mirror of
https://github.com/facebookresearch/faiss.git
synced 2026-10-11 22:50:00 +00:00
Tia Lim
0f0f728166
Summary: Pull Request resolved: https://github.com/facebookresearch/faiss/pull/5349 # this is a no-op change Ran `black -l 80` over all tracked Python files under `fbcode/faiss/`, using line length 80 to match faiss's documented coding style (`CONTRIBUTING.md`: "80 character line length (both for C++ and Python)"). 172 files were reformatted; 28 were already compliant. This is a pure-formatting change. `black` runs its AST-equivalence safety check on every file, so no identifiers, string/numeric values, operators, or control flow were altered — only whitespace, indentation, line wrapping, blank lines, trailing commas, and string-quote normalization (single to double quotes). `fbcode/faiss/` is intentionally excluded from Meta's standard Python autoformatter (`arc f` / `arc lint -a` report no formatter for these paths) because it mirrors to public GitHub, so the Python had drifted out of any consistent style. The C++ is already clang-format-clean (0 of 807 files change), so this effort is Python-only. This diff brings the Python to canonical `black` formatting. Excluded `demos/index_pq_flat_separate_codes_from_codebook.py`: it contains a Jupyter `!rm` shell-magic line and is not valid Python, so `black` cannot parse it. This is the base of a 3-diff stack: (1) this black reformat; (2) `.flake8` alignment (max-line-length 80 + black-compatible ignores E203/W503); (3) genuine lint fixes (F401/F403/F841/B011). Reviewed By: mnorris11 Differential Revision: D109736099 fbshipit-source-id: 9a054635766ed11aa3760a788395babd3d198abf
65 lines
2.0 KiB
Python
65 lines
2.0 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
#
|
|
# This source code is licensed under the MIT license found in the
|
|
# LICENSE file in the root directory of this source tree.
|
|
|
|
from typing import List
|
|
import faiss
|
|
import logging
|
|
|
|
LOG = logging.getLogger(__name__)
|
|
|
|
|
|
def merge_ondisk(
|
|
trained_index: faiss.Index,
|
|
shard_fnames: List[str],
|
|
ivfdata_fname: str,
|
|
shift_ids=False,
|
|
) -> None:
|
|
"""Add the contents of the indexes stored in shard_fnames into the index
|
|
trained_index. The on-disk data is stored in ivfdata_fname"""
|
|
assert not isinstance(
|
|
trained_index, faiss.IndexIVFPQR
|
|
), "IndexIVFPQR is not supported as an on disk index."
|
|
# merge the images into an on-disk index
|
|
# first load the inverted lists
|
|
ivfs = []
|
|
for fname in shard_fnames:
|
|
# the IO_FLAG_MMAP is to avoid actually loading the data thus
|
|
# the total size of the inverted lists can exceed the
|
|
# available RAM
|
|
LOG.info("read " + fname)
|
|
index = faiss.read_index(fname, faiss.IO_FLAG_MMAP)
|
|
index_ivf = faiss.extract_index_ivf(index)
|
|
ivfs.append(index_ivf.invlists)
|
|
|
|
# avoid that the invlists get deallocated with the index
|
|
index_ivf.own_invlists = False
|
|
|
|
# construct the output index
|
|
index = trained_index
|
|
index_ivf = faiss.extract_index_ivf(index)
|
|
|
|
assert index.ntotal == 0, "works only on empty index"
|
|
|
|
# prepare the output inverted lists. They will be written
|
|
# to merged_index.ivfdata
|
|
invlists = faiss.OnDiskInvertedLists(
|
|
index_ivf.nlist, index_ivf.code_size, ivfdata_fname
|
|
)
|
|
|
|
# merge all the inverted lists
|
|
ivf_vector = faiss.InvertedListsPtrVector()
|
|
for ivf in ivfs:
|
|
ivf_vector.push_back(ivf)
|
|
|
|
LOG.info("merge %d inverted lists " % ivf_vector.size())
|
|
ntotal = invlists.merge_from_multiple(
|
|
ivf_vector.data(), ivf_vector.size(), shift_ids
|
|
)
|
|
|
|
# now replace the inverted lists in the output index
|
|
index.ntotal = index_ivf.ntotal = ntotal
|
|
index_ivf.replace_invlists(invlists, True)
|
|
invlists.this.disown()
|