mirror of
https://github.com/qdrant/qdrant-client.git
synced 2026-07-23 11:11:01 -05:00
update interface and version for fastembed (#340)
* update interface and version for fastembed * fix types * fix types * regen async * use python 3.11 to check compatibility * fix docstring * regen async * propagate batch size
This commit is contained in:
Andrey Vasnetsov
committed by
generall
generall
parent
2a07215787
commit
0cfc45a340
2
.github/workflows/integration-tests.yml
vendored
2
.github/workflows/integration-tests.yml
vendored
@@ -39,7 +39,7 @@ jobs:
|
||||
poetry install --no-interaction --no-ansi --all-extras
|
||||
- name: Run async client generation tests
|
||||
run: |
|
||||
if [[ ${{ matrix.python-version }} == "3.9.x" ]]; then
|
||||
if [[ ${{ matrix.python-version }} == "3.11.x" ]]; then
|
||||
./tests/async-client-consistency-check.sh
|
||||
fi
|
||||
shell: bash
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
# See https://pre-commit.com for more information
|
||||
# See https://pre-commit.com/hooks.html for more hooks
|
||||
default_language_version:
|
||||
python: python3.9
|
||||
python: python3.11
|
||||
|
||||
exclude: 'qdrant_client/(grpc|http|models)/'
|
||||
|
||||
|
||||
196
poetry.lock
generated
196
poetry.lock
generated
@@ -1,4 +1,4 @@
|
||||
# This file is automatically @generated by Poetry 1.6.1 and should not be changed by hand.
|
||||
# This file is automatically @generated by Poetry 1.5.1 and should not be changed by hand.
|
||||
|
||||
[[package]]
|
||||
name = "alabaster"
|
||||
@@ -365,13 +365,13 @@ test = ["pytest (>=6)"]
|
||||
|
||||
[[package]]
|
||||
name = "fastembed"
|
||||
version = "0.0.5"
|
||||
version = "0.1.1"
|
||||
description = "Fast, light, accurate library built for retrieval embedding generation"
|
||||
optional = true
|
||||
python-versions = ">=3.8.0,<3.12"
|
||||
files = [
|
||||
{file = "fastembed-0.0.5-py3-none-any.whl", hash = "sha256:dd2f89c7e77a47f1de5d77a6fda0a24c4659f25bd95eb08b6429b28c86d12f37"},
|
||||
{file = "fastembed-0.0.5.tar.gz", hash = "sha256:dca558d358b3fec5f79ce55bb693bc1812f24eb96ab36b6aed6cad395f3eef01"},
|
||||
{file = "fastembed-0.1.1-py3-none-any.whl", hash = "sha256:131413ae52cd72f4c8cced7a675f8269dbfd1a852abade3c815e265114bcc05a"},
|
||||
{file = "fastembed-0.1.1.tar.gz", hash = "sha256:f7e524ee4f74bb8aad16be5b687d1f77f608d40e96e292c87881dc36baf8f4c7"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
@@ -797,38 +797,38 @@ tests = ["pytest (>=4.6)"]
|
||||
|
||||
[[package]]
|
||||
name = "mypy"
|
||||
version = "1.5.1"
|
||||
version = "1.6.0"
|
||||
description = "Optional static typing for Python"
|
||||
optional = false
|
||||
python-versions = ">=3.8"
|
||||
files = [
|
||||
{file = "mypy-1.5.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:f33592ddf9655a4894aef22d134de7393e95fcbdc2d15c1ab65828eee5c66c70"},
|
||||
{file = "mypy-1.5.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:258b22210a4a258ccd077426c7a181d789d1121aca6db73a83f79372f5569ae0"},
|
||||
{file = "mypy-1.5.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a9ec1f695f0c25986e6f7f8778e5ce61659063268836a38c951200c57479cc12"},
|
||||
{file = "mypy-1.5.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:abed92d9c8f08643c7d831300b739562b0a6c9fcb028d211134fc9ab20ccad5d"},
|
||||
{file = "mypy-1.5.1-cp310-cp310-win_amd64.whl", hash = "sha256:a156e6390944c265eb56afa67c74c0636f10283429171018446b732f1a05af25"},
|
||||
{file = "mypy-1.5.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6ac9c21bfe7bc9f7f1b6fae441746e6a106e48fc9de530dea29e8cd37a2c0cc4"},
|
||||
{file = "mypy-1.5.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:51cb1323064b1099e177098cb939eab2da42fea5d818d40113957ec954fc85f4"},
|
||||
{file = "mypy-1.5.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:596fae69f2bfcb7305808c75c00f81fe2829b6236eadda536f00610ac5ec2243"},
|
||||
{file = "mypy-1.5.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:32cb59609b0534f0bd67faebb6e022fe534bdb0e2ecab4290d683d248be1b275"},
|
||||
{file = "mypy-1.5.1-cp311-cp311-win_amd64.whl", hash = "sha256:159aa9acb16086b79bbb0016145034a1a05360626046a929f84579ce1666b315"},
|
||||
{file = "mypy-1.5.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:f6b0e77db9ff4fda74de7df13f30016a0a663928d669c9f2c057048ba44f09bb"},
|
||||
{file = "mypy-1.5.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:26f71b535dfc158a71264e6dc805a9f8d2e60b67215ca0bfa26e2e1aa4d4d373"},
|
||||
{file = "mypy-1.5.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2fc3a600f749b1008cc75e02b6fb3d4db8dbcca2d733030fe7a3b3502902f161"},
|
||||
{file = "mypy-1.5.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:26fb32e4d4afa205b24bf645eddfbb36a1e17e995c5c99d6d00edb24b693406a"},
|
||||
{file = "mypy-1.5.1-cp312-cp312-win_amd64.whl", hash = "sha256:82cb6193de9bbb3844bab4c7cf80e6227d5225cc7625b068a06d005d861ad5f1"},
|
||||
{file = "mypy-1.5.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:4a465ea2ca12804d5b34bb056be3a29dc47aea5973b892d0417c6a10a40b2d65"},
|
||||
{file = "mypy-1.5.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:9fece120dbb041771a63eb95e4896791386fe287fefb2837258925b8326d6160"},
|
||||
{file = "mypy-1.5.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d28ddc3e3dfeab553e743e532fb95b4e6afad51d4706dd22f28e1e5e664828d2"},
|
||||
{file = "mypy-1.5.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:57b10c56016adce71fba6bc6e9fd45d8083f74361f629390c556738565af8eeb"},
|
||||
{file = "mypy-1.5.1-cp38-cp38-win_amd64.whl", hash = "sha256:ff0cedc84184115202475bbb46dd99f8dcb87fe24d5d0ddfc0fe6b8575c88d2f"},
|
||||
{file = "mypy-1.5.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:8f772942d372c8cbac575be99f9cc9d9fb3bd95c8bc2de6c01411e2c84ebca8a"},
|
||||
{file = "mypy-1.5.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:5d627124700b92b6bbaa99f27cbe615c8ea7b3402960f6372ea7d65faf376c14"},
|
||||
{file = "mypy-1.5.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:361da43c4f5a96173220eb53340ace68cda81845cd88218f8862dfb0adc8cddb"},
|
||||
{file = "mypy-1.5.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:330857f9507c24de5c5724235e66858f8364a0693894342485e543f5b07c8693"},
|
||||
{file = "mypy-1.5.1-cp39-cp39-win_amd64.whl", hash = "sha256:c543214ffdd422623e9fedd0869166c2f16affe4ba37463975043ef7d2ea8770"},
|
||||
{file = "mypy-1.5.1-py3-none-any.whl", hash = "sha256:f757063a83970d67c444f6e01d9550a7402322af3557ce7630d3c957386fa8f5"},
|
||||
{file = "mypy-1.5.1.tar.gz", hash = "sha256:b031b9601f1060bf1281feab89697324726ba0c0bae9d7cd7ab4b690940f0b92"},
|
||||
{file = "mypy-1.6.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:091f53ff88cb093dcc33c29eee522c087a438df65eb92acd371161c1f4380ff0"},
|
||||
{file = "mypy-1.6.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:eb7ff4007865833c470a601498ba30462b7374342580e2346bf7884557e40531"},
|
||||
{file = "mypy-1.6.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:49499cf1e464f533fc45be54d20a6351a312f96ae7892d8e9f1708140e27ce41"},
|
||||
{file = "mypy-1.6.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:4c192445899c69f07874dabda7e931b0cc811ea055bf82c1ababf358b9b2a72c"},
|
||||
{file = "mypy-1.6.0-cp310-cp310-win_amd64.whl", hash = "sha256:3df87094028e52766b0a59a3e46481bb98b27986ed6ded6a6cc35ecc75bb9182"},
|
||||
{file = "mypy-1.6.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:3c8835a07b8442da900db47ccfda76c92c69c3a575872a5b764332c4bacb5a0a"},
|
||||
{file = "mypy-1.6.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:24f3de8b9e7021cd794ad9dfbf2e9fe3f069ff5e28cb57af6f873ffec1cb0425"},
