diff --git a/backend/Dockerfile b/backend/Dockerfile index a276cefe8..c7ac4fdd7 100644 --- a/backend/Dockerfile +++ b/backend/Dockerfile @@ -1,5 +1,5 @@ # Using a slim version for a smaller base image -FROM python:3.11.6-slim-bullseye@sha256:0c1fbb294096d842ad795ee232d783cab436c90b034210fe894f2bb2f2be7626 AS base +FROM python:3.11.6-slim-bullseye ARG DEV_MODE ENV DEV_MODE=$DEV_MODE @@ -73,7 +73,7 @@ COPY ./ci-migration.sh /code/ COPY supabase /code/supabase/ # Run install -RUN poetry install --no-root && \ +RUN poetry install --no-root --with dev,test && \ playwright install --with-deps && \ rm -rf $POETRY_CACHE_DIR diff --git a/backend/api/pyproject.toml b/backend/api/pyproject.toml index d99172402..b57d761df 100644 --- a/backend/api/pyproject.toml +++ b/backend/api/pyproject.toml @@ -75,7 +75,6 @@ ragas = "*" datasets = "*" fpdf2 = "*" unidecode = "*" -flashrank = "*" langchain-cohere = "*" pyinstrument = "*" playwright = "*" diff --git a/backend/api/quivr_api/modules/brain/rags/quivr_rag.py b/backend/api/quivr_api/modules/brain/rags/quivr_rag.py index 5e762fad1..904f16dce 100644 --- a/backend/api/quivr_api/modules/brain/rags/quivr_rag.py +++ b/backend/api/quivr_api/modules/brain/rags/quivr_rag.py @@ -1,5 +1,4 @@ import datetime -import os from operator import itemgetter from typing import List, Optional from uuid import UUID @@ -8,7 +7,6 @@ from langchain.chains import ConversationalRetrievalChain from langchain.llms.base import BaseLLM from langchain.prompts import HumanMessagePromptTemplate, SystemMessagePromptTemplate from langchain.retrievers import ContextualCompressionRetriever -from langchain.retrievers.document_compressors import FlashrankRerank from langchain.schema import format_document from langchain_cohere import CohereRerank from langchain_community.chat_models import ChatLiteLLM @@ -299,10 +297,11 @@ class QuivrRAG(BaseModel): # TODO(@aminediro) : Should be a class level attribute compressor = None - if os.getenv("COHERE_API_KEY"): - compressor = CohereRerank(top_n=20) - else: - compressor = FlashrankRerank(model="ms-marco-TinyBERT-L-2-v2", top_n=20) + # TODO @stangirard fix + # if os.getenv("COHERE_API_KEY"): + compressor = CohereRerank(top_n=20) + # else: + # compressor = FlashrankRerank(model="ms-marco-TinyBERT-L-2-v2", top_n=20) retriever_doc = self.get_retriever() compression_retriever = ContextualCompressionRetriever( diff --git a/backend/api/quivr_api/packages/quivr_core/quivr_rag.py b/backend/api/quivr_api/packages/quivr_core/quivr_rag.py index 29f61316b..dbab57c37 100644 --- a/backend/api/quivr_api/packages/quivr_core/quivr_rag.py +++ b/backend/api/quivr_api/packages/quivr_core/quivr_rag.py @@ -1,11 +1,8 @@ import logging -import os from operator import itemgetter from typing import AsyncGenerator -from flashrank import Ranker from langchain.retrievers import ContextualCompressionRetriever -from langchain.retrievers.document_compressors.flashrank_rerank import FlashrankRerank from langchain_cohere import CohereRerank from langchain_community.chat_models import ChatLiteLLM from langchain_core.messages.ai import AIMessageChunk @@ -13,7 +10,6 @@ from langchain_core.output_parsers import StrOutputParser from langchain_core.runnables import RunnableLambda, RunnablePassthrough from langchain_core.vectorstores import