feat: support multiple input formats for --docs argument

- Add support for multiple directories: --docs ./src ./tests ./config
- Add support for individual files: --docs ./file1.py ./file2.txt
- Add support for mixed files and directories: --docs ./README.md ./src/ ./config.json
- Add git ls-files integration: --docs $(git ls-files)
- Add git submodule detection and skip logic to avoid indexing third-party dependencies
- Add comprehensive error handling for path resolution issues
- Update MCP README with advanced usage examples including git integration
- Fix ruff linting issues with closure variable binding

Breaking changes: None - fully backward compatible with existing single directory usage

Examples:
  leann build my-repo --docs $(git ls-files) --embedding-mode sentence-transformers --embedding-model all-MiniLM-L6-v2 --backend hnsw
  leann build my-code --docs ./src ./tests ./docs --embedding-mode sentence-transformers --embedding-model all-MiniLM-L6-v2 --backend hnsw
  leann build my-configs --docs ./package.json ./tsconfig.json ./webpack.config.js --embedding-mode sentence-transformers --embedding-model all-MiniLM-L6-v2 --backend hnsw

.github/workflows/build-reusable.yml

@@ -64,16 +64,6 @@ jobs:
             python: '3.12'
           - os: macos-14
             python: '3.13'
-          - os: macos-15
-            python: '3.9'
-          - os: macos-15
-            python: '3.10'
-          - os: macos-15
-            python: '3.11'
-          - os: macos-15
-            python: '3.12'
-          - os: macos-15
-            python: '3.13'
           - os: macos-13
             python: '3.9'
           - os: macos-13
@@ -157,14 +147,7 @@ jobs:
             # Use system clang for better compatibility
             export CC=clang
             export CXX=clang++
-            # Homebrew libraries on each macOS version require matching minimum version
+            export MACOSX_DEPLOYMENT_TARGET=11.0
-            if [[ "${{ matrix.os }}" == "macos-13" ]]; then
-              export MACOSX_DEPLOYMENT_TARGET=13.0
-            elif [[ "${{ matrix.os }}" == "macos-14" ]]; then
-              export MACOSX_DEPLOYMENT_TARGET=14.0
-            elif [[ "${{ matrix.os }}" == "macos-15" ]]; then
-              export MACOSX_DEPLOYMENT_TARGET=15.0
-            fi
             uv build --wheel --python ${{ matrix.python }} --find-links ${GITHUB_WORKSPACE}/packages/leann-core/dist
           else
             uv build --wheel --python ${{ matrix.python }} --find-links ${GITHUB_WORKSPACE}/packages/leann-core/dist
@@ -178,14 +161,7 @@ jobs:
             export CC=clang
             export CXX=clang++
             # DiskANN requires macOS 13.3+ for sgesdd_ LAPACK function
-            # But Homebrew libraries on each macOS version require matching minimum version
+            export MACOSX_DEPLOYMENT_TARGET=13.3
-            if [[ "${{ matrix.os }}" == "macos-13" ]]; then
-              export MACOSX_DEPLOYMENT_TARGET=13.3
-            elif [[ "${{ matrix.os }}" == "macos-14" ]]; then
-              export MACOSX_DEPLOYMENT_TARGET=14.0
-            elif [[ "${{ matrix.os }}" == "macos-15" ]]; then
-              export MACOSX_DEPLOYMENT_TARGET=15.0
-            fi
             uv build --wheel --python ${{ matrix.python }} --find-links ${GITHUB_WORKSPACE}/packages/leann-core/dist
           else
             uv build --wheel --python ${{ matrix.python }} --find-links ${GITHUB_WORKSPACE}/packages/leann-core/dist
@@ -221,24 +197,10 @@ jobs:
       - name: Repair wheels (macOS)
         if: runner.os == 'macOS'
         run: |
-          # Determine deployment target based on runner OS
-          # Must match the Homebrew libraries for each macOS version
-          if [[ "${{ matrix.os }}" == "macos-13" ]]; then
-            HNSW_TARGET="13.0"
-            DISKANN_TARGET="13.3"
-          elif [[ "${{ matrix.os }}" == "macos-14" ]]; then
-            HNSW_TARGET="14.0"
-            DISKANN_TARGET="14.0"
-          elif [[ "${{ matrix.os }}" == "macos-15" ]]; then
-            HNSW_TARGET="15.0"
-            DISKANN_TARGET="15.0"
-          fi
-
           # Repair HNSW wheel
           cd packages/leann-backend-hnsw
           if [ -d dist ]; then
-            export MACOSX_DEPLOYMENT_TARGET=$HNSW_TARGET
+            delocate-wheel -w dist_repaired -v dist/*.whl
-            delocate-wheel -w dist_repaired -v --require-target-macos-version $HNSW_TARGET dist/*.whl
             rm -rf dist
             mv dist_repaired dist
           fi
@@ -247,8 +209,7 @@ jobs:
           # Repair DiskANN wheel
           cd packages/leann-backend-diskann
           if [ -d dist ]; then
-            export MACOSX_DEPLOYMENT_TARGET=$DISKANN_TARGET
+            delocate-wheel -w dist_repaired -v dist/*.whl
-            delocate-wheel -w dist_repaired -v --require-target-macos-version $DISKANN_TARGET dist/*.whl
             rm -rf dist
             mv dist_repaired dist
           fi
@@ -288,8 +249,8 @@ jobs:
           # Activate virtual environment
           source .venv/bin/activate || source .venv/Scripts/activate
 