|
||||
{file = "mypy-1.6.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:856bad61ebc7d21dbc019b719e98303dc6256cec6dcc9ebb0b214b81d6901bd8"},
|
||||
{file = "mypy-1.6.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:89513ddfda06b5c8ebd64f026d20a61ef264e89125dc82633f3c34eeb50e7d60"},
|
||||
{file = "mypy-1.6.0-cp311-cp311-win_amd64.whl", hash = "sha256:9f8464ed410ada641c29f5de3e6716cbdd4f460b31cf755b2af52f2d5ea79ead"},
|
||||
{file = "mypy-1.6.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:971104bcb180e4fed0d7bd85504c9036346ab44b7416c75dd93b5c8c6bb7e28f"},
|
||||
{file = "mypy-1.6.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:ab98b8f6fdf669711f3abe83a745f67f50e3cbaea3998b90e8608d2b459fd566"},
|
||||
{file = "mypy-1.6.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1a69db3018b87b3e6e9dd28970f983ea6c933800c9edf8c503c3135b3274d5ad"},
|
||||
{file = "mypy-1.6.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:dccd850a2e3863891871c9e16c54c742dba5470f5120ffed8152956e9e0a5e13"},
|
||||
{file = "mypy-1.6.0-cp312-cp312-win_amd64.whl", hash = "sha256:f8598307150b5722854f035d2e70a1ad9cc3c72d392c34fffd8c66d888c90f17"},
|
||||
{file = "mypy-1.6.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:fea451a3125bf0bfe716e5d7ad4b92033c471e4b5b3e154c67525539d14dc15a"},
|
||||
{file = "mypy-1.6.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:e28d7b221898c401494f3b77db3bac78a03ad0a0fff29a950317d87885c655d2"},
|
||||
{file = "mypy-1.6.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e4b7a99275a61aa22256bab5839c35fe8a6887781862471df82afb4b445daae6"},
|
||||
{file = "mypy-1.6.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:7469545380dddce5719e3656b80bdfbb217cfe8dbb1438532d6abc754b828fed"},
|
||||
{file = "mypy-1.6.0-cp38-cp38-win_amd64.whl", hash = "sha256:7807a2a61e636af9ca247ba8494031fb060a0a744b9fee7de3a54bed8a753323"},
|
||||
{file = "mypy-1.6.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:d2dad072e01764823d4b2f06bc7365bb1d4b6c2f38c4d42fade3c8d45b0b4b67"},
|
||||
{file = "mypy-1.6.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:b19006055dde8a5425baa5f3b57a19fa79df621606540493e5e893500148c72f"},
|
||||
{file = "mypy-1.6.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:31eba8a7a71f0071f55227a8057468b8d2eb5bf578c8502c7f01abaec8141b2f"},
|
||||
{file = "mypy-1.6.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:8e0db37ac4ebb2fee7702767dfc1b773c7365731c22787cb99f507285014fcaf"},
|
||||
{file = "mypy-1.6.0-cp39-cp39-win_amd64.whl", hash = "sha256:c69051274762cccd13498b568ed2430f8d22baa4b179911ad0c1577d336ed849"},
|
||||
{file = "mypy-1.6.0-py3-none-any.whl", hash = "sha256:9e1589ca150a51d9d00bb839bfeca2f7a04f32cd62fad87a847bc0818e15d7dc"},
|
||||
{file = "mypy-1.6.0.tar.gz", hash = "sha256:4f3d27537abde1be6d5f2c96c29a454da333a2a271ae7d5bc7110e6d4b7beb3f"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
@@ -905,43 +905,43 @@ files = [
|
||||
|
||||
[[package]]
|
||||
name = "numpy"
|
||||
version = "1.26.0"
|
||||
version = "1.26.1"
|
||||
description = "Fundamental package for array computing in Python"
|
||||
optional = false
|
||||
python-versions = "<3.13,>=3.9"
|
||||
files = [
|
||||
{file = "numpy-1.26.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:f8db2f125746e44dce707dd44d4f4efeea8d7e2b43aace3f8d1f235cfa2733dd"},
|
||||
{file = "numpy-1.26.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:0621f7daf973d34d18b4e4bafb210bbaf1ef5e0100b5fa750bd9cde84c7ac292"},
|
||||
{file = "numpy-1.26.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:51be5f8c349fdd1a5568e72713a21f518e7d6707bcf8503b528b88d33b57dc68"},
|
||||
{file = "numpy-1.26.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:767254ad364991ccfc4d81b8152912e53e103ec192d1bb4ea6b1f5a7117040be"},
|
||||
{file = "numpy-1.26.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:436c8e9a4bdeeee84e3e59614d38c3dbd3235838a877af8c211cfcac8a80b8d3"},
|
||||
{file = "numpy-1.26.0-cp310-cp310-win32.whl", hash = "sha256:c2e698cb0c6dda9372ea98a0344245ee65bdc1c9dd939cceed6bb91256837896"},
|
||||
{file = "numpy-1.26.0-cp310-cp310-win_amd64.whl", hash = "sha256:09aaee96c2cbdea95de76ecb8a586cb687d281c881f5f17bfc0fb7f5890f6b91"},
|
||||
{file = "numpy-1.26.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:637c58b468a69869258b8ae26f4a4c6ff8abffd4a8334c830ffb63e0feefe99a"},
|
||||
{file = "numpy-1.26.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:306545e234503a24fe9ae95ebf84d25cba1fdc27db971aa2d9f1ab6bba19a9dd"},
|
||||
{file = "numpy-1.26.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8c6adc33561bd1d46f81131d5352348350fc23df4d742bb246cdfca606ea1208"},
|
||||
{file = "numpy-1.26.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e062aa24638bb5018b7841977c360d2f5917268d125c833a686b7cbabbec496c"},
|
||||
{file = "numpy-1.26.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:546b7dd7e22f3c6861463bebb000646fa730e55df5ee4a0224408b5694cc6148"},
|
||||
{file = "numpy-1.26.0-cp311-cp311-win32.whl", hash = "sha256:c0b45c8b65b79337dee5134d038346d30e109e9e2e9d43464a2970e5c0e93229"},
|
||||
{file = "numpy-1.26.0-cp311-cp311-win_amd64.whl", hash = "sha256:eae430ecf5794cb7ae7fa3808740b015aa80747e5266153128ef055975a72b99"},
|
||||
{file = "numpy-1.26.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:166b36197e9debc4e384e9c652ba60c0bacc216d0fc89e78f973a9760b503388"},
|
||||
{file = "numpy-1.26.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:f042f66d0b4ae6d48e70e28d487376204d3cbf43b84c03bac57e28dac6151581"},
|
||||
{file = "numpy-1.26.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e5e18e5b14a7560d8acf1c596688f4dfd19b4f2945b245a71e5af4ddb7422feb"},
|
||||
{file = "numpy-1.26.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7f6bad22a791226d0a5c7c27a80a20e11cfe09ad5ef9084d4d3fc4a299cca505"},
|
||||
{file = "numpy-1.26.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:4acc65dd65da28060e206c8f27a573455ed724e6179941edb19f97e58161bb69"},
|
||||
{file = "numpy-1.26.0-cp312-cp312-win32.whl", hash = "sha256:bb0d9a1aaf5f1cb7967320e80690a1d7ff69f1d47ebc5a9bea013e3a21faec95"},
|
||||
{file = "numpy-1.26.0-cp312-cp312-win_amd64.whl", hash = "sha256:ee84ca3c58fe48b8ddafdeb1db87388dce2c3c3f701bf447b05e4cfcc3679112"},
|
||||
{file = "numpy-1.26.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:4a873a8180479bc829313e8d9798d5234dfacfc2e8a7ac188418189bb8eafbd2"},
|
||||
{file = "numpy-1.26.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:914b28d3215e0c721dc75db3ad6d62f51f630cb0c277e6b3bcb39519bed10bd8"},
|
||||
{file = "numpy-1.26.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c78a22e95182fb2e7874712433eaa610478a3caf86f28c621708d35fa4fd6e7f"},
|
||||
{file = "numpy-1.26.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:86f737708b366c36b76e953c46ba5827d8c27b7a8c9d0f471810728e5a2fe57c"},
|
||||
{file = "numpy-1.26.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:b44e6a09afc12952a7d2a58ca0a2429ee0d49a4f89d83a0a11052da696440e49"},
|
||||
{file = "numpy-1.26.0-cp39-cp39-win32.whl", hash = "sha256:5671338034b820c8d58c81ad1dafc0ed5a00771a82fccc71d6438df00302094b"},
|
||||
{file = "numpy-1.26.0-cp39-cp39-win_amd64.whl", hash = "sha256:020cdbee66ed46b671429c7265cf00d8ac91c046901c55684954c3958525dab2"},
|
||||
{file = "numpy-1.26.0-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:0792824ce2f7ea0c82ed2e4fecc29bb86bee0567a080dacaf2e0a01fe7654369"},
|
||||
{file = "numpy-1.26.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7d484292eaeb3e84a51432a94f53578689ffdea3f90e10c8b203a99be5af57d8"},
