diff --git a/libs/community/poetry.lock b/libs/community/poetry.lock index 7e77841664f1a..d66935d750c5e 100644 --- a/libs/community/poetry.lock +++ b/libs/community/poetry.lock @@ -1,4 +1,4 @@ -# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand. +# This file is automatically @generated by Poetry 1.8.4 and should not be changed by hand. [[package]] name = "aiohappyeyeballs" @@ -2532,30 +2532,41 @@ files = [ {file = "pandas-2.2.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:381175499d3802cde0eabbaf6324cce0c4f5d52ca6f8c377c29ad442f50f6348"}, {file = "pandas-2.2.3-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:d9c45366def9a3dd85a6454c0e7908f2b3b8e9c138f5dc38fed7ce720d8453ed"}, {file = "pandas-2.2.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:86976a1c5b25ae3f8ccae3a5306e443569ee3c3faf444dfd0f41cda24667ad57"}, + {file = "pandas-2.2.3-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:b8661b0238a69d7aafe156b7fa86c44b881387509653fdf857bebc5e4008ad42"}, {file = "pandas-2.2.3-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:37e0aced3e8f539eccf2e099f65cdb9c8aa85109b0be6e93e2baff94264bdc6f"}, {file = "pandas-2.2.3-cp310-cp310-win_amd64.whl", hash = "sha256:56534ce0746a58afaf7942ba4863e0ef81c9c50d3f0ae93e9497d6a41a057645"}, {file = "pandas-2.2.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:66108071e1b935240e74525006034333f98bcdb87ea116de573a6a0dccb6c039"}, {file = "pandas-2.2.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:7c2875855b0ff77b2a64a0365e24455d9990730d6431b9e0ee18ad8acee13dbd"}, + {file = "pandas-2.2.3-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cd8d0c3be0515c12fed0bdbae072551c8b54b7192c7b1fda0ba56059a0179698"}, {file = "pandas-2.2.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c124333816c3a9b03fbeef3a9f230ba9a737e9e5bb4060aa2107a86cc0a497fc"}, + {file = "pandas-2.2.3-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:63cc132e40a2e084cf01adf0775b15ac515ba905d7dcca47e9a251819c575ef3"}, {file = "pandas-2.2.3-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:29401dbfa9ad77319367d36940cd8a0b3a11aba16063e39632d98b0e931ddf32"}, {file = "pandas-2.2.3-cp311-cp311-win_amd64.whl", hash = "sha256:3fc6873a41186404dad67245896a6e440baacc92f5b716ccd1bc9ed2995ab2c5"}, {file = "pandas-2.2.3-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:b1d432e8d08679a40e2a6d8b2f9770a5c21793a6f9f47fdd52c5ce1948a5a8a9"}, {file = "pandas-2.2.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:a5a1595fe639f5988ba6a8e5bc9649af3baf26df3998a0abe56c02609392e0a4"}, + {file = "pandas-2.2.3-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:5de54125a92bb4d1c051c0659e6fcb75256bf799a732a87184e5ea503965bce3"}, {file = "pandas-2.2.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fffb8ae78d8af97f849404f21411c95062db1496aeb3e56f146f0355c9989319"}, + {file = "pandas-2.2.3-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:6dfcb5ee8d4d50c06a51c2fffa6cff6272098ad6540aed1a76d15fb9318194d8"}, {file = "pandas-2.2.3-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:062309c1b9ea12a50e8ce661145c6aab431b1e99530d3cd60640e255778bd43a"}, {file = "pandas-2.2.3-cp312-cp312-win_amd64.whl", hash = "sha256:59ef3764d0fe818125a5097d2ae867ca3fa64df032331b7e0917cf5d7bf66b13"}, {file = "pandas-2.2.3-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:f00d1345d84d8c86a63e476bb4955e46458b304b9575dcf71102b5c705320015"}, {file = "pandas-2.2.3-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:3508d914817e153ad359d7e069d752cdd736a247c322d932eb89e6bc84217f28"}, + {file = "pandas-2.2.3-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:22a9d949bfc9a502d320aa04e5d02feab689d61da4e7764b62c30b991c42c5f0"}, {file = "pandas-2.2.3-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f3a255b2c19987fbbe62a9dfd6cff7ff2aa9ccab3fc75218fd4b7530f01efa24"}, + {file = "pandas-2.2.3-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:800250ecdadb6d9c78eae4990da62743b857b470883fa27f652db8bdde7f6659"}, {file = "pandas-2.2.3-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:6374c452ff3ec675a8f46fd9ab25c4ad0ba590b71cf0656f8b6daa5202bca3fb"}, {file = "pandas-2.2.3-cp313-cp313-win_amd64.whl", hash = "sha256:61c5ad4043f791b61dd4752191d9f07f0ae412515d59ba8f005832a532f8736d"}, {file = "pandas-2.2.3-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:3b71f27954685ee685317063bf13c7709a7ba74fc996b84fc6821c59b0f06468"}, {file = "pandas-2.2.3-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:38cf8125c40dae9d5acc10fa66af8ea6fdf760b2714ee482ca691fc66e6fcb18"}, + {file = "pandas-2.2.3-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:ba96630bc17c875161df3818780af30e43be9b166ce51c9a18c1feae342906c2"}, {file = "pandas-2.2.3-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1db71525a1538b30142094edb9adc10be3f3e176748cd7acc2240c2f2e5aa3a4"}, + {file = "pandas-2.2.3-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:15c0e1e02e93116177d29ff83e8b1619c93ddc9c49083f237d4312337a61165d"}, {file = "pandas-2.2.3-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:ad5b65698ab28ed8d7f18790a0dc58005c7629f227be9ecc1072aa74c0c1d43a"}, {file = "pandas-2.2.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:bc6b93f9b966093cb0fd62ff1a7e4c09e6d546ad7c1de191767baffc57628f39"}, {file = "pandas-2.2.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:5dbca4c1acd72e8eeef4753eeca07de9b1db4f398669d5994086f788a5d7cc30"}, + {file = "pandas-2.2.3-cp39-cp39-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:8cd6d7cc958a3910f934ea8dbdf17b2364827bb4dafc38ce6eef6bb3d65ff09c"}, {file = "pandas-2.2.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:99df71520d25fade9db7c1076ac94eb994f4d2673ef2aa2e86ee039b6746d20c"}, + {file = "pandas-2.2.3-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:31d0ced62d4ea3e231a9f228366919a5ea0b07440d9d4dac345376fd8e1477ea"}, {file = "pandas-2.2.3-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:7eee9e7cea6adf3e3d24e304ac6b8300646e2a5d1cd3a3c2abed9101b0846761"}, {file = "pandas-2.2.3-cp39-cp39-win_amd64.whl", hash = "sha256:4850ba03528b6dd51d6c5d273c46f183f39a9baf3f0143e566b89450965b105e"}, {file = "pandas-2.2.3.tar.gz", hash = "sha256:4f18ba62b61d7e192368b84517265a99b4d7ee8912f8708660fb4a366cc82667"}, @@ -3054,6 +3065,28 @@ files = [ [package.extras] windows-terminal = ["colorama (>=0.4.6)"] +[[package]] +name = "pypdf" +version = "5.1.0" +description = "A pure-python PDF library capable of splitting, merging, cropping, and transforming PDF files" +optional = false +python-versions = ">=3.8" +files = [ + {file = "pypdf-5.1.0-py3-none-any.whl", hash = "sha256:3bd4f503f4ebc58bae40d81e81a9176c400cbbac2ba2d877367595fb524dfdfc"}, + {file = "pypdf-5.1.0.tar.gz", hash = "sha256:425a129abb1614183fd1aca6982f650b47f8026867c0ce7c4b9f281c443d2740"}, +] + +[package.dependencies] +typing_extensions = {version = ">=4.0", markers = "python_version < \"3.11\""} + +[package.extras] +crypto = ["cryptography"] +cryptodome = ["PyCryptodome"] +dev = ["black", "flit", "pip-tools", "pre-commit (<2.18.0)", "pytest-cov", "pytest-socket", "pytest-timeout", "pytest-xdist", "wheel"] +docs = ["myst_parser", "sphinx", "sphinx_rtd_theme"] +full = ["Pillow (>=8.0.0)", "cryptography"] +image = ["Pillow (>=8.0.0)"] + [[package]] name = "pytest" version = "7.4.4" @@ -3774,7 +3807,9 @@ python-versions = ">=3.7" files = [ {file = "SQLAlchemy-2.0.35-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:67219632be22f14750f0d1c70e62f204ba69d28f62fd6432ba05ab295853de9b"}, {file = "SQLAlchemy-2.0.35-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:4668bd8faf7e5b71c0319407b608f278f279668f358857dbfd10ef1954ac9f90"}, + {file = "SQLAlchemy-2.0.35-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cb8bea573863762bbf45d1e13f87c2d2fd32cee2dbd50d050f83f87429c9e1ea"}, {file = "SQLAlchemy-2.0.35-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f552023710d4b93d8fb29a91fadf97de89c5926c6bd758897875435f2a939f33"}, + {file = "SQLAlchemy-2.0.35-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:016b2e665f778f13d3c438651dd4de244214b527a275e0acf1d44c05bc6026a9"}, {file = "SQLAlchemy-2.0.35-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:7befc148de64b6060937231cbff8d01ccf0bfd75aa26383ffdf8d82b12ec04ff"}, {file = "SQLAlchemy-2.0.35-cp310-cp310-win32.whl", hash = "sha256:22b83aed390e3099584b839b93f80a0f4a95ee7f48270c97c90acd40ee646f0b"}, {file = "SQLAlchemy-2.0.35-cp310-cp310-win_amd64.whl", hash = "sha256:a29762cd3d116585278ffb2e5b8cc311fb095ea278b96feef28d0b423154858e"}, @@ -3795,22 +3830,29 @@ files = [ {file = "SQLAlchemy-2.0.35-cp312-cp312-win32.whl", hash = "sha256:0f9f3f9a3763b9c4deb8c5d09c4cc52ffe49f9876af41cc1b2ad0138878453cf"}, {file = "SQLAlchemy-2.0.35-cp312-cp312-win_amd64.whl", hash = "sha256:25b0f63e7fcc2a6290cb5f7f5b4fc4047843504983a28856ce9b35d8f7de03cc"}, {file = "SQLAlchemy-2.0.35-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:f021d334f2ca692523aaf7bbf7592ceff70c8594fad853416a81d66b35e3abf9"}, + {file = "SQLAlchemy-2.0.35-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:05c3f58cf91683102f2f0265c0db3bd3892e9eedabe059720492dbaa4f922da1"}, {file = "SQLAlchemy-2.0.35-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:032d979ce77a6c2432653322ba4cbeabf5a6837f704d16fa38b5a05d8e21fa00"}, + {file = "SQLAlchemy-2.0.35-cp37-cp37m-musllinux_1_2_aarch64.whl", hash = "sha256:2e795c2f7d7249b75bb5f479b432a51b59041580d20599d4e112b5f2046437a3"}, {file = "SQLAlchemy-2.0.35-cp37-cp37m-musllinux_1_2_x86_64.whl", hash = "sha256:cc32b2990fc34380ec2f6195f33a76b6cdaa9eecf09f0c9404b74fc120aef36f"}, {file = "SQLAlchemy-2.0.35-cp37-cp37m-win32.whl", hash = "sha256:9509c4123491d0e63fb5e16199e09f8e262066e58903e84615c301dde8fa2e87"}, {file = "SQLAlchemy-2.0.35-cp37-cp37m-win_amd64.whl", hash = "sha256:3655af10ebcc0f1e4e06c5900bb33e080d6a1fa4228f502121f28a3b1753cde5"}, {file = "SQLAlchemy-2.0.35-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:4c31943b61ed8fdd63dfd12ccc919f2bf95eefca133767db6fbbd15da62078ec"}, {file = "SQLAlchemy-2.0.35-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:a62dd5d7cc8626a3634208df458c5fe4f21200d96a74d122c83bc2015b333bc1"}, + {file = "SQLAlchemy-2.0.35-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0630774b0977804fba4b6bbea6852ab56c14965a2b0c7fc7282c5f7d90a1ae72"}, {file = "SQLAlchemy-2.0.35-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8d625eddf7efeba2abfd9c014a22c0f6b3796e0ffb48f5d5ab106568ef01ff5a"}, + {file = "SQLAlchemy-2.0.35-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:ada603db10bb865bbe591939de854faf2c60f43c9b763e90f653224138f910d9"}, {file = "SQLAlchemy-2.0.35-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:c41411e192f8d3ea39ea70e0fae48762cd11a2244e03751a98bd3c0ca9a4e936"}, {file = "SQLAlchemy-2.0.35-cp38-cp38-win32.whl", hash = "sha256:d299797d75cd747e7797b1b41817111406b8b10a4f88b6e8fe5b5e59598b43b0"}, {file = "SQLAlchemy-2.0.35-cp38-cp38-win_amd64.whl", hash = "sha256:0375a141e1c0878103eb3d719eb6d5aa444b490c96f3fedab8471c7f6ffe70ee"}, {file = "SQLAlchemy-2.0.35-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:ccae5de2a0140d8be6838c331604f91d6fafd0735dbdcee1ac78fc8fbaba76b4"}, {file = "SQLAlchemy-2.0.35-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:2a275a806f73e849e1c309ac11108ea1a14cd7058577aba962cd7190e27c9e3c"}, + {file = "SQLAlchemy-2.0.35-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:732e026240cdd1c1b2e3ac515c7a23820430ed94292ce33806a95869c46bd139"}, {file = "SQLAlchemy-2.0.35-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:890da8cd1941fa3dab28c5bac3b9da8502e7e366f895b3b8e500896f12f94d11"}, + {file = "SQLAlchemy-2.0.35-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:c0d8326269dbf944b9201911b0d9f3dc524d64779a07518199a58384c3d37a44"}, {file = "SQLAlchemy-2.0.35-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:b76d63495b0508ab9fc23f8152bac63205d2a704cd009a2b0722f4c8e0cba8e0"}, {file = "SQLAlchemy-2.0.35-cp39-cp39-win32.whl", hash = "sha256:69683e02e8a9de37f17985905a5eca18ad651bf592314b4d3d799029797d0eb3"}, {file = "SQLAlchemy-2.0.35-cp39-cp39-win_amd64.whl", hash = "sha256:aee110e4ef3c528f3abbc3c2018c121e708938adeeff9006428dd7c8555e9b3f"}, + {file = "SQLAlchemy-2.0.35-py3-none-any.whl", hash = "sha256:2ab3f0336c0387662ce6221ad30ab3a5e6499aab01b9790879b6578fd9b8faa1"}, {file = "sqlalchemy-2.0.35.tar.gz", hash = "sha256:e11d7ea4d24f0a262bccf9a7cd6284c976c5369dac21db237cff59586045ab9f"}, ] @@ -4553,4 +4595,4 @@ type = ["pytest-mypy"] [metadata] lock-version = "2.0" python-versions = ">=3.9,<4.0" -content-hash = "f1f67f510295d6d3a4895bed9b6a0ae73bc85a993ef51b37884e60f5094c0298" +content-hash = "4d9f0c6f2d43392bbd9a3355bbe7ab7e3cfc0a92c17ead586f232d8251faedf2" diff --git a/libs/community/pyproject.toml b/libs/community/pyproject.toml index cf9939cbce867..c1c8d97660e56 100644 --- a/libs/community/pyproject.toml +++ b/libs/community/pyproject.toml @@ -44,6 +44,7 @@ dataclasses-json = ">= 0.5.7, < 0.7" pydantic-settings = "^2.4.0" langsmith = "^0.1.125" httpx-sse = "^0.4.0" +pypdf = "^5.1.0" [[tool.poetry.dependencies.numpy]] version = ">=1.22.4,<2" python = "<3.12" diff --git a/libs/community/tests/unit_tests/test_dependencies.py b/libs/community/tests/unit_tests/test_dependencies.py index a5c8c7c12c100..9f0fde82d26ee 100644 --- a/libs/community/tests/unit_tests/test_dependencies.py +++ b/libs/community/tests/unit_tests/test_dependencies.py @@ -47,6 +47,7 @@ def test_required_dependencies(poetry_conf: Mapping[str, Any]) -> None: "langchain-core", "langsmith", "numpy", + "pypdf", "python", "requests", "pydantic-settings", diff --git a/libs/core/extended_testing_deps.txt b/libs/core/extended_testing_deps.txt index 5ad9c8930daf9..eb408cd10ad8a 100644 --- a/libs/core/extended_testing_deps.txt +++ b/libs/core/extended_testing_deps.txt @@ -1 +1,2 @@ jinja2>=3,<4 +pypdf>=5,<6 \ No newline at end of file diff --git a/libs/core/langchain_core/prompts/chat.py b/libs/core/langchain_core/prompts/chat.py index 1629962ba1333..de87750db2578 100644 --- a/libs/core/langchain_core/prompts/chat.py +++ b/libs/core/langchain_core/prompts/chat.py @@ -2,6 +2,8 @@ from __future__ import annotations +import base64 +import io from abc import ABC, abstractmethod from collections.abc import Sequence from pathlib import Path @@ -22,6 +24,7 @@ SkipValidation, model_validator, ) +from pypdf import PdfReader from langchain_core._api import deprecated from langchain_core.load import Serializable @@ -48,6 +51,22 @@ from langchain_core.utils.interactive_env import is_interactive_env +# extract pdf into bytes +def extract_pdf_text(pdf_data: str) -> str: + # Decode the base64 back into bytes + pdf_bytes = base64.b64decode(pdf_data) + pdf_text = "" + + # Read the PDF and extract text + with io.BytesIO(pdf_bytes) as pdf_file: + reader = PdfReader(pdf_file) + for