diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 0acdb95..c44450b 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -38,6 +38,7 @@ jobs: run: poetry run pytest -v env: OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }} + PYTEST_TIMEOUT: 120 - name: check openapi client up to date run: | poetry run poe extract-openapi diff --git a/dewy-client/dewy_client/__init__.py b/dewy-client/dewy_client/__init__.py index a96f200..a6847a2 100644 --- a/dewy-client/dewy_client/__init__.py +++ b/dewy-client/dewy_client/__init__.py @@ -1,4 +1,5 @@ -""" A client library for accessing Dewy Knowledge Base API """ +"""A client library for accessing Dewy Knowledge Base API""" + from .client import AuthenticatedClient, Client __all__ = ( diff --git a/dewy-client/dewy_client/api/__init__.py b/dewy-client/dewy_client/api/__init__.py index dc035f4..81f9fa2 100644 --- a/dewy-client/dewy_client/api/__init__.py +++ b/dewy-client/dewy_client/api/__init__.py @@ -1 +1 @@ -""" Contains methods for accessing the API """ +"""Contains methods for accessing the API""" diff --git a/dewy-client/dewy_client/api/kb/add_document.py b/dewy-client/dewy_client/api/kb/add_document.py index 70353ec..5a0eb20 100644 --- a/dewy-client/dewy_client/api/kb/add_document.py +++ b/dewy-client/dewy_client/api/kb/add_document.py @@ -66,7 +66,7 @@ def sync_detailed( ) -> Response[Union[Document, HTTPValidationError]]: """Add Document - Add a document from a URL. + Add a document to a collection. Args: body (AddDocumentRequest): @@ -97,7 +97,7 @@ def sync( ) -> Optional[Union[Document, HTTPValidationError]]: """Add Document - Add a document from a URL. + Add a document to a collection. Args: body (AddDocumentRequest): @@ -123,7 +123,7 @@ async def asyncio_detailed( ) -> Response[Union[Document, HTTPValidationError]]: """Add Document - Add a document from a URL. + Add a document to a collection. Args: body (AddDocumentRequest): @@ -152,7 +152,7 @@ async def asyncio( ) -> Optional[Union[Document, HTTPValidationError]]: """Add Document - Add a document from a URL. + Add a document to a collection. Args: body (AddDocumentRequest): diff --git a/dewy-client/dewy_client/errors.py b/dewy-client/dewy_client/errors.py index 426f8a2..be532ad 100644 --- a/dewy-client/dewy_client/errors.py +++ b/dewy-client/dewy_client/errors.py @@ -1,4 +1,4 @@ -""" Contains shared errors types that can be raised from API functions """ +"""Contains shared errors types that can be raised from API functions""" class UnexpectedStatus(Exception): diff --git a/dewy-client/dewy_client/models/__init__.py b/dewy-client/dewy_client/models/__init__.py index a1f0b33..64705ac 100644 --- a/dewy-client/dewy_client/models/__init__.py +++ b/dewy-client/dewy_client/models/__init__.py @@ -1,4 +1,4 @@ -""" Contains all the data models used in inputs/outputs """ +"""Contains all the data models used in inputs/outputs""" from .add_document_request import AddDocumentRequest from .body_upload_document_content import BodyUploadDocumentContent diff --git a/dewy-client/dewy_client/types.py b/dewy-client/dewy_client/types.py index dbdcc5d..21fac10 100644 --- a/dewy-client/dewy_client/types.py +++ b/dewy-client/dewy_client/types.py @@ -1,4 +1,5 @@ -""" Contains some shared types for properties """ +"""Contains some shared types for properties""" + from http import HTTPStatus from typing import BinaryIO, Generic, Literal, MutableMapping, Optional, Tuple, TypeVar diff --git a/dewy-client/pyproject.toml b/dewy-client/pyproject.toml index ae4eda9..cd3a650 100644 --- a/dewy-client/pyproject.toml +++ b/dewy-client/pyproject.toml @@ -21,5 +21,7 @@ requires = ["poetry-core>=1.0.0"] build-backend = "poetry.core.masonry.api" [tool.ruff] -select = ["F", "I", "UP"] line-length = 120 + +[tool.ruff.lint] +select = ["F", "I", "UP"] diff --git a/dewy/common/collection_embeddings.py b/dewy/common/collection_embeddings.py index f220b3c..0056289 100644 --- a/dewy/common/collection_embeddings.py +++ b/dewy/common/collection_embeddings.py @@ -250,7 +250,7 @@ def encode_chunk(c: str) -> str: # (https://github.com/DewyKB/dewy/issues/20). We do not know # that all of this is truly necessary. encoded = c.encode("utf-8").decode("utf-8", "ignore") - return encoded.replace("\x00", "\uFFFD") + return encoded.replace("\x00", "\ufffd") # First, insert the chunks. await conn.executemany( diff --git a/openapi.yaml b/openapi.yaml index 24734fa..85d7a39 100644 --- a/openapi.yaml +++ b/openapi.yaml @@ -114,7 +114,7 @@ paths: tags: - kb summary: Add Document - description: Add a document from a URL. + description: Add a document to a collection. operationId: addDocument requestBody: required: true diff --git a/poetry.lock b/poetry.lock index 45bfee4..41c3bcf 100644 --- a/poetry.lock +++ b/poetry.lock @@ -976,13 +976,13 @@ socks = ["socksio (==1.