diff --git a/docker-compose.yaml b/docker-compose.yaml index 1f9fa511e..e1e8b88d2 100644 --- a/docker-compose.yaml +++ b/docker-compose.yaml @@ -8,11 +8,12 @@ services: # This service builds from an external Dockerfile and runs the Ollama mode. private-gpt-ollama: image: ${PGPT_IMAGE:-zylonai/private-gpt}:${PGPT_TAG:-0.6.2}-ollama # x-release-please-version + user: root build: context: . dockerfile: Dockerfile.ollama volumes: - - ./local_data/:/home/worker/app/local_data + - ./local_data:/home/worker/app/local_data ports: - "8001:8001" environment: @@ -27,11 +28,14 @@ services: - ollama-cpu - ollama-cuda - ollama-api + depends_on: + - ollama # Private-GPT service for the local mode # This service builds from a local Dockerfile and runs the application in local mode. private-gpt-llamacpp-cpu: image: ${PGPT_IMAGE:-zylonai/private-gpt}:${PGPT_TAG:-0.6.2}-llamacpp-cpu # x-release-please-version + user: root build: context: . dockerfile: Dockerfile.llamacpp-cpu @@ -44,7 +48,7 @@ services: environment: PORT: 8001 PGPT_PROFILES: local - HF_TOKEN: ${HF_TOKEN} + HF_TOKEN: ${HF_TOKEN:-} profiles: - llamacpp-cpu @@ -57,7 +61,7 @@ services: ollama: image: traefik:v2.10 ports: - - "8081:8080" + - "8080:8080" command: - "--providers.file.filename=/etc/router.yml" - "--log.level=ERROR" @@ -102,4 +106,4 @@ services: count: 1 capabilities: [gpu] profiles: - - ollama-cuda \ No newline at end of file + - ollama-cuda diff --git a/poetry.lock b/poetry.lock index 40f273eb6..c595edcb1 100644 --- a/poetry.lock +++ b/poetry.lock @@ -434,17 +434,17 @@ uvloop = ["uvloop (>=0.15.2)"] [[package]] name = "boto3" -version = "1.35.26" +version = "1.35.27" description = "The AWS SDK for Python" optional = true python-versions = ">=3.8" files = [ - {file = "boto3-1.35.26-py3-none-any.whl", hash = "sha256:c31db992655db233d98762612690cfe60723c9e1503b5709aad92c1c564877bb"}, - {file = "boto3-1.35.26.tar.gz", hash = "sha256:b04087afd3570ba540fd293823c77270ec675672af23da9396bd5988a3f8128b"}, + {file = "boto3-1.35.27-py3-none-any.whl", hash = "sha256:3da139ca038032e92086e26d23833b557f0c257520162bfd3d6f580bf8032c86"}, + {file = "boto3-1.35.27.tar.gz", hash = "sha256:10d0fe15670b83a3f26572ab20d9152a064cee4c54b5ea9a1eeb1f0c3b807a7b"}, ] [package.dependencies] -botocore = ">=1.35.26,<1.36.0" +botocore = ">=1.35.27,<1.36.0" jmespath = ">=0.7.1,<2.0.0" s3transfer = ">=0.10.0,<0.11.0" @@ -453,13 +453,13 @@ crt = ["botocore[crt] (>=1.21.0,<2.0a0)"] [[package]] name = "botocore" -version = "1.35.26" +version = "1.35.27" description = "Low-level, data-driven core of boto 3." optional = true python-versions = ">=3.8" files = [ - {file = "botocore-1.35.26-py3-none-any.whl", hash = "sha256:0b9dee5e4a3314e251e103585837506b17fcc7485c3c8adb61a9a913f46da1e7"}, - {file = "botocore-1.35.26.tar.gz", hash = "sha256:19efc3a22c9df77960712b4e203f912486f8bcd3794bff0fd7b2a0f5f1d5712d"}, + {file = "botocore-1.35.27-py3-none-any.whl", hash = "sha256:c299c70b5330a8634e032883ce8a72c2c6d9fdbc985d8191199cb86b92e7cbbd"}, + {file = "botocore-1.35.27.tar.gz", hash = "sha256:f68875c26cd57a9d22c0f7a981ecb1636d7ce4d0e35797e04765b53e7bfed3e7"}, ] [package.dependencies] @@ -747,13 +747,13 @@ numpy = "*" [[package]] name = "chromadb" -version = "0.5.7" +version = "0.5.9" description = "Chroma." optional = true python-versions = ">=3.8" files = [ - {file = "chromadb-0.5.7-py3-none-any.whl", hash = "sha256:2358f92804cd198b125de73076ec48f9f55c729df119919a76a6716ad0e465f6"}, - {file = "chromadb-0.5.7.tar.gz", hash = "sha256:3432865025ef3ceeaee0a59b265a784d8b5978cb7c41593c74ddd2427c776c94"}, + {file = "chromadb-0.5.9-py3-none-any.whl", hash = "sha256:0e7a05f03e0d27d31135abf8e681913c193c314fcbeeba456adeaa17395d697e"}, + {file = "chromadb-0.5.9.tar.gz", hash = "sha256:1e47fffe72625e1cddf2af4d570eb39aa06c2613d509dfeb9204ac57d6cf03d9"}, ] [package.dependencies] @@ -1314,6 +1314,20 @@ django = ["dj-database-url", "dj-email-url", "django-cache-url"] lint = ["flake8 (==4.0.1)", "flake8-bugbear (==21.9.2)", "mypy (==0.910)", "pre-commit (>=2.4,<3.0)"] tests = ["dj-database-url", "dj-email-url", "django-cache-url", "pytest"] +[[package]] +name = "eval-type-backport" +version = "0.2.0" +description = "Like `typing._eval_type`, but lets older Python versions use newer typing features." +optional = true +python-versions = ">=3.8" +files = [ + {file = "eval_type_backport-0.2.0-py3-none-any.whl", hash = "sha256:ac2f73d30d40c5a30a80b8739a789d6bb5e49fdffa66d7912667e2015d9c9933"}, + {file = "eval_type_backport-0.2.0.tar.gz", hash = "sha256:68796cfbc7371ebf923f03bdf7bef415f3ec098aeced24e054b253a0e78f7b37"}, +] + +[package.extras] +tests = ["pytest"] + [[package]] name = "fastapi" version = "0.115.0" @@ -2438,6 +2452,17 @@ files = [ {file = "joblib-1.4.2.tar.gz", hash = "sha256:2382c5816b2636fbd20a09e0f4e9dad4736765fdfb7dca582943b9c1366b3f0e"}, ] +[[package]] +name = "jsonpath-python" +version = "1.0.6" +description = "A more powerful JSONPath implementation in modern python" +optional = true +python-versions = ">=3.6" +files = [ + {file = "jsonpath-python-1.0.6.tar.gz", hash = "sha256:dd5be4a72d8a2995c3f583cf82bf3cd1a9544cfdabf2d22595b67aff07349666"}, + {file = "jsonpath_python-1.0.6-py3-none-any.whl", hash = "sha256:1e3b78df579f5efc23565293612decee04214609208a2335884b3ee3f786b575"}, +] + [[package]] name = "kiwisolver" version = "1.4.7" @@ -2691,6 +2716,21 @@ huggingface-hub = {version = ">=0.19.0", extras = ["inference"]} llama-index-core = ">=0.11.0,<0.12.0" sentence-transformers = ">=2.6.1" +[[package]] +name = "llama-index-embeddings-mistralai" +version = "0.2.0" +description = "llama-index embeddings mistralai integration" +optional = true +python-versions = "<4.0,>=3.9" +files = [ + {file = "llama_index_embeddings_mistralai-0.2.0-py3-none-any.whl", hash = "sha256:e753209edb29d535c09bd2ecdc960350e62f80574a1eedf44a6479a7c4453cca"}, + {file = "llama_index_embeddings_mistralai-0.2.0.tar.gz", hash = "sha256:c334b6ae5a0a6656ff36271070ae714b10c3b00489daa8fc0fd4f07f6ccc49bc"}, +] + +[package.dependencies] +llama-index-core = ">=0.11.0,<0.12.0" +mistralai = ">=1.0.0" + [[package]] name = "llama-index-embeddings-ollama" version = "0.3.1" @@ -3228,6 +3268,28 @@ files = [ {file = "minijinja-2.2.0.tar.gz", hash = "sha256:4411052c7a60f8d56468cc6d17d45d72be3d5e89e9578a04f8336cc56601523c"}, ] +[[package]] +name = "mistralai" +version = "1.1.0" +description = "Python Client SDK for the Mistral AI API." +optional = true +python-versions = "<4.0,>=3.8" +files = [ + {file = "mistralai-1.1.0-py3-none-any.whl", hash = "sha256:eea0938975195f331d0ded12d14e3c982f09f1b68210200ed4ff0c6b9b22d0fb"}, + {file = "mistralai-1.1.0.tar.gz", hash = "sha256:9d1fe778e0e8c6ddab714e6a64c6096bd39cfe119ff38ceb5019d8e089df08ba"}, +] + +[package.dependencies] +eval-type-backport = ">=0.2.0,<0.3.0" +httpx = ">=0.27.0,<0.28.0" +jsonpath-python = ">=1.0.6,<2.0.0" +pydantic = ">=2.9.0,<3.0.0" +python-dateutil = "2.8.2" +typing-inspect = ">=0.9.0,<0.10.0" + +[package.extras] +gcp = ["google-auth (==2.27.0)", "requests (>=2.32.3,<3.0.0)"] + [[package]] name = "mmh3" version = "5.0.1" @@ -3889,13 +3951,13 @@ sympy = "*" [[package]] name = "openai" -version = "1.47.1" +version = "1.48.0" description = "The official Python library for the openai API" optional = true python-versions = ">=3.7.1" files = [ - {file = "openai-1.47.1-py3-none-any.whl", hash = "sha256:34277583bf268bb2494bc03f48ac123788c5e2a914db1d5a23d5edc29d35c825"}, - {file = "openai-1.47.1.tar.gz", hash = "sha256:62c8f5f478f82ffafc93b33040f8bb16a45948306198bd0cba2da2ecd9cf7323"}, + {file = "openai-1.48.0-py3-none-any.whl", hash = "sha256:7c4af223f0bf615ce4a12453729952c9a8b04ffe8c78aa77981b12fd970149cf"}, + {file = "openai-1.48.0.tar.gz", hash = "sha256:1d3b69ea62c287c4885a6f3ce840768564cd5f52c60ac5f890fef80d43cc4799"}, ] [package.dependencies] @@ -4820,13 +4882,13 @@ tests = ["coverage[toml] (==5.0.4)", "pytest (>=6.0.0,<7.0.0)"] [[package]] name = "pymilvus" -version = "2.4.6" +version = "2.4.7" description = "Python Sdk for Milvus" optional = true python-versions = ">=3.8" files = [ - {file = "pymilvus-2.4.6-py3-none-any.whl", hash = "sha256:b4c43472edc313b845d313be50610e19054e6954b2c5c3b515565c596c2d3d97"}, - {file = "pymilvus-2.4.6.tar.gz", hash = "sha256:6ac3eb91c92cc01bbe444fe83f895f02d7b2546d96ac67998630bf31ac074d66"}, + {file = "pymilvus-2.4.7-py3-none-any.whl", hash = "sha256:1e5d377bd40fa7eb459d3958dbd96201758f5cf997d41eb3d2d169d0b7fa462e"}, + {file = "pymilvus-2.4.7.tar.gz", hash = "sha256:9ef460b940782a42e1b7b8ae0da03d8cc02d9d80044d13f4b689a7c935ec7aa7"}, ] [package.dependencies] @@ -4968,13 +5030,13 @@ testing = ["fields", "hunter", "process-tests", "pytest-xdist", "virtualenv"] [[package]] name = "python-dateutil" -version = "2.9.0.post0" +version = "2.8.2" description = "Extensions to the standard Python datetime module" optional = false python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,>=2.7" files = [ - {file = "python-dateutil-2.9.0.post0.tar.gz", hash = "sha256:37dd54208da7e1cd875388217d5e00ebd4179249f90fb72437e91a35459a0ad3"}, - {file = "python_dateutil-2.9.0.post0-py2.py3-none-any.whl", hash = "sha256:a8b2bc7bffae282281c8140a97d3aa9c14da0b136dfe83f850eea9a5f7470427"}, + {file = "python-dateutil-2.8.2.tar.gz", hash = "sha256:0123cacc1627ae19ddf3c27a5de5bd67ee4586fbdd6440d9748f8abb483d3e86"}, + {file = "python_dateutil-2.8.2-py2.py3-none-any.whl", hash = "sha256:961d03dc3453ebbc59dbdea9e4e11c5651520a876d0f4db161e8674aae935da9"}, ] [package.dependencies] @@ -5899,111 +5961,111 @@ blobfile = ["blobfile (>=2)"] [[package]] name = "tokenizers" -version = "0.19.1" +version = "0.20.0" description = "" optional = false python-versions = ">=3.7" files = [ - {file = "tokenizers-0.19.1-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:952078130b3d101e05ecfc7fc3640282d74ed26bcf691400f872563fca15ac97"}, - {file = "tokenizers-0.19.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:82c8b8063de6c0468f08e82c4e198763e7b97aabfe573fd4cf7b33930ca4df77"}, - {file = "tokenizers-0.19.1-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:f03727225feaf340ceeb7e00604825addef622d551cbd46b7b775ac834c1e1c4"}, - {file = "tokenizers-0.19.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:453e4422efdfc9c6b6bf2eae00d5e323f263fff62b29a8c9cd526c5003f3f642"}, - {file = "tokenizers-0.19.1-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:02e81bf089ebf0e7f4df34fa0207519f07e66d8491d963618252f2e0729e0b46"}, - {file = "tokenizers-0.19.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b07c538ba956843833fee1190cf769c60dc62e1cf934ed50d77d5502194d63b1"}, - {file = "tokenizers-0.19.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e28cab1582e0eec38b1f38c1c1fb2e56bce5dc180acb1724574fc5f47da2a4fe"}, - {file = "tokenizers-0.19.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8b01afb7193d47439f091cd8f070a1ced347ad0f9144952a30a41836902fe09e"}, - {file = "tokenizers-0.19.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:7fb297edec6c6841ab2e4e8f357209519188e4a59b557ea4fafcf4691d1b4c98"}, - {file = "tokenizers-0.19.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:2e8a3dd055e515df7054378dc9d6fa8c8c34e1f32777fb9a01fea81496b3f9d3"}, - {file = "tokenizers-0.19.1-cp310-none-win32.whl", hash = "sha256:7ff898780a155ea053f5d934925f3902be2ed1f4d916461e1a93019cc7250837"}, - {file = "tokenizers-0.19.1-cp310-none-win_amd64.whl", hash = "sha256:bea6f9947e9419c2fda21ae6c32871e3d398cba549b93f4a65a2d369662d9403"}, - {file = "tokenizers-0.19.1-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:5c88d1481f1882c2e53e6bb06491e474e420d9ac7bdff172610c4f9ad3898059"}, - {file = "tokenizers-0.19.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:ddf672ed719b4ed82b51499100f5417d7d9f6fb05a65e232249268f35de5ed14"}, - {file = "tokenizers-0.19.1-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:dadc509cc8a9fe460bd274c0e16ac4184d0958117cf026e0ea8b32b438171594"}, - {file = "tokenizers-0.19.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dfedf31824ca4915b511b03441784ff640378191918264268e6923da48104acc"}, - {file = "tokenizers-0.19.1-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:ac11016d0a04aa6487b1513a3a36e7bee7eec0e5d30057c9c0408067345c48d2"}, - {file = "tokenizers-0.19.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:76951121890fea8330d3a0df9a954b3f2a37e3ec20e5b0530e9a0044ca2e11fe"}, - {file = "tokenizers-0.19.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b342d2ce8fc8d00f376af068e3274e2e8649562e3bc6ae4a67784ded6b99428d"}, - {file = "tokenizers-0.19.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d16ff18907f4909dca9b076b9c2d899114dd6abceeb074eca0c93e2353f943aa"}, - {file = "tokenizers-0.19.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:706a37cc5332f85f26efbe2bdc9ef8a9b372b77e4645331a405073e4b3a8c1c6"}, - {file = "tokenizers-0.19.