|
||||
{file = "numpy-1.26.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:186ba67fad3c60dbe8a3abff3b67a91351100f2661c8e2a80364ae6279720299"},
|
||||
{file = "numpy-1.26.0.tar.gz", hash = "sha256:f93fc78fe8bf15afe2b8d6b6499f1c73953169fad1e9a8dd086cdff3190e7fdf"},
|
||||
{file = "numpy-1.26.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:82e871307a6331b5f09efda3c22e03c095d957f04bf6bc1804f30048d0e5e7af"},
|
||||
{file = "numpy-1.26.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:cdd9ec98f0063d93baeb01aad472a1a0840dee302842a2746a7a8e92968f9575"},
|
||||
{file = "numpy-1.26.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d78f269e0c4fd365fc2992c00353e4530d274ba68f15e968d8bc3c69ce5f5244"},
|
||||
{file = "numpy-1.26.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8ab9163ca8aeb7fd32fe93866490654d2f7dda4e61bc6297bf72ce07fdc02f67"},
|
||||
{file = "numpy-1.26.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:78ca54b2f9daffa5f323f34cdf21e1d9779a54073f0018a3094ab907938331a2"},
|
||||
{file = "numpy-1.26.1-cp310-cp310-win32.whl", hash = "sha256:d1cfc92db6af1fd37a7bb58e55c8383b4aa1ba23d012bdbba26b4bcca45ac297"},
|
||||
{file = "numpy-1.26.1-cp310-cp310-win_amd64.whl", hash = "sha256:d2984cb6caaf05294b8466966627e80bf6c7afd273279077679cb010acb0e5ab"},
|
||||
{file = "numpy-1.26.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:cd7837b2b734ca72959a1caf3309457a318c934abef7a43a14bb984e574bbb9a"},
|
||||
{file = "numpy-1.26.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:1c59c046c31a43310ad0199d6299e59f57a289e22f0f36951ced1c9eac3665b9"},
|
||||
{file = "numpy-1.26.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d58e8c51a7cf43090d124d5073bc29ab2755822181fcad978b12e144e5e5a4b3"},
|
||||
{file = "numpy-1.26.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6081aed64714a18c72b168a9276095ef9155dd7888b9e74b5987808f0dd0a974"},
|
||||
{file = "numpy-1.26.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:97e5d6a9f0702c2863aaabf19f0d1b6c2628fbe476438ce0b5ce06e83085064c"},
|
||||
{file = "numpy-1.26.1-cp311-cp311-win32.whl", hash = "sha256:b9d45d1dbb9de84894cc50efece5b09939752a2d75aab3a8b0cef6f3a35ecd6b"},
|
||||
{file = "numpy-1.26.1-cp311-cp311-win_amd64.whl", hash = "sha256:3649d566e2fc067597125428db15d60eb42a4e0897fc48d28cb75dc2e0454e53"},
|
||||
{file = "numpy-1.26.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:1d1bd82d539607951cac963388534da3b7ea0e18b149a53cf883d8f699178c0f"},
|
||||
{file = "numpy-1.26.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:afd5ced4e5a96dac6725daeb5242a35494243f2239244fad10a90ce58b071d24"},
|
||||
{file = "numpy-1.26.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a03fb25610ef560a6201ff06df4f8105292ba56e7cdd196ea350d123fc32e24e"},
|
||||
{file = "numpy-1.26.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dcfaf015b79d1f9f9c9fd0731a907407dc3e45769262d657d754c3a028586124"},
|
||||
{file = "numpy-1.26.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:e509cbc488c735b43b5ffea175235cec24bbc57b227ef1acc691725beb230d1c"},
|
||||
{file = "numpy-1.26.1-cp312-cp312-win32.whl", hash = "sha256:af22f3d8e228d84d1c0c44c1fbdeb80f97a15a0abe4f080960393a00db733b66"},
|
||||
{file = "numpy-1.26.1-cp312-cp312-win_amd64.whl", hash = "sha256:9f42284ebf91bdf32fafac29d29d4c07e5e9d1af862ea73686581773ef9e73a7"},
|
||||
{file = "numpy-1.26.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:bb894accfd16b867d8643fc2ba6c8617c78ba2828051e9a69511644ce86ce83e"},
|
||||
{file = "numpy-1.26.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:e44ccb93f30c75dfc0c3aa3ce38f33486a75ec9abadabd4e59f114994a9c4617"},
|
||||
{file = "numpy-1.26.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9696aa2e35cc41e398a6d42d147cf326f8f9d81befcb399bc1ed7ffea339b64e"},
|
||||
{file = "numpy-1.26.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a5b411040beead47a228bde3b2241100454a6abde9df139ed087bd73fc0a4908"},
|
||||
{file = "numpy-1.26.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:1e11668d6f756ca5ef534b5be8653d16c5352cbb210a5c2a79ff288e937010d5"},
|
||||
{file = "numpy-1.26.1-cp39-cp39-win32.whl", hash = "sha256:d1d2c6b7dd618c41e202c59c1413ef9b2c8e8a15f5039e344af64195459e3104"},
|
||||
{file = "numpy-1.26.1-cp39-cp39-win_amd64.whl", hash = "sha256:59227c981d43425ca5e5c01094d59eb14e8772ce6975d4b2fc1e106a833d5ae2"},
|
||||
{file = "numpy-1.26.1-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:06934e1a22c54636a059215d6da99e23286424f316fddd979f5071093b648668"},
|
||||
{file = "numpy-1.26.1-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:76ff661a867d9272cd2a99eed002470f46dbe0943a5ffd140f49be84f68ffc42"},
|
||||
{file = "numpy-1.26.1-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:6965888d65d2848e8768824ca8288db0a81263c1efccec881cb35a0d805fcd2f"},
|
||||
{file = "numpy-1.26.1.tar.gz", hash = "sha256:c8c6c72d4a9f831f328efb1312642a1cafafaa88981d9ab76368d50d07d93cbe"},
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -994,35 +994,35 @@ lint = ["lintrunner (>=0.10.0)", "lintrunner-adapters (>=0.3)"]
|
||||
|
||||
[[package]]
|
||||
name = "onnxruntime"
|
||||
version = "1.16.0"
|
||||
version = "1.16.1"
|
||||
description = "ONNX Runtime is a runtime accelerator for Machine Learning models"
|
||||
optional = true
|
||||
python-versions = "*"
|
||||
files = [
|
||||
{file = "onnxruntime-1.16.0-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:69c86ba3d90c166944c4a3c8a5b2a24a7bc45e68ae5997d83279af21ffd0f5f3"},
|
||||
{file = "onnxruntime-1.16.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:604a46aa2ad6a51f2fc4df1a984ea571a43aa02424aea93464c32ce02d23b3bb"},
|
||||
{file = "onnxruntime-1.16.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a40660516b382031279fb690fc3d068ad004173c2bd12bbdc0bd0fe01ef8b7c3"},
|
||||
{file = "onnxruntime-1.16.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:349fd9c7875c1a76609d45b079484f8059adfb1fb87a30506934fb667ceab249"},
|
||||
{file = "onnxruntime-1.16.0-cp310-cp310-win32.whl", hash = "sha256:22c9e2f1a1f15b41b01195cd2520c013c22228efc4795ae4118048ea4118aad2"},
|
||||
{file = "onnxruntime-1.16.0-cp310-cp310-win_amd64.whl", hash = "sha256:b9667a131abfd226a728cc1c1ecf5cc5afa4fff37422f95a84bc22f7c175b57f"},
|
||||
{file = "onnxruntime-1.16.0-cp311-cp311-macosx_10_15_x86_64.whl", hash = "sha256:f7b292726a1f3fa4a483d7e902da083a5889a86a860dbc3a6479988cad342578"},
|
||||
{file = "onnxruntime-1.16.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:61eaf288a2482c5561f620fb686c80c32709e92724bbb59a5e4a0d349429e205"},
|
||||
{file = "onnxruntime-1.16.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5fe2239d5821d5501eecccfe5c408485591b5d73eb76a61491a8f78179c2e65a"},
|
||||
{file = "onnxruntime-1.16.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5a4924604fcdf1704b7f7e087b4c0b0e181c58367a687da55b1aec2705631943"},
|
||||
{file = "onnxruntime-1.16.0-cp311-cp311-win32.whl", hash = "sha256:55d8456f1ab28c32aec9c478b7638ed145102b03bb9b719b79e065ffc5de9c72"},
|
||||
{file = "onnxruntime-1.16.0-cp311-cp311-win_amd64.whl", hash = "sha256:c2a53ffd456187028c841ac7ed0d83b4c2b7e48bd2b1cf2a42d253ecf1e97cb3"},
|
||||
{file = "onnxruntime-1.16.0-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:bf5769aa4095cfe2503307867fa95b5f73732909ee21b67fe24da443af445925"},
|
||||
{file = "onnxruntime-1.16.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:c0974deadf11ddab201d915a10517be00fa9d6816def56fa374e4c1a0008985a"},
|
||||