*)"] [[package]] name = "huggingface-hub" -version = "0.21.1" +version = "0.21.3" description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub" optional = false python-versions = ">=3.8.0" files = [ - {file = "huggingface_hub-0.21.1-py3-none-any.whl", hash = "sha256:b40dd1dc5c589b7c73178f5f17996bac516524dce83f16d5219a83e33a565712"}, - {file = "huggingface_hub-0.21.1.tar.gz", hash = "sha256:c458ae6b3e8e197472c4ef01d8cc5f8b3ddb70e9288afcd494753d832dac3a70"}, + {file = "huggingface_hub-0.21.3-py3-none-any.whl", hash = "sha256:b183144336fdf2810a8c109822e0bb6ef1fd61c65da6fb60e8c3f658b7144016"}, + {file = "huggingface_hub-0.21.3.tar.gz", hash = "sha256:26a15b604e4fc7bad37c467b76456543ec849386cbca9cd7e1e135f53e500423"}, ] [package.dependencies] @@ -1278,13 +1278,13 @@ extended-testing = ["aiosqlite (>=0.19.0,<0.20.0)", "aleph-alpha-client (>=2.15. [[package]] name = "langchain-core" -version = "0.1.27" +version = "0.1.28" description = "Building applications with LLMs through composability" optional = false python-versions = ">=3.8.1,<4.0" files = [ - {file = "langchain_core-0.1.27-py3-none-any.whl", hash = "sha256:68eb89dc4a932baf4fb6b4b75b7119eec9e5405e892d2137e9fe0a1d24a40d0c"}, - {file = "langchain_core-0.1.27.tar.gz", hash = "sha256:698414223525c0bc130d85a614e1493905d588ab72fe0c9ad3b537b1dc62067f"}, + {file = "langchain_core-0.1.28-py3-none-any.whl", hash = "sha256:f40ca31257e003eb404e6275345d13a1b3839df147153684bab56bb8d80162c6"}, + {file = "langchain_core-0.1.28.tar.gz", hash = "sha256:04e761a513200b6e5b5818613821945799c07bc5349087d7692e50823107c9d6"}, ] [package.dependencies] @@ -1318,13 +1318,13 @@ tiktoken = ">=0.5.2,<1" [[package]] name = "langsmith" -version = "0.1.9" +version = "0.1.10" description = "Client library to connect to the LangSmith LLM Tracing and Evaluation Platform." optional = false python-versions = ">=3.8.1,<4.0" files = [ - {file = "langsmith-0.1.9-py3-none-any.whl", hash = "sha256:f821b3cb07a87eac5cb2181ff0b61051811e4eef09ae4b46e700981f7ae5dfb9"}, - {file = "langsmith-0.1.9.tar.gz", hash = "sha256:9bd3e80607722c3d2db84cf3440005491a859b80b5e499bc988032d5c2da91f0"}, + {file = "langsmith-0.1.10-py3-none-any.whl", hash = "sha256:2997a80aea60ed235d83502a7ccdc1f62ffb4dd6b3b7dd4218e8fa4de68a6725"}, + {file = "langsmith-0.1.10.tar.gz", hash = "sha256:13e7e8b52e694aa4003370cefbb9e79cce3540c65dbf1517902bf7aa4dbbb653"}, ] [package.dependencies] @@ -1906,13 +1906,13 @@ files = [ [[package]] name = "openai" -version = "1.12.0" +version = "1.13.3" description = "The official Python library for the openai API" optional = false python-versions = ">=3.7.1" files = [ - {file = "openai-1.12.0-py3-none-any.whl", hash = "sha256:a54002c814e05222e413664f651b5916714e4700d041d5cf5724d3ae1a3e3481"}, - {file = "openai-1.12.0.tar.gz", hash = "sha256:99c5d257d09ea6533d689d1cc77caa0ac679fa21efef8893d8b0832a86877f1b"}, + {file = "openai-1.13.3-py3-none-any.whl", hash = "sha256:5769b62abd02f350a8dd1a3a242d8972c947860654466171d60fb0972ae0a41c"}, + {file = "openai-1.13.3.tar.gz", hash = "sha256:ff6c6b3bc7327e715e4b3592a923a5a1c7519ff5dd764a83d69f633d49e77a7b"}, ] [package.dependencies] @@ -2146,6 +2146,91 @@ files = [ [package.dependencies] numpy = "*" +[[package]] +name = "pillow" +version = "10.2.0" +description = "Python Imaging Library (Fork)" +optional = false +python-versions = ">=3.8" +files = [ + {file = "pillow-10.2.0-cp310-cp310-macosx_10_10_x86_64.whl", hash = "sha256:7823bdd049099efa16e4246bdf15e5a13dbb18a51b68fa06d6c1d4d8b99a796e"}, + {file = "pillow-10.2.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:83b2021f2ade7d1ed556bc50a399127d7fb245e725aa0113ebd05cfe88aaf588"}, + {file = "pillow-10.2.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6fad5ff2f13d69b7e74ce5b4ecd12cc0ec530fcee76356cac6742785ff71c452"}, + {file = "pillow-10.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:da2b52b37dad6d9ec64e653637a096905b258d2fc2b984c41ae7d08b938a67e4"}, + {file = "pillow-10.2.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:47c0995fc4e7f79b5cfcab1fc437ff2890b770440f7696a3ba065ee0fd496563"}, + {file = "pillow-10.2.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:322bdf3c9b556e9ffb18f93462e5f749d3444ce081290352c6070d014c93feb2"}, + {file = "pillow-10.2.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:51f1a1bffc50e2e9492e87d8e09a17c5eea8409cda8d3f277eb6edc82813c17c"}, + {file = "pillow-10.2.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:69ffdd6120a4737710a9eee73e1d2e37db89b620f702754b8f6e62594471dee0"}, + {file = "pillow-10.2.0-cp310-cp310-win32.whl", hash = "sha256:c6dafac9e0f2b3c78df97e79af707cdc5ef8e88208d686a4847bab8266870023"}, + {file = "pillow-10.2.0-cp310-cp310-win_amd64.whl", hash = "sha256:aebb6044806f2e16ecc07b2a2637ee1ef67a11840a66752751714a0d924adf72"}, + {file = "pillow-10.2.0-cp310-cp310-win_arm64.whl", hash = "sha256:7049e301399273a0136ff39b84c3678e314f2158f50f517bc50285fb5ec847ad"}, + {file = "pillow-10.2.0-cp311-cp311-macosx_10_10_x86_64.whl", hash = "sha256:35bb52c37f256f662abdfa49d2dfa6ce5d93281d323a9af377a120e89a9eafb5"}, + {file = "pillow-10.2.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:9c23f307202661071d94b5e384e1e1dc7dfb972a28a2310e4ee16103e66ddb67"}, + {file = "pillow-10.2.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:773efe0603db30c281521a7c0214cad7836c03b8ccff897beae9b47c0b657d61"}, + {file = "pillow-10.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:11fa2e5984b949b0dd6d7a94d967743d87c577ff0b83392f17cb3990d0d2fd6e"}, + {file = "pillow-10.2.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:716d30ed977be8b37d3ef185fecb9e5a1d62d110dfbdcd1e2a122ab46fddb03f"}, + {file = "pillow-10.2.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:a086c2af425c5f62a65e12fbf385f7c9fcb8f107d0849dba5839461a129cf311"}, + {file = "pillow-10.2.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:c8de2789052ed501dd829e9cae8d3dcce7acb4777ea4a479c14521c942d395b1"}, + {file = "pillow-10.2.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:609448742444d9290fd687940ac0b57fb35e6fd92bdb65386e08e99af60bf757"}, + {file = "pillow-10.2.0-cp311-cp311-win32.whl", hash = "sha256:823ef7a27cf86df6597fa0671066c1b596f69eba53efa3d1e1cb8b30f3533068"}, + {file = "pillow-10.2.0-cp311-cp311-win_amd64.whl", hash = "sha256:1da3b2703afd040cf65ec97efea81cfba59cdbed9c11d8efc5ab09df9509fc56"}, + {file = "pillow-10.2.0-cp311-cp311-win_arm64.whl", hash = "sha256:edca80cbfb2b68d7b56930b84a0e45ae1694aeba0541f798e908a49d66b837f1"}, + {file = "pillow-10.2.0-cp312-cp312-macosx_10_10_x86_64.whl", hash = "sha256:1b5e1b74d1bd1b78bc3477528919414874748dd363e6272efd5abf7654e68bef"}, + {file = "pillow-10.2.