmB,EAAE,YAAY,EAAE,MAAM,cAAc,CAAA;AAEhE,+CAA+C;AAC/C,OAAO;AACP,+CAA+C;AAE/C,MAAM,SAAS,GAAG;;;;;;;;;;;;;;;;yCAgBuB,CAAA;AAYzC;;;;GAIG;AACH,SAAS,SAAS,CAAC,IAAc;IAC/B,IAAI,IAAI,GAAG,KAAK,CAAA;IAChB,IAAI,MAA0B,CAAA;IAC9B,IAAI,QAA4B,CAAA;IAEhC,IAAI,CAAC,GAAG,CAAC,CAAA;IACT,OAAO,CAAC,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC;QACvB,MAAM,GAAG,GAAG,IAAI,CAAC,CAAC,CAAE,CAAA;QAEpB,IAAI,GAAG,KAAK,IAAI,IAAI,GAAG,KAAK,QAAQ,EAAE,CAAC;YACrC,IAAI,GAAG,IAAI,CAAA;YACX,CAAC,EAAE,CAAA;QACL,CAAC;aAAM,IAAI,GAAG,KAAK,UAAU,EAAE,CAAC;YAC9B,MAAM,KAAK,GAAG,IAAI,CAAC,EAAE,CAAC,CAAC,CAAA;YACvB,IAAI,KAAK,KAAK,SAAS,IAAI,KAAK,CAAC,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC;gBACjD,OAAO,CAAC,KAAK,CAAC,4BAA4B,CAAC,CAAA;gBAC3C,OAAO,CAAC,KAAK,CAAC,SAAS,CAAC,CAAA;gBACxB,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;YACjB,CAAC;YACD,MAAM,GAAG,KAAK,CAAA;YACd,CAAC,EAAE,CAAA;QACL,CAAC;aAAM,IAAI,GAAG,CAAC,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC;YAC/B,OAAO,CAAC,KAAK,CAAC,mBAAmB,GAAG,EAAE,CAAC,CAAA;YACvC,OAAO,CAAC,KAAK,CAAC,SAAS,CAAC,CAAA;YACxB,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QACjB,CAAC;aAAM,CAAC;YACN,iCAAiC;YACjC,QAAQ,GAAG,GAAG,CAAA;YACd,CAAC,EAAE,CAAA;QACL,CAAC;IACH,CAAC;IAED,MAAM,MAAM,GAAe,EAAE,IAAI,EAAE,CAAA;IACnC,IAAI,MAAM,KAAK,SAAS;QAAE,MAAM,CAAC,MAAM,GAAG,MAAM,CAAA;IAChD,IAAI,QAAQ,KAAK,SAAS;QAAE,MAAM,CAAC,QAAQ,GAAG,QAAQ,CAAA;IACtD,OAAO,MAAM,CAAA;AACf,CAAC;AAED,+CAA+C;AAC/C,mBAAmB;AACnB,+CAA+C;AAE/C;;;;GAIG;AACH,MAAM,CAAC,KAAK,UAAU,SAAS,CAAC,IAAc,EAAE,gBAA+B,EAAE;IAC/E,oBAAoB;IACpB,MAAM,MAAM,GAAG,SAAS,CAAC,IAAI,CAAC,CAAA;IAE9B,gBAAgB;IAChB,IAAI,MAAM,CAAC,IAAI,EAAE,CAAC;QAChB,OAAO,CAAC,KAAK,CAAC,SAAS,CAAC,CAAA;QACxB,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;IACjB,CAAC;IAED,4DAA4D;IAC5D,IAAI,CAAC,MAAM,CAAC,QAAQ,IAAI,CAAC,MAAM,CAAC,MAAM,EAAE,CAAC;QACvC,OAAO,CAAC,KAAK,CAAC,4CAA4C,CAAC,CAAA;QAC3D,OAAO,CAAC,KAAK,CAAC,SAAS,CAAC,CAAA;QACxB,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;IACjB,CAAC;IAED,IAAI,MAAM,CAAC,QAAQ,IAAI,MAAM,CAAC,MAAM,EAAE,CAAC;QACrC,OAAO,CAAC,KAAK,CAAC,8CAA8C,CAAC,CAAA;QAC7D,OAAO,CAAC,KAAK,CAAC,SAAS,CAAC,CAAA;QACxB,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;IACjB,CAAC;IAED,wBAAwB;IACxB,MAAM,YAAY,GAAG,mBAAmB,CAAC,aAAa,CAAC,CAAA;IAEvD,IAAI,CAAC;QACH,oEAAoE;QACpE,MAAM,WAAW,GAAG,iBAAiB,CAAC,YAAY,CAAC,CAAA;QACnD,MAAM,WAAW,CAAC,UAAU,EAAE,CAAA;QAE9B,6BAA6B;QAC7B,IAAI,UAAkB,CAAA;QAEtB,IAAI,MAAM,CAAC,MAAM,EAAE,CAAC;YAClB,yCAAyC;YACzC,UAAU,GAAG,mBAAmB,CAAC,YAAY,CAAC,MAAM,EAAE,MAAM,CAAC,MAAM,EAAE,UAAU,CAAC,CAAA;QAClF,CAAC;aAAM,CAAC;YACN,8CAA8C;YAC9C,UAAU,GAAG,OAAO,CAAC,MAAM,CAAC,QAAS,CAAC,CAAA;YAEtC,sDAAsD;YACtD,MAAM,SAAS,GAAG,YAAY,CAAC,UAAU,EAAE,aAAa,CAAC,CAAA;YACzD,IAAI,SAAS,EAAE,CAAC;gBACd,OAAO,CAAC,KAAK,CAAC,SAAS,CAAC,CAAA;gBACxB,OAAO,CAAC,QAAQ,GAAG,CAAC,CAAA;gBACpB,OAAM;YACR,CAAC;QACH,CAAC;QAED,iCAAiC;QACjC,MAAM,WAAW,CAAC,YAAY,CAAC,UAAU,CAAC,CAAA;QAE1C,iDAAiD;QACjD,IAAI,aAAa,CAAC,UAAU,CAAC,EAAE,CAAC;YAC9B,IAAI,CAAC;gBACH,MAAM,MAAM,CAAC,UAAU,CAAC,CAAA;YAC1B,CAAC;YAAC,OAAO,KAAc,EAAE,CAAC;gBACxB,uDAAuD;gBACvD,IACE,CAAC,CAAC,KAAK,YAAY,KAAK,CAAC;oBACzB,CAAC,CAAC,MAAM,IAAI,KAAK,CAAC;oBACjB,KAA+B,CAAC,IAAI,KAAK,QAAQ,EAClD,CAAC;oBACD,MAAM,KAAK,CAAA;gBACb,CAAC;YACH,CAAC;YAED,IAAI,CAAC;gBACH,MAAM,MAAM,CAAC,oBAAoB,CAAC,UAAU,CAAC,CAAC,CAAA;YAChD,CAAC;YAAC,OAAO,KAAc,EAAE,CAAC;gBACxB,gBAAgB;gBAChB,IACE,CAAC,CAAC,KAAK,YAAY,KAAK,CAAC;oBACzB,CAAC,CAAC,MAAM,IAAI,KAAK,CAAC;oBACjB,KAA+B,CAAC,IAAI,KAAK,QAAQ,EAClD,CAAC;oBACD,MAAM,KAAK,CAAA;gBACb,CAAC;YACH,CAAC;QACH,CAAC;QAED,sCAAsC;QACtC,MAAM,WAAW,CAAC,QAAQ,EAAE,CAAA;QAE5B,+BAA+B;QAC/B,MAAM,MAAM,GAAG;YACb,QAAQ,EAAE,UAAU;YACpB,OAAO,EAAE,IAAI;YACb,SAAS,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;SACpC,CAAA;QACD,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,CAAC,CAAA;IAC9C,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACf,MAAM,MAAM,GAAG,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAA;QACrE,OAAO,CAAC,KAAK,CAAC,UAAU,MAAM,EAAE,CAAC,CAAA;QACjC,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;IACjB,CAAC;AACH,CAAC"}

package/dist/cli/ingest.d.ts

@@ -0,0 +1,37 @@
+import type { GlobalOptions, ResolvedGlobalConfig } from './options.js';
+interface IngestConfig {
+    baseDir: string;
+    dbPath: string;
+    cacheDir: string;
+    modelName: string;
+    maxFileSize: number;
+}
+interface IngestCliOptions {
+    baseDir?: string | undefined;
+    maxFileSize?: number | undefined;
+}
+interface ParsedArgs {
+    positional: string | undefined;
+    options: IngestCliOptions;
+    help: boolean;
+}
+/**
+ * Parse ingest-specific CLI arguments into options and a positional path.