-          # Run tests
+          # Run all tests
-          pytest -v tests/
+          pytest tests/
 
       - name: Run sanity checks (optional)
         run: |

README.md

@@ -71,8 +71,6 @@ source .venv/bin/activate
 uv pip install leann
 ```
 
-> Low-resource? See “Low-resource setups” in the [Configuration Guide](docs/configuration-guide.md#low-resource-setups).
-
 <details>
 <summary>
 <strong>🔧 Build from Source (Recommended for development)</strong>

docs/configuration-guide.md

@@ -259,80 +259,24 @@ Every configuration choice involves trade-offs:
 
 The key is finding the right balance for your specific use case. Start small and simple, measure performance, then scale up only where needed.
 
-## Low-resource setups
+## Deep Dive: Critical Configuration Decisions
 
-If you don’t have a local GPU or builds/searches are too slow, use one or more of the options below.
+### When to Disable Recomputation
 
-### 1) Use OpenAI embeddings (no local compute)
+LEANN's recomputation feature provides exact distance calculations but can be disabled for extreme QPS requirements:
-
-Fastest path with zero local GPU requirements. Set your API key and use OpenAI embeddings during build and search:
 
 ```bash
-export OPENAI_API_KEY=sk-...
+--no-recompute  # Disable selective recomputation
-
-# Build with OpenAI embeddings
-leann build my-index \
-  --embedding-mode openai \
-  --embedding-model text-embedding-3-small
-
-# Search with OpenAI embeddings (recompute at query time)
-leann search my-index "your query" \
-  --recompute-embeddings
 ```
 
-### 2) Run remote builds with SkyPilot (cloud GPU)
+**Trade-offs**:
+- **With recomputation** (default): Exact distances, best quality, higher latency, minimal storage (only stores metadata, recomputes embeddings on-demand)
+- **Without recomputation**: Must store full embeddings, significantly higher memory and storage usage (10-100x more), but faster search
 
-Offload embedding generation and index building to a GPU VM using SkyPilot. A template is provided at `sky/leann-build.yaml`.
+**Disable when**:
-
+- You have abundant storage and memory
-```bash
+- Need extremely low latency (< 100ms)
-# One-time: install and configure SkyPilot
+- Running a read-heavy workload where storage cost is acceptable
-pip install skypilot
-sky launch -c leann-gpu sky/leann-build.yaml
-
-# Build remotely (template installs uv + leann CLI)
-sky exec leann-gpu -- "leann build my-index --docs ~/leann-data --backend hnsw --complexity 64 --graph-degree 32"
-```
-
-Details: see “Running Builds on SkyPilot (Optional)” below.
-
-### 3) Disable recomputation to trade storage for speed
-
-If you need lower latency and have more storage/memory, disable recomputation. This stores full embeddings and avoids recomputing at search time.
-
-```bash
-# Build without recomputation (HNSW requires non-compact in this mode)
-leann build my-index --no-recompute --no-compact
-
-# Search without recomputation
-leann search my-index "your query" --no-recompute
-```
-
-Trade-offs: lower query-time latency, but significantly higher storage usage.
-
-## Running Builds on SkyPilot (Optional)
-
-You can offload embedding generation and index building to a cloud GPU VM using SkyPilot, without changing any LEANN code. This is useful when your local machine lacks a GPU or you want faster throughput.
-
-### Quick Start
-
-1) Install SkyPilot by following their docs (`pip install skypilot`), then configure cloud credentials.
-
-2) Use the provided SkyPilot template:
-
-```bash
-sky launch -c leann-gpu sky/leann-build.yaml
-```
-
-3) On the remote, either put your data under the mounted path or adjust `file_mounts` in `sky/leann-build.yaml`. Then run the LEANN build:
-
-```bash
-sky exec leann-gpu -- "leann build my-index --docs ~/leann-data --backend hnsw --complexity 64 --graph-degree 32"
-```
-
-Notes:
-- The template installs `uv` and the `leann` CLI globally on the remote instance.
-- Change the `accelerators` and `cloud` settings in `sky/leann-build.yaml` to match your budget/availability (e.g., `A10G:1`, `A100:1`, or CPU-only if you prefer).
-- You can also build with `diskann` by switching `--backend diskann`.
 
 ## Further Reading
 

packages/leann-backend-diskann/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "scikit_build_core.build"
 
 [project]
 name = "leann-backend-diskann"
-version = "0.2.9"
+version = "0.2.7"
-dependencies = ["leann-core==0.2.9", "numpy", "protobuf>=3.19.0"]
+dependencies = ["leann-core==0.2.7", "numpy", "protobuf>=3.19.0"]
 
 [tool.scikit-build]
 # Key: simplified CMake path

packages/leann-backend-hnsw/leann_backend_hnsw/hnsw_embedding_server.py

@@ -95,8 +95,6 @@ def create_hnsw_embedding_server(
         passage_sources.append(source_copy)
 
     passages = PassageManager(passage_sources)
-    # Use index dimensions from metadata for shaping fallback responses
-    embedding_dim: int = int(meta.get("dimensions", 0))
     logger.info(
         f"Loaded PassageManager with {len(passages.global_offset_map)} passages from metadata"
     )