{file = "onnxruntime-1.16.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:99dccf1d2eba5ecd7b6c0e8e80d92d0030291f3506726c156e018a4d7a187c6f"},
|
||||
{file = "onnxruntime-1.16.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0170ed05d3a8a7c24fe01fc262a6bc603837751f3bb273df7006a2da73f37fff"},
|
||||
{file = "onnxruntime-1.16.0-cp38-cp38-win32.whl", hash = "sha256:5ecd38e98ccdcbbaa7e529e96852f4c1c136559802354b76378d9a19532018ee"},
|
||||
{file = "onnxruntime-1.16.0-cp38-cp38-win_amd64.whl", hash = "sha256:1c585c60e9541a9bd4fb319ba9a3ef6122a28dcf4f3dbcdf014df44570cad6f8"},
|
||||
{file = "onnxruntime-1.16.0-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:efe59c1e51ad647fb18860233f5971e309961d09ca10697170ef9b7d9fa728f4"},
|
||||
{file = "onnxruntime-1.16.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:e3c9a9cccab8f6512a0c0207b2816dd8864f2f720f6e9df5cf01e30c4f80194f"},
|
||||
{file = "onnxruntime-1.16.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dcf16a252308ec6e0737db7028b63fed0ac28fbad134f86216c0dfb051a31f38"},
|
||||
{file = "onnxruntime-1.16.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f533aa90ee7189e88b6b612d6adae7d290971090598cfd47ce034ab0d106fc9c"},
|
||||
{file = "onnxruntime-1.16.0-cp39-cp39-win32.whl", hash = "sha256:306c7f5d8a0c24c65afb34f7deb0bc526defde2249e53538f1dce083945a2d6e"},
|
||||
{file = "onnxruntime-1.16.0-cp39-cp39-win_amd64.whl", hash = "sha256:df8a00a7b057ba497e2822175cc68731d84b89a6d50a3a2a3ec51e98e9c91125"},
|
||||
{file = "onnxruntime-1.16.1-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:28b2c7f444b4119950b69370801cd66067f403d19cbaf2a444735d7c269cce4a"},
|
||||
{file = "onnxruntime-1.16.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:c24e04f33e7899f6aebb03ed51e51d346c1f906b05c5569d58ac9a12d38a2f58"},
|
||||
{file = "onnxruntime-1.16.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9fa93b166f2d97063dc9f33c5118c5729a4a5dd5617296b6dbef42f9047b3e81"},
|
||||
{file = "onnxruntime-1.16.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:042dd9201b3016ee18f8f8bc4609baf11ff34ca1ff489c0a46bcd30919bf883d"},
|
||||
{file = "onnxruntime-1.16.1-cp310-cp310-win32.whl", hash = "sha256:c20aa0591f305012f1b21aad607ed96917c86ae7aede4a4dd95824b3d124ceb7"},
|
||||
{file = "onnxruntime-1.16.1-cp310-cp310-win_amd64.whl", hash = "sha256:5581873e578917bea76d6434ee7337e28195d03488dcf72d161d08e9398c6249"},
|
||||
{file = "onnxruntime-1.16.1-cp311-cp311-macosx_10_15_x86_64.whl", hash = "sha256:ef8c0c8abf5f309aa1caf35941380839dc5f7a2fa53da533be4a3f254993f120"},
|
||||
{file = "onnxruntime-1.16.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:e680380bea35a137cbc3efd67a17486e96972901192ad3026ee79c8d8fe264f7"},
|
||||
{file = "onnxruntime-1.16.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5e62cc38ce1a669013d0a596d984762dc9c67c56f60ecfeee0d5ad36da5863f6"},
|
||||
{file = "onnxruntime-1.16.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:025c7a4d57bd2e63b8a0f84ad3df53e419e3df1cc72d63184f2aae807b17c13c"},
|
||||
{file = "onnxruntime-1.16.1-cp311-cp311-win32.whl", hash = "sha256:9ad074057fa8d028df248b5668514088cb0937b6ac5954073b7fb9b2891ffc8c"},
|
||||
{file = "onnxruntime-1.16.1-cp311-cp311-win_amd64.whl", hash = "sha256:d5e43a3478bffc01f817ecf826de7b25a2ca1bca8547d70888594ab80a77ad24"},
|
||||
{file = "onnxruntime-1.16.1-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:3aef4d70b0930e29a8943eab248cd1565664458d3a62b2276bd11181f28fd0a3"},
|
||||
{file = "onnxruntime-1.16.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:55a7b843a57c8ca0c8ff169428137958146081d5d76f1a6dd444c4ffcd37c3c2"},
|
||||
{file = "onnxruntime-1.16.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:62c631af1941bf3b5f7d063d24c04aacce8cff0794e157c497e315e89ac5ad7b"},
|
||||
{file = "onnxruntime-1.16.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5671f296c3d5c233f601e97a10ab5a1dd8e65ba35c7b7b0c253332aba9dff330"},
|
||||
{file = "onnxruntime-1.16.1-cp38-cp38-win32.whl", hash = "sha256:eb3802305023dd05e16848d4e22b41f8147247894309c0c27122aaa08793b3d2"},
|
||||
{file = "onnxruntime-1.16.1-cp38-cp38-win_amd64.whl", hash = "sha256:fecfb07443d09d271b1487f401fbdf1ba0c829af6fd4fe8f6af25f71190e7eb9"},
|
||||
{file = "onnxruntime-1.16.1-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:de3e12094234db6545c67adbf801874b4eb91e9f299bda34c62967ef0050960f"},
|
||||
{file = "onnxruntime-1.16.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:ff723c2a5621b5e7103f3be84d5aae1e03a20621e72219dddceae81f65f240af"},
|
||||
{file = "onnxruntime-1.16.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:14a7fb3073aaf6b462e3d7fb433320f7700558a8892e5021780522dc4574292a"},
|
||||
{file = "onnxruntime-1.16.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:963159f1f699b0454cd72fcef3276c8a1aab9389a7b301bcd8e320fb9d9e8597"},
|
||||
{file = "onnxruntime-1.16.1-cp39-cp39-win32.whl", hash = "sha256:85771adb75190db9364b25ddec353ebf07635b83eb94b64ed014f1f6d57a3857"},
|
||||
{file = "onnxruntime-1.16.1-cp39-cp39-win_amd64.whl", hash = "sha256:d32d2b30799c1f950123c60ae8390818381fd5f88bdf3627eeca10071c155dc5"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
@@ -1301,13 +1301,13 @@ files = [
|
||||
|
||||
[[package]]
|
||||
name = "pyright"
|
||||
version = "1.1.329"
|
||||
version = "1.1.331"
|
||||
description = "Command line wrapper for pyright"
|
||||
optional = false
|
||||
python-versions = ">=3.7"
|
||||
files = [
|
||||
{file = "pyright-1.1.329-py3-none-any.whl", hash = "sha256:c16f88a7ac14ddd0513e62fec56d69c37e3c6b412161ad16aa23a9c7e3dabaf4"},
|
||||
{file = "pyright-1.1.329.tar.gz", hash = "sha256:5baf82ff5ecb8c8b3ac400e8536348efbde0b94a09d83d5b440c0d143fd151a8"},
|
||||
{file = "pyright-1.1.331-py3-none-any.whl", hash = "sha256:d200a01794e7f2a04d5042a6c3abee36ce92780287d3037edfc3604d45488f0e"},
|
||||
{file = "pyright-1.1.331.tar.gz", hash = "sha256:c3e7b86154cac86c3bd61ea0f963143d001c201e246825aaabdddfcce5d04293"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
@@ -1359,13 +1359,13 @@ testing = ["coverage (>=6.2)", "flaky (>=3.5.0)", "hypothesis (>=5.7.1)", "mypy
|
||||
|
||||
[[package]]
|
||||
name = "pytest-timeout"
|
||||
version = "2.1.0"
|
||||
version = "2.2.0"
|
||||
description = "pytest plugin to abort hanging tests"
|
||||
optional = false
|
||||
python-versions = ">=3.6"
|
||||
python-versions = ">=3.7"
|
||||
files = [
|
||||
{file = "pytest-timeout-2.1.0.tar.gz", hash = "sha256:c07ca07404c612f8abbe22294b23c368e2e5104b521c1790195561f37e1ac3d9"},
|
||||
{file = "pytest_timeout-2.1.0-py3-none-any.whl", hash = "sha256:f6f50101443ce70ad325ceb4473c4255e9d74e3c7cd0ef827309dfa4c0d975c6"},
|
||||
{file = "pytest-timeout-2.2.0.tar.gz", hash = "sha256:3b0b95dabf3cb50bac9ef5ca912fa0cfc286526af17afc806824df20c2f72c90"},
|
||||
{file = "pytest_timeout-2.2.0-py3-none-any.whl", hash = "sha256:bde531e096466f49398a59f2dde76fa78429a09a12411466f88a07213e220de2"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
@@ -1764,4 +1764,4 @@ fastembed = ["fastembed"]
|
||||
[metadata]
|
||||
lock-version = "2.0"
|
||||
python-versions = ">=3.8,<3.13"
|
||||
content-hash = "f491a0d3e5d7cd8cc90987274aa39ce8e91c6a0febcd5627ea874c470a20c79e"
|
||||
content-hash = "0df37e1fa4e332c61077b4b1a538285fb21b5d3d18d01859a886a78751669fed"
|
||||
|
||||
@@ -27,7 +27,7 @@ grpcio-tools = ">=1.41.0"
|
||||
urllib3 = "^1.26.14"
|
||||
portalocker = "^2.7.0"
|
||||
fastembed = [
|
||||
{ version = "0.0.5", optional = true, python = "<3.12" }
|
||||
{ version = "0.1.1", optional = true, python = "<3.12" }
|
||||
]
|
||||
|
||||
[tool.poetry.group.dev.dependencies]