VectorStore from langchain_openai import ChatOpenAI - from quivr_api.modules.knowledge.entity.knowledge import Knowledge from quivr_api.packages.quivr_core.config import RAGConfig from quivr_api.packages.quivr_core.models import ( @@ -59,14 +55,13 @@ class QuivrQARAG: def _create_reranker(self): # TODO: reranker config - if os.getenv("COHERE_API_KEY"): - compressor = CohereRerank(top_n=20) - else: - ranker_model_name = "ms-marco-TinyBERT-L-2-v2" - flashrank_client = Ranker(model_name=ranker_model_name) - compressor = FlashrankRerank( - client=flashrank_client, model=ranker_model_name, top_n=20 - ) + compressor = CohereRerank(top_n=20) + # else: + # ranker_model_name = "ms-marco-TinyBERT-L-2-v2" + # flashrank_client = Ranker(model_name=ranker_model_name) + # compressor = FlashrankRerank( + # client=flashrank_client, model=ranker_model_name, top_n=20 + # ) # TODO @stangirard fix return compressor # TODO : refactor and simplify diff --git a/backend/core/quivr_core/quivr_rag.py b/backend/core/quivr_core/quivr_rag.py index cb5583a2a..a8ced690b 100644 --- a/backend/core/quivr_core/quivr_rag.py +++ b/backend/core/quivr_core/quivr_rag.py @@ -1,11 +1,8 @@ import logging -import os from operator import itemgetter from typing import AsyncGenerator -from flashrank import Ranker from langchain.retrievers import ContextualCompressionRetriever -from langchain.retrievers.document_compressors.flashrank_rerank import FlashrankRerank from langchain_cohere import CohereRerank from langchain_community.chat_models import ChatLiteLLM from langchain_core.messages.ai import AIMessageChunk @@ -55,14 +52,15 @@ class QuivrQARAG: def _create_reranker(self): # TODO: reranker config - if os.getenv("COHERE_API_KEY"): - compressor = CohereRerank(top_n=20) - else: - ranker_model_name = "ms-marco-TinyBERT-L-2-v2" - flashrank_client = Ranker(model_name=ranker_model_name) - compressor = FlashrankRerank( - client=flashrank_client, model=ranker_model_name, top_n=20 - ) + # if os.getenv("COHERE_API_KEY"): + compressor = CohereRerank(top_n=20) + # else: + # ranker_model_name = "ms-marco-TinyBERT-L-2-v2" + # flashrank_client = Ranker(model_name=ranker_model_name) + # compressor = FlashrankRerank( + # client=flashrank_client, model=ranker_model_name, top_n=20 + # ) + # TODO @stangirard fix return compressor # TODO : refactor and simplify diff --git a/backend/poetry.lock b/backend/poetry.lock index 75a6a5cbb..7378d4b6a 100644 --- a/backend/poetry.lock +++ b/backend/poetry.lock @@ -402,17 +402,17 @@ uvloop = ["uvloop (>=0.15.2)"] [[package]] name = "boto3" -version = "1.34.134" +version = "1.34.135" description = "The AWS SDK for Python" optional = false python-versions = ">=3.8" files = [ - {file = "boto3-1.34.134-py3-none-any.whl", hash = "sha256:342782c02ff077aae118c9c61179eed95c585831fba666baacc5588ff04aa6e1"}, - {file = "boto3-1.34.134.tar.gz", hash = "sha256:f6d6e5b0c9ab022a75373fa16c01f0cd54bc1bb64ef3b6ac64ac7cedd56cbe9c"}, + {file = "boto3-1.34.135-py3-none-any.whl", hash = "sha256:6f5d7a20afbe45e3f7c6b5e96071752d36c3942535b1f7924964f1fdf25376a7"}, + {file = "boto3-1.34.135.tar.gz", hash = "sha256:344f635233c85dbb509b87638232ff9132739f90bb5e6bf01fa0e0a521a9107e"}, ] [package.dependencies] -botocore = ">=1.34.134,<1.35.0" +botocore = ">=1.34.135,<1.35.0" jmespath = ">=0.7.1,<2.0.0" s3transfer = ">=0.10.0,<0.11.0" @@ -421,13 +421,13 @@ crt = ["botocore[crt] (>=1.21.0,<2.0a0)"] [[package]] name = "botocore" -version = "1.34.134" +version = "1.34.135" description = "Low-level, data-driven core of boto 3." optional = false python-versions = ">=3.8" files = [ - {file = "botocore-1.34.134-py3-none-any.whl", hash = "sha256:45219e00639755f92569b29f8f279d5dde721494791412c1f7026a3779e8d9f4"}, - {file = "botocore-1.34.134.tar.gz", hash = "sha256:e29c299599426ed16dd2d4c1e20eef784f96b15e1850ebbc59a3250959285b95"}, + {file = "botocore-1.34.135-py3-none-any.whl", hash = "sha256:3aa9e85e7c479babefb5a590e844435449df418085f3c74d604277bc52dc3109"}, + {file = "botocore-1.34.135.tar.gz", hash = "sha256:2e72f37072f75cb1391fca9d7a4c32cecb52a3557d62431d0f59d5311dc7d0cf"}, ] [package.dependencies] @@ -1186,17 +1186,6 @@ files = [ {file = "dirtyjson-1.0.8.tar.gz", hash = "sha256:90ca4a18f3ff30ce849d100dcf4a003953c79d3a2348ef056f1d9c22231a25fd"}, ] -[[package]] -name = "diskcache" -version = "5.6.3" -description = "Disk Cache -- Disk and file backed persistent cache." -optional = false -python-versions = ">=3" -files = [ - {file = "diskcache-5.6.3-py3-none-any.whl", hash = "sha256:5e31b2d5fbad117cc363ebaf6b689474db18a1f6438bc82358b024abd4c2ca19"}, - {file = "diskcache-5.6.3.tar.gz", hash = "sha256:2c3a3fa2743d8535d832ec61c2054a1641f41775aa7c556758a109941e33e4fc"}, -] - [[package]] name = "distlib" version = "0.3.8" @@ -1634,25 +1623,6 @@ flake8 = ">=3" [package.extras] develop = ["build", "twine"] -[[package]] -name = "flashrank" -version = "0.2.6" -description = "Ultra lite & Super fast SoTA cross-encoder based re-ranking for your search & retrieval pipelines." -optional = false -python-versions = ">=3.6" -files = [ - {file = "FlashRank-0.2.6-py3-none-any.whl", hash = "sha256:afe3a8db9909b375b7a0805ae653e8ec8beaf0cf0b3ea908250ff05b67dbe953"}, - {file = "FlashRank-0.2.6.tar.gz", hash = "sha256:46c3763d23f5de6fa8d11df699adef2578168686b724b5adc873fe5ee4525822"}, -] - -[package.dependencies] -llama-cpp-python = "0.2.76" -numpy = "*" -onnxruntime = "*" -requests = "*" -tokenizers = "*" -tqdm = "*" - [[package]] name = "flatbuffers" version = "24.3.25" @@ -1947,13 +1917,13 @@ grpcio-gcp = ["grpcio-gcp (>=0.2.2,<1.0.dev0)"] [[package]] name = "google-api-python-client" -version = "2.134.0" +version = "2.135.0" description = "Google API Client Library for Python" optional = false python-versions = ">=3.7" files = [ - {file = "google-api-python-client-2.134.0.tar.gz", hash = "sha256:4a8f0bea651a212997cc83c0f271fc86f80ef93d1cee9d84de7dfaeef2a858b6"}, - {file = "google_api_python_client-2.134.0-py2.py3-none-any.whl", hash = "sha256:ba05d60f6239990b7994f6328f17bb154c602d31860fb553016dc9f8ce886945"}, + {file = "google-api-python-client-2.135.0.tar.gz", hash = "sha256:b552a28123ed95493035698db80e8ed78c9106a8b422e63a175150b9b55b704e"}, + {file = "google_api_python_client-2.135.0-py2.py3-none-any.whl", hash = "sha256:91742fa4c779d48456c0256ef346fa1cc185ba427176d3277e35141fa3268026"}, ] [package.dependencies] @@ -2559,13 +2529,13 @@ test = ["flaky", "ipyparallel", "pre-commit", "pytest (>=7.0)", "pytest-asyncio [[package]] name = "ipython" -version = "8.25.0" +version = "8.26.0" description = "IPython: Productive Interactive Computing" optional = false python-versions = ">=3.10" files = [ - {file = "ipython-8.25.0-py3-none-any.whl", hash = "sha256:53eee7ad44df903a06655871cbab66d156a051fd86f3ec6750470ac9604ac1ab"}, - {file = "ipython-8.25.0.tar.gz", hash = "sha256:c6ed726a140b6e725b911528f80439c534fac915246af3efc39440a6b0f9d716"}, + {file = "ipython-8.26.0-py3-none-any.whl", hash = "sha256:e6b347c27bdf9c32ee9d31ae85defc525755a1869f14057e900675b9e8d6e6ff"}, + {file = "ipython-8.26.0.tar.gz", hash = "sha256:1cec0fbba8404af13facebe83d04436a7434c7400e59f47acf467c64abd0956c"}, ] [package.dependencies] @@ -2591,7 +2561,7 @@ nbformat = ["nbformat"] notebook = ["ipywidgets", "notebook"] parallel = ["ipyparallel"] qtconsole = ["qtconsole"] -test = ["pickleshare", "pytest", "pytest-asyncio (<0.22)", "testpath"] +test = ["packaging", "pickleshare", "pytest", "pytest-asyncio (<0.22)", "testpath"] test-extra = ["curio", "ipython[test]", "matplotlib (!=3.2.0)", "nbformat", "numpy (>=1.23)", "pandas", "trio"] [[package]] @@ -3061,18 +3031,18 @@ tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<9.0.0" [[package]] name = "langchain-openai" -version = "0.1.10" +version = "0.1.11" description = "An integration package connecting OpenAI and LangChain" optional = false python-versions = "<4.0,>=3.8.1" files = [ - {file = "langchain_openai-0.1.10-py3-none-any.whl", hash = "sha256:62eb000980eb45e4f16c88acdbaeccf3d59266554b0dd3ce6bebea1bbe8143dd"}, - {file = "langchain_openai-0.1.10.tar.gz", hash = "sha256:30f881f8ccaec28c054759837c41fd2a2264fcc5564728ce12e1715891a9ce3c"}, + {file = "langchain_openai-0.1.11-py3-none-any.whl", hash = "sha256:12676e02846db63938ed40177d3271c8419a0659023afaee6da42518a0a28630"}, + {file = "langchain_openai-0.1.11.tar.gz", hash = "sha256:a5901bfee091060b7915fd6de6fd98aa429544de8cab51ac9b13ba484d9caffb"}, ] [package.dependencies] langchain-core = ">=0.2.2,<0.3" -openai = ">=1.26.0,<2.0.0" +openai = ">=1.32.0,<2.0.0" tiktoken = ">=0.7,<1" [[package]] @@ -3129,13 +3099,13 @@ openai = ["openai (>=0.27.8)"] [[package]] name = "langgraph" -version = "0.1.2" +version = "0.1.3" description = "Building stateful, multi-actor applications with LLMs" optional = false python-versions = "<4.0,>=3.9.0" files = [ - {file = "langgraph-0.1.2-py3-none-any.whl", hash = "sha256:92ca172839e11f8ed166a9d31ad1946a5d657430009a47bf4ba9d03cb4ef0810"}, - {file = "langgraph-0.1.2.tar.gz", hash = "sha256:2a90df777afc920a777b854773d4ce77d44b2b70691481c6fb5f2bca69564944"}, + {file = "langgraph-0.1.3-py3-none-any.whl", hash = "sha256:4d12b16f57a47763796c78a7e55a70ce1bd84d9989d064d63c1819370af6f3a8"}, + {file = "langgraph-0.1.3.tar.gz", hash = "sha256:bc6cd90d6cecfa67ae4e807b226362c057e94d5e0832f490917ff1a872760775"}, ] [package.dependencies] @@ -3196,13 +3166,13 @@ tesseract = ["pytesseract"] [[package]] name = "litellm" -version = "1.40.28" +version = "1.40.29" description = "Library to easily interface with LLM API providers" optional = false python-versions = "!=2.7.*,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,!=3.7.