@@ -111,9 +109,6 @@ def create_hnsw_embedding_server(
         socket.setsockopt(zmq.RCVTIMEO, 300000)
         socket.setsockopt(zmq.SNDTIMEO, 300000)
 
-        # Track last request type for safe fallback responses on exceptions
-        last_request_type = "unknown"  # one of: 'text', 'distance', 'embedding', 'unknown'
-        last_request_length = 0
         while True:
             try:
                 message_bytes = socket.recv()
@@ -126,8 +121,6 @@ def create_hnsw_embedding_server(
                 if isinstance(request_payload, list) and len(request_payload) > 0:
                     # Check if this is a direct text request (list of strings)
                     if all(isinstance(item, str) for item in request_payload):
-                        last_request_type = "text"
-                        last_request_length = len(request_payload)
                         logger.info(
                             f"Processing direct text embedding request for {len(request_payload)} texts in {embedding_mode} mode"
                         )
@@ -152,66 +145,43 @@ def create_hnsw_embedding_server(
                 ):
                     node_ids = request_payload[0]
                     query_vector = np.array(request_payload[1], dtype=np.float32)
-                    last_request_type = "distance"
-                    last_request_length = len(node_ids)
 
                     logger.debug("Distance calculation request received")
                     logger.debug(f"    Node IDs: {node_ids}")
                     logger.debug(f"    Query vector dim: {len(query_vector)}")
 
-                    # Get embeddings for node IDs, tolerate missing IDs
+                    # Get embeddings for node IDs
-                    texts: list[str] = []
+                    texts = []
-                    found_indices: list[int] = []
+                    for nid in node_ids:
-                    for idx, nid in enumerate(node_ids):
                         try:
                             passage_data = passages.get_passage(str(nid))
-                            txt = passage_data.get("text", "")
+                            txt = passage_data["text"]
-                            if isinstance(txt, str) and len(txt) > 0:
+                            texts.append(txt)
-                                texts.append(txt)
-                                found_indices.append(idx)
-                            else:
-                                logger.error(f"Empty text for passage ID {nid}")
                         except KeyError:
                             logger.error(f"Passage ID {nid} not found")
+                            raise RuntimeError(f"FATAL: Passage with ID {nid} not found")
                         except Exception as e:
                             logger.error(f"Exception looking up passage ID {nid}: {e}")
+                            raise
 
-                    # Prepare full-length response distances with safe fallbacks
+                    # Process embeddings
-                    large_distance = 1e9
+                    embeddings = compute_embeddings(texts, model_name, mode=embedding_mode)
-                    response_distances = [large_distance] * len(node_ids)
+                    logger.info(
-
+                        f"Computed embeddings for {len(texts)} texts, shape: {embeddings.shape}"
-                    if texts:
-                        try:
-                            # Process embeddings only for found indices
-                            embeddings = compute_embeddings(texts, model_name, mode=embedding_mode)
-                            logger.info(
-                                f"Computed embeddings for {len(texts)} texts, shape: {embeddings.shape}"
-                            )
-
-                            # Calculate distances for found embeddings only
-                            if distance_metric == "l2":
-                                partial_distances = np.sum(
-                                    np.square(embeddings - query_vector.reshape(1, -1)), axis=1
-                                )
-                            else:  # mips or cosine
-                                partial_distances = -np.dot(embeddings, query_vector)
-
-                            # Place computed distances back into the full response array
-                            for pos, dval in zip(
-                                found_indices, partial_distances.flatten().tolist()
-                            ):
-                                response_distances[pos] = float(dval)
-                        except Exception as e:
-                            logger.error(
-                                f"Distance computation error, falling back to large distances: {e}"
-                            )
-
-                    # Always reply with exactly len(node_ids) distances
-                    response_bytes = msgpack.packb([response_distances], use_single_float=True)
-                    logger.debug(