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:16baac68651701364b0289979ecec728546133e8e8fe38f66fe48ad07996b88b"}, - {file = "tokenizers-0.19.1-cp311-none-win32.whl", hash = "sha256:9ed240c56b4403e22b9584ee37d87b8bfa14865134e3e1c3fb4b2c42fafd3256"}, - {file = "tokenizers-0.19.1-cp311-none-win_amd64.whl", hash = "sha256:ad57d59341710b94a7d9dbea13f5c1e7d76fd8d9bcd944a7a6ab0b0da6e0cc66"}, - {file = "tokenizers-0.19.1-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:621d670e1b1c281a1c9698ed89451395d318802ff88d1fc1accff0867a06f153"}, - {file = "tokenizers-0.19.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:d924204a3dbe50b75630bd16f821ebda6a5f729928df30f582fb5aade90c818a"}, - {file = "tokenizers-0.19.1-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:4f3fefdc0446b1a1e6d81cd4c07088ac015665d2e812f6dbba4a06267d1a2c95"}, - {file = "tokenizers-0.19.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9620b78e0b2d52ef07b0d428323fb34e8ea1219c5eac98c2596311f20f1f9266"}, - {file = "tokenizers-0.19.1-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:04ce49e82d100594715ac1b2ce87d1a36e61891a91de774755f743babcd0dd52"}, - {file = "tokenizers-0.19.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c5c2ff13d157afe413bf7e25789879dd463e5a4abfb529a2d8f8473d8042e28f"}, - {file = "tokenizers-0.19.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3174c76efd9d08f836bfccaca7cfec3f4d1c0a4cf3acbc7236ad577cc423c840"}, - {file = "tokenizers-0.19.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7c9d5b6c0e7a1e979bec10ff960fae925e947aab95619a6fdb4c1d8ff3708ce3"}, - {file = "tokenizers-0.19.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:a179856d1caee06577220ebcfa332af046d576fb73454b8f4d4b0ba8324423ea"}, - {file = "tokenizers-0.19.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:952b80dac1a6492170f8c2429bd11fcaa14377e097d12a1dbe0ef2fb2241e16c"}, - {file = "tokenizers-0.19.1-cp312-none-win32.whl", hash = "sha256:01d62812454c188306755c94755465505836fd616f75067abcae529c35edeb57"}, - {file = "tokenizers-0.19.1-cp312-none-win_amd64.whl", hash = "sha256:b70bfbe3a82d3e3fb2a5e9b22a39f8d1740c96c68b6ace0086b39074f08ab89a"}, - {file = "tokenizers-0.19.1-cp37-cp37m-macosx_10_12_x86_64.whl", hash = "sha256:bb9dfe7dae85bc6119d705a76dc068c062b8b575abe3595e3c6276480e67e3f1"}, - {file = "tokenizers-0.19.1-cp37-cp37m-macosx_11_0_arm64.whl", hash = "sha256:1f0360cbea28ea99944ac089c00de7b2e3e1c58f479fb8613b6d8d511ce98267"}, - {file = "tokenizers-0.19.1-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:71e3ec71f0e78780851fef28c2a9babe20270404c921b756d7c532d280349214"}, - {file = "tokenizers-0.19.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b82931fa619dbad979c0ee8e54dd5278acc418209cc897e42fac041f5366d626"}, - {file = "tokenizers-0.19.1-cp37-cp37m-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:e8ff5b90eabdcdaa19af697885f70fe0b714ce16709cf43d4952f1f85299e73a"}, - {file = "tokenizers-0.19.1-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e742d76ad84acbdb1a8e4694f915fe59ff6edc381c97d6dfdd054954e3478ad4"}, - {file = "tokenizers-0.19.1-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d8c5d59d7b59885eab559d5bc082b2985555a54cda04dda4c65528d90ad252ad"}, - {file = "tokenizers-0.19.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6b2da5c32ed869bebd990c9420df49813709e953674c0722ff471a116d97b22d"}, - {file = "tokenizers-0.19.1-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:638e43936cc8b2cbb9f9d8dde0fe5e7e30766a3318d2342999ae27f68fdc9bd6"}, - {file = "tokenizers-0.19.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:78e769eb3b2c79687d9cb0f89ef77223e8e279b75c0a968e637ca7043a84463f"}, - {file = "tokenizers-0.19.1-cp37-none-win32.whl", hash = "sha256:72791f9bb1ca78e3ae525d4782e85272c63faaef9940d92142aa3eb79f3407a3"}, - {file = "tokenizers-0.19.1-cp37-none-win_amd64.whl", hash = "sha256:f3bbb7a0c5fcb692950b041ae11067ac54826204318922da754f908d95619fbc"}, - {file = "tokenizers-0.19.1-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:07f9295349bbbcedae8cefdbcfa7f686aa420be8aca5d4f7d1ae6016c128c0c5"}, - {file = "tokenizers-0.19.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:10a707cc6c4b6b183ec5dbfc5c34f3064e18cf62b4a938cb41699e33a99e03c1"}, - {file = "tokenizers-0.19.1-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:6309271f57b397aa0aff0cbbe632ca9d70430839ca3178bf0f06f825924eca22"}, - {file = "tokenizers-0.19.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4ad23d37d68cf00d54af184586d79b84075ada495e7c5c0f601f051b162112dc"}, - {file = "tokenizers-0.19.1-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:427c4f0f3df9109314d4f75b8d1f65d9477033e67ffaec4bca53293d3aca286d"}, - {file = "tokenizers-0.19.1-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e83a31c9cf181a0a3ef0abad2b5f6b43399faf5da7e696196ddd110d332519ee"}, - {file = "tokenizers-0.19.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c27b99889bd58b7e301468c0838c5ed75e60c66df0d4db80c08f43462f82e0d3"}, - {file = "tokenizers-0.19.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bac0b0eb952412b0b196ca7a40e7dce4ed6f6926489313414010f2e6b9ec2adf"}, - {file = "tokenizers-0.19.1-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:8a6298bde623725ca31c9035a04bf2ef63208d266acd2bed8c2cb7d2b7d53ce6"}, - {file = "tokenizers-0.19.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:08a44864e42fa6d7d76d7be4bec62c9982f6f6248b4aa42f7302aa01e0abfd26"}, - {file = "tokenizers-0.19.1-cp38-none-win32.whl", hash = "sha256:1de5bc8652252d9357a666e609cb1453d4f8e160eb1fb2830ee369dd658e8975"}, - {file = "tokenizers-0.19.1-cp38-none-win_amd64.whl", hash = "sha256:0bcce02bf1ad9882345b34d5bd25ed4949a480cf0e656bbd468f4d8986f7a3f1"}, - {file = "tokenizers-0.19.1-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:0b9394bd204842a2a1fd37fe29935353742be4a3460b6ccbaefa93f58a8df43d"}, - {file = "tokenizers-0.19.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:4692ab92f91b87769d950ca14dbb61f8a9ef36a62f94bad6c82cc84a51f76f6a"}, - {file = "tokenizers-0.19.1-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:6258c2ef6f06259f70a682491c78561d492e885adeaf9f64f5389f78aa49a051"}, - {file = "tokenizers-0.19.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c85cf76561fbd01e0d9ea2d1cbe711a65400092bc52b5242b16cfd22e51f0c58"}, - {file = "tokenizers-0.19.1-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:670b802d4d82bbbb832ddb0d41df7015b3e549714c0e77f9bed3e74d42400fbe"}, - {file = "tokenizers-0.19.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:85aa3ab4b03d5e99fdd31660872249df5e855334b6c333e0bc13032ff4469c4a"}, - {file = "tokenizers-0.19.