*,>=3.8" files = [ - {file = "litellm-1.40.28-py3-none-any.whl", hash = "sha256:aa6d59390f24d1b1168a202b966249f9f5f93d08deba38ed9528654544065e96"}, - {file = "litellm-1.40.28.tar.gz", hash = "sha256:08fdfcb01715006f9dadb8d05b94143f782e08d1944e5691d9faf20300e62739"}, + {file = "litellm-1.40.29-py3-none-any.whl", hash = "sha256:f541c6a868e62a9018d1502a2043d9e3a669833a6a4ed4946635eec26329540a"}, + {file = "litellm-1.40.29.tar.gz", hash = "sha256:167357fcfe33813bf3410c5f13058c7d8ca39a38a476a4ddb80ffd3c18dab770"}, ] [package.dependencies] @@ -3237,28 +3207,6 @@ files = [ httpx = ">=0.20.0" pydantic = ">=1.10" -[[package]] -name = "llama-cpp-python" -version = "0.2.76" -description = "Python bindings for the llama.cpp library" -optional = false -python-versions = ">=3.8" -files = [ - {file = "llama_cpp_python-0.2.76.tar.gz", hash = "sha256:a4e2ab6b74dc87f565a21e4f1617c030f92d5b341375d7173876d238613a50ab"}, -] - -[package.dependencies] -diskcache = ">=5.6.1" -jinja2 = ">=2.11.3" -numpy = ">=1.20.0" -typing-extensions = ">=4.5.0" - -[package.extras] -all = ["llama_cpp_python[dev,server,test]"] -dev = ["black (>=23.3.0)", "httpx (>=0.24.1)", "mkdocs (>=1.4.3)", "mkdocs-material (>=9.1.18)", "mkdocstrings[python] (>=0.22.0)", "pytest (>=7.4.0)", "twine (>=4.0.2)"] -server = ["PyYAML (>=5.1)", "fastapi (>=0.100.0)", "pydantic-settings (>=2.0.1)", "sse-starlette (>=1.6.1)", "starlette-context (>=0.3.6,<0.4)", "uvicorn (>=0.22.0)"] -test = ["httpx (>=0.24.1)", "pytest (>=7.4.0)", "scipy (>=1.10)"] - [[package]] name = "llama-index" version = "0.10.50" @@ -4445,6 +4393,7 @@ description = "Nvidia JIT LTO Library" optional = false python-versions = ">=3" files = [ + {file = "nvidia_nvjitlink_cu12-12.5.40-py3-none-manylinux2014_aarch64.whl", hash = "sha256:004186d5ea6a57758fd6d57052a123c73a4815adf365eb8dd6a85c9eaa7535ff"}, {file = "nvidia_nvjitlink_cu12-12.5.40-py3-none-manylinux2014_x86_64.whl", hash = "sha256:d9714f27c1d0f0895cd8915c07a87a1d0029a0aa36acaf9156952ec2a8a12189"}, {file = "nvidia_nvjitlink_cu12-12.5.40-py3-none-win_amd64.whl", hash = "sha256:c3401dc8543b52d3a8158007a0c1ab4e9c768fcbd24153a48c86972102197ddd"}, ] @@ -4590,13 +4539,13 @@ sympy = "*" [[package]] name = "openai" -version = "1.35.5" +version = "1.35.7" description = "The official Python library for the openai API" optional = false python-versions = ">=3.7.1" files = [ - {file = "openai-1.35.5-py3-none-any.whl", hash = "sha256:28d92503c6e4b6a32a89277b36693023ef41f60922a4b5c8c621e8c5697ae3a6"}, - {file = "openai-1.35.5.tar.gz", hash = "sha256:67ef289ae22d350cbf9381d83ae82c4e3596d71b7ad1cc886143554ee12fe0c9"}, + {file = "openai-1.35.7-py3-none-any.whl", hash = "sha256:3d1e0b0aac9b0db69a972d36dc7efa7563f8e8d65550b27a48f2a0c2ec207e80"}, + {file = "openai-1.35.7.tar.gz", hash = "sha256:009bfa1504c9c7ef64d87be55936d142325656bbc6d98c68b669d6472e4beb09"}, ] [package.dependencies] @@ -4635,13 +4584,13 @@ numpy = [ [[package]] name = "openpyxl" -version = "3.1.4" +version = "3.1.5" description = "A Python library to read/write Excel 2010 xlsx/xlsm files" optional = false python-versions = ">=3.8" files = [ - {file = "openpyxl-3.1.4-py2.py3-none-any.whl", hash = "sha256:ec17f6483f2b8f7c88c57e5e5d3b0de0e3fb9ac70edc084d28e864f5b33bbefd"}, - {file = "openpyxl-3.1.4.tar.gz", hash = "sha256:8d2c8adf5d20d6ce8f9bca381df86b534835e974ed0156dacefa76f68c1d69fb"}, + {file = "openpyxl-3.1.5-py2.py3-none-any.whl", hash = "sha256:5282c12b107bffeef825f4617dc029afaf41d0ea60823bbb665ef3079dc79de2"}, + {file = "openpyxl-3.1.5.tar.gz", hash = "sha256:cf0e3cf56142039133628b5acffe8ef0c12bc902d2aadd3e0fe5878dc08d1050"}, ] [package.dependencies] @@ -6497,7 +6446,6 @@ datasets = "*" docx2txt = "*" duckduckgo-search = "*" fastapi = "*" -flashrank = "*" flower = "*" fpdf2 = "*" gitpython = "*" @@ -7171,13 +7119,13 @@ test = ["Cython", "array-api-strict", "asv", "gmpy2", "hypothesis (>=6.30)", "me [[package]] name = "sentry-sdk" -version = "2.7.0" +version = "2.7.1" description = "Python client for Sentry (https://sentry.io)" optional = false python-versions = ">=3.6" files = [ - {file = "sentry_sdk-2.7.0-py2.py3-none-any.whl", hash = "sha256:db9594c27a4d21c1ebad09908b1f0dc808ef65c2b89c1c8e7e455143262e37c1"}, - {file = "sentry_sdk-2.7.0.tar.gz", hash = "sha256:d846a211d4a0378b289ced3c434480945f110d0ede00450ba631fc2852e7a0d4"}, + {file = "sentry_sdk-2.7.1-py2.py3-none-any.whl", hash = "sha256:ef1b3d54eb715825657cd4bb3cb42bb4dc85087bac14c56b0fd8c21abd968c9a"}, + {file = "sentry_sdk-2.7.1.tar.gz", hash = "sha256:25006c7e68b75aaa5e6b9c6a420ece22e8d7daec4b7a906ffd3a8607b67c037b"}, ] [package.dependencies] @@ -7218,7 +7166,7 @@ sanic = ["sanic (>=0.8)"] sqlalchemy = ["sqlalchemy (>=1.2)"] starlette = ["starlette (>=0.19.1)"] starlite = ["starlite (>=1.48)"] -tornado = ["tornado (>=5)"] +tornado = ["tornado (>=6)"] [[package]] name = "setuptools" @@ -7389,13 +7337,13 @@ sqlcipher = ["sqlcipher3_binary"] [[package]] name = "sqlglot" -version = "25.3.3" +version = "25.4.0" description = "An easily customizable SQL parser and transpiler" optional = false python-versions = ">=3.7" files = [ - {file = "sqlglot-25.3.3-py3-none-any.whl", hash = "sha256:678adad59a01ce58a7f33463b907dcdb43a0309caa5d55d6ac0af33acf698494"}, - {file = "sqlglot-25.3.3.tar.gz", hash = "sha256:6b9a4c740fb8c78509eb3f51ab1d79f7c4ab3dc9d274251007acdd85faf4aeeb"}, + {file = "sqlglot-25.4.0-py3-none-any.whl", hash = "sha256:c8eb1b45ff7e3382639012aca050a3d40c373049c2d2d47393bf23666135c8bb"}, + {file = "sqlglot-25.4.0.tar.gz", hash = "sha256:12f198afd0b5d5722be9eecb1f364e4e01cb63935086f1b3af1b333b22b78254"}, ] [package.dependencies] @@ -8108,19 +8056,19 @@ test = ["argcomplete (>=3.0.3)", "mypy (>=1.7.0)", "pre-commit", "pytest (>=7.0, [[package]] name = "transformers" -version = "4.41.2" +version = "4.42.3" description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow" optional = false python-versions = ">=3.8.0" files = [ - {file = "transformers-4.41.2-py3-none-any.whl", hash = "sha256:05555d20e43f808de1ef211ab64803cdb513170cef70d29a888b589caebefc67"}, - {file = "transformers-4.41.2.tar.gz", hash = "sha256:80a4db216533d573e9cc7388646c31ed9480918feb7c55eb211249cb23567f87"}, + {file = "transformers-4.42.3-py3-none-any.whl", hash = "sha256:a61a0df9609b7d69229d941b2fd857c841ba3043d6da503d0da1a4b133f65b92"}, + {file = "transformers-4.42.3.tar.gz", hash = "sha256:7539873ff45809145265cbc94ea4619d2713c41ceaa277b692d8b0be3430f7eb"}, ] [package.dependencies] filelock = "*" -huggingface-hub = ">=0.23.0,<1.0" -numpy = ">=1.17" +huggingface-hub = ">=0.23.2,<1.0" +numpy = ">=1.17,<2.0" packaging = ">=20.0" pyyaml = ">=5.1" regex = "!=2019.12.17" @@ -8132,14 +8080,15 @@ tqdm = ">=4.27" [package.extras] accelerate = ["accelerate (>=0.21.0)"] agents = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "datasets (!=2.5.0)", "diffusers", "opencv-python", "sentencepiece (>=0.1.91,!