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:0eae2073305f451d8ecacb5474997c08569fb4eb4ac231ffa4ad7d342fdc25ac"}, + {file = "pillow-10.2.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b7c2286c23cd350b80d2fc9d424fc797575fb16f854b831d16fd47ceec078f2c"}, + {file = "pillow-10.2.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1e23412b5c41e58cec602f1135c57dfcf15482013ce6e5f093a86db69646a5aa"}, + {file = "pillow-10.2.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:52a50aa3fb3acb9cf7213573ef55d31d6eca37f5709c69e6858fe3bc04a5c2a2"}, + {file = "pillow-10.2.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:127cee571038f252a552760076407f9cff79761c3d436a12af6000cd182a9d04"}, + {file = "pillow-10.2.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:8d12251f02d69d8310b046e82572ed486685c38f02176bd08baf216746eb947f"}, + {file = "pillow-10.2.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:54f1852cd531aa981bc0965b7d609f5f6cc8ce8c41b1139f6ed6b3c54ab82bfb"}, + {file = "pillow-10.2.0-cp312-cp312-win32.whl", hash = "sha256:257d8788df5ca62c980314053197f4d46eefedf4e6175bc9412f14412ec4ea2f"}, + {file = "pillow-10.2.0-cp312-cp312-win_amd64.whl", hash = "sha256:154e939c5f0053a383de4fd3d3da48d9427a7e985f58af8e94d0b3c9fcfcf4f9"}, + {file = "pillow-10.2.0-cp312-cp312-win_arm64.whl", hash = "sha256:f379abd2f1e3dddb2b61bc67977a6b5a0a3f7485538bcc6f39ec76163891ee48"}, + {file = "pillow-10.2.0-cp38-cp38-macosx_10_10_x86_64.whl", hash = "sha256:8373c6c251f7ef8bda6675dd6d2b3a0fcc31edf1201266b5cf608b62a37407f9"}, + {file = "pillow-10.2.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:870ea1ada0899fd0b79643990809323b389d4d1d46c192f97342eeb6ee0b8483"}, + {file = "pillow-10.2.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b4b6b1e20608493548b1f32bce8cca185bf0480983890403d3b8753e44077129"}, + {file = "pillow-10.2.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3031709084b6e7852d00479fd1d310b07d0ba82765f973b543c8af5061cf990e"}, + {file = "pillow-10.2.0-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:3ff074fc97dd4e80543a3e91f69d58889baf2002b6be64347ea8cf5533188213"}, + {file = "pillow-10.2.0-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:cb4c38abeef13c61d6916f264d4845fab99d7b711be96c326b84df9e3e0ff62d"}, + {file = "pillow-10.2.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:b1b3020d90c2d8e1dae29cf3ce54f8094f7938460fb5ce8bc5c01450b01fbaf6"}, + {file = "pillow-10.2.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:170aeb00224ab3dc54230c797f8404507240dd868cf52066f66a41b33169bdbe"}, + {file = "pillow-10.2.0-cp38-cp38-win32.whl", hash = "sha256:c4225f5220f46b2fde568c74fca27ae9771536c2e29d7c04f4fb62c83275ac4e"}, + {file = "pillow-10.2.0-cp38-cp38-win_amd64.whl", hash = "sha256:0689b5a8c5288bc0504d9fcee48f61a6a586b9b98514d7d29b840143d6734f39"}, + {file = "pillow-10.2.0-cp39-cp39-macosx_10_10_x86_64.whl", hash = "sha256:b792a349405fbc0163190fde0dc7b3fef3c9268292586cf5645598b48e63dc67"}, + {file = "pillow-10.2.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:c570f24be1e468e3f0ce7ef56a89a60f0e05b30a3669a459e419c6eac2c35364"}, + {file = "pillow-10.2.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d8ecd059fdaf60c1963c58ceb8997b32e9dc1b911f5da5307aab614f1ce5c2fb"}, + {file = "pillow-10.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c365fd1703040de1ec284b176d6af5abe21b427cb3a5ff68e0759e1e313a5e7e"}, + {file = "pillow-10.2.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:70c61d4c475835a19b3a5aa42492409878bbca7438554a1f89d20d58a7c75c01"}, + {file = "pillow-10.2.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:b6f491cdf80ae540738859d9766783e3b3c8e5bd37f5dfa0b76abdecc5081f13"}, + {file = "pillow-10.2.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:9d189550615b4948f45252d7f005e53c2040cea1af5b60d6f79491a6e147eef7"}, + {file = "pillow-10.2.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:49d9ba1ed0ef3e061088cd1e7538a0759aab559e2e0a80a36f9fd9d8c0c21591"}, + {file = "pillow-10.2.0-cp39-cp39-win32.whl", hash = "sha256:babf5acfede515f176833ed6028754cbcd0d206f7f614ea3447d67c33be12516"}, + {file = "pillow-10.2.0-cp39-cp39-win_amd64.whl", hash = "sha256:0304004f8067386b477d20a518b50f3fa658a28d44e4116970abfcd94fac34a8"}, + {file = "pillow-10.2.0-cp39-cp39-win_arm64.whl", hash = "sha256:0fb3e7fc88a14eacd303e90481ad983fd5b69c761e9e6ef94c983f91025da869"}, + {file = "pillow-10.2.0-pp310-pypy310_pp73-macosx_10_10_x86_64.whl", hash = "sha256:322209c642aabdd6207517e9739c704dc9f9db943015535783239022002f054a"}, + {file = "pillow-10.2.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3eedd52442c0a5ff4f887fab0c1c0bb164d8635b32c894bc1faf4c618dd89df2"}, + {file = "pillow-10.2.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cb28c753fd5eb3dd859b4ee95de66cc62af91bcff5db5f2571d32a520baf1f04"}, + {file = "pillow-10.2.0-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:33870dc4653c5017bf4c8873e5488d8f8d5f8935e2f1fb9a2208c47cdd66efd2"}, + {file = "pillow-10.2.0-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:3c31822339516fb3c82d03f30e22b1d038da87ef27b6a78c9549888f8ceda39a"}, + {file = "pillow-10.2.