+ * Flags: --base-dir, --max-file-size, -h/--help
+ * Unknown flags (including global flags passed after subcommand) cause an error.
+ */
+export declare function parseArgs(args: string[]): ParsedArgs;
+/**
+ * Resolve ingest config by merging global config with ingest-specific options.
+ * Ingest-specific: baseDir, maxFileSize (CLI flags > env vars > defaults).
+ * Validates all resolved values before returning.
+ */
+export declare function resolveConfig(globalConfig: ResolvedGlobalConfig, ingestOptions?: IngestCliOptions): IngestConfig;
+/**
+ * Run the ingest CLI subcommand.
+ * @param args - Arguments after "ingest" (e.g., option flags and file/directory path)
+ * @param globalOptions - Global options parsed before the subcommand
+ */
+export declare function runIngest(args: string[], globalOptions?: GlobalOptions): Promise<void>;
+export {};
+//# sourceMappingURL=ingest.d.ts.map

package/dist/cli/ingest.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"ingest.d.ts","sourceRoot":"","sources":["../../src/cli/ingest.ts"],"names":[],"mappings":"AAWA,OAAO,KAAK,EAAE,aAAa,EAAE,oBAAoB,EAAE,MAAM,cAAc,CAAA;AAavE,UAAU,YAAY;IACpB,OAAO,EAAE,MAAM,CAAA;IACf,MAAM,EAAE,MAAM,CAAA;IACd,QAAQ,EAAE,MAAM,CAAA;IAChB,SAAS,EAAE,MAAM,CAAA;IACjB,WAAW,EAAE,MAAM,CAAA;CACpB;AAQD,UAAU,gBAAgB;IACxB,OAAO,CAAC,EAAE,MAAM,GAAG,SAAS,CAAA;IAC5B,WAAW,CAAC,EAAE,MAAM,GAAG,SAAS,CAAA;CACjC;AAED,UAAU,UAAU;IAClB,UAAU,EAAE,MAAM,GAAG,SAAS,CAAA;IAC9B,OAAO,EAAE,gBAAgB,CAAA;IACzB,IAAI,EAAE,OAAO,CAAA;CACd;AAgCD;;;;GAIG;AACH,wBAAgB,SAAS,CAAC,IAAI,EAAE,MAAM,EAAE,GAAG,UAAU,CAqDpD;AAiBD;;;;GAIG;AACH,wBAAgB,aAAa,CAC3B,YAAY,EAAE,oBAAoB,EAClC,aAAa,GAAE,gBAAqB,GACnC,YAAY,CA8Bd;AAuJD;;;;GAIG;AACH,wBAAsB,SAAS,CAAC,IAAI,EAAE,MAAM,EAAE,EAAE,aAAa,GAAE,aAAkB,GAAG,OAAO,CAAC,IAAI,CAAC,CA0FhG"}

package/dist/cli/ingest.js

@@ -0,0 +1,345 @@
+// CLI ingest subcommand — bulk file ingestion with single optimize() at end
+import { randomUUID } from 'node:crypto';
+import { opendir, stat } from 'node:fs/promises';
+import { extname, join, resolve } from 'node:path';
+import { SemanticChunker } from '../chunker/index.js';
+import { DocumentParser, SUPPORTED_EXTENSIONS } from '../parser/index.js';
+import { createEmbedder, createVectorStore } from './common.js';
+import { resolveGlobalConfig, validateMaxFileSize, validatePath } from './options.js';
+// ============================================
+// Constants
+// ============================================
+const MAX_DEPTH = 10;
+// ============================================
+// Defaults
+// ============================================
+const INGEST_DEFAULTS = {
+    maxFileSize: 104857600,
+};
+// ============================================
+// Help
+// ============================================
+const HELP_TEXT = `Usage: mcp-local-rag [global-options] ingest [options] <path>
+
+Ingest a single file or all supported files under a directory.