=0.1.92)", "torch"] -all = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.7.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf", "pyctcdecode (>=0.4.0)", "ray[tune] (>=2.7.0)", "scipy (<1.13.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timm", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision"] +all = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.7.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf", "pyctcdecode (>=0.4.0)", "ray[tune] (>=2.7.0)", "scipy (<1.13.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timm (<=0.9.16)", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision"] audio = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"] +benchmark = ["optimum-benchmark (>=0.2.0)"] codecarbon = ["codecarbon (==1.2.0)"] deepspeed = ["accelerate (>=0.21.0)", "deepspeed (>=0.9.3)"] -deepspeed-testing = ["GitPython (<3.1.19)", "accelerate (>=0.21.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "deepspeed (>=0.9.3)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "nltk", "optuna", "parameterized", "protobuf", "psutil", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "timeout-decorator"] -dev = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "beautifulsoup4", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "decord (==0.6.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "flax (>=0.4.1,<=0.7.0)", "fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "scipy (<1.13.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorboard", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timeout-decorator", "timm", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"] -dev-tensorflow = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "isort (>=5.5.4)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timeout-decorator", "tokenizers (>=0.19,<0.20)", "urllib3 (<2.0.0)"] -dev-torch = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "beautifulsoup4", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "kenlm", "librosa", "nltk", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorboard", "timeout-decorator", "timm", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"] +deepspeed-testing = ["GitPython (<3.1.19)", "accelerate (>=0.21.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "deepspeed (>=0.9.3)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "nltk", "optuna", "parameterized", "protobuf", "psutil", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.4.4)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "timeout-decorator"] +dev = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "beautifulsoup4", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "decord (==0.6.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "flax (>=0.4.1,<=0.7.0)", "fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.4.4)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "scipy (<1.13.