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cbf001afbbed111a79ca47d75941e9e5361297a87d186cbfc11ed45e30b5daba"}, - {file = "tokenizers-0.19.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b4c89aa46c269e4e70c4d4f9d6bc644fcc39bb409cb2a81227923404dd6f5227"}, - {file = "tokenizers-0.19.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:39c1ec76ea1027438fafe16ecb0fb84795e62e9d643444c1090179e63808c69d"}, - {file = "tokenizers-0.19.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:c2a0d47a89b48d7daa241e004e71fb5a50533718897a4cd6235cb846d511a478"}, - {file = "tokenizers-0.19.1-cp39-none-win32.whl", hash = "sha256:61b7fe8886f2e104d4caf9218b157b106207e0f2a4905c9c7ac98890688aabeb"}, - {file = "tokenizers-0.19.1-cp39-none-win_amd64.whl", hash = "sha256:f97660f6c43efd3e0bfd3f2e3e5615bf215680bad6ee3d469df6454b8c6e8256"}, - {file = "tokenizers-0.19.1-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:3b11853f17b54c2fe47742c56d8a33bf49ce31caf531e87ac0d7d13d327c9334"}, - {file = "tokenizers-0.19.1-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:d26194ef6c13302f446d39972aaa36a1dda6450bc8949f5eb4c27f51191375bd"}, - {file = "tokenizers-0.19.1-pp310-pypy310_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:e8d1ed93beda54bbd6131a2cb363a576eac746d5c26ba5b7556bc6f964425594"}, - {file = "tokenizers-0.19.1-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ca407133536f19bdec44b3da117ef0d12e43f6d4b56ac4c765f37eca501c7bda"}, - {file = "tokenizers-0.19.1-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ce05fde79d2bc2e46ac08aacbc142bead21614d937aac950be88dc79f9db9022"}, - {file = "tokenizers-0.19.1-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:35583cd46d16f07c054efd18b5d46af4a2f070a2dd0a47914e66f3ff5efb2b1e"}, - {file = "tokenizers-0.19.1-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:43350270bfc16b06ad3f6f07eab21f089adb835544417afda0f83256a8bf8b75"}, - {file = "tokenizers-0.19.1-pp37-pypy37_pp73-macosx_10_12_x86_64.whl", hash = "sha256:b4399b59d1af5645bcee2072a463318114c39b8547437a7c2d6a186a1b5a0e2d"}, - {file = "tokenizers-0.19.1-pp37-pypy37_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:6852c5b2a853b8b0ddc5993cd4f33bfffdca4fcc5d52f89dd4b8eada99379285"}, - {file = "tokenizers-0.19.1-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bcd266ae85c3d39df2f7e7d0e07f6c41a55e9a3123bb11f854412952deacd828"}, - {file = "tokenizers-0.19.1-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ecb2651956eea2aa0a2d099434134b1b68f1c31f9a5084d6d53f08ed43d45ff2"}, - {file = "tokenizers-0.19.1-pp37-pypy37_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:b279ab506ec4445166ac476fb4d3cc383accde1ea152998509a94d82547c8e2a"}, - {file = "tokenizers-0.19.1-pp37-pypy37_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:89183e55fb86e61d848ff83753f64cded119f5d6e1f553d14ffee3700d0a4a49"}, - {file = "tokenizers-0.19.1-pp38-pypy38_pp73-macosx_10_12_x86_64.whl", hash = "sha256:b2edbc75744235eea94d595a8b70fe279dd42f3296f76d5a86dde1d46e35f574"}, - {file = "tokenizers-0.19.1-pp38-pypy38_pp73-macosx_11_0_arm64.whl", hash = "sha256:0e64bfde9a723274e9a71630c3e9494ed7b4c0f76a1faacf7fe294cd26f7ae7c"}, - {file = "tokenizers-0.19.1-pp38-pypy38_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:0b5ca92bfa717759c052e345770792d02d1f43b06f9e790ca0a1db62838816f3"}, - {file = "tokenizers-0.19.1-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6f8a20266e695ec9d7a946a019c1d5ca4eddb6613d4f466888eee04f16eedb85"}, - {file = "tokenizers-0.19.1-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:63c38f45d8f2a2ec0f3a20073cccb335b9f99f73b3c69483cd52ebc75369d8a1"}, - {file = "tokenizers-0.19.1-pp38-pypy38_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:dd26e3afe8a7b61422df3176e06664503d3f5973b94f45d5c45987e1cb711876"}, - {file = "tokenizers-0.19.1-pp38-pypy38_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:eddd5783a4a6309ce23432353cdb36220e25cbb779bfa9122320666508b44b88"}, - {file = "tokenizers-0.19.1-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:56ae39d4036b753994476a1b935584071093b55c7a72e3b8288e68c313ca26e7"}, - {file = "tokenizers-0.19.1-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:f9939ca7e58c2758c01b40324a59c034ce0cebad18e0d4563a9b1beab3018243"}, - {file = "tokenizers-0.19.1-pp39-pypy39_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:6c330c0eb815d212893c67a032e9dc1b38a803eccb32f3e8172c19cc69fbb439"}, - {file = "tokenizers-0.19.1-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ec11802450a2487cdf0e634b750a04cbdc1c4d066b97d94ce7dd2cb51ebb325b"}, - {file = "tokenizers-0.19.1-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a2b718f316b596f36e1dae097a7d5b91fc5b85e90bf08b01ff139bd8953b25af"}, - {file = "tokenizers-0.19.1-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:ed69af290c2b65169f0ba9034d1dc39a5db9459b32f1dd8b5f3f32a3fcf06eab"}, - {file = "tokenizers-0.19.1-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:f8a9c828277133af13f3859d1b6bf1c3cb6e9e1637df0e45312e6b7c2e622b1f"}, - {file = "tokenizers-0.19.1.tar.gz", hash = "sha256:ee59e6680ed0fdbe6b724cf38bd70400a0c1dd623b07ac729087270caeac88e3"}, + {file = "tokenizers-0.20.0-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:6cff5c5e37c41bc5faa519d6f3df0679e4b37da54ea1f42121719c5e2b4905c0"}, + {file = "tokenizers-0.20.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:62a56bf75c27443432456f4ca5ca055befa95e25be8a28141cc495cac8ae4d6d"}, + {file = "tokenizers-0.20.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:68cc7de6a63f09c4a86909c2597b995aa66e19df852a23aea894929c74369929"}, + {file = "tokenizers-0.20.0-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:053c37ecee482cc958fdee53af3c6534286a86f5d35aac476f7c246830e53ae5"}, + {file = "tokenizers-0.20.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3d7074aaabc151a6363fa03db5493fc95b423b2a1874456783989e96d541c7b6"}, + {file = "tokenizers-0.20.0-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a11435780f2acd89e8fefe5e81cecf01776f6edb9b3ac95bcb76baee76b30b90"}, + {file = "tokenizers-0.20.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9a81cd2712973b007d84268d45fc3f6f90a79c31dfe7f1925e6732f8d2959987"}, + {file = "tokenizers-0.20.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d7dfd796ab9d909f76fb93080e1c7c8309f196ecb316eb130718cd5e34231c69"}, + {file = "tokenizers-0.20.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:8029ad2aa8cb00605c9374566034c1cc1b15130713e0eb5afcef6cface8255c9"}, + {file = "tokenizers-0.20.