Archives
/
langchain
mirror of https://github.com/hwchase17/langchain
2
0
Fork 1
Code Issues Packages Projects Releases Wiki Activity

fixed error message and a check for processor name (#12200)

Browse Source 
Replace this entire comment with:
- **Description:** a small fix on error description / a check for
processor name
  - **Issue:** the issue #11407
pull/12352/head
Leonid Kuligin 11 months ago committed by GitHub
parent 9298aff783
commit 4e47fe1dce
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 144 additions and 10 deletions
Show Stats Download Patch File Download Diff File

12
libs/langchain/langchain/