docs: cli

README.md

@@ -294,6 +294,71 @@ Once the index is built, you can ask questions like:
 
 </details>
 
+## 🖥️ Command Line Interface
+
+LEANN includes a powerful CLI for document processing and search. Perfect for quick document indexing and interactive chat.
+
+```bash
+# Build an index from documents
+leann build my-docs --docs ./documents
+
+# Search your documents  
+leann search my-docs "machine learning concepts"
+
+# Interactive chat with your documents
+leann ask my-docs --interactive
+
+# List all your indexes
+leann list
+```
+
+**Key CLI features:**
+- Auto-detects document formats (PDF, TXT, MD, DOCX)
+- Smart text chunking with overlap
+- Multiple LLM providers (Ollama, OpenAI, HuggingFace)
+- Organized index storage in `~/.leann/indexes/`
+- Support for advanced search parameters
+
+<details>
+<summary><strong>📋 Click to expand: Complete CLI Reference</strong></summary>
+
+**Build Command:**
+```bash
+leann build INDEX_NAME --docs DIRECTORY [OPTIONS]
+
+Options:
+  --backend {hnsw,diskann}     Backend to use (default: hnsw)
+  --embedding-model MODEL      Embedding model (default: facebook/contriever)
+  --graph-degree N            Graph degree (default: 32)
+  --complexity N              Build complexity (default: 64)
+  --force                     Force rebuild existing index
+  --compact                   Use compact storage (default: true)
+  --recompute                 Enable recomputation (default: true)
+```
+
+**Search Command:**
+```bash
+leann search INDEX_NAME QUERY [OPTIONS]
+
+Options:
+  --top-k N                   Number of results (default: 5)
+  --complexity N              Search complexity (default: 64)
+  --recompute-embeddings      Use recomputation for highest accuracy
+  --pruning-strategy {global,local,proportional}
+```
+
+**Ask Command:**
+```bash
+leann ask INDEX_NAME [OPTIONS]
+
+Options:
+  --llm {ollama,openai,hf}    LLM provider (default: ollama)
+  --model MODEL               Model name (default: qwen3:8b)
+  --interactive              Interactive chat mode
+  --top-k N                  Retrieval count (default: 20)
+```
+
+</details>
 
 ## 🏗️ Architecture & How It Works
 

packages/leann-core/src/leann/cli.py

@@ -1,10 +1,6 @@
-#!/usr/bin/env python3
 import argparse
 import asyncio
-import sys
 from pathlib import Path
-from typing import Optional
-import os
 
 from llama_index.core import SimpleDirectoryReader
 from llama_index.core.node_parser import SentenceSplitter
@@ -41,7 +37,7 @@ Examples:
   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
-            """
+            """,
         )
 
         subparsers = parser.add_subparsers(dest="command", help="Available commands")
@@ -49,10 +45,18 @@ Examples:
         # Build command
         build_parser = subparsers.add_parser("build", help="Build document index")
         build_parser.add_argument("index_name", help="Index name")
-        build_parser.add_argument("--docs", type=str, required=True, help="Documents directory")
+        build_parser.add_argument(
-        build_parser.add_argument("--backend", type=str, default="hnsw", choices=["hnsw", "diskann"])
+            "--docs", type=str, required=True, help="Documents directory"
-        build_parser.add_argument("--embedding-model", type=str, default="facebook/contriever")
+        )
-        build_parser.add_argument("--force", "-f", action="store_true", help="Force rebuild")
+        build_parser.add_argument(
+            "--backend", type=str, default="hnsw", choices=["hnsw", "diskann"]
+        )
+        build_parser.add_argument(
+            "--embedding-model", type=str, default="facebook/contriever"
+        )
+        build_parser.add_argument(
+            "--force", "-f", action="store_true", help="Force rebuild"
+        )
         build_parser.add_argument("--graph-degree", type=int, default=32)
         build_parser.add_argument("--complexity", type=int, default=64)
         build_parser.add_argument("--num-threads", type=int, default=1)
@@ -68,12 +72,21 @@ Examples:
         search_parser.add_argument("--beam-width", type=int, default=1)
         search_parser.add_argument("--prune-ratio", type=float, default=0.0)
         search_parser.add_argument("--recompute-embeddings", action="store_true")
-        search_parser.add_argument("--pruning-strategy", choices=["global", "local", "proportional"], default="global")
+        search_parser.add_argument(
+            "--pruning-strategy",
+            choices=["global", "local", "proportional"],
+            default="global",
+        )
 