page in reader.pages: + extracted_text = page.extract_text() + pdf_text += extracted_text + "\n" + + return pdf_text + + class BaseMessagePromptTemplate(Serializable, ABC): """Base class for message prompt templates.""" @@ -468,6 +487,10 @@ class _ImageTemplateParam(TypedDict, total=False): image_url: Union[str, dict] +class _PdfTemplateParam(TypedDict, total=False): + data: str + + class _StringImageMessagePromptTemplate(BaseMessagePromptTemplate): """Human message prompt template. This is a message sent from the user.""" @@ -571,6 +594,12 @@ def from_template( msg = f"Invalid image template: {tmpl}" raise ValueError(msg) prompt.append(img_template_obj) + elif isinstance(tmpl, dict) and "data" in tmpl: + if tmpl.get("mime_type") == "application/pdf": + pdf_template = cast(_PdfTemplateParam, tmpl)["data"] + pdf_text = extract_pdf_text(pdf_template) + + prompt.append(PromptTemplate.from_template(pdf_text)) else: msg = f"Invalid template: {tmpl}" raise ValueError(msg) diff --git a/libs/core/poetry.lock b/libs/core/poetry.lock index dfc6f8a05c59f..2b37e739dfadf 100644 --- a/libs/core/poetry.lock +++ b/libs/core/poetry.lock @@ -1,4 +1,4 @@ -# This file is automatically @generated by Poetry 1.6.1 and should not be changed by hand. +# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand. [[package]] name = "annotated-types" @@ -2052,6 +2052,28 @@ files = [ [package.extras] diagrams = ["jinja2", "railroad-diagrams"] +[[package]] +name = "pypdf" +version = "5.1.0" +description = "A pure-python PDF library capable of splitting, merging, cropping, and transforming PDF files" +optional = false +python-versions = ">=3.8" +files = [ + {file = "pypdf-5.1.0-py3-none-any.whl", hash = "sha256:3bd4f503f4ebc58bae40d81e81a9176c400cbbac2ba2d877367595fb524dfdfc"}, + {file = "pypdf-5.1.0.tar.gz", hash = "sha256:425a129abb1614183fd1aca6982f650b47f8026867c0ce7c4b9f281c443d2740"}, +] + +[package.dependencies] +typing_extensions = {version = ">=4.0", markers = "python_version < \"3.11\""} + +[package.extras] +crypto = ["cryptography"] +cryptodome = ["PyCryptodome"] +dev = ["black", "flit", "pip-tools", "pre-commit (<2.18.0)", "pytest-cov", "pytest-socket", "pytest-timeout", "pytest-xdist", "wheel"] +docs = ["myst_parser", "sphinx", "sphinx_rtd_theme"] +full = ["Pillow (>=8.0.0)", "cryptography"] +image = ["Pillow (>=8.0.0)"] + [[package]] name = "pytest" version = "8.3.3" @@ -3033,4 +3055,4 @@ type = ["pytest-mypy"] [metadata] lock-version = "2.0" python-versions = ">=3.9,<4.0" -content-hash = "02bfef4d884d17f83dde79a4076a3d07f94a1b3dbf2414f07379dab64a78e183" +content-hash = "511698949338038a7d3c2640e82ede34685cb2d68a564a936fe1358816190a7b" diff --git a/libs/core/pyproject.toml b/libs/core/pyproject.toml index 8ba3b07011ce5..78a3b12924962 100644 --- a/libs/core/pyproject.toml +++ b/libs/core/pyproject.toml @@ -39,6 +39,7 @@ jsonpatch = "^1.33" PyYAML = ">=5.3" packaging = ">=23.2,<25" typing-extensions = ">=4.7" +pypdf = "^5.1.0" [[tool.poetry.dependencies.pydantic]] version = "^2.5.2" python = "<3.12.4" diff --git a/libs/core/tests/unit_tests/prompts/test_chat.py b/libs/core/tests/unit_tests/prompts/test_chat.py index 6249aa6f47893..bb47e95677563 100644 --- a/libs/core/tests/unit_tests/prompts/test_chat.py +++ b/libs/core/tests/unit_tests/prompts/test_chat.py @@ -37,6 +37,36 @@ from tests.unit_tests.pydantic_utils import _normalize_schema +def test_create_chat_prompt_template() -> None: + """Test chat prompt with pdf data as bytes.""" + file_path = ( + Path(__file__).parent.parent.parent.parent.parent + / "community/tests/examples/hello.pdf" + ) + + with open(file_path, "rb") as file: + file_data = file.read() + + pdf_data = base64.b64encode(file_data).decode("utf-8") + prompt = ChatPromptTemplate( + [ + ( + "human", + [ + {"type": "media", "mime_type": "application/pdf", "data": pdf_data}, + ], + ) + ] + ) + + expected_prompt = PromptTemplate(template="Hello world!