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:ca4d54260ebe97d59dfa9a30baa20d0c4dd9137d99a8801700055c561145c24e"}, + {file = "tokenizers-0.20.0-cp310-none-win32.whl", hash = "sha256:95ee16b57cec11b86a7940174ec5197d506439b0f415ab3859f254b1dffe9df0"}, + {file = "tokenizers-0.20.0-cp310-none-win_amd64.whl", hash = "sha256:0a61a11e93eeadbf02aea082ffc75241c4198e0608bbbac4f65a9026851dcf37"}, + {file = "tokenizers-0.20.0-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:6636b798b3c4d6c9b1af1a918bd07c867808e5a21c64324e95318a237e6366c3"}, + {file = "tokenizers-0.20.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:5ec603e42eaf499ffd58b9258162add948717cf21372458132f14e13a6bc7172"}, + {file = "tokenizers-0.20.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cce124264903a8ea6f8f48e1cc7669e5ef638c18bd4ab0a88769d5f92debdf7f"}, + {file = "tokenizers-0.20.0-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:07bbeba0231cf8de07aa6b9e33e9779ff103d47042eeeb859a8c432e3292fb98"}, + {file = "tokenizers-0.20.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:06c0ca8397b35d38b83a44a9c6929790c1692957d88541df061cb34d82ebbf08"}, + {file = "tokenizers-0.20.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ca6557ac3b83d912dfbb1f70ab56bd4b0594043916688e906ede09f42e192401"}, + {file = "tokenizers-0.20.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2a5ad94c9e80ac6098328bee2e3264dbced4c6faa34429994d473f795ec58ef4"}, + {file = "tokenizers-0.20.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0b5c7f906ee6bec30a9dc20268a8b80f3b9584de1c9f051671cb057dc6ce28f6"}, + {file = "tokenizers-0.20.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:31e087e9ee1b8f075b002bfee257e858dc695f955b43903e1bb4aa9f170e37fe"}, + {file = "tokenizers-0.20.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:c3124fb6f3346cb3d8d775375d3b429bf4dcfc24f739822702009d20a4297990"}, + {file = "tokenizers-0.20.0-cp311-none-win32.whl", hash = "sha256:a4bb8b40ba9eefa621fdcabf04a74aa6038ae3be0c614c6458bd91a4697a452f"}, + {file = "tokenizers-0.20.0-cp311-none-win_amd64.whl", hash = "sha256:2b709d371f1fe60a28ef0c5c67815952d455ca7f34dbe7197eaaed3cc54b658e"}, + {file = "tokenizers-0.20.0-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:15c81a17d0d66f4987c6ca16f4bea7ec253b8c7ed1bb00fdc5d038b1bb56e714"}, + {file = "tokenizers-0.20.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:6a531cdf1fb6dc41c984c785a3b299cb0586de0b35683842a3afbb1e5207f910"}, + {file = "tokenizers-0.20.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:06caabeb4587f8404e0cd9d40f458e9cba3e815c8155a38e579a74ff3e2a4301"}, + {file = "tokenizers-0.20.0-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:8768f964f23f5b9f50546c0369c75ab3262de926983888bbe8b98be05392a79c"}, + {file = "tokenizers-0.20.0-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:626403860152c816f97b649fd279bd622c3d417678c93b4b1a8909b6380b69a8"}, + {file = "tokenizers-0.20.0-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9c1b88fa9e5ff062326f4bf82681da5a96fca7104d921a6bd7b1e6fcf224af26"}, + {file = "tokenizers-0.20.0-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3d7e559436a07dc547f22ce1101f26d8b2fad387e28ec8e7e1e3b11695d681d8"}, + {file = "tokenizers-0.20.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e48afb75e50449848964e4a67b0da01261dd3aa8df8daecf10db8fd7f5b076eb"}, + {file = "tokenizers-0.20.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:baf5d0e1ff44710a95eefc196dd87666ffc609fd447c5e5b68272a7c3d342a1d"}, + {file = "tokenizers-0.20.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:e5e56df0e8ed23ba60ae3848c3f069a0710c4b197218fe4f89e27eba38510768"}, + {file = "tokenizers-0.20.0-cp312-none-win32.whl", hash = "sha256:ec53e5ecc142a82432f9c6c677dbbe5a2bfee92b8abf409a9ecb0d425ee0ce75"}, + {file = "tokenizers-0.20.0-cp312-none-win_amd64.whl", hash = "sha256:f18661ece72e39c0dfaa174d6223248a15b457dbd4b0fc07809b8e6d3ca1a234"}, + {file = "tokenizers-0.20.0-cp37-cp37m-macosx_10_12_x86_64.whl", hash = "sha256:f7065b1084d8d1a03dc89d9aad69bcbc8415d4bc123c367063eb32958cd85054"}, + {file = "tokenizers-0.20.0-cp37-cp37m-macosx_11_0_arm64.whl", hash = "sha256:e5d4069e4714e3f7ba0a4d3d44f9d84a432cd4e4aa85c3d7dd1f51440f12e4a1"}, + {file = "tokenizers-0.20.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:799b808529e54b7e1a36350bda2aeb470e8390e484d3e98c10395cee61d4e3c6"}, + {file = "tokenizers-0.20.0-cp37-cp37m-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:7f9baa027cc8a281ad5f7725a93c204d7a46986f88edbe8ef7357f40a23fb9c7"}, + {file = "tokenizers-0.20.0-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:010ec7f3f7a96adc4c2a34a3ada41fa14b4b936b5628b4ff7b33791258646c6b"}, + {file = "tokenizers-0.20.0-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:98d88f06155335b14fd78e32ee28ca5b2eb30fced4614e06eb14ae5f7fba24ed"}, + {file = "tokenizers-0.20.0-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e13eb000ef540c2280758d1b9cfa5fe424b0424ae4458f440e6340a4f18b2638"}, + {file = "tokenizers-0.20.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fab3cf066ff426f7e6d70435dc28a9ff01b2747be83810e397cba106f39430b0"}, + {file = "tokenizers-0.20.0-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:39fa3761b30a89368f322e5daf4130dce8495b79ad831f370449cdacfb0c0d37"}, + {file = "tokenizers-0.20.0-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:c8da0fba4d179ddf2607821575998df3c294aa59aa8df5a6646dc64bc7352bce"}, + {file = "tokenizers-0.20.0-cp37-none-win32.whl", hash = "sha256:fada996d6da8cf213f6e3c91c12297ad4f6cdf7a85c2fadcd05ec32fa6846fcd"}, + {file = "tokenizers-0.20.0-cp37-none-win_amd64.whl", hash = "sha256:7d29aad702279e0760c265fcae832e89349078e3418dd329732d4503259fd6bd"}, + {file = "tokenizers-0.20.0-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:099c68207f3ef0227ecb6f80ab98ea74de559f7b124adc7b17778af0250ee90a"}, + {file = "tokenizers-0.20.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:68012d8a8cddb2eab3880870d7e2086cb359c7f7a2b03f5795044f5abff4e850"}, + {file = "tokenizers-0.20.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9253bdd209c6aee168deca7d0e780581bf303e0058f268f9bb06859379de19b6"}, + {file = "tokenizers-0.20.0-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:8f868600ddbcb0545905ed075eb7218a0756bf6c09dae7528ea2f8436ebd2c93"}, + {file = "tokenizers-0.20.0-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9a9643d9c8c5f99b6aba43fd10034f77cc6c22c31f496d2f0ee183047d948fa0"}, + {file = "tokenizers-0.20.0-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c375c6a889aeab44734028bc65cc070acf93ccb0f9368be42b67a98e1063d3f6"}, + {file = "tokenizers-0.20.0-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e359f852328e254f070bbd09a19a568421d23388f04aad9f2fb7da7704c7228d"}, + {file = "tokenizers-0.20.