-                        f"Sending distance response with {len(response_distances)} distances (found={len(found_indices)})"
                     )
 
+                    # Calculate distances
+                    if distance_metric == "l2":
+                        distances = np.sum(
+                            np.square(embeddings - query_vector.reshape(1, -1)), axis=1
+                        )
+                    else:  # mips or cosine
+                        distances = -np.dot(embeddings, query_vector)
+
+                    response_payload = distances.flatten().tolist()
+                    response_bytes = msgpack.packb([response_payload], use_single_float=True)
+                    logger.debug(f"Sending distance response with {len(distances)} distances")
+
                     socket.send(response_bytes)
                     e2e_end = time.time()
                     logger.info(f"⏱️  Distance calculation E2E time: {e2e_end - e2e_start:.6f}s")
@@ -231,61 +201,40 @@ def create_hnsw_embedding_server(
 
                 node_ids = request_payload[0]
                 logger.debug(f"Request for {len(node_ids)} node embeddings")
-                last_request_type = "embedding"
-                last_request_length = len(node_ids)
 
-                # Allocate output buffer (B, D) and fill with zeros for robustness
+                # Look up texts by node IDs
-                if embedding_dim <= 0:
+                texts = []
-                    logger.error("Embedding dimension unknown; cannot serve embedding request")
+                for nid in node_ids:
-                    dims = [0, 0]
-                    data = []
-                else:
-                    dims = [len(node_ids), embedding_dim]
-                    data = [0.0] * (dims[0] * dims[1])
-
-                # Look up texts by node IDs; compute embeddings where available
-                texts: list[str] = []
-                found_indices: list[int] = []
-                for idx, nid in enumerate(node_ids):
                     try:
                         passage_data = passages.get_passage(str(nid))
-                        txt = passage_data.get("text", "")
+                        txt = passage_data["text"]
-                        if isinstance(txt, str) and len(txt) > 0:
+                        if not txt:
-                            texts.append(txt)
+                            raise RuntimeError(f"FATAL: Empty text for passage ID {nid}")
-                            found_indices.append(idx)
+                        texts.append(txt)
-                        else:
-                            logger.error(f"Empty text for passage ID {nid}")
                     except KeyError:
-                        logger.error(f"Passage with ID {nid} not found")
+                        raise RuntimeError(f"FATAL: Passage with ID {nid} not found")
                     except Exception as e:
                         logger.error(f"Exception looking up passage ID {nid}: {e}")
+                        raise
 
-                if texts:
+                # Process embeddings
-                    try:
+                embeddings = compute_embeddings(texts, model_name, mode=embedding_mode)
-                        # Process embeddings for found texts only
+                logger.info(
-                        embeddings = compute_embeddings(texts, model_name, mode=embedding_mode)
+                    f"Computed embeddings for {len(texts)} texts, shape: {embeddings.shape}"
-                        logger.info(
+                )
-                            f"Computed embeddings for {len(texts)} texts, shape: {embeddings.shape}"
-                        )
 
-                        if np.isnan(embeddings).any() or np.isinf(embeddings).any():
+                # Serialization and response
-                            logger.error(
+                if np.isnan(embeddings).any() or np.isinf(embeddings).any():
-                                f"NaN or Inf detected in embeddings! Requested IDs: {node_ids[:5]}..."
+                    logger.error(
-                            )
+                        f"NaN or Inf detected in embeddings! Requested IDs: {node_ids[:5]}..."
-                            dims = [0, embedding_dim]
+                    )
-                            data = []
+                    raise AssertionError()
-                        else:
-                            # Copy computed embeddings into the correct positions
-                            emb_f32 = np.ascontiguousarray(embeddings, dtype=np.float32)
-                            flat = emb_f32.flatten().tolist()
-                            for j, pos in enumerate(found_indices):
-                                start = pos * embedding_dim
-                                end = start + embedding_dim
-                                data[start:end] = flat[j * embedding_dim : (j + 1) * embedding_dim]
-                    except Exception as e:
-                        logger.error(f"Embedding computation error, returning zeros: {e}")
 
-                response_payload = [dims, data]