|
||||
|
||||
@@ -1,3 +1,14 @@
|
||||
# ****** WARNING: THIS FILE IS AUTOGENERATED ******
|
||||
#
|
||||
# This file is autogenerated. Do not edit it manually.
|
||||
# To regenerate this file, use
|
||||
#
|
||||
# ```
|
||||
# bash -x tools/generate_async_client.sh
|
||||
# ```
|
||||
#
|
||||
# ****** WARNING: THIS FILE IS AUTOGENERATED ******
|
||||
|
||||
from typing import Any, Dict, Iterable, List, Mapping, Optional, Sequence, Tuple, Union
|
||||
|
||||
from qdrant_client.conversions import common_types as types
|
||||
|
||||
@@ -1,3 +1,14 @@
|
||||
# ****** WARNING: THIS FILE IS AUTOGENERATED ******
|
||||
#
|
||||
# This file is autogenerated. Do not edit it manually.
|
||||
# To regenerate this file, use
|
||||
#
|
||||
# ```
|
||||
# bash -x tools/generate_async_client.sh
|
||||
# ```
|
||||
#
|
||||
# ****** WARNING: THIS FILE IS AUTOGENERATED ******
|
||||
|
||||
from typing import Any, Dict, Iterable, List, Mapping, Optional, Sequence, Tuple, Union
|
||||
|
||||
from qdrant_client import grpc as grpc
|
||||
|
||||
@@ -1,3 +1,14 @@
|
||||
# ****** WARNING: THIS FILE IS AUTOGENERATED ******
|
||||
#
|
||||
# This file is autogenerated. Do not edit it manually.
|
||||
# To regenerate this file, use
|
||||
#
|
||||
# ```
|
||||
# bash -x tools/generate_async_client.sh
|
||||
# ```
|
||||
#
|
||||
# ****** WARNING: THIS FILE IS AUTOGENERATED ******
|
||||
|
||||
import uuid
|
||||
from typing import Any, Dict, Iterable, List, Optional, Tuple, Union
|
||||
|
||||
@@ -5,6 +16,7 @@ from pydantic import BaseModel
|
||||
|
||||
from qdrant_client.async_client_base import AsyncQdrantBase
|
||||
from qdrant_client.conversions import common_types as types
|
||||
from qdrant_client.fastembed_common import QueryResponse
|
||||
from qdrant_client.http import models
|
||||
from qdrant_client.uploader.uploader import iter_batch
|
||||
|
||||
@@ -16,17 +28,12 @@ SUPPORTED_EMBEDDING_MODELS: Dict[str, Tuple[int, models.Distance]] = {
|
||||
"BAAI/bge-base-en": (768, models.Distance.COSINE),
|
||||
"sentence-transformers/all-MiniLM-L6-v2": (384, models.Distance.COSINE),
|
||||
"BAAI/bge-small-en": (384, models.Distance.COSINE),
|
||||
"BAAI/bge-small-en-v1.5": (384, models.Distance.COSINE),
|
||||
"BAAI/bge-base-en-v1.5": (768, models.Distance.COSINE),
|
||||
"intfloat/multilingual-e5-large": (1024, models.Distance.COSINE),
|
||||
}
|
||||
|
||||
|
||||
class QueryResponse(BaseModel, extra="forbid"):
|
||||
id: Union[str, int]
|
||||
embedding: Optional[List[float]]
|
||||
metadata: Dict[str, Any]
|
||||
document: str
|
||||
score: float
|
||||
|
||||
|
||||
class AsyncQdrantFastembedMixin(AsyncQdrantBase):
|
||||
DEFAULT_EMBEDDING_MODEL = "BAAI/bge-small-en"
|
||||
embedding_models: Dict[str, "DefaultEmbedding"] = {}
|
||||
@@ -82,27 +89,37 @@ class AsyncQdrantFastembedMixin(AsyncQdrantBase):
|
||||
|
||||
def _embed_documents(
|
||||
self,
|
||||
documents: List[str],
|
||||
documents: Iterable[str],
|
||||
embedding_model_name: str = DEFAULT_EMBEDDING_MODEL,
|
||||
batch_size: int = 32,
|
||||
embed_type: str = "default",
|
||||
) -> Iterable[List[float]]:
|
||||
parallel: Optional[int] = None,
|
||||
) -> Iterable[Tuple[str, List[float]]]:
|
||||
embedding_model = self._get_or_init_model(model_name=embedding_model_name)
|
||||
for batch_docs in iter_batch(documents, batch_size):
|
||||
if embed_type == "passage":
|
||||
vectors_batches = embedding_model.passage_embed(batch_docs, batch_size=batch_size)
|
||||
vectors_batches = embedding_model.passage_embed(
|
||||
batch_docs, batch_size=batch_size, parallel=parallel
|
||||
)
|
||||
elif embed_type == "query":
|
||||
vectors_batches = (
|
||||
list(embedding_model.query_embed(query=query))[0] for query in batch_docs
|
||||
)
|
||||
elif embed_type == "default":
|
||||
vectors_batches = embedding_model.embed(batch_docs, batch_size=batch_size)
|
||||
vectors_batches = embedding_model.embed(
|
||||
batch_docs, batch_size=batch_size, parallel=parallel
|
||||
)
|
||||
else:
|
||||
raise ValueError(f"Unknown embed type: {embed_type}")
|
||||
for vector in vectors_batches:
|
||||
yield vector.tolist()
|
||||
for vector, doc in zip(vectors_batches, batch_docs):
|
||||
yield (doc, vector.tolist())
|
||||
|
||||
def _get_vector_field_name(self) -> str:
|
||||
def get_vector_field_name(self) -> str:
|
||||
"""
|
||||
Returns name of the vector field in qdrant collection, used by current fastembed model.
|
||||
Returns:
|
||||
Name of the vector field.
|
||||
"""
|
||||
model_name = self.embedding_model_name.split("/")[-1].lower()
|
||||
return f"fast-{model_name}"
|
||||
|
||||
@@ -113,7 +130,7 @@ class AsyncQdrantFastembedMixin(AsyncQdrantBase):
|
||||
for scored_point in scored_points:
|
||||
embedding = None
|
||||
if scored_point.vector is not None:
|
||||
embedding = scored_point.vector.get(self._get_vector_field_name(), None)
|
||||
embedding = scored_point.vector.get(self.get_vector_field_name(), None)
|
||||
response.append(
|
||||
QueryResponse(
|
||||
id=scored_point.id,
|
||||
@@ -125,15 +142,62 @@ class AsyncQdrantFastembedMixin(AsyncQdrantBase):
|
||||
)
|
||||
return response
|
||||
|
||||
def _records_iterator(
|
||||
self,
|
||||
ids: Optional[Iterable[models.ExtendedPointId]],
|
||||
metadata: Optional[Iterable[Dict[str, Any]]],
|
||||
encoded_docs: Iterable[Tuple[str, List[float]]],
|
||||
ids_accumulator: list,
|
||||
) -> Iterable[models.Record]:
|
||||
if ids is None:
|
||||
ids = iter(lambda: uuid.uuid4().hex, None)
|
||||
if metadata is None:
|
||||
metadata = iter(lambda: {}, None)
|
||||
vector_name = self.get_vector_field_name()
|
||||
for idx, meta, (doc, vector) in zip(ids, metadata, encoded_docs):
|
||||
ids_accumulator.append(idx)
|
||||
payload = {"document": doc, **meta}
|
||||
yield models.Record(id=idx, payload=payload, vector={vector_name: vector})
|
||||
|
||||
def get_fastembed_vector_params(
|
||||
self,
|
||||
on_disk: Optional[bool] = None,
|
||||
quantization_config: Optional[models.QuantizationConfig] = None,
|
||||
hnsw_config: Optional[models.HnswConfigDiff] = None,
|
||||
) -> Dict[str, models.VectorParams]:
|
||||
"""
|
||||
Generates vector configuration, compatible with fastembed models.