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d98b01a309d4387f3b1c1dd68a8b8136af50376cf146c1b7e8d8ead217a5be4b"}, + {file = "tokenizers-0.20.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:459f7537119554c2899067dec1ac74a00d02beef6558f4ee2e99513bf6d568af"}, + {file = "tokenizers-0.20.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:392b87ec89452628c045c9f2a88bc2a827f4c79e7d84bc3b72752b74c2581f70"}, + {file = "tokenizers-0.20.0-cp38-none-win32.whl", hash = "sha256:55a393f893d2ed4dd95a1553c2e42d4d4086878266f437b03590d3f81984c4fe"}, + {file = "tokenizers-0.20.0-cp38-none-win_amd64.whl", hash = "sha256:30ffe33c5c2f2aab8e9a3340d0110dd9f7ace7eec7362e20a697802306bd8068"}, + {file = "tokenizers-0.20.0-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:aa2d4a6fed2a7e3f860c7fc9d48764bb30f2649d83915d66150d6340e06742b8"}, + {file = "tokenizers-0.20.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:b5ef0f814084a897e9071fc4a868595f018c5c92889197bdc4bf19018769b148"}, + {file = "tokenizers-0.20.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fc1e1b791e8c3bf4c4f265f180dadaff1c957bf27129e16fdd5e5d43c2d3762c"}, + {file = "tokenizers-0.20.0-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:2b69e55e481459c07885263743a0d3c18d52db19bae8226a19bcca4aaa213fff"}, + {file = "tokenizers-0.20.0-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4806b4d82e27a2512bc23057b2986bc8b85824914286975b84d8105ff40d03d9"}, + {file = "tokenizers-0.20.0-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9859e9ef13adf5a473ccab39d31bff9c550606ae3c784bf772b40f615742a24f"}, + {file = "tokenizers-0.20.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ef703efedf4c20488a8eb17637b55973745b27997ff87bad88ed499b397d1144"}, + {file = "tokenizers-0.20.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6eec0061bab94b1841ab87d10831fdf1b48ebaed60e6d66d66dbe1d873f92bf5"}, + {file = "tokenizers-0.20.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:980f3d0d7e73f845b69087f29a63c11c7eb924c4ad6b358da60f3db4cf24bdb4"}, + {file = "tokenizers-0.20.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:7c157550a2f3851b29d7fdc9dc059fcf81ff0c0fc49a1e5173a89d533ed043fa"}, + {file = "tokenizers-0.20.0-cp39-none-win32.whl", hash = "sha256:8a3d2f4d08608ec4f9895ec25b4b36a97f05812543190a5f2c3cd19e8f041e5a"}, + {file = "tokenizers-0.20.0-cp39-none-win_amd64.whl", hash = "sha256:d90188d12afd0c75e537f9a1d92f9c7375650188ee4f48fdc76f9e38afbd2251"}, + {file = "tokenizers-0.20.0-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:d68e15f1815357b059ec266062340c343ea7f98f7f330602df81ffa3474b6122"}, + {file = "tokenizers-0.20.0-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:23f9ecec637b9bc80da5f703808d29ed5329e56b5aa8d791d1088014f48afadc"}, + {file = "tokenizers-0.20.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f830b318ee599e3d0665b3e325f85bc75ee2d2ca6285f52e439dc22b64691580"}, + {file = "tokenizers-0.20.0-pp310-pypy310_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b3dc750def789cb1de1b5a37657919545e1d9ffa667658b3fa9cb7862407a1b8"}, + {file = "tokenizers-0.20.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e26e6c755ae884c2ea6135cd215bdd0fccafe4ee62405014b8c3cd19954e3ab9"}, + {file = "tokenizers-0.20.0-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:a1158c7174f427182e08baa2a8ded2940f2b4a3e94969a85cc9cfd16004cbcea"}, + {file = "tokenizers-0.20.0-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:6324826287a3fc198898d3dcf758fe4a8479e42d6039f4c59e2cedd3cf92f64e"}, + {file = "tokenizers-0.20.0-pp37-pypy37_pp73-macosx_10_12_x86_64.whl", hash = "sha256:7d8653149405bb0c16feaf9cfee327fdb6aaef9dc2998349fec686f35e81c4e2"}, + {file = "tokenizers-0.20.0-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b8a2dc1e402a155e97309287ca085c80eb1b7fab8ae91527d3b729181639fa51"}, + {file = "tokenizers-0.20.0-pp37-pypy37_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:07bef67b20aa6e5f7868c42c7c5eae4d24f856274a464ae62e47a0f2cccec3da"}, + {file = "tokenizers-0.20.0-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:da06e397182ff53789c506c7833220c192952c57e1581a53f503d8d953e2d67e"}, + {file = "tokenizers-0.20.0-pp37-pypy37_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:302f7e11a14814028b7fc88c45a41f1bbe9b5b35fd76d6869558d1d1809baa43"}, + {file = "tokenizers-0.20.0-pp37-pypy37_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:055ec46e807b875589dfbe3d9259f9a6ee43394fb553b03b3d1e9541662dbf25"}, + {file = "tokenizers-0.20.0-pp38-pypy38_pp73-macosx_10_12_x86_64.whl", hash = "sha256:e3144b8acebfa6ae062e8f45f7ed52e4b50fb6c62f93afc8871b525ab9fdcab3"}, + {file = "tokenizers-0.20.0-pp38-pypy38_pp73-macosx_11_0_arm64.whl", hash = "sha256:b52aa3fd14b2a07588c00a19f66511cff5cca8f7266ca3edcdd17f3512ad159f"}, + {file = "tokenizers-0.20.0-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2b8cf52779ffc5d4d63a0170fbeb512372bad0dd014ce92bbb9149756c831124"}, + {file = "tokenizers-0.20.0-pp38-pypy38_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:983a45dd11a876124378dae71d6d9761822199b68a4c73f32873d8cdaf326a5b"}, + {file = "tokenizers-0.20.0-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:df6b819c9a19831ebec581e71a7686a54ab45d90faf3842269a10c11d746de0c"}, + {file = "tokenizers-0.20.0-pp38-pypy38_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:e738cfd80795fcafcef89c5731c84b05638a4ab3f412f97d5ed7765466576eb1"}, + {file = "tokenizers-0.20.0-pp38-pypy38_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:c8842c7be2fadb9c9edcee233b1b7fe7ade406c99b0973f07439985c1c1d0683"}, + {file = "tokenizers-0.20.0-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:e47a82355511c373a4a430c4909dc1e518e00031207b1fec536c49127388886b"}, + {file = "tokenizers-0.20.0-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:9afbf359004551179a5db19424180c81276682773cff2c5d002f6eaaffe17230"}, + {file = "tokenizers-0.20.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a07eaa8799a92e6af6f472c21a75bf71575de2af3c0284120b7a09297c0de2f3"}, + {file = "tokenizers-0.20.0-pp39-pypy39_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0994b2e5fc53a301071806bc4303e4bc3bdc3f490e92a21338146a36746b0872"}, + {file = "tokenizers-0.20.