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:a2b56ba36e05f973d450582fb015594aaa78834fefe8dfb8fcd79b93e64ba4c6"}, + {file = "pillow-10.2.0-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:d8e6aeb9201e655354b3ad049cb77d19813ad4ece0df1249d3c793de3774f8c7"}, + {file = "pillow-10.2.0-pp39-pypy39_pp73-macosx_10_10_x86_64.whl", hash = "sha256:2247178effb34a77c11c0e8ac355c7a741ceca0a732b27bf11e747bbc950722f"}, + {file = "pillow-10.2.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:15587643b9e5eb26c48e49a7b33659790d28f190fc514a322d55da2fb5c2950e"}, + {file = "pillow-10.2.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:753cd8f2086b2b80180d9b3010dd4ed147efc167c90d3bf593fe2af21265e5a5"}, + {file = "pillow-10.2.0-pp39-pypy39_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:7c8f97e8e7a9009bcacbe3766a36175056c12f9a44e6e6f2d5caad06dcfbf03b"}, + {file = "pillow-10.2.0-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:d1b35bcd6c5543b9cb547dee3150c93008f8dd0f1fef78fc0cd2b141c5baf58a"}, + {file = "pillow-10.2.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:fe4c15f6c9285dc54ce6553a3ce908ed37c8f3825b5a51a15c91442bb955b868"}, + {file = "pillow-10.2.0.tar.gz", hash = "sha256:e87f0b2c78157e12d7686b27d63c070fd65d994e8ddae6f328e0dcf4a0cd007e"}, +] + +[package.extras] +docs = ["furo", "olefile", "sphinx (>=2.4)", "sphinx-copybutton", "sphinx-inline-tabs", "sphinx-removed-in", "sphinxext-opengraph"] +fpx = ["olefile"] +mic = ["olefile"] +tests = ["check-manifest", "coverage", "defusedxml", "markdown2", "olefile", "packaging", "pyroma", "pytest", "pytest-cov", "pytest-timeout"] +typing = ["typing-extensions"] +xmp = ["defusedxml"] + [[package]] name = "platformdirs" version = "4.2.0" @@ -2355,13 +2440,13 @@ files = [ [[package]] name = "pydantic" -version = "2.6.2" +version = "2.6.3" description = "Data validation using Python type hints" optional = false python-versions = ">=3.8" files = [ - {file = "pydantic-2.6.2-py3-none-any.whl", hash = "sha256:37a5432e54b12fecaa1049c5195f3d860a10e01bdfd24f1840ef14bd0d3aeab3"}, - {file = "pydantic-2.6.2.tar.gz", hash = "sha256:a09be1c3d28f3abe37f8a78af58284b236a92ce520105ddc91a6d29ea1176ba7"}, + {file = "pydantic-2.6.3-py3-none-any.whl", hash = "sha256:72c6034df47f46ccdf81869fddb81aade68056003900a8724a4f160700016a2a"}, + {file = "pydantic-2.6.3.tar.gz", hash = "sha256:e07805c4c7f5c6826e33a1d4c9d47950d7eaf34868e2690f8594d2e30241f11f"}, ] [package.dependencies] @@ -2499,42 +2584,37 @@ windows-terminal = ["colorama (>=0.4.6)"] [[package]] name = "pymupdf" -version = "1.23.25" +version = "1.23.26" description = "A high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents." optional = false python-versions = ">=3.8" files = [ - {file = "PyMuPDF-1.23.25-cp310-none-macosx_10_9_x86_64.whl", hash = "sha256:6be2b20fbff40602f673fc8e60fde3e5911397f8ca9ed6aa2d15be94b12cc2c4"}, - {file = "PyMuPDF-1.23.25-cp310-none-macosx_11_0_arm64.whl", hash = "sha256:0f6923a44fbeaeefaabb2fa10955dcef3624e8826db661201951f3b3409fed32"}, - {file = "PyMuPDF-1.23.25-cp310-none-manylinux2014_aarch64.whl", hash = "sha256:8eeb2e97347586ec293fddaf61e8dfc58d6b2763406e8f7a6e45b560bf9b15a3"}, - {file = "PyMuPDF-1.23.25-cp310-none-manylinux2014_x86_64.whl", hash = "sha256:dca46799c152051697c5e88d66c17ba6d0244668d0c4dd8a2ba2d8d3cb745988"}, - {file = "PyMuPDF-1.23.25-cp310-none-win32.whl", hash = "sha256:88bfed1bd13ec84869489fc7b97381016cb8b99956073f4c3e8ac8c840bbb15a"}, - {file = "PyMuPDF-1.23.25-cp310-none-win_amd64.whl", hash = "sha256:98a78582c8a0c61b372e2bcd63dc61efc873e40b7d1f0b896a195e1a9ef9ffa7"}, - {file = "PyMuPDF-1.23.25-cp311-none-macosx_10_9_x86_64.whl", hash = "sha256:d7792810634036a745ea3eb3c4ccf2b6adab55ca9644e3352747d2b5aa5327f9"}, - {file = "PyMuPDF-1.23.25-cp311-none-macosx_11_0_arm64.whl", hash = "sha256:03bd1985b0234c3d2b8e26bb3e9ab1d2641dbada1e199b838a6bf884f35224c8"}, - {file = "PyMuPDF-1.23.25-cp311-none-manylinux2014_aarch64.whl", hash = "sha256:638fcb1f7551eb5ab582e412e204e8ded94acbbc37bc7f1e891a5dfc428881ee"}, - {file = "PyMuPDF-1.23.25-cp311-none-manylinux2014_x86_64.whl", hash = "sha256:067c88b4e6609cb7e74d98d0b0a35c11eb8e29f4fc51dc7ed1dd448b81d347c7"}, - {file = "PyMuPDF-1.23.25-cp311-none-win32.whl", hash = "sha256:a694f160d1701285cf3152951430740878d168511cd9ea0a3adcfaf3cac00322"}, - {file = "PyMuPDF-1.23.25-cp311-none-win_amd64.whl", hash = "sha256:514bcb679926b33413637b0bd73b223c90fb0d19352caf3395d0f23b1d47e8af"}, - {file = "PyMuPDF-1.23.25-cp312-none-macosx_10_9_x86_64.whl", hash = "sha256:bba342321e1b5574631894d7d34ec046605d953a23553b7d2f9c0e4d3c27254b"}, - {file = "PyMuPDF-1.23.25-cp312-none-macosx_11_0_arm64.whl", hash = "sha256:b2cb058c8229f9697deebe0574f7d95e4b9a5e295ceafd554346bbd464141e89"}, - {file = "PyMuPDF-1.23.25-cp312-none-manylinux2014_aarch64.whl", hash = "sha256:2479473b533936593428ce78499a1e9901570110ac602f03f1f3174efa0fa6a8"}, - {file = "PyMuPDF-1.23.25-cp312-none-manylinux2014_x86_64.whl", hash = "sha256:a247a4be1e43a6127ee305eae9f65767ee7519a2aa0cb1a2aa6acfd4e7fe7a9b"}, - {file = "PyMuPDF-1.23.25-cp312-none-win32.whl", hash = "sha256:b062be400bbaff6e8b17c0a8da9481e01ec935f97967e0870e9aacd7ba60a52a"}, - {file = "PyMuPDF-1.23.25-cp312-none-win_amd64.whl", hash = "sha256:b12e608761e1586a65f6e96a34417a91f814dbab29f2929b41d825ab32fab6ef"}, - {file = "PyMuPDF-1.23.25-cp38-none-macosx_10_9_x86_64.whl", hash = "sha256:ac97691c0e0e23607626d394bd660a46ea33f64921dc9288cf24daee207f9fe3"}, - {file = "PyMuPDF-1.23.25-cp38-none-macosx_11_0_arm64.whl", hash = "sha256:c0a16cda5dc9b59d494ae23bdd9c4a3db53d04f2b6390265f5c0fe6269777975"}, - {file = "PyMuPDF-1.23.25-cp38-none-manylinux2014_aarch64.whl", hash = "sha256:23d735db51722a889bb50636d161d2747f08fa0b82cc2e4a7eb8e228b25d1c4e"}, - {file = "PyMuPDF-1.23.25-cp38-none-manylinux2014_x86_64.whl", hash = "sha256:cbc1407dcf01b2e3e547b2d7643b97cc44c0950d2bb4b12c74322664c5cb37d7"}, - {file = "PyMuPDF-1.23.25-cp38-none-win32.whl", hash = "sha256:c29518701d6360beb01c25cf69a77b6426db90a9e7cd11179b3bd783c7fb4cb1"}, - {file = "PyMuPDF-1.23.25-cp38-none-win_amd64.whl", hash = "sha256:c1bb6fa9e00c846e6829dec2bee8326754adaef5c80626b99233c01923f0342c"}, - {file = "PyMuPDF-1.23.25-cp39-none-macosx_10_9_x86_64.whl", hash = "sha256:514b272bfcd897f9ae29384da04167dcdea3b13ce0f2b9099b645314355d037d"}, - {file = "PyMuPDF-1.23.25-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:ef345a5b050d0869ef404845075edd5f4bd7fd99e235f4d32ce85f423779a120"}, - {file = "PyMuPDF-1.23.25-cp39-none-manylinux2014_aarch64.whl", hash = "sha256:b3ade5b349c38ddffb24f8c266fbcd7161f488c43960ff0f03f977d40d4df967"}, - {file = "PyMuPDF-1.23.25-cp39-none-manylinux2014_x86_64.whl", hash = "sha256:111d795a3e840aec2ad66beebd90a5327994ec85ed56fd68312f5463062dbbfa"}, - {file = "PyMuPDF-1.23.25-cp39-none-win32.whl", hash = "sha256:2237ce9897771f4af686cc0c81517ffb020fc1a011b95ccf5ccf05383492bd6d"}, - {file = "PyMuPDF-1.23.25-cp39-none-win_amd64.whl", hash = "sha256:251c9c321a2112716068d5ae11deedd1911d0387cbdd0ef19adb216a3adf882c"}, - {file = "PyMuPDF-1.23.25.tar.gz", hash = "sha256:eb414e92f08107f43576a1fedea28aa837220b15ad58c8e32015435fe96cc03e"}, + {file = "PyMuPDF-1.23.26-cp310-none-macosx_10_9_x86_64.whl", hash = "sha256:645a05321aecc8c45739f71f0eb574ce33138d19189582ffa5241fea3a8e2549"}, + {file = "PyMuPDF-1.23.26-cp310-none-macosx_11_0_arm64.whl", hash = "sha256:2dfc9e010669ae92fade6fb72aaea49ebe3b8dcd7ee4dcbbe50115abcaa4d3fe"}, + {file = "PyMuPDF-1.23.26-cp310-none-manylinux2014_x86_64.whl", hash = "sha256:b22f8d854f8196ad5b20308c1cebad3d5189ed9f0988acbafa043947ea7e6c55"}, + {file = "PyMuPDF-1.23.26-cp310-none-win32.whl", hash = "sha256:cc0f794e3466bc96b5bf79d42fbc1551428751e3fef38ebc10ac70396b676144"}, + {file = "PyMuPDF-1.23.26-cp310-none-win_amd64.whl", hash = "sha256:2eb701247d8e685a24e45899d1175f01a3ce5fc792a4431c91fbb68633b29298"}, + {file = "PyMuPDF-1.23.26-cp311-none-macosx_10_9_x86_64.whl", hash = "sha256:e2804a64bb57da414781e312fb0561f6be67658ad57ed4a73dce008b23fc70a6"}, + {file = "PyMuPDF-1.23.26-cp311-none-macosx_11_0_arm64.whl", hash = "sha256:97b40bb22e3056874634617a90e0ed24a5172cf71791b9e25d1d91c6743bc567"}, + {file = "PyMuPDF-1.23.26-cp311-none-manylinux2014_x86_64.whl", hash = "sha256:f25aafd3e7fb9d7761a22acf2b67d704f04cc36d4dc33a3773f0eb3f4ec3606f"}, + {file = "PyMuPDF-1.23.26-cp311-none-win32.whl", hash = "sha256:05e672ed3e82caca7ef02a88ace30130b1dd392a1190f03b2b58ffe7aa331400"}, + {file = "PyMuPDF-1.23.26-cp311-none-win_amd64.whl", hash = "sha256:92b3c4dd4d0491d495f333be2d41f4e1c155a409bc9d04b5ff29655dccbf4655"}, + {file = "PyMuPDF-1.23.26-cp312-none-macosx_10_9_x86_64.whl", hash = "sha256:a217689ede18cc6991b4e6a78afee8a440b3075d53b9dec4ba5ef7487d4547e9"}, + {file = "PyMuPDF-1.23.26-cp312-none-macosx_11_0_arm64.whl", hash = "sha256:42ad2b819b90ce1947e11b90ec5085889df0a2e3aa0207bc97ecacfc6157cabc"}, + {file = "PyMuPDF-1.23.26-cp312-none-manylinux2014_x86_64.whl", hash = "sha256:bb42d4b8407b4de7cb58c28f01449f16f32a6daed88afb41108f1aeb3552bdd4"}, + {file = "PyMuPDF-1.23.26-cp312-none-win32.whl", hash = "sha256:c40d044411615e6f0baa7d3d933b3032cf97e168c7fa77d1be8a46008c109aee"}, + {file = "PyMuPDF-1.23.26-cp312-none-win_amd64.whl", hash = "sha256:3f876533aa7f9a94bcd9a0225ce72571b7808260903fec1d95c120bc842fb52d"}, + {file = "PyMuPDF-1.23.26-cp38-none-macosx_10_9_x86_64.whl", hash = "sha256:52df831d46beb9ff494f5fba3e5d069af6d81f49abf6b6e799ee01f4f8fa6799"}, + {file = "PyMuPDF-1.23.26-cp38-none-macosx_11_0_arm64.whl", hash = "sha256:0bbb0cf6593e53524f3fc26fb5e6ead17c02c64791caec7c4afe61b677dedf80"}, + {file = "PyMuPDF-1.23.26-cp38-none-manylinux2014_x86_64.whl", hash = "sha256:d7cd88842b2e7f4c71eef4d87c98c35646b80b60e6375392d7ce40e519261f59"}, + {file = "PyMuPDF-1.23.26-cp38-none-win32.whl", hash = "sha256:6577e2f473625e2d0df5f5a3bf1e4519e94ae749733cc9937994d1b256687bfa"}, + {file = "PyMuPDF-1.23.26-cp38-none-win_amd64.whl", hash = "sha256:fbe1a3255b2cd0d769b2da2c4efdd0c0f30d4961a1aac02c0f75cf951b337aa4"}, + {file = "PyMuPDF-1.23.26-cp39-none-macosx_10_9_x86_64.whl", hash = "sha256:73fce034f2afea886a59ead2d0caedf27e2b2a8558b5da16d0286882e0b1eb82"}, + {file = "PyMuPDF-1.23.26-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:b3de8618b7cb5b36db611083840b3bcf09b11a893e2d8262f4e042102c7e65de"}, + {file = "PyMuPDF-1.23.26-cp39-none-manylinux2014_x86_64.whl", hash = "sha256:deee96c2fd415ded7b5070d8d5b2c60679aee6ed0e28ac0d2cb998060d835c2c"}, + {file = "PyMuPDF-1.23.26-cp39-none-win32.whl", hash = "sha256:9f7f4ef99dd8ac97fb0b852efa3dcbee515798078b6c79a6a13c7b1e7c5d41a4"}, + {file = "PyMuPDF-1.23.26-cp39-none-win_amd64.whl", hash = "sha256:ba9a54552c7afb9ec85432c765e2fa9a81413acfaa7d70db7c9b528297749e5b"}, + {file = "PyMuPDF-1.23.26.tar.gz", hash = "sha256:a904261b317b761b0aa2bd2c1f6cd25d25aa4258be67a90c02a878efc5dca649"}, ] [package.dependencies] @@ -2984,28 +3064,28 @@ use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"] [[package]] name = "ruff" -version = "0.1.15" +version = "0.3.0" description = "An extremely fast Python linter and code formatter, written in Rust." optional = false python-versions = ">=3.7" files = [ - {file = "ruff-0.1.15-py3-none-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:5fe8d54df166ecc24106db7dd6a68d44852d14eb0729ea4672bb4d96c320b7df"}, - {file = "ruff-0.1.15-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:6f0bfbb53c4b4de117ac4d6ddfd33aa5fc31beeaa21d23c45c6dd249faf9126f"}, - {file = "ruff-0.1.15-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e0d432aec35bfc0d800d4f70eba26e23a352386be3a6cf157083d18f6f5881c8"}, - {file = "ruff-0.1.15-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:9405fa9ac0e97f35aaddf185a1be194a589424b8713e3b97b762336ec79ff807"}, - {file = "ruff-0.1.15-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c66ec24fe36841636e814b8f90f572a8c0cb0e54d8b5c2d0e300d28a0d7bffec"}, - {file = "ruff-0.1.15-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:6f8ad828f01e8dd32cc58bc28375150171d198491fc901f6f98d2a39ba8e3ff5"}, - {file = "ruff-0.1.15-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:86811954eec63e9ea162af0ffa9f8d09088bab51b7438e8b6488b9401863c25e"}, - {file = "ruff-0.1.15-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:fd4025ac5e87d9b80e1f300207eb2fd099ff8200fa2320d7dc066a3f4622dc6b"}, - {file = "ruff-0.1.15-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b17b93c02cdb6aeb696effecea1095ac93f3884a49a554a9afa76bb125c114c1"}, - {file = "ruff-0.1.15-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:ddb87643be40f034e97e97f5bc2ef7ce39de20e34608f3f829db727a93fb82c5"}, - {file = "ruff-0.1.15-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:abf4822129ed3a5ce54383d5f0e964e7fef74a41e48eb1dfad404151efc130a2"}, - {file = "ruff-0.1.15-py3-none-musllinux_1_2_i686.whl", hash = "sha256:6c629cf64bacfd136c07c78ac10a54578ec9d1bd2a9d395efbee0935868bf852"}, - {file = "ruff-0.1.15-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:1bab866aafb53da39c2cadfb8e1c4550ac5340bb40300083eb8967ba25481447"}, - {file = "ruff-0.1.15-py3-none-win32.whl", hash = "sha256:2417e1cb6e2068389b07e6fa74c306b2810fe3ee3476d5b8a96616633f40d14f"}, - {file = "ruff-0.1.15-py3-none-win_amd64.whl", hash = "sha256:3837ac73d869efc4182d9036b1405ef4c73d9b1f88da2413875e34e0d6919587"}, - {file = "ruff-0.1.15-py3-none-win_arm64.whl", hash = "sha256:9a933dfb1c14ec7a33cceb1e49ec4a16b51ce3c20fd42663198746efc0427360"}, - {file = "ruff-0.1.15.tar.gz", hash = "sha256:f6dfa8c1b21c913c326919056c390966648b680966febcb796cc9d1aaab8564e"}, + {file = "ruff-0.3.0-py3-none-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:7deb528029bacf845bdbb3dbb2927d8ef9b4356a5e731b10eef171e3f0a85944"}, + {file = "ruff-0.3.0-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:e1e0d4381ca88fb2b73ea0766008e703f33f460295de658f5467f6f229658c19"}, + {file = "ruff-0.3.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2f7dbba46e2827dfcb0f0cc55fba8e96ba7c8700e0a866eb8cef7d1d66c25dcb"}, + {file = "ruff-0.3.0-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:23dbb808e2f1d68eeadd5f655485e235c102ac6f12ad31505804edced2a5ae77"}, + {file = "ruff-0.3.0-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3ef655c51f41d5fa879f98e40c90072b567c666a7114fa2d9fe004dffba00932"}, + {file = "ruff-0.3.0-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:d0d3d7ef3d4f06433d592e5f7d813314a34601e6c5be8481cccb7fa760aa243e"}, + {file = "ruff-0.3.0-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b08b356d06a792e49a12074b62222f9d4ea2a11dca9da9f68163b28c71bf1dd4"}, + {file = "ruff-0.3.0-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9343690f95710f8cf251bee1013bf43030072b9f8d012fbed6ad702ef70d360a"}, + {file = "ruff-0.3.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a1f3ed501a42f60f4dedb7805fa8d4534e78b4e196f536bac926f805f0743d49"}, + {file = "ruff-0.3.0-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:cc30a9053ff2f1ffb505a585797c23434d5f6c838bacfe206c0e6cf38c921a1e"}, + {file = "ruff-0.3.0-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:5da894a29ec018a8293d3d17c797e73b374773943e8369cfc50495573d396933"}, + {file = "ruff-0.3.0-py3-none-musllinux_1_2_i686.whl", hash = "sha256:755c22536d7f1889be25f2baf6fedd019d0c51d079e8417d4441159f3bcd30c2"}, + {file = "ruff-0.3.0-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:dd73fe7f4c28d317855da6a7bc4aa29a1500320818dd8f27df95f70a01b8171f"}, + {file = "ruff-0.3.0-py3-none-win32.whl", hash = "sha256:19eacceb4c9406f6c41af806418a26fdb23120dfe53583df76d1401c92b7c14b"}, + {file = "ruff-0.3.0-py3-none-win_amd64.whl", hash = "sha256:128265876c1d703e5f5e5a4543bd8be47c73a9ba223fd3989d4aa87dd06f312f"}, + {file = "ruff-0.3.0-py3-none-win_arm64.whl", hash = "sha256:e3a4a6d46aef0a84b74fcd201a4401ea9a6cd85614f6a9435f2d33dd8cefbf83"}, + {file = "ruff-0.3.0.tar.gz", hash = "sha256:0886184ba2618d815067cf43e005388967b67ab9c80df52b32ec1152ab49f53a"}, ] [[package]] @@ -3140,6 +3220,111 @@ tensorflow = ["safetensors[numpy]", "tensorflow (>=2.11.0)"] testing = ["h5py (>=3.7.0)", "huggingface_hub (>=0.12.1)", "hypothesis (>=6.70.2)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "safetensors[numpy]", "setuptools_rust (>=1.5.2)"] torch = ["safetensors[numpy]", "torch (>=1.10)"] +[[package]] +name = "scikit-learn" +version = "1.4.1.post1" +description = "A set of python modules for machine learning and data mining" +optional = false +python-versions = ">=3.9" +files = [ + {file = "scikit-learn-1.4.1.post1.tar.gz", hash = "sha256:93d3d496ff1965470f9977d05e5ec3376fb1e63b10e4fda5e39d23c2d8969a30"}, + {file = "scikit_learn-1.4.1.post1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:c540aaf44729ab5cd4bd5e394f2b375e65ceaea9cdd8c195788e70433d91bbc5"}, + {file = "scikit_learn-1.4.1.post1-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:4310bff71aa98b45b46cd26fa641309deb73a5d1c0461d181587ad4f30ea3c36"}, + {file = "scikit_learn-1.4.1.post1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9f43dd527dabff5521af2786a2f8de5ba381e182ec7292663508901cf6ceaf6e"}, + {file = "scikit_learn-1.4.1.post1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c02e27d65b0c7dc32f2c5eb601aaf5530b7a02bfbe92438188624524878336f2"}, + {file = "scikit_learn-1.4.1.post1-cp310-cp310-win_amd64.whl", hash = "sha256:629e09f772ad42f657ca60a1a52342eef786218dd20cf1369a3b8d085e55ef8f"}, + {file = "scikit_learn-1.4.1.post1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6145dfd9605b0b50ae72cdf72b61a2acd87501369a763b0d73d004710ebb76b5"}, + {file = "scikit_learn-1.4.1.post1-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:1afed6951bc9d2053c6ee9a518a466cbc9b07c6a3f9d43bfe734192b6125d508"}, + {file = "scikit_learn-1.4.1.post1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ce03506ccf5f96b7e9030fea7eb148999b254c44c10182ac55857bc9b5d4815f"}, + {file = "scikit_learn-1.4.1.post1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4ba516fcdc73d60e7f48cbb0bccb9acbdb21807de3651531208aac73c758e3ab"}, + {file = "scikit_learn-1.4.1.post1-cp311-cp311-win_amd64.whl", hash = "sha256:78cd27b4669513b50db4f683ef41ea35b5dddc797bd2bbd990d49897fd1c8a46"}, + {file = "scikit_learn-1.4.1.post1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:a1e289f33f613cefe6707dead50db31930530dc386b6ccff176c786335a7b01c"}, + {file = "scikit_learn-1.4.1.post1-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:0df87de9ce1c0140f2818beef310fb2e2afdc1e66fc9ad587965577f17733649"}, + {file = "scikit_learn-1.4.1.post1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:712c1c69c45b58ef21635360b3d0a680ff7d83ac95b6f9b82cf9294070cda710"}, + {file = "scikit_learn-1.4.1.post1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1754b0c2409d6ed5a3380512d0adcf182a01363c669033a2b55cca429ed86a81"}, + {file = "scikit_learn-1.4.1.post1-cp312-cp312-win_amd64.whl", hash = "sha256:1d491ef66e37f4e812db7e6c8286520c2c3fc61b34bf5e59b67b4ce528de93af"}, + {file = "scikit_learn-1.4.1.post1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:aa0029b78ef59af22cfbd833e8ace8526e4df90212db7ceccbea582ebb5d6794"}, + {file = "scikit_learn-1.4.1.post1-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:14e4c88436ac96bf69eb6d746ac76a574c314a23c6961b7d344b38877f20fee1"}, + {file = "scikit_learn-1.4.1.post1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d7cd3a77c32879311f2aa93466d3c288c955ef71d191503cf0677c3340ae8ae0"}, + {file = "scikit_learn-1.4.1.post1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2a3ee19211ded1a52ee37b0a7b373a8bfc66f95353af058a210b692bd4cda0dd"}, + {file = "scikit_learn-1.4.1.post1-cp39-cp39-win_amd64.whl", hash = "sha256:234b6bda70fdcae9e4abbbe028582ce99c280458665a155eed0b820599377d25"}, +] + +[package.dependencies] +joblib = ">=1.2.0" +numpy = ">=1.19.5,<2.0" +scipy = ">=1.6.0" +threadpoolctl = ">=2.0.0" + +[package.extras] +benchmark = ["matplotlib (>=3.3.4)", "memory-profiler (>=0.57.0)", "pandas (>=1.1.5)"] +docs = ["Pillow (>=7.1.2)", "matplotlib (>=3.3.4)", "memory-profiler (>=0.57.0)", "numpydoc (>=1.2.0)", "pandas (>=1.1.5)", "plotly (>=5.14.0)", "pooch (>=1.6.0)", "scikit-image (>=0.17.2)", "seaborn (>=0.9.0)", "sphinx (>=6.0.0)", "sphinx-copybutton (>=0.5.2)", "sphinx-gallery (>=0.15.0)", "sphinx-prompt (>=1.3.0)", "sphinxext-opengraph (>=0.4.2)"] +examples = ["matplotlib (>=3.3.4)", "pandas (>=1.1.5)", "plotly (>=5.14.0)", "pooch (>=1.6.0)", "scikit-image (>=0.17.2)", "seaborn (>=0.9.0)"] +tests = ["black (>=23.3.0)", "matplotlib (>=3.3.4)", "mypy (>=1.3)", "numpydoc (>=1.2.0)", "pandas (>=1.1.5)", "polars (>=0.19.12)", "pooch (>=1.6.0)", "pyamg (>=4.0.0)", "pyarrow (>=12.0.0)", "pytest (>=7.1.2)", "pytest-cov (>=2.9.0)", "ruff (>=0.0.272)", "scikit-image (>=0.17.2)"] + +[[package]] +name = "scipy" +version = "1.12.0" +description = "Fundamental algorithms for scientific computing in Python" +optional = false +python-versions = ">=3.9" +files = [ + {file = "scipy-1.12.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:78e4402e140879387187f7f25d91cc592b3501a2e51dfb320f48dfb73565f10b"}, + {file = "scipy-1.12.0-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:f5f00ebaf8de24d14b8449981a2842d404152774c1a1d880c901bf454cb8e2a1"}, + {file = "scipy-1.12.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e53958531a7c695ff66c2e7bb7b79560ffdc562e2051644c5576c39ff8efb563"}, + {file = "scipy-1.12.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5e32847e08da8d895ce09d108a494d9eb78974cf6de23063f93306a3e419960c"}, + {file = "scipy-1.12.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:4c1020cad92772bf44b8e4cdabc1df5d87376cb219742549ef69fc9fd86282dd"}, + {file = "scipy-1.12.0-cp310-cp310-win_amd64.whl", hash = "sha256:75ea2a144096b5e39402e2ff53a36fecfd3b960d786b7efd3c180e29c39e53f2"}, + {file = "scipy-1.12.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:408c68423f9de16cb9e602528be4ce0d6312b05001f3de61fe9ec8b1263cad08"}, + {file = "scipy-1.12.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:5adfad5dbf0163397beb4aca679187d24aec085343755fcdbdeb32b3679f254c"}, + {file = "scipy-1.12.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c3003652496f6e7c387b1cf63f4bb720951cfa18907e998ea551e6de51a04467"}, + {file = "scipy-1.12.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8b8066bce124ee5531d12a74b617d9ac0ea59245246410e19bca549656d9a40a"}, + {file = "scipy-1.12.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:8bee4993817e204d761dba10dbab0774ba5a8612e57e81319ea04d84945375ba"}, + {file = "scipy-1.12.0-cp311-cp311-win_amd64.whl", hash = "sha256:a24024d45ce9a675c1fb8494e8e5244efea1c7a09c60beb1eeb80373d0fecc70"}, + {file = "scipy-1.12.