|
||||
|
||||
Args:
|
||||
on_disk: if True, vectors will be stored on disk. If None, default value will be used.
|
||||
quantization_config: Quantization configuration. If None, quantization will be disabled.
|
||||
hnsw_config: HNSW configuration. If None, default configuration will be used.
|
||||
|
||||
Returns:
|
||||
Configuration for `vectors_config` argument in `create_collection` method.
|
||||
"""
|
||||
vector_field_name = self.get_vector_field_name()
|
||||
embeddings_size, distance = self._get_model_params(model_name=self.embedding_model_name)
|
||||
return {
|
||||
vector_field_name: models.VectorParams(
|
||||
size=embeddings_size,
|
||||
distance=distance,
|
||||
on_disk=on_disk,
|
||||
quantization_config=quantization_config,
|
||||
hnsw_config=hnsw_config,
|
||||
)
|
||||
}
|
||||
|
||||
async def add(
|
||||
self,
|
||||
collection_name: str,
|
||||
documents: List[str],
|
||||
metadata: Optional[List[Dict[str, Any]]] = None,
|
||||
ids: Optional[List[models.ExtendedPointId]] = None,
|
||||
documents: Iterable[str],
|
||||
metadata: Optional[Iterable[Dict[str, Any]]] = None,
|
||||
ids: Optional[Iterable[models.ExtendedPointId]] = None,
|
||||
batch_size: int = 32,
|
||||
parallel: Optional[int] = None,
|
||||
**kwargs: Any,
|
||||
) -> List[str]:
|
||||
) -> List[Union[str, int]]:
|
||||
"""
|
||||
Adds text documents into qdrant collection.
|
||||
If collection does not exist, it will be created with default parameters.
|
||||
@@ -145,48 +209,40 @@ class AsyncQdrantFastembedMixin(AsyncQdrantBase):
|
||||
Args:
|
||||
collection_name (str):
|
||||
Name of the collection to add documents to.
|
||||
documents (List[str]):
|
||||
documents (Iterable[str]):
|
||||
List of documents to embed and add to the collection.
|
||||
metadata (List[Dict[str, Any]], optional):
|
||||
metadata (Iterable[Dict[str, Any]], optional):
|
||||
List of metadata dicts. Defaults to None.
|
||||
ids (List[models.ExtendedPointId], optional):
|
||||
ids (Iterable[models.ExtendedPointId], optional):
|
||||
List of ids to assign to documents.
|
||||
If not specified, UUIDs will be generated. Defaults to None.
|
||||
batch_size (int, optional):
|
||||
How many documents to embed and upload in single request. Defaults to 32.
|
||||
parallel (Optional[int], optional):
|
||||
How many parallel workers to use for embedding. Defaults to None.
|
||||
If number is specified, data-parallel process will be used.
|
||||
|
||||
Raises:
|
||||
ImportError: If fastembed is not installed.
|
||||
|
||||
Returns:
|
||||
List[str]: List of UUIDs of added documents. UUIDs are randomly generated on client side.
|
||||
List of IDs of added documents. If no ids provided, UUIDs will be randomly generated on client side.
|
||||
|
||||
"""
|
||||
embeddings = self._embed_documents(
|
||||
encoded_docs = self._embed_documents(
|
||||
documents=documents,
|
||||
embedding_model_name=self.embedding_model_name,
|
||||
batch_size=batch_size,
|
||||
embed_type="passage",
|
||||
parallel=parallel,
|
||||
)
|
||||
if metadata is None:
|
||||
metadata = [{} for _ in range(len(documents))]
|
||||
else:
|
||||
assert len(metadata) == len(
|
||||
documents
|
||||
), f"metadata length mismatch: {len(metadata)} != {len(documents)}"
|
||||
payloads = ({"document": doc, **metadata} for (doc, metadata) in zip(documents, metadata))
|
||||
if ids is None:
|
||||
ids = [uuid.uuid4().hex for _ in range(len(documents))]
|
||||
(embeddings_size, distance) = self._get_model_params(model_name=self.embedding_model_name)
|
||||
vector_field_name = self._get_vector_field_name()
|
||||
embeddings_size, distance = self._get_model_params(model_name=self.embedding_model_name)
|
||||
vector_field_name = self.get_vector_field_name()
|
||||
try:
|
||||
collection_info = await self.get_collection(collection_name=collection_name)
|
||||
except Exception:
|
||||
await self.create_collection(
|
||||
collection_name=collection_name,
|
||||
vectors_config={
|
||||
vector_field_name: models.VectorParams(size=embeddings_size, distance=distance)
|
||||
},
|
||||
collection_name=collection_name, vectors_config=self.get_fastembed_vector_params()
|
||||
)
|
||||
collection_info = await self.get_collection(collection_name=collection_name)
|
||||
assert isinstance(
|
||||
@@ -202,12 +258,19 @@ class AsyncQdrantFastembedMixin(AsyncQdrantBase):
|
||||
assert (
|
||||
distance == vector_params.distance
|
||||
), f"Distance mismatch: {distance} != {vector_params.distance}"
|
||||
records = (
|
||||
models.Record(id=idx, payload=payload, vector={vector_field_name: vector})
|
||||
for (idx, payload, vector) in zip(ids, payloads, embeddings)
|
||||
inserted_ids: list = []
|
||||
records = self._records_iterator(
|
||||
ids=ids, metadata=metadata, encoded_docs=encoded_docs, ids_accumulator=inserted_ids
|
||||
)
|
||||
self.upload_records(collection_name=collection_name, records=records, wait=True, **kwargs)
|
||||
return ids
|
||||
self.upload_records(
|
||||
collection_name=collection_name,
|
||||
records=records,
|
||||
wait=True,
|
||||
parallel=parallel or 1,
|
||||
batch_size=batch_size,
|
||||
**kwargs,
|
||||
)
|
||||
return inserted_ids
|
||||
|
||||
async def query(
|
||||
self,
|
||||
@@ -244,7 +307,7 @@ class AsyncQdrantFastembedMixin(AsyncQdrantBase):
|
||||
await self.search(
|
||||
collection_name=collection_name,
|
||||
query_vector=models.NamedVector(
|
||||
name=self._get_vector_field_name(), vector=query_vector.tolist()
|
||||
name=self.get_vector_field_name(), vector=query_vector.tolist()
|
||||
),
|
||||
query_filter=query_filter,
|
||||
limit=limit,
|
||||
@@ -290,7 +353,7 @@ class AsyncQdrantFastembedMixin(AsyncQdrantBase):
|
||||
for vector in query_vectors:
|
||||
request = models.SearchRequest(
|
||||
vector=models.NamedVector(
|
||||
name=self._get_vector_field_name(), vector=vector.tolist()
|
||||
name=self.get_vector_field_name(), vector=vector.tolist()