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0b6466e0355b603d10e3cc3d282d350b646341b601e50969464a54939f9848d0"}, + {file = "tokenizers-0.20.0-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:1e86594c2a433cb1ea09cfbe596454448c566e57ee8905bd557e489d93e89986"}, + {file = "tokenizers-0.20.0-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:3e14cdef1efa96ecead6ea64a891828432c3ebba128bdc0596e3059fea104ef3"}, + {file = "tokenizers-0.20.0.tar.gz", hash = "sha256:39d7acc43f564c274085cafcd1dae9d36f332456de1a31970296a6b8da4eac8d"}, ] [package.dependencies] @@ -6101,13 +6163,13 @@ telegram = ["requests"] [[package]] name = "transformers" -version = "4.44.2" +version = "4.45.0" description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow" optional = false python-versions = ">=3.8.0" files = [ - {file = "transformers-4.44.2-py3-none-any.whl", hash = "sha256:1c02c65e7bfa5e52a634aff3da52138b583fc6f263c1f28d547dc144ba3d412d"}, - {file = "transformers-4.44.2.tar.gz", hash = "sha256:36aa17cc92ee154058e426d951684a2dab48751b35b49437896f898931270826"}, + {file = "transformers-4.45.0-py3-none-any.whl", hash = "sha256:f04a82926676056afb3bbf4df7d76ceb1fc2b2746247a87f3f9be4674adc95d7"}, + {file = "transformers-4.45.0.tar.gz", hash = "sha256:29629f87965acc7b15e458a24580832d85da18ddc119410211747fe778c200ce"}, ] [package.dependencies] @@ -6119,21 +6181,21 @@ pyyaml = ">=5.1" regex = "!=2019.12.17" requests = "*" safetensors = ">=0.4.1" -tokenizers = ">=0.19,<0.20" +tokenizers = ">=0.20,<0.21" 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,<0.14.0)", "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"] +accelerate = ["accelerate (>=0.26.0)"] +agents = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.26.0)", "datasets (!=2.5.0)", "diffusers", "opencv-python", "sentencepiece (>=0.1.91,!=0.1.92)", "torch"] +all = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.26.0)", "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,<0.14.0)", "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 (>=0.20,<0.21)", "torch", "torchaudio", "torchvision"] audio = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"] -benchmark = ["optimum-benchmark (>=0.2.0)"] +benchmark = ["optimum-benchmark (>=0.3.0)"] 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 (==0.5.1)", "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,<0.14.0)", "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 (==0.5.1)", "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,<0.14.0)", "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 (==0.5.1)", "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 (==0.5.1)", "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)"] +deepspeed = ["accelerate (>=0.26.0)", "deepspeed (>=0.9.3)"] +deepspeed-testing = ["GitPython (<3.1.19)", "accelerate (>=0.26.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "deepspeed (>=0.9.3)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "nltk (<=3.8.1)", "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 (==0.5.1)", "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 (>=0.26.0)", "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,<0.14.0)", "libcst", "librosa", "nltk (<=3.8.1)", "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)", "rich", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.5.1)", "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 (>=0.20,<0.21)", "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,<0.14.0)", "libcst", "librosa", "nltk (<=3.8.1)", "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", "rich", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.5.1)", "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 (>=0.20,<0.21)", "urllib3 (<2.0.0)"] +dev-torch = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.26.0)", "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", "libcst", "librosa", "nltk (<=3.8.1)", "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)", "rich", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.5.1)", "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 (>=0.20,<0.21)", "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"] @@ -6144,7 +6206,7 @@ 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 (==0.5.1)", "urllib3 (<2.0.0)"] +quality = ["GitPython (<3.1.19)", "datasets (!=2.5.0)", "isort (>=5.5.4)", "libcst", "rich", "ruff (==0.5.1)", "urllib3 (<2.0.0)"] ray = ["ray[tune] (>=2.7.0)"] retrieval = ["datasets (!=2.5.0)", "faiss-cpu"] ruff = ["ruff (==0.5.1)"] @@ -6154,16 +6216,17 @@ 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 (==0.5.1)", "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 (<=3.8.1)", "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 (==0.5.1)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "timeout-decorator"] tf = ["keras-nlp (>=0.3.1,<0.14.0)", "onnxconverter-common", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx"] tf-cpu = ["keras (>2.9,<2.16)", "keras-nlp (>=0.3.1,<0.14.0)", "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)"] +tiktoken = ["blobfile", "tiktoken"] timm = ["timm (<=0.9.16)"] -tokenizers = ["tokenizers (>=0.19,<0.20)"] -torch = ["accelerate (>=0.21.0)", "torch"] +tokenizers = ["tokenizers (>=0.20,<0.21)"] +torch = ["accelerate (>=0.26.0)", "torch"] torch-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"] torch-vision = ["Pillow (>=10.0.1,<=15.0)", "torchvision"] -torchhub = ["filelock", "huggingface-hub (>=0.23.2,<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)", "packaging (>=20.0)", "protobuf", "regex (!=2019.12.17)", "requests", "sentencepiece (>=0.1.91,!