\n1\n", input_variables=[]) + + assert len(prompt.messages) == 1 + output_prompt = prompt.messages[0] + assert isinstance(output_prompt, HumanMessagePromptTemplate) + assert output_prompt.prompt == [expected_prompt] + + @pytest.fixture def messages() -> list[BaseMessagePromptTemplate]: """Create messages.""" diff --git a/libs/langchain/poetry.lock b/libs/langchain/poetry.lock index b74085c071bac..ef171b6162193 100644 --- a/libs/langchain/poetry.lock +++ b/libs/langchain/poetry.lock @@ -1,4 +1,4 @@ -# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand. +# This file is automatically @generated by Poetry 1.8.4 and should not be changed by hand. [[package]] name = "aiohappyeyeballs" @@ -2697,30 +2697,41 @@ files = [ {file = "pandas-2.2.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:381175499d3802cde0eabbaf6324cce0c4f5d52ca6f8c377c29ad442f50f6348"}, {file = "pandas-2.2.3-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:d9c45366def9a3dd85a6454c0e7908f2b3b8e9c138f5dc38fed7ce720d8453ed"}, {file = "pandas-2.2.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:86976a1c5b25ae3f8ccae3a5306e443569ee3c3faf444dfd0f41cda24667ad57"}, + {file = "pandas-2.2.3-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:b8661b0238a69d7aafe156b7fa86c44b881387509653fdf857bebc5e4008ad42"}, {file = "pandas-2.2.3-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:37e0aced3e8f539eccf2e099f65cdb9c8aa85109b0be6e93e2baff94264bdc6f"}, {file = "pandas-2.2.3-cp310-cp310-win_amd64.whl", hash = "sha256:56534ce0746a58afaf7942ba4863e0ef81c9c50d3f0ae93e9497d6a41a057645"}, {file = "pandas-2.2.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:66108071e1b935240e74525006034333f98bcdb87ea116de573a6a0dccb6c039"}, {file = "pandas-2.2.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:7c2875855b0ff77b2a64a0365e24455d9990730d6431b9e0ee18ad8acee13dbd"}, + {file = "pandas-2.2.3-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cd8d0c3be0515c12fed0bdbae072551c8b54b7192c7b1fda0ba56059a0179698"}, {file = "pandas-2.2.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c124333816c3a9b03fbeef3a9f230ba9a737e9e5bb4060aa2107a86cc0a497fc"}, + {file = "pandas-2.2.3-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:63cc132e40a2e084cf01adf0775b15ac515ba905d7dcca47e9a251819c575ef3"}, {file = "pandas-2.2.3-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:29401dbfa9ad77319367d36940cd8a0b3a11aba16063e39632d98b0e931ddf32"}, {file = "pandas-2.2.3-cp311-cp311-win_amd64.whl", hash = "sha256:3fc6873a41186404dad67245896a6e440baacc92f5b716ccd1bc9ed2995ab2c5"}, {file = "pandas-2.2.3-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:b1d432e8d08679a40e2a6d8b2f9770a5c21793a6f9f47fdd52c5ce1948a5a8a9"}, {file = "pandas-2.2.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:a5a1595fe639f5988ba6a8e5bc9649af3baf26df3998a0abe56c02609392e0a4"}, + {file = "pandas-2.2.3-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:5de54125a92bb4d1c051c0659e6fcb75256bf799a732a87184e5ea503965bce3"}, {file = "pandas-2.2.