|
||||
),
|
||||
filter=query_filter,
|
||||
limit=limit,
|
||||
|
||||
@@ -1,3 +1,14 @@
|
||||
# ****** WARNING: THIS FILE IS AUTOGENERATED ******
|
||||
#
|
||||
# This file is autogenerated. Do not edit it manually.
|
||||
# To regenerate this file, use
|
||||
#
|
||||
# ```
|
||||
# bash -x tools/generate_async_client.sh
|
||||
# ```
|
||||
#
|
||||
# ****** WARNING: THIS FILE IS AUTOGENERATED ******
|
||||
|
||||
import logging
|
||||
import warnings
|
||||
from multiprocessing import get_all_start_methods
|
||||
@@ -69,7 +80,7 @@ class AsyncQdrantRemote(AsyncQdrantBase):
|
||||
if url.startswith("localhost"):
|
||||
url = f"//{url}"
|
||||
parsed_url: Url = parse_url(url)
|
||||
(self._host, self._port) = (parsed_url.host, parsed_url.port)
|
||||
self._host, self._port = (parsed_url.host, parsed_url.port)
|
||||
if parsed_url.scheme:
|
||||
self._https = parsed_url.scheme == "https"
|
||||
self._scheme = parsed_url.scheme
|
||||
@@ -138,7 +149,7 @@ class AsyncQdrantRemote(AsyncQdrantBase):
|
||||
@staticmethod
|
||||
def _parse_url(url: str) -> Tuple[Optional[str], str, Optional[int], Optional[str]]:
|
||||
parse_result: Url = parse_url(url)
|
||||
(scheme, host, port, prefix) = (
|
||||
scheme, host, port, prefix = (
|
||||
parse_result.scheme,
|
||||
parse_result.host,
|
||||
parse_result.port,
|
||||
@@ -937,7 +948,7 @@ class AsyncQdrantRemote(AsyncQdrantBase):
|
||||
assert grpc_result is not None, "Delete vectors returned None result"
|
||||
return GrpcToRest.convert_update_result(grpc_result)
|
||||
else:
|
||||
(_points, _filter) = self._try_argument_to_rest_points_and_filter(points)
|
||||
_points, _filter = self._try_argument_to_rest_points_and_filter(points)
|
||||
return (
|
||||
await self.openapi_client.points_api.delete_vectors(
|
||||
collection_name=collection_name,
|
||||
@@ -1157,7 +1168,7 @@ class AsyncQdrantRemote(AsyncQdrantBase):
|
||||
).result
|
||||
)
|
||||
else:
|
||||
(_points, _filter) = self._try_argument_to_rest_points_and_filter(points)
|
||||
_points, _filter = self._try_argument_to_rest_points_and_filter(points)
|
||||
result: Optional[types.UpdateResult] = (
|
||||
await self.openapi_client.points_api.set_payload(
|
||||
collection_name=collection_name,
|
||||
@@ -1197,7 +1208,7 @@ class AsyncQdrantRemote(AsyncQdrantBase):
|
||||
).result
|
||||
)
|
||||
else:
|
||||
(_points, _filter) = self._try_argument_to_rest_points_and_filter(points)
|
||||
_points, _filter = self._try_argument_to_rest_points_and_filter(points)
|
||||
result: Optional[types.UpdateResult] = (
|
||||
await self.openapi_client.points_api.overwrite_payload(
|
||||
collection_name=collection_name,
|
||||
@@ -1237,7 +1248,7 @@ class AsyncQdrantRemote(AsyncQdrantBase):
|
||||
).result
|
||||
)
|
||||
else:
|
||||
(_points, _filter) = self._try_argument_to_rest_points_and_filter(points)
|
||||
_points, _filter = self._try_argument_to_rest_points_and_filter(points)
|
||||
result: Optional[types.UpdateResult] = (
|
||||
await self.openapi_client.points_api.delete_payload(
|
||||
collection_name=collection_name,
|
||||
|
||||
11
qdrant_client/fastembed_common.py
Normal file
11
qdrant_client/fastembed_common.py
Normal file
@@ -0,0 +1,11 @@
|
||||
from typing import Any, Dict, List, Optional, Union
|
||||
|
||||
from pydantic import BaseModel
|
||||
|
||||
|
||||
class QueryResponse(BaseModel, extra="forbid"): # type: ignore
|
||||
id: Union[str, int]
|
||||
embedding: Optional[List[float]]
|
||||
metadata: Dict[str, Any]
|
||||
document: str
|
||||
score: float
|
||||
@@ -5,6 +5,7 @@ from pydantic import BaseModel
|
||||
|
||||
from qdrant_client.client_base import QdrantBase
|
||||
from qdrant_client.conversions import common_types as types
|
||||
from qdrant_client.fastembed_common import QueryResponse
|
||||
from qdrant_client.http import models
|
||||
from qdrant_client.uploader.uploader import iter_batch
|
||||
|
||||
@@ -17,17 +18,12 @@ SUPPORTED_EMBEDDING_MODELS: Dict[str, Tuple[int, models.Distance]] = {
|
||||
"BAAI/bge-base-en": (768, models.Distance.COSINE),
|
||||
"sentence-transformers/all-MiniLM-L6-v2": (384, models.Distance.COSINE),
|
||||
"BAAI/bge-small-en": (384, models.Distance.COSINE),
|
||||
"BAAI/bge-small-en-v1.5": (384, models.Distance.COSINE),
|
||||
"BAAI/bge-base-en-v1.5": (768, models.Distance.COSINE),
|
||||
"intfloat/multilingual-e5-large": (1024, models.Distance.COSINE),
|
||||
}
|
||||
|
||||
|
||||
class QueryResponse(BaseModel, extra="forbid"): # type: ignore
|
||||
id: Union[str, int]
|
||||
embedding: Optional[List[float]]
|
||||
metadata: Dict[str, Any]
|
||||
document: str
|
||||
score: float
|
||||
|
||||
|
||||
class QdrantFastembedMixin(QdrantBase):
|
||||
DEFAULT_EMBEDDING_MODEL = "BAAI/bge-small-en"
|
||||
|
||||
@@ -92,27 +88,37 @@ class QdrantFastembedMixin(QdrantBase):
|
||||
|
||||
def _embed_documents(
|
||||
self,
|
||||
documents: List[str],
|
||||
documents: Iterable[str],
|
||||
embedding_model_name: str = DEFAULT_EMBEDDING_MODEL,
|
||||
batch_size: int = 32,
|
||||
embed_type: str = "default",
|
||||
) -> Iterable[List[float]]:
|
||||
parallel: Optional[int] = None,
|
||||
) -> Iterable[Tuple[str, List[float]]]:
|
||||
embedding_model = self._get_or_init_model(model_name=embedding_model_name)
|
||||
for batch_docs in iter_batch(documents, batch_size):
|
||||
if embed_type == "passage":
|
||||
vectors_batches = embedding_model.passage_embed(batch_docs, batch_size=batch_size)
|
||||
vectors_batches = embedding_model.passage_embed(
|
||||
batch_docs, batch_size=batch_size, parallel=parallel
|
||||
)
|
||||
elif embed_type == "query":
|
||||
vectors_batches = (
|
||||
list(embedding_model.query_embed(query=query))[0] for query in batch_docs
|
||||
)
|
||||
elif embed_type == "default":
|
||||
vectors_batches = embedding_model.embed(batch_docs, batch_size=batch_size)
|
||||
vectors_batches = embedding_model.embed(
|
||||
batch_docs, batch_size=batch_size, parallel=parallel
|
||||
)
|
||||
else:
|
||||
raise ValueError(f"Unknown embed type: {embed_type}")
|
||||
for vector in vectors_batches:
|
||||
yield vector.tolist()
|
||||
for vector, doc in zip(vectors_batches, batch_docs):
|
||||
yield doc, vector.tolist()
|
||||
|
||||
def _get_vector_field_name(self) -> str:
|
||||
def get_vector_field_name(self) -> str:
|
||||
"""
|
||||
Returns name of the vector field in qdrant collection, used by current fastembed model.
|
||||
Returns:
|
||||
Name of the vector field.
|
||||
"""
|
||||
model_name = self.embedding_model_name.split("/")[-1].lower()
|
||||
return f"fast-{model_name}"
|
||||
|
||||
@@ -124,7 +130,7 @@ class QdrantFastembedMixin(QdrantBase):
|
||||
for scored_point in scored_points:
|
||||
embedding = None
|
||||
if scored_point.vector is not None:
|
||||
embedding = scored_point.vector.get(self._get_vector_field_name(), None)
|
||||
embedding = scored_point.vector.get(self.get_vector_field_name(), None)
|
||||
|
||||
response.append(
|
||||
QueryResponse(
|
||||
@@ -137,15 +143,65 @@ class QdrantFastembedMixin(QdrantBase):
|
||||
)
|
||||
return response
|
||||
|
||||
def _records_iterator(
|
||||
self,
|
||||
ids: Optional[Iterable[models.ExtendedPointId]],
|
||||
metadata: Optional[Iterable[Dict[str, Any]]],
|
||||
encoded_docs: Iterable[Tuple[str, List[float]]],
|
||||
ids_accumulator: list,
|
||||
) -> Iterable[models.Record]:
|
||||
if ids is None:
|
||||
ids = iter(lambda: uuid.uuid4().hex, None)
|
||||
|
||||
if metadata is None:
|
||||
metadata = iter(lambda: {}, None)
|
||||
|
||||
vector_name = self.get_vector_field_name()
|
||||
|
||||
for idx, meta, (doc, vector) in zip(ids, metadata, encoded_docs):
|
||||
ids_accumulator.append(idx)
|
||||
payload = {"document": doc, **meta}
|
||||
yield models.Record(id=idx, payload=payload, vector={vector_name: vector})
|
||||
|
||||
def get_fastembed_vector_params(
|
||||
self,
|
||||
on_disk: Optional[bool] = None,
|
||||
quantization_config: Optional[models.QuantizationConfig] = None,
|
||||
hnsw_config: Optional[models.HnswConfigDiff] = None,
|
||||
) -> Dict[str, models.VectorParams]:
|
||||
"""
|
||||
Generates vector configuration, compatible with fastembed models.