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorboard", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timeout-decorator", "timm (<=0.9.16)", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"] +dev-tensorflow = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "isort (>=5.5.4)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.4.4)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timeout-decorator", "tokenizers (>=0.19,<0.20)", "urllib3 (<2.0.0)"] +dev-torch = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "beautifulsoup4", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "kenlm", "librosa", "nltk", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.4.4)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorboard", "timeout-decorator", "timm (<=0.9.16)", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"] flax = ["flax (>=0.4.1,<=0.7.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "optax (>=0.0.8,<=0.1.4)", "scipy (<1.13.0)"] flax-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"] ftfy = ["ftfy"] @@ -8150,25 +8099,26 @@ natten = ["natten (>=0.14.6,<0.15.0)"] onnx = ["onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "tf2onnx"] onnxruntime = ["onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)"] optuna = ["optuna"] -quality = ["GitPython (<3.1.19)", "datasets (!=2.5.0)", "isort (>=5.5.4)", "ruff (==0.1.5)", "urllib3 (<2.0.0)"] +quality = ["GitPython (<3.1.19)", "datasets (!=2.5.0)", "isort (>=5.5.4)", "ruff (==0.4.4)", "urllib3 (<2.0.0)"] ray = ["ray[tune] (>=2.7.0)"] retrieval = ["datasets (!=2.5.0)", "faiss-cpu"] +ruff = ["ruff (==0.4.4)"] sagemaker = ["sagemaker (>=2.31.0)"] sentencepiece = ["protobuf", "sentencepiece (>=0.1.91,!=0.1.92)"] serving = ["fastapi", "pydantic", "starlette", "uvicorn"] sigopt = ["sigopt"] sklearn = ["scikit-learn"] speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"] -testing = ["GitPython (<3.1.19)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "nltk", "parameterized", "psutil", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "timeout-decorator"] +testing = ["GitPython (<3.1.19)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "nltk", "parameterized", "psutil", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.4.4)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "timeout-decorator"] tf = ["keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx"] -tf-cpu = ["keras (>2.9,<2.16)", "keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow-cpu (>2.9,<2.16)", "tensorflow-probability (<2.16)", "tensorflow-text (<2.16)", "tf2onnx"] +tf-cpu = ["keras (>2.9,<2.16)", "keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow-cpu (>2.9,<2.16)", "tensorflow-probability (<0.24)", "tensorflow-text (<2.16)", "tf2onnx"] tf-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"] -timm = ["timm"] +timm = ["timm (<=0.9.16)"] tokenizers = ["tokenizers (>=0.19,<0.20)"] torch = ["accelerate (>=0.21.0)", "torch"] torch-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"] torch-vision = ["Pillow (>=10.0.1,<=15.0)", "torchvision"] -torchhub = ["filelock", "huggingface-hub (>=0.23.0,<1.0)", "importlib-metadata", "numpy (>=1.17)", "packaging (>=20.0)", "protobuf", "regex (!=2019.12.17)", "requests", "sentencepiece (>=0.1.91,!=0.1.92)", "tokenizers (>=0.19,<0.20)", "torch", "tqdm (>=4.27)"] +torchhub = ["filelock", "huggingface-hub (>=0.23.2,<1.0)", "importlib-metadata", "numpy (>=1.17,<2.0)", "packaging (>=20.0)", "protobuf", "regex (!=2019.12.17)", "requests", "sentencepiece (>=0.1.91,!=0.1.92)", "tokenizers (>=0.19,<0.20)", "torch", "tqdm (>=4.27)"] video = ["av (==9.2.0)", "decord (==0.6.0)"] vision = ["Pillow (>=10.0.1,<=15.0)"]