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fffb8ae78d8af97f849404f21411c95062db1496aeb3e56f146f0355c9989319"}, + {file = "pandas-2.2.3-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:6dfcb5ee8d4d50c06a51c2fffa6cff6272098ad6540aed1a76d15fb9318194d8"}, {file = "pandas-2.2.3-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:062309c1b9ea12a50e8ce661145c6aab431b1e99530d3cd60640e255778bd43a"}, {file = "pandas-2.2.3-cp312-cp312-win_amd64.whl", hash = "sha256:59ef3764d0fe818125a5097d2ae867ca3fa64df032331b7e0917cf5d7bf66b13"}, {file = "pandas-2.2.3-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:f00d1345d84d8c86a63e476bb4955e46458b304b9575dcf71102b5c705320015"}, {file = "pandas-2.2.3-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:3508d914817e153ad359d7e069d752cdd736a247c322d932eb89e6bc84217f28"}, + {file = "pandas-2.2.3-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:22a9d949bfc9a502d320aa04e5d02feab689d61da4e7764b62c30b991c42c5f0"}, {file = "pandas-2.2.3-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f3a255b2c19987fbbe62a9dfd6cff7ff2aa9ccab3fc75218fd4b7530f01efa24"}, + {file = "pandas-2.2.3-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:800250ecdadb6d9c78eae4990da62743b857b470883fa27f652db8bdde7f6659"}, {file = "pandas-2.2.3-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:6374c452ff3ec675a8f46fd9ab25c4ad0ba590b71cf0656f8b6daa5202bca3fb"}, {file = "pandas-2.2.3-cp313-cp313-win_amd64.whl", hash = "sha256:61c5ad4043f791b61dd4752191d9f07f0ae412515d59ba8f005832a532f8736d"}, {file = "pandas-2.2.3-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:3b71f27954685ee685317063bf13c7709a7ba74fc996b84fc6821c59b0f06468"}, {file = "pandas-2.2.3-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:38cf8125c40dae9d5acc10fa66af8ea6fdf760b2714ee482ca691fc66e6fcb18"}, + {file = "pandas-2.2.3-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:ba96630bc17c875161df3818780af30e43be9b166ce51c9a18c1feae342906c2"}, {file = "pandas-2.2.3-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1db71525a1538b30142094edb9adc10be3f3e176748cd7acc2240c2f2e5aa3a4"}, + {file = "pandas-2.2.3-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:15c0e1e02e93116177d29ff83e8b1619c93ddc9c49083f237d4312337a61165d"}, {file = "pandas-2.2.3-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:ad5b65698ab28ed8d7f18790a0dc58005c7629f227be9ecc1072aa74c0c1d43a"}, {file = "pandas-2.2.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:bc6b93f9b966093cb0fd62ff1a7e4c09e6d546ad7c1de191767baffc57628f39"}, {file = "pandas-2.2.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:5dbca4c1acd72e8eeef4753eeca07de9b1db4f398669d5994086f788a5d7cc30"}, + {file = "pandas-2.2.3-cp39-cp39-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:8cd6d7cc958a3910f934ea8dbdf17b2364827bb4dafc38ce6eef6bb3d65ff09c"}, {file = "pandas-2.2.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:99df71520d25fade9db7c1076ac94eb994f4d2673ef2aa2e86ee039b6746d20c"}, + {file = "pandas-2.2.3-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:31d0ced62d4ea3e231a9f228366919a5ea0b07440d9d4dac345376fd8e1477ea"}, {file = "pandas-2.2.3-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:7eee9e7cea6adf3e3d24e304ac6b8300646e2a5d1cd3a3c2abed9101b0846761"}, {file = "pandas-2.2.3-cp39-cp39-win_amd64.whl", hash = "sha256:4850ba03528b6dd51d6c5d273c46f183f39a9baf3f0143e566b89450965b105e"}, {file = "pandas-2.2.3.tar.gz", hash = "sha256:4f18ba62b61d7e192368b84517265a99b4d7ee8912f8708660fb4a366cc82667"}, @@ -3236,6 +3247,28 @@ files = [ [package.extras] windows-terminal = ["colorama (>=0.4.6)"] +[[package]] +name = "pypdf" +version = "5.1.0" +description = "A pure-python PDF library capable of splitting, merging, cropping, and transforming PDF files" +optional = false +python-versions = ">=3.8" +files = [ + {file = "pypdf-5.1.0-py3-none-any.whl", hash = "sha256:3bd4f503f4ebc58bae40d81e81a9176c400cbbac2ba2d877367595fb524dfdfc"}, + {file = "pypdf-5.1.0.tar.gz", hash = "sha256:425a129abb1614183fd1aca6982f650b47f8026867c0ce7c4b9f281c443d2740"}, +] + +[package.dependencies] +typing_extensions = {version = ">=4.0", markers = "python_version < \"3.11\""} + +[package.extras] +crypto = ["cryptography"] +cryptodome = ["PyCryptodome"] +dev = ["black", "flit", "pip-tools", "pre-commit (<2.18.0)", "pytest-cov", "pytest-socket", "pytest-timeout", "pytest-xdist", "wheel"] +docs = ["myst_parser", "sphinx", "sphinx_rtd_theme"] +full = ["Pillow (>=8.0.0)", "cryptography"] +image = ["Pillow (>=8.0.0)"] + [[package]] name = "pytest" version = "8.3.3" @@ -4897,4 +4930,4 @@ type = ["pytest-mypy"] [metadata] lock-version = "2.0" python-versions = ">=3.9,<4.0" -content-hash = "7437aea710de404325d497f9b9275234b1f7fefd38aa27649897a48dccd55317" +content-hash = "8bef5de12c9294c6839f08acf3882df854b806e04058ca480d5d0657a068873f" diff --git a/libs/langchain/pyproject.toml b/libs/langchain/pyproject.toml index ae54e79129cf4..3e24798d05aa3 100644 --- a/libs/langchain/pyproject.toml +++ b/libs/langchain/pyproject.toml @@ -42,6 +42,7 @@ requests = "^2" PyYAML = ">=5.3" aiohttp = "^3.8.3" tenacity = ">=8.1.0,!=8.4.0,<10" +pypdf = "^5.1.0" [[tool.poetry.dependencies.numpy]] version = ">=1.22.4,<2" python = "<3.12" diff --git a/libs/langchain/tests/unit_tests/test_dependencies.py b/libs/langchain/tests/unit_tests/test_dependencies.py index 664e313e0f5aa..3dad53e963405 100644 --- a/libs/langchain/tests/unit_tests/test_dependencies.py +++ b/libs/langchain/tests/unit_tests/test_dependencies.py @@ -46,6 +46,7 @@ def test_required_dependencies(poetry_conf: Mapping[str, Any]) -> None: "langchain-core", "langchain-text-splitters", "langsmith", + "pypdf", "numpy", "pydantic", "python", diff --git a/libs/partners/prompty/poetry.lock b/libs/partners/prompty/poetry.lock index 3753802ecc0df..6816e776f595d 100644 --- a/libs/partners/prompty/poetry.lock +++ b/libs/partners/prompty/poetry.lock @@ -1,4 +1,4 @@ -# This file is automatically @generated by Poetry 1.8.2 and should not be changed by hand. +# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand. [[package]] name = "aiohappyeyeballs" @@ -1152,6 +1152,28 @@ files = [ [package.dependencies] typing-extensions = ">=4.6.0,<4.7.0 || >4.7.0" +[[package]] +name = "pypdf" +version = "5.1.0" +description = "A pure-python PDF library capable of splitting, merging, cropping, and transforming PDF files" +optional = false +python-versions = ">=3.8" +files = [ + {file = "pypdf-5.1.0-py3-none-any.whl", hash = "sha256:3bd4f503f4ebc58bae40d81e81a9176c400cbbac2ba2d877367595fb524dfdfc"}, + {file = "pypdf-5.1.0.tar.gz", hash = "sha256:425a129abb1614183fd1aca6982f650b47f8026867c0ce7c4b9f281c443d2740"}, +] + +[package.dependencies] +typing_extensions = {version = ">=4.0", markers = "python_version < \"3.11\""} + +[package.extras] +crypto = ["cryptography"] +cryptodome = ["PyCryptodome"] +dev = ["black", "flit", "pip-tools", "pre-commit (<2.18.0)", "pytest-cov", "pytest-socket", "pytest-timeout", "pytest-xdist", "wheel"] +docs = ["myst_parser", "sphinx", "sphinx_rtd_theme"] +full = ["Pillow (>=8.0.0)", "cryptography"] +image = ["Pillow (>=8.0.0)"] + [[package]] name = "pytest" version = "7.4.4" @@ -1699,4 +1721,4 @@ multidict = ">=4.0" [metadata] lock-version = "2.0" python-versions = ">=3.9,<4.0" -content-hash = "320579abcfcbf377b14b4dd467dd33c0e7daf1de42fa53f81e2a226bbc00e4ba" +content-hash = "a81197c5a119b0c416f989168e8377ec98f4cdb482858f04e1ba60c7a98a9793" diff --git a/libs/partners/prompty/pyproject.toml b/libs/partners/prompty/pyproject.toml index e3e82d36ca44d..70327aa6ca64d 100644 --- a/libs/partners/prompty/pyproject.toml +++ b/libs/partners/prompty/pyproject.toml @@ -25,6 +25,7 @@ disallow_untyped_defs = "True" python = ">=3.9,<4.0" langchain-core = "^0.3.15" pyyaml = "^6.0.1" +pypdf = "^5.1.0" [tool.coverage.run] omit = [ "tests/*",]