+                hidden_contiguous_f32 = np.ascontiguousarray(embeddings, dtype=np.float32)
+                response_payload = [
+                    list(hidden_contiguous_f32.shape),
+                    hidden_contiguous_f32.flatten().tolist(),
+                ]
                 response_bytes = msgpack.packb(response_payload, use_single_float=True)
 
                 socket.send(response_bytes)
@@ -300,22 +249,7 @@ def create_hnsw_embedding_server(
                 import traceback
 
                 traceback.print_exc()
-                # Fallback to a safe, minimal-structure response to avoid client crashes
+                socket.send(msgpack.packb([[], []]))
-                if last_request_type == "distance":
-                    # Return a vector of large distances with the expected length
-                    fallback_len = max(0, int(last_request_length))
-                    large_distance = 1e9
-                    safe_response = [[large_distance] * fallback_len]
-                elif last_request_type == "embedding":
-                    # Return an empty embedding block with known dimension if available
-                    if embedding_dim > 0:
-                        safe_response = [[0, embedding_dim], []]
-                    else:
-                        safe_response = [[0, 0], []]
-                else:
-                    # Unknown request type: default to empty embedding structure
-                    safe_response = [[0, int(embedding_dim) if embedding_dim > 0 else 0], []]
-                socket.send(msgpack.packb(safe_response, use_single_float=True))
 
     zmq_thread = threading.Thread(target=zmq_server_thread, daemon=True)
     zmq_thread.start()

packages/leann-backend-hnsw/pyproject.toml

@@ -6,10 +6,10 @@ build-backend = "scikit_build_core.build"
 
 [project]
 name = "leann-backend-hnsw"
-version = "0.2.9"
+version = "0.2.7"
 description = "Custom-built HNSW (Faiss) backend for the Leann toolkit."
 dependencies = [
-    "leann-core==0.2.9",
+    "leann-core==0.2.7",
     "numpy",
     "pyzmq>=23.0.0",
     "msgpack>=1.0.0",

packages/leann-core/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "leann-core"
-version = "0.2.9"
+version = "0.2.7"
 description = "Core API and plugin system for LEANN"
 readme = "README.md"
 requires-python = ">=3.9"

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

@@ -117,19 +117,7 @@ Examples:
         build_parser.add_argument("--complexity", type=int, default=64)
         build_parser.add_argument("--num-threads", type=int, default=1)
         build_parser.add_argument("--compact", action="store_true", default=True)
-        build_parser.add_argument(
-            "--no-compact",
-            dest="compact",
-            action="store_false",
-            help="Disable compact index storage (store full embeddings; higher storage)",
-        )
         build_parser.add_argument("--recompute", action="store_true", default=True)
-        build_parser.add_argument(
-            "--no-recompute",
-            dest="recompute",
-            action="store_false",
-            help="Disable embedding recomputation (store full embeddings; lower query latency)",
-        )
         build_parser.add_argument(
             "--file-types",
             type=str,
@@ -150,18 +138,6 @@ Examples:
             default=True,
             help="Recompute embeddings (default: True)",
         )
-        search_parser.add_argument(
-            "--no-recompute-embeddings",
-            dest="recompute_embeddings",
-            action="store_false",
-            help="Disable embedding recomputation during search",
-        )
-        search_parser.add_argument(
-            "--no-recompute",
-            dest="recompute_embeddings",
-            action="store_false",
-            help="Alias for --no-recompute-embeddings",
-        )
         search_parser.add_argument(
             "--pruning-strategy",
             choices=["global", "local", "proportional"],
@@ -190,18 +166,6 @@ Examples:
             default=True,
             help="Recompute embeddings (default: True)",
         )
-        ask_parser.add_argument(
-            "--no-recompute-embeddings",
-            dest="recompute_embeddings",
-            action="store_false",
-            help="Disable embedding recomputation during ask",
-        )
-        ask_parser.add_argument(
-            "--no-recompute",
-            dest="recompute_embeddings",
-            action="store_false",
-            help="Alias for --no-recompute-embeddings",
-        )
         ask_parser.add_argument(
             "--pruning-strategy",
             choices=["global", "local", "proportional"],

packages/leann-mcp/README.md

@@ -4,12 +4,20 @@ Transform your development workflow with intelligent code assistance using LEANN
 
 ## Prerequisites
 
-Install LEANN globally for MCP integration (with default backend):
+**Step 1:** First, complete the basic LEANN installation following the [📦 Installation guide](../../README.md#installation) in the root README:
 