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:e7e76cc48638228212c747ada851ef355c2bb5e7f939e10952bc504c11f4e372"}, + {file = "scipy-1.12.0-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:f7ce148dffcd64ade37b2df9315541f9adad6efcaa86866ee7dd5db0c8f041c3"}, + {file = "scipy-1.12.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9c39f92041f490422924dfdb782527a4abddf4707616e07b021de33467f917bc"}, + {file = "scipy-1.12.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a7ebda398f86e56178c2fa94cad15bf457a218a54a35c2a7b4490b9f9cb2676c"}, + {file = "scipy-1.12.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:95e5c750d55cf518c398a8240571b0e0782c2d5a703250872f36eaf737751338"}, + {file = "scipy-1.12.0-cp312-cp312-win_amd64.whl", hash = "sha256:e646d8571804a304e1da01040d21577685ce8e2db08ac58e543eaca063453e1c"}, + {file = "scipy-1.12.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:913d6e7956c3a671de3b05ccb66b11bc293f56bfdef040583a7221d9e22a2e35"}, + {file = "scipy-1.12.0-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:bba1b0c7256ad75401c73e4b3cf09d1f176e9bd4248f0d3112170fb2ec4db067"}, + {file = "scipy-1.12.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:730badef9b827b368f351eacae2e82da414e13cf8bd5051b4bdfd720271a5371"}, + {file = "scipy-1.12.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6546dc2c11a9df6926afcbdd8a3edec28566e4e785b915e849348c6dd9f3f490"}, + {file = "scipy-1.12.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:196ebad3a4882081f62a5bf4aeb7326aa34b110e533aab23e4374fcccb0890dc"}, + {file = "scipy-1.12.0-cp39-cp39-win_amd64.whl", hash = "sha256:b360f1b6b2f742781299514e99ff560d1fe9bd1bff2712894b52abe528d1fd1e"}, + {file = "scipy-1.12.0.tar.gz", hash = "sha256:4bf5abab8a36d20193c698b0f1fc282c1d083c94723902c447e5d2f1780936a3"}, +] + +[package.dependencies] +numpy = ">=1.22.4,<1.29.0" + +[package.extras] +dev = ["click", "cython-lint (>=0.12.2)", "doit (>=0.36.0)", "mypy", "pycodestyle", "pydevtool", "rich-click", "ruff", "types-psutil", "typing_extensions"] +doc = ["jupytext", "matplotlib (>2)", "myst-nb", "numpydoc", "pooch", "pydata-sphinx-theme (==0.9.0)", "sphinx (!=4.1.0)", "sphinx-design (>=0.2.0)"] +test = ["asv", "gmpy2", "hypothesis", "mpmath", "pooch", "pytest", "pytest-cov", "pytest-timeout", "pytest-xdist", "scikit-umfpack", "threadpoolctl"] + +[[package]] +name = "sentence-transformers" +version = "2.5.0" +description = "Multilingual text embeddings" +optional = false +python-versions = ">=3.8.0" +files = [ + {file = "sentence-transformers-2.5.0.tar.gz", hash = "sha256:42cbd4130d58e8e08ea966bf94b012136f0939bbe692ab28dcd00d3e69c57989"}, + {file = "sentence_transformers-2.5.0-py3-none-any.whl", hash = "sha256:2a8df56b1c2171a2c625294bd371ebd61bbbfd1208f4fbac0f8cf95aeaffb79d"}, +] + +[package.dependencies] +huggingface-hub = ">=0.15.1" +numpy = "*" +Pillow = "*" +scikit-learn = "*" +scipy = "*" +torch = ">=1.11.0" +tqdm = "*" +transformers = ">=4.32.0,<5.0.0" + [[package]] name = "shellingham" version = "1.5.4" @@ -3324,6 +3509,17 @@ files = [ [package.extras] doc = ["reno", "sphinx", "tornado (>=4.5)"] +[[package]] +name = "threadpoolctl" +version = "3.3.0" +description = "threadpoolctl" +optional = false +python-versions = ">=3.8" +files = [ + {file = "threadpoolctl-3.3.0-py3-none-any.whl", hash = "sha256:6155be1f4a39f31a18ea70f94a77e0ccd57dced08122ea61109e7da89883781e"}, + {file = "threadpoolctl-3.3.0.tar.gz", hash = "sha256:5dac632b4fa2d43f42130267929af3ba01399ef4bd1882918e92dbc30365d30c"}, +] + [[package]] name = "tiktoken" version = "0.6.0" @@ -4021,4 +4217,4 @@ multidict = ">=4.0" [metadata] lock-version = "2.0" python-versions = "^3.11" -content-hash = "2be93300aebd274a79a282a83eaf8c014beb4811096bff4fff320ef558aa08a7" +content-hash = "4a9b034bed7e53cd5371668a7eb61ae2e988eba552b931aa37ccfb7aa04a5106" diff --git a/pyproject.toml b/pyproject.toml index 73e0a86..35781b8 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -70,9 +70,10 @@ langchain-core = "^0.1.27" langchain-openai = "^0.0.8" langchain-community = "^0.0.24" langchain = "^0.1.9" +sentence-transformers = "^2.5.0" [tool.poetry.group.dev.dependencies] -ruff = "^0.1.11" +ruff = "^0.3.0" mypy = "^1.8.0" ipykernel = "^6.28.0" asyncpg-stubs = "^0.29.1" @@ -93,6 +94,10 @@ build-backend = "poetry.core.masonry.api" [tool.ruff] line-length = 98 +# Assume Python 3.11. +target-version = "py311" + +[tool.ruff.lint] # Enable Pyflakes `E` and `F` codes by default. select = [ # Pyflakes @@ -108,10 +113,7 @@ ignore = [] # Allow unused variables when underscore-prefixed. dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$" -# Assume Python 3.11. -target-version = "py311" - -[tool.ruff.mccabe] +[tool.ruff.lint.mccabe] # Unlike Flake8, default to a complexity level of 10. max-complexity = 10 @@ -125,4 +127,4 @@ show_error_context = true [tool.pytest.ini_options] testpaths = ["tests"] asyncio_mode = "auto" -timeout = 10 \ No newline at end of file +timeout = 20 \ No newline at end of file diff --git a/tests/test_e2e.py b/tests/test_e2e.py index 2bcb573..6a002d2 100644 --- a/tests/test_e2e.py +++ b/tests/test_e2e.py @@ -30,7 +30,6 @@ "embedding_model", ["openai:text-embedding-ada-002", "hf:BAAI/bge-small-en", "hf:BAAI/bge-small-en-v1.5"], ) -@pytest.mark.timeout(120) # slow due to embedding (especially in CI) async def test_index_retrieval(client, embedding_model): collection_name = "".join(random.choices(string.ascii_lowercase, k=5))