         # Ask command
         ask_parser = subparsers.add_parser("ask", help="Ask questions")
         ask_parser.add_argument("index_name", help="Index name")
-        ask_parser.add_argument("--llm", type=str, default="ollama", choices=["simulated", "ollama", "hf", "openai"])
+        ask_parser.add_argument(
+            "--llm",
+            type=str,
+            default="ollama",
+            choices=["simulated", "ollama", "hf", "openai"],
+        )
         ask_parser.add_argument("--model", type=str, default="qwen3:8b")
         ask_parser.add_argument("--host", type=str, default="http://localhost:11434")
         ask_parser.add_argument("--interactive", "-i", action="store_true")
@@ -82,7 +95,11 @@ Examples:
         ask_parser.add_argument("--beam-width", type=int, default=1)
         ask_parser.add_argument("--prune-ratio", type=float, default=0.0)
         ask_parser.add_argument("--recompute-embeddings", action="store_true")
-        ask_parser.add_argument("--pruning-strategy", choices=["global", "local", "proportional"], default="global")
+        ask_parser.add_argument(
+            "--pruning-strategy",
+            choices=["global", "local", "proportional"],
+            default="global",
+        )
 
         # List command
         list_parser = subparsers.add_parser("list", help="List all indexes")
@@ -93,13 +110,17 @@ Examples:
         print("Stored LEANN indexes:")
 
         if not self.indexes_dir.exists():
-            print("No indexes found. Use 'leann build <name> --docs <dir>' to create one.")
+            print(
+                "No indexes found. Use 'leann build <name> --docs <dir>' to create one."
+            )
             return
 
         index_dirs = [d for d in self.indexes_dir.iterdir() if d.is_dir()]
 
         if not index_dirs:
-            print("No indexes found. Use 'leann build <name> --docs <dir>' to create one.")
+            print(
+                "No indexes found. Use 'leann build <name> --docs <dir>' to create one."
+            )
             return
 
         print(f"Found {len(index_dirs)} indexes:")
@@ -110,13 +131,15 @@ Examples:
             print(f"  {i}. {index_name} [{status}]")
             if self.index_exists(index_name):
                 meta_file = index_dir / "documents.leann.meta.json"
-                size_mb = sum(f.stat().st_size for f in index_dir.iterdir() if f.is_file()) / (1024 * 1024)
+                size_mb = sum(
+                    f.stat().st_size for f in index_dir.iterdir() if f.is_file()
+                ) / (1024 * 1024)
                 print(f"     Size: {size_mb:.1f} MB")
 
         if index_dirs:
             example_name = index_dirs[0].name
             print(f"\nUsage:")
-            print(f"  leann search {example_name} \"your query\"")
+            print(f'  leann search {example_name} "your query"')
             print(f"  leann ask {example_name} --interactive")
 
     def load_documents(self, docs_dir: str):
@@ -179,7 +202,9 @@ Examples:
         index_path = self.get_index_path(index_name)
 
         if not self.index_exists(index_name):
-            print(f"Index '{index_name}' not found. Use 'leann build {index_name} --docs <dir>' to create it.")
+            print(
+                f"Index '{index_name}' not found. Use 'leann build {index_name} --docs <dir>' to create it."
+            )
             return
 
         searcher = LeannSearcher(index_path=index_path)
@@ -190,7 +215,7 @@ Examples:
             beam_width=args.beam_width,
             prune_ratio=args.prune_ratio,
             recompute_embeddings=args.recompute_embeddings,
-            pruning_strategy=args.pruning_strategy
+            pruning_strategy=args.pruning_strategy,
         )
 
         print(f"Search results for '{query}' (top {len(results)}):")
@@ -204,7 +229,9 @@ Examples:
         index_path = self.get_index_path(index_name)
 
         if not self.index_exists(index_name):
-            print(f"Index '{index_name}' not found. Use 'leann build {index_name} --docs <dir>' to create it.")
+            print(
+                f"Index '{index_name}' not found. Use 'leann build {index_name} --docs <dir>' to create it."
+            )
             return
 
         print(f"Starting chat with index '{index_name}'...")
@@ -222,7 +249,7 @@ Examples:
 
             while True:
                 user_input = input("\nYou: ").strip()
-                if user_input.lower() in ['quit', 'exit', 'q']:
+                if user_input.lower() in ["quit", "exit", "q"]:
                     print("Goodbye!")
                     break
 
@@ -236,7 +263,7 @@ Examples:
                     beam_width=args.beam_width,
                     prune_ratio=args.prune_ratio,
                     recompute_embeddings=args.recompute_embeddings,
-                    pruning_strategy=args.pruning_strategy
+                    pruning_strategy=args.pruning_strategy,
                 )
                 print(f"LEANN: {response}")
         else:
@@ -249,7 +276,7 @@ Examples:
                     beam_width=args.beam_width,
                     prune_ratio=args.prune_ratio,
                     recompute_embeddings=args.recompute_embeddings,
-                    pruning_strategy=args.pruning_strategy
+                    pruning_strategy=args.pruning_strategy,
                 )
                 print(f"LEANN: {response}")
 
@@ -277,6 +304,7 @@ Examples:
 
 def main():
     import dotenv
+
     dotenv.load_dotenv()
 
     cli = LeannCLI()