 ```bash
-uv tool install leann-core --with leann
+uv venv
+source .venv/bin/activate
+uv pip install leann
 ```
-This installs the `leann` CLI into an isolated tool environment and includes both backends so `leann build` works out-of-the-box.
+
+**Step 2:** Install LEANN globally for MCP integration:
+```bash
+uv tool install leann-core
+```
+
+This makes the `leann` command available system-wide, which `leann_mcp` requires.
 
 ## 🚀 Quick Setup
 

packages/leann/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "leann"
-version = "0.2.9"
+version = "0.2.7"
 description = "LEANN - The smallest vector index in the world. RAG Everything with LEANN!"
 readme = "README.md"
 requires-python = ">=3.9"

sky/leann-build.yaml

@@ -1,62 +0,0 @@
-name: leann-build
-
-resources:
-  # Choose a GPU for fast embeddings (examples: L4, A10G, A100). CPU also works but is slower.
-  accelerators: L4:1
-  # Optionally pin a cloud, otherwise SkyPilot will auto-select
-  # cloud: aws
-  disk_size: 100
-
-env:
-  # Build parameters (override with: sky launch -c leann-gpu sky/leann-build.yaml -e key=value)
-  index_name: my-index
-  docs: ./data
-  backend: hnsw               # hnsw | diskann
-  complexity: 64
-  graph_degree: 32
-  num_threads: 8
-  # Embedding selection
-  embedding_mode: sentence-transformers   # sentence-transformers | openai | mlx | ollama
-  embedding_model: facebook/contriever
-  # Storage/latency knobs
-  recompute: true             # true => selective recomputation; false => store full embeddings
-  compact: true               # for HNSW only: false when recompute=false
-  # Optional pass-through
-  extra_args: ""
-
-# Sync local paths to the remote VM. Adjust as needed.
-file_mounts:
-  # Example: mount your local data directory used for building
-  ~/leann-data: ${docs}
-
-setup: |
-  set -e
-  # Install uv (package manager)
-  curl -LsSf https://astral.sh/uv/install.sh | sh
-  export PATH="$HOME/.local/bin:$PATH"
-
-  # Install the LEANN CLI globally on the remote machine
-  uv tool install leann
-
-run: |
-  export PATH="$HOME/.local/bin:$PATH"
-  # Derive flags from env
-  recompute_flag=""
-  if [ "${recompute}" = "false" ] || [ "${recompute}" = "0" ]; then
-    recompute_flag="--no-recompute"
-  fi
-  compact_flag=""
-  if [ "${compact}" = "false" ] || [ "${compact}" = "0" ]; then
-    compact_flag="--no-compact"
-  fi
-
-  # Build command
-  leann build ${index_name} \
-    --docs ~/leann-data \
-    --backend ${backend} \
-    --complexity ${complexity} \
-    --graph-degree ${graph_degree} \
-    --num-threads ${num_threads} \
-    --embedding-mode ${embedding_mode} \
-    --embedding-model ${embedding_model} \
-    ${recompute_flag} ${compact_flag} ${extra_args}