feat: implement GPU-backed FAISS support and dynamic tokenization scaling

.gitmodules

@@ -14,6 +14,3 @@
 [submodule "packages/leann-backend-hnsw/third_party/libzmq"]
 	path = packages/leann-backend-hnsw/third_party/libzmq
 	url = https://github.com/zeromq/libzmq.git
-[submodule "packages/astchunk-leann"]
-	path = packages/astchunk-leann
-	url = https://github.com/yichuan-w/astchunk-leann.git

apps/multimodal/vision-based-pdf-multi-vector/colqwen_forward.py

@@ -71,7 +71,7 @@ def main():
     # Step 2: Load model
     print("\n[Step 2] Loading ColQwen2 model...")
     try:
-        model_name, model, processor, device_str, device, dtype = _load_colvision("colqwen2")
+        model_name, model, processor, device_str, _device, dtype = _load_colvision("colqwen2")
         print(f"✓ Model loaded: {model_name}")
         print(f"✓ Device: {device_str}, dtype: {dtype}")
 

benchmarks/financebench/verify_recall.py

@@ -127,11 +127,11 @@ def evaluate_recall_at_k(
         query = query_embeddings[i : i + 1]  # Keep 2D shape
 
         # Get ground truth from Flat index (standard FAISS API)
-        flat_distances, flat_indices = flat_index.search(query, k)
+        _flat_distances, flat_indices = flat_index.search(query, k)
         ground_truth_ids = {passage_ids[idx] for idx in flat_indices[0]}
 
         # Get results from HNSW index (standard FAISS API)
-        hnsw_distances, hnsw_indices = hnsw_index.search(query, k)
+        _hnsw_distances, hnsw_indices = hnsw_index.search(query, k)
         hnsw_ids = {passage_ids[idx] for idx in hnsw_indices[0]}
 
         # Calculate recall

benchmarks/update/bench_hnsw_rng_recompute.py

@@ -677,7 +677,7 @@ def _fmt_ms(v: float) -> str:
                     else max(second * 1.2, lower_cap * 1.02)
                 )
                 ymax = max(values) * 1.10 if values else 1.0
-                fig, (ax_top, ax_bottom) = plt.subplots(
+                _fig, (ax_top, ax_bottom) = plt.subplots(
                     2,
                     1,
                     sharex=True,

benchmarks/update/bench_update_vs_offline_search.py

@@ -488,7 +488,7 @@ def main() -> None:
             _ = _search(index, q_emb, 1)
 
             t_s0 = time.time()
-            D_upd, I_upd = _search(index, q_emb, args.k)
+            _D_upd, _I_upd = _search(index, q_emb, args.k)
             search_after_add = time.time() - t_s0
             total_seq = time.time() - t0
         finally:

llms.txt

@@ -8,7 +8,7 @@ install: uv tool install leann-core --with leann
 
 # MCP Server Entry Point
 mcp.server: leann_mcp
-mcp.protocol_version: 2024-11-05
+mcp.protocol_version: 2025-11-25
 
 # Tools
 mcp.tools: leann_list, leann_search

packages/astchunk-leann/.gitignore

@@ -0,0 +1,194 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the enitre vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore

packages/astchunk-leann/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Yilin (Jason) Zhang
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.