+
+Options:
+  --base-dir <path>      Base directory for documents (default: cwd)
+  --max-file-size <n>    Max file size in bytes (default: ${INGEST_DEFAULTS.maxFileSize})
+  -h, --help             Show this help
+
+Global options (must appear before "ingest"):
+  --db-path <path>       LanceDB database path
+  --cache-dir <path>     Model cache directory
+  --model-name <name>    Embedding model`;
+// ============================================
+// Arg Parsing
+// ============================================
+/**
+ * Parse ingest-specific CLI arguments into options and a positional path.
+ * Flags: --base-dir, --max-file-size, -h/--help
+ * Unknown flags (including global flags passed after subcommand) cause an error.
+ */
+export function parseArgs(args) {
+    const options = {};
+    let positional;
+    let help = false;
+    let i = 0;
+    while (i < args.length) {
+        const arg = args[i];
+        switch (arg) {
+            case '-h':
+            case '--help':
+                help = true;
+                i++;
+                break;
+            case '--base-dir': {
+                const value = args[++i];
+                if (value === undefined || value.startsWith('-')) {
+                    console.error('Missing value for --base-dir');
+                    process.exit(1);
+                }
+                options.baseDir = value;
+                i++;
+                break;
+            }
+            case '--max-file-size': {
+                const raw = args[++i];
+                if (raw === undefined || raw.startsWith('-')) {
+                    console.error('Missing value for --max-file-size');
+                    process.exit(1);
+                }
+                const parsed = Number.parseInt(raw, 10);
+                options.maxFileSize = Number.isNaN(parsed) ? undefined : parsed;
+                i++;
+                break;
+            }
+            default:
+                if (arg.startsWith('-')) {
+                    console.error(`Unknown option: ${arg}`);
+                    console.error(HELP_TEXT);
+                    process.exit(1);
+                }
+                if (positional !== undefined) {
+                    console.error(`Unexpected argument: ${arg}`);
+                    console.error('Only one path is accepted. Use a directory to ingest multiple files.');
+                    process.exit(1);
+                }
+                positional = arg;
+                i++;
+                break;
+        }
+    }
+    return { positional, options, help };
+}
+// ============================================
+// NaN Defense
+// ============================================
+/**
+ * Ensure maxFileSize is a valid number, falling back to default if NaN.
+ */
+function sanitizeMaxFileSize(value) {
+    return Number.isNaN(value) ? INGEST_DEFAULTS.maxFileSize : value;
+}
+// ============================================
+// Config Resolution
+// ============================================
+/**
+ * Resolve ingest config by merging global config with ingest-specific options.
+ * Ingest-specific: baseDir, maxFileSize (CLI flags > env vars > defaults).
+ * Validates all resolved values before returning.
+ */
+export function resolveConfig(globalConfig, ingestOptions = {}) {
+    const baseDir = ingestOptions.baseDir ?? process.env['BASE_DIR'] ?? process.cwd();
+    const maxFileSize = sanitizeMaxFileSize(ingestOptions.maxFileSize ??