|
||||
|
||||
Args:
|
||||
on_disk: if True, vectors will be stored on disk. If None, default value will be used.
|
||||
quantization_config: Quantization configuration. If None, quantization will be disabled.
|
||||
hnsw_config: HNSW configuration. If None, default configuration will be used.
|
||||
|
||||
Returns:
|
||||
Configuration for `vectors_config` argument in `create_collection` method.
|
||||
"""
|
||||
vector_field_name = self.get_vector_field_name()
|
||||
embeddings_size, distance = self._get_model_params(model_name=self.embedding_model_name)
|
||||
return {
|
||||
vector_field_name: models.VectorParams(
|
||||
size=embeddings_size,
|
||||
distance=distance,
|
||||
on_disk=on_disk,
|
||||
quantization_config=quantization_config,
|
||||
hnsw_config=hnsw_config,
|
||||
)
|
||||
}
|
||||
|
||||
def add(
|
||||
self,
|
||||
collection_name: str,
|
||||
documents: List[str],
|
||||
metadata: Optional[List[Dict[str, Any]]] = None,
|
||||
ids: Optional[List[models.ExtendedPointId]] = None,
|
||||
documents: Iterable[str],
|
||||
metadata: Optional[Iterable[Dict[str, Any]]] = None,
|
||||
ids: Optional[Iterable[models.ExtendedPointId]] = None,
|
||||
batch_size: int = 32,
|
||||
parallel: Optional[int] = None,
|
||||
**kwargs: Any,
|
||||
) -> List[str]:
|
||||
) -> List[Union[str, int]]:
|
||||
"""
|
||||
Adds text documents into qdrant collection.
|
||||
If collection does not exist, it will be created with default parameters.
|
||||
@@ -157,47 +213,38 @@ class QdrantFastembedMixin(QdrantBase):
|
||||
Args:
|
||||
collection_name (str):
|
||||
Name of the collection to add documents to.
|
||||
documents (List[str]):
|
||||
documents (Iterable[str]):
|
||||
List of documents to embed and add to the collection.
|
||||
metadata (List[Dict[str, Any]], optional):
|
||||
metadata (Iterable[Dict[str, Any]], optional):
|
||||
List of metadata dicts. Defaults to None.
|
||||
ids (List[models.ExtendedPointId], optional):
|
||||
ids (Iterable[models.ExtendedPointId], optional):
|
||||
List of ids to assign to documents.
|
||||
If not specified, UUIDs will be generated. Defaults to None.
|
||||
batch_size (int, optional):
|
||||
How many documents to embed and upload in single request. Defaults to 32.
|
||||
parallel (Optional[int], optional):
|
||||
How many parallel workers to use for embedding. Defaults to None.
|
||||
If number is specified, data-parallel process will be used.
|
||||
|
||||
Raises:
|
||||
ImportError: If fastembed is not installed.
|
||||
|
||||
Returns:
|
||||
List[str]: List of UUIDs of added documents. UUIDs are randomly generated on client side.
|
||||
List of IDs of added documents. If no ids provided, UUIDs will be randomly generated on client side.
|
||||
|
||||
"""
|
||||
|
||||
# check if we have fastembed installed
|
||||
embeddings = self._embed_documents(
|
||||
encoded_docs = self._embed_documents(
|
||||
documents=documents,
|
||||
embedding_model_name=self.embedding_model_name,
|
||||
batch_size=batch_size,
|
||||
embed_type="passage",
|
||||
parallel=parallel,
|
||||
)
|
||||
|
||||
if metadata is None:
|
||||
metadata = [{} for _ in range(len(documents))]
|
||||
else:
|
||||
assert len(metadata) == len(
|
||||
documents
|
||||
), f"metadata length mismatch: {len(metadata)} != {len(documents)}"
|
||||
|
||||
payloads = ({"document": doc, **metadata} for doc, metadata in zip(documents, metadata))
|
||||
|
||||
if ids is None:
|
||||
ids = [uuid.uuid4().hex for _ in range(len(documents))]
|
||||
|
||||
embeddings_size, distance = self._get_model_params(model_name=self.embedding_model_name)
|
||||
|
||||
vector_field_name = self._get_vector_field_name()
|
||||
vector_field_name = self.get_vector_field_name()
|
||||
|
||||
# Check if collection by same name exists, if not, create it
|
||||
try:
|
||||
@@ -205,9 +252,7 @@ class QdrantFastembedMixin(QdrantBase):
|
||||
except Exception:
|
||||
self.create_collection(
|
||||
collection_name=collection_name,
|
||||
vectors_config={
|
||||
vector_field_name: models.VectorParams(size=embeddings_size, distance=distance)
|
||||
},
|
||||
vectors_config=self.get_fastembed_vector_params(),
|
||||
)
|
||||
collection_info = self.get_collection(collection_name=collection_name)
|
||||
|
||||
@@ -230,19 +275,25 @@ class QdrantFastembedMixin(QdrantBase):
|
||||
distance == vector_params.distance
|
||||
), f"Distance mismatch: {distance} != {vector_params.distance}"
|
||||
|
||||
records = (
|
||||
models.Record(id=idx, payload=payload, vector={vector_field_name: vector})
|
||||
for idx, payload, vector in zip(ids, payloads, embeddings)
|
||||
inserted_ids: list = []
|
||||
|
||||
records = self._records_iterator(
|
||||
ids=ids,
|
||||
metadata=metadata,
|
||||
encoded_docs=encoded_docs,
|
||||
ids_accumulator=inserted_ids,
|
||||
)
|
||||
|
||||
self.upload_records(
|
||||
collection_name=collection_name,
|
||||
records=records,
|
||||
wait=True,
|
||||
parallel=parallel or 1,
|
||||
batch_size=batch_size,
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
return ids
|
||||
return inserted_ids
|
||||
|
||||
def query(
|
||||
self,
|
||||
@@ -280,7 +331,7 @@ class QdrantFastembedMixin(QdrantBase):
|
||||
self.search(
|
||||
collection_name=collection_name,
|
||||
query_vector=models.NamedVector(
|
||||
name=self._get_vector_field_name(), vector=query_vector.tolist()
|
||||
name=self.get_vector_field_name(), vector=query_vector.tolist()
|
||||
),
|
||||
query_filter=query_filter,
|
||||
limit=limit,
|
||||
@@ -326,7 +377,7 @@ class QdrantFastembedMixin(QdrantBase):
|
||||
for vector in query_vectors:
|
||||
request = models.SearchRequest(
|
||||
vector=models.NamedVector(
|
||||
name=self._get_vector_field_name(), vector=vector.tolist()
|
||||
name=self.get_vector_field_name(), vector=vector.tolist()
|
||||
),
|
||||
filter=query_filter,
|
||||
limit=limit,
|
||||
|
||||
@@ -1,6 +1,8 @@
|
||||
import ast
|
||||
from typing import List
|
||||
|
||||
from tools.async_client_generator.config import AUTOGEN_WARNING_MESSAGE
|
||||
|
||||
|
||||
class BaseGenerator:
|
||||
def __init__(self) -> None:
|
||||
@@ -12,4 +14,4 @@ class BaseGenerator:
|
||||
for transformer in self.transformers:
|
||||
nodes = transformer.visit(nodes)
|
||||
|
||||
return ast.unparse(nodes)
|
||||
return AUTOGEN_WARNING_MESSAGE + ast.unparse(nodes)
|
||||
|
||||
@@ -3,3 +3,18 @@ from pathlib import Path
|
||||
CODE_DIR = Path(__file__).parent
|
||||
ROOT_DIR = CODE_DIR.parent.parent
|
||||
CLIENT_DIR = ROOT_DIR / "qdrant_client"
|
||||
|
||||
|
||||
AUTOGEN_WARNING_MESSAGE = """
|
||||
# ****** WARNING: THIS FILE IS AUTOGENERATED ******
|
||||
#
|
||||
# This file is autogenerated. Do not edit it manually.
|
||||
# To regenerate this file, use
|
||||
#
|
||||
# ```
|
||||
# bash -x tools/generate_async_client.sh
|
||||
# ```
|
||||
#
|
||||
# ****** WARNING: THIS FILE IS AUTOGENERATED ******
|
||||
|
||||
"""
|
||||
|
||||
@@ -54,6 +54,8 @@ if __name__ == "__main__":
|
||||
keep_sync=[
|
||||
"__init__",
|
||||
"set_model",
|
||||
"get_vector_field_name",
|
||||
"get_fastembed_vector_params",
|
||||
],
|
||||
class_replace_map={
|
||||
"QdrantBase": "AsyncQdrantBase",
|
||||
|
||||
Reference in New Issue
Block a user