[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
Python aifaissgpt-osslangchainllama-indexllmlocalstorageoffline-firstollamaprivacypythonragretrieval-augmented-generationvector-databasevector-searchvectors
more support for type of docs in cli
yichuan520030910320c96d653072b2
diff --git a/packages/leann-backend-diskann/third_party/DiskANN b/packages/leann-backend-diskann/third_party/DiskANNindex 67a2611..b2dc4ea 160000--- a/packages/leann-backend-diskann/third_party/DiskANN+++ b/packages/leann-backend-diskann/third_party/DiskANN@@ -1 +1 @@-Subproject commit 67a2611ad14bc11d84dfdb554c5567cfb78a2656+Subproject commit b2dc4ea2c7e52e8a6481d3ba10003e192192a7b7diff --git a/packages/leann-core/src/leann/cli.py b/packages/leann-core/src/leann/cli.pyindex 489c5d1..3563265 100644--- a/packages/leann-core/src/leann/cli.py+++ b/packages/leann-core/src/leann/cli.py@@ -74,10 +74,11 @@ class LeannCLI:formatter_class=argparse.RawDescriptionHelpFormatter,epilog="""Examples:- leann build my-docs --docs ./documents # Build index named my-docs- leann search my-docs "query" # Search in my-docs index- leann ask my-docs "question" # Ask my-docs index- leann list # List all stored indexes+ leann build my-docs --docs ./documents # Build index named my-docs+ leann build my-ppts --docs ./ --file-types .pptx,.pdf # Index only PowerPoint and PDF files+ leann search my-docs "query" # Search in my-docs index+ leann ask my-docs "question" # Ask my-docs index+ leann list # List all stored indexes""",)@@ -99,6 +100,11 @@ Examples:build_parser.add_argument("--num-threads", type=int, default=1)build_parser.add_argument("--compact", action="store_true", default=True)build_parser.add_argument("--recompute", action="store_true", default=True)+ build_parser.add_argument(+ "--file-types",+ type=str,+ help="Comma-separated list of file extensions to include (e.g., '.txt,.pdf,.pptx'). If not specified, uses default supported types.",+ )# Search commandsearch_parser = subparsers.add_parser("search", help="Search documents")@@ -254,8 +260,10 @@ Examples:print(f' leann search {example_name} "your query"')print(f" leann ask {example_name} --interactive")- def load_documents(self, docs_dir: str):+ def load_documents(self, docs_dir: str, custom_file_types: str | None = None):print(f"Loading documents from {docs_dir}...")+ if custom_file_types:+ print(f"Using custom file types: {custom_file_types}")# Try to use better PDF parsers firstdocuments = []@@ -287,59 +295,67 @@ Examples:documents.extend(default_docs)# Load other file types with default reader- code_extensions = [- # Original document types- ".txt",- ".md",- ".docx",- # Code files for Claude Code integration- ".py",- ".js",- ".ts",- ".jsx",- ".tsx",- ".java",- ".cpp",- ".c",- ".h",- ".hpp",- ".cs",- ".go",- ".rs",- ".rb",- ".php",- ".swift",- ".kt",- ".scala",- ".r",- ".sql",- ".sh",- ".bash",- ".zsh",- ".fish",- ".ps1",- ".bat",- # Config and markup files- ".json",- ".yaml",- ".yml",- ".xml",- ".toml",- ".ini",- ".cfg",- ".conf",- ".html",- ".css",- ".scss",- ".less",- ".vue",- ".svelte",- # Data science- ".ipynb",- ".R",- ".py",- ".jl",- ]+ if custom_file_types:+ # Parse custom file types from comma-separated string+ code_extensions = [ext.strip() for ext in custom_file_types.split(",") if ext.strip()]+ # Ensure extensions start with a dot+ code_extensions = [ext if ext.startswith(".") else f".{ext}" for ext in code_extensions]+ else:+ # Use default supported file types+ code_extensions = [+ # Original document types+ ".txt",+ ".md",+ ".docx",+ ".pptx",+ # Code files for Claude Code integration+ ".py",+ ".js",+ ".ts",+ ".jsx",+ ".tsx",+ ".java",+ ".cpp",+ ".c",+ ".h",+ ".hpp",+ ".cs",+ ".go",+ ".rs",+ ".rb",+ ".php",+ ".swift",+ ".kt",+ ".scala",+ ".r",+ ".sql",+ ".sh",+ ".bash",+ ".zsh",+ ".fish",+ ".ps1",+ ".bat",+ # Config and markup files+ ".json",+ ".yaml",+ ".yml",+ ".xml",+ ".toml",+ ".ini",+ ".cfg",+ ".conf",+ ".html",+ ".css",+ ".scss",+ ".less",+ ".vue",+ ".svelte",+ # Data science+ ".ipynb",+ ".R",+ ".py",+ ".jl",+ ]other_docs = SimpleDirectoryReader(docs_dir,recursive=True,@@ -424,7 +440,7 @@ Examples:print(f"Index '{index_name}' already exists. Use --force to rebuild.")return- all_texts = self.load_documents(docs_dir)+ all_texts = self.load_documents(docs_dir, args.file_types)if not all_texts:print("No documents found")return