+        (process.env['MAX_FILE_SIZE']
+            ? Number.parseInt(process.env['MAX_FILE_SIZE'], 10)
+            : INGEST_DEFAULTS.maxFileSize));
+    // Validate baseDir path
+    const baseDirError = validatePath(baseDir, '--base-dir');
+    if (baseDirError) {
+        console.error(baseDirError);
+        process.exit(1);
+    }
+    // Validate maxFileSize range
+    const maxFileSizeError = validateMaxFileSize(maxFileSize);
+    if (maxFileSizeError) {
+        console.error(maxFileSizeError);
+        process.exit(1);
+    }
+    return {
+        dbPath: globalConfig.dbPath,
+        cacheDir: globalConfig.cacheDir,
+        modelName: globalConfig.modelName,
+        baseDir,
+        maxFileSize,
+    };
+}
+// ============================================
+// File Collection
+// ============================================
+/**
+ * Collect files to ingest from a path.
+ * - If path is a file with supported extension, return [path].
+ * - If path is a directory, walk with BFS up to MAX_DEPTH levels.
+ * - Skip symlinks, permission errors, and excluded directories.
+ */
+async function collectFiles(targetPath, excludePaths) {
+    const resolved = resolve(targetPath);
+    const info = await stat(resolved);
+    if (info.isFile()) {
+        const ext = extname(resolved).toLowerCase();
+        if (!SUPPORTED_EXTENSIONS.has(ext)) {
+            console.error(`Unsupported file extension: ${ext} (supported: ${[...SUPPORTED_EXTENSIONS].join(', ')})`);
+            return [];
+        }
+        return [resolved];
+    }
+    if (info.isDirectory()) {
+        const files = [];
+        let depthLimited = false;
+        const queue = [{ dirPath: resolved, depth: 0 }];
+        while (queue.length > 0) {
+            const { dirPath, depth } = queue.shift();
+            if (depth >= MAX_DEPTH) {
+                depthLimited = true;
+                continue;
+            }
+            let dir;
+            try {
+                dir = await opendir(dirPath);
+            }
+            catch {
+                console.error(`Warning: cannot read directory: ${dirPath}`);
+                continue;
+            }
+            for await (const entry of dir) {
+                const fullPath = join(dirPath, entry.name);
+                if (!fullPath.startsWith(resolved))
+                    continue;
+                if (entry.isSymbolicLink())
+                    continue;
+                if (excludePaths.some((ep) => fullPath.startsWith(ep)))
+                    continue;
+                if (entry.isDirectory()) {
+                    queue.push({ dirPath: fullPath, depth: depth + 1 });
+                }
+                else if (entry.isFile() && SUPPORTED_EXTENSIONS.has(extname(entry.name).toLowerCase())) {
+                    files.push(fullPath);
+                }
+            }
+        }
+        if (depthLimited) {
+            console.error(`Warning: some directories were skipped because they exceed the maximum depth (${MAX_DEPTH})`);
+        }
+        return files.sort();
+    }
+    return [];
+}
+// ============================================
+// Per-file Ingestion
+// ============================================
+/**
+ * Ingest a single file: parse, chunk, embed, delete old chunks, insert new chunks.
+ * Returns the number of chunks inserted.
+ */
+async function ingestSingleFile(filePath, parser, chunker, embedder, vectorStore) {
+    // Parse file
+    const isPdf = filePath.toLowerCase().endsWith('.pdf');
+    let text;
+    let title = null;
+    if (isPdf) {
+        const result = await parser.parsePdf(filePath, embedder);
+        text = result.content;
+        title = result.title || null;
+    }
+    else {
+        const result = await parser.parseFile(filePath);
+        text = result.content;
+        title = result.title || null;
+    }
+    // Chunk text
+    const chunks = await chunker.chunkText(text, embedder);
+    if (chunks.length === 0) {
+        console.error(`  Warning: 0 chunks generated (file may be empty or too short)`);
+        return 0;
+    }
+    // Generate embeddings
+    const embeddings = await embedder.embedBatch(chunks.map((c) => c.text));
+    // Delete existing chunks for this file
+    await vectorStore.deleteChunks(filePath);
+    // Build vector chunks
+    const timestamp = new Date().toISOString();
+    const vectorChunks = chunks.map((chunk, index) => {
+        const embedding = embeddings[index];
+        if (!embedding) {
+            throw new Error(`Missing embedding for chunk ${index}`);
+        }
+        return {
+            id: randomUUID(),
+            filePath,
+            chunkIndex: chunk.index,
+            text: chunk.text,
+            vector: embedding,
+            metadata: {
+                fileName: filePath.split('/').pop() || filePath,
+                fileSize: text.length,
+                fileType: filePath.split('.').pop() || '',
+            },
+            fileTitle: title,
+            timestamp,
+        };
+    });
+    // Insert chunks
+    await vectorStore.insertChunks(vectorChunks);
+    return vectorChunks.length;
+}
+// ============================================
+// Main Entry Point
+// ============================================
+/**
+ * Run the ingest CLI subcommand.