=0.1.92)", "tokenizers (>=0.20,<0.21)", "torch", "tqdm (>=4.27)"] video = ["av (==9.2.0)", "decord (==0.6.0)"] vision = ["Pillow (>=10.0.1,<=15.0)"] @@ -7021,6 +7084,7 @@ cffi = ["cffi (>=1.11)"] embeddings-azopenai = ["llama-index-embeddings-azure-openai"] embeddings-gemini = ["llama-index-embeddings-gemini"] embeddings-huggingface = ["einops", "llama-index-embeddings-huggingface"] +embeddings-mistral = ["llama-index-embeddings-mistralai"] embeddings-ollama = ["llama-index-embeddings-ollama"] embeddings-openai = ["llama-index-embeddings-openai"] embeddings-sagemaker = ["boto3"] @@ -7043,4 +7107,4 @@ vector-stores-qdrant = ["llama-index-vector-stores-qdrant"] [metadata] lock-version = "2.0" python-versions = ">=3.11,<3.12" -content-hash = "a16c1280818f54b7980de14ba852bfb8216924ab2cfd91a8fff409d8c4724755" +content-hash = "16e3be4521aa64c936ee8fb841655f15090b71cf8faaeed7e73a4bcdf3fbdea2" diff --git a/private_gpt/components/embedding/embedding_component.py b/private_gpt/components/embedding/embedding_component.py index 5d3e99749..b55cef873 100644 --- a/private_gpt/components/embedding/embedding_component.py +++ b/private_gpt/components/embedding/embedding_component.py @@ -144,6 +144,23 @@ def __init__(self, settings: Settings) -> None: api_key=settings.gemini.api_key, model_name=settings.gemini.embedding_model, ) + case "mistralai": + try: + from llama_index.embeddings.mistralai import ( # type: ignore + MistralAIEmbedding, + ) + except ImportError as e: + raise ImportError( + "Mistral dependencies not found, install with `poetry install --extras embeddings-mistral`" + ) from e + + api_key = settings.openai.api_key + model = settings.openai.embedding_model + + self.embedding_model = MistralAIEmbedding( + api_key=api_key, + model=model, + ) case "mock": # Not a random number, is the dimensionality used by # the default embedding model diff --git a/private_gpt/components/ingest/ingest_helper.py b/private_gpt/components/ingest/ingest_helper.py index a11090702..da62568bc 100644 --- a/private_gpt/components/ingest/ingest_helper.py +++ b/private_gpt/components/ingest/ingest_helper.py @@ -92,7 +92,13 @@ def _load_file_to_documents(file_name: str, file_data: Path) -> list[Document]: return string_reader.load_data([file_data.read_text()]) logger.debug("Specific reader found for extension=%s", extension) - return reader_cls().load_data(file_data) + documents = reader_cls().load_data(file_data) + + # Sanitize NUL bytes in text which can't be stored in Postgres + for i in range(len(documents)): + documents[i].text = documents[i].text.replace("\u0000", "") + + return documents @staticmethod def _exclude_metadata(documents: list[Document]) -> None: diff --git a/private_gpt/settings/settings.py b/private_gpt/settings/settings.py index 5781a386f..0589f13a3 100644 --- a/private_gpt/settings/settings.py +++ b/private_gpt/settings/settings.py @@ -197,7 +197,14 @@ class HuggingFaceSettings(BaseModel): class EmbeddingSettings(BaseModel): mode: Literal[ - "huggingface", "openai", "azopenai", "sagemaker", "ollama", "mock", "gemini" + "huggingface", + "openai", + "azopenai", + "sagemaker", + "ollama", + "mock", + "gemini", + "mistralai", ] ingest_mode: Literal["simple", "batch", "parallel", "pipeline"] = Field( "simple", @@ -350,6 +357,10 @@ class AzureOpenAISettings(BaseModel): class UISettings(BaseModel): enabled: bool path: str + default_mode: Literal["RAG", "Search", "Basic", "Summarize"] = Field( + "RAG", + description="The default mode.", + ) default_chat_system_prompt: str = Field( None, description="The default system prompt to use for the chat mode.", diff --git a/private_gpt/ui/ui.py b/private_gpt/ui/ui.py index 5b9459040..abdfb0c6d 100644 --- a/private_gpt/ui/ui.py +++ b/private_gpt/ui/ui.py @@ -100,8 +100,11 @@ def __init__( self._selected_filename = None # Initialize system prompt based on default mode - self.mode = MODES[0] - self._system_prompt = self._get_default_system_prompt(self.mode) + default_mode_map = {mode.value: mode for mode in Modes} + self._default_mode = default_mode_map.get( + settings().ui.default_mode, Modes.RAG_MODE + ) + self._system_prompt = self._get_default_system_prompt(self._default_mode) def _chat( self, message: str, history: list[list[str]], mode: Modes, *_: Any @@ -391,7 +394,7 @@ def _build_ui_blocks(self) -> gr.Blocks: with gr.Row(equal_height=False): with gr.Column(scale=3): - default_mode = MODES[0] + default_mode = self._default_mode mode = gr.Radio( [mode.value for mode in MODES], label="Mode", diff --git a/pyproject.toml b/pyproject.toml index 1544306f5..ca355c16b 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -30,6 +30,7 @@ llama-index-embeddings-huggingface = {version ="*", optional = true} llama-index-embeddings-openai = {version ="*", optional = true} llama-index-embeddings-azure-openai = {version ="*", optional = true} llama-index-embeddings-gemini = {version ="*", optional = true} +llama-index-embeddings-mistralai = {version ="*", optional = true} llama-index-vector-stores-qdrant = {version ="*", optional = true} llama-index-vector-stores-milvus = {version ="*", optional = true} llama-index-vector-stores-chroma = {version ="*", optional = true} @@ -74,6 +75,7 @@ embeddings-openai = ["llama-index-embeddings-openai"] embeddings-sagemaker = ["boto3"] embeddings-azopenai = ["llama-index-embeddings-azure-openai"] embeddings-gemini = ["llama-index-embeddings-gemini"] +embeddings-mistral = ["llama-index-embeddings-mistralai"] vector-stores-qdrant = ["llama-index-vector-stores-qdrant"] vector-stores-clickhouse = ["llama-index-vector-stores-clickhouse", "clickhouse_connect"] vector-stores-chroma = ["llama-index-vector-stores-chroma"] diff --git a/settings.yaml b/settings.yaml index f030604a3..eda1af860 100644 --- a/settings.yaml +++ b/settings.yaml @@ -25,21 +25,23 @@ data: ui: enabled: true path: / + # "RAG", "Search", "Basic", or "Summarize" + default_mode: "RAG" default_chat_system_prompt: > - You are a helpful, respectful and honest assistant. + You are a helpful, respectful and honest assistant. Always answer as helpfully as possible and follow ALL given instructions. Do not speculate or make up information. Do not reference any given instructions or context. default_query_system_prompt: > - You can only answer questions about the provided context. - If you know the answer but it is not based in the provided context, don't provide + You can only answer questions about the provided context. + If you know the answer but it is not based in the provided context, don't provide the answer, just state the answer is not in the context provided. default_summarization_system_prompt: > - Provide a comprehensive summary of the provided context information. + Provide a comprehensive summary of the provided context information. The summary should cover all the key points and main ideas presented in - the original text, while also condensing the information into a concise + the original text, while also condensing the information into a concise and easy-to-understand format. Please ensure that the summary includes - relevant details and examples that support the main ideas, while avoiding + relevant details and examples that support the main ideas, while avoiding any unnecessary information or repetition. delete_file_button_enabled: true delete_all_files_button_enabled: true