+ * @param args - Arguments after "ingest" (e.g., option flags and file/directory path)
+ * @param globalOptions - Global options parsed before the subcommand
+ */
+export async function runIngest(args, globalOptions = {}) {
+    // Parse CLI options
+    const { positional, options, help } = parseArgs(args);
+    // Handle --help
+    if (help) {
+        console.error(HELP_TEXT);
+        process.exit(0);
+    }
+    // Validate positional argument
+    if (!positional) {
+        console.error('Usage: mcp-local-rag ingest [options] <path>');
+        console.error('  Ingest a single file or all supported files under a directory.');
+        console.error('  Run with --help for all options.');
+        process.exit(1);
+    }
+    const targetPath = positional;
+    // Validate path exists
+    try {
+        await stat(targetPath);
+    }
+    catch {
+        console.error(`Error: path does not exist: ${targetPath}`);
+        process.exit(1);
+    }
+    // Resolve config: CLI flags > env vars > defaults
+    const globalConfig = resolveGlobalConfig(globalOptions);
+    const config = resolveConfig(globalConfig, options);
+    const excludePaths = [`${resolve(config.dbPath)}/`, `${resolve(config.cacheDir)}/`];
+    // Collect files
+    const files = await collectFiles(targetPath, excludePaths);
+    if (files.length === 0) {
+        console.error('No supported files found.');
+        process.exit(1);
+    }
+    console.error(`Found ${files.length} file(s) to ingest.`);
+    // Initialize components (single instances reused across all files)
+    const parser = new DocumentParser({
+        baseDir: config.baseDir,
+        maxFileSize: config.maxFileSize,
+    });
+    const chunker = new SemanticChunker();
+    const embedder = createEmbedder(globalConfig);
+    const vectorStore = createVectorStore(globalConfig);
+    await vectorStore.initialize();
+    // Process each file
+    const summary = { succeeded: 0, failed: 0, totalChunks: 0 };
+    for (let i = 0; i < files.length; i++) {
+        const filePath = files[i];
+        const label = `[${i + 1}/${files.length}]`;
+        try {
+            const chunkCount = await ingestSingleFile(filePath, parser, chunker, embedder, vectorStore);
+            if (chunkCount === 0) {
+                // 0 chunks is a skip/warning, not a failure
+                console.error(`${label} ${filePath} ... SKIPPED (0 chunks)`);
+                summary.succeeded++;
+            }
+            else {
+                console.error(`${label} ${filePath} ... OK (${chunkCount} chunks)`);
+                summary.succeeded++;
+                summary.totalChunks += chunkCount;
+            }
+        }
+        catch (error) {
+            const reason = error instanceof Error ? error.message : String(error);
+            console.error(`${label} ${filePath} ... FAILED: ${reason}`);
+            summary.failed++;
+        }
+    }
+    // Optimize once at end (not per-file)
+    await vectorStore.optimize();
+    // Print summary
+    console.error('');
+    console.error('--- Ingest Summary ---');
+    console.error(`Succeeded: ${summary.succeeded}`);
+    console.error(`Failed:    ${summary.failed}`);
+    console.error(`Total chunks: ${summary.totalChunks}`);
+    if (summary.failed > 0) {
+        process.exitCode = 1;
+    }
+}
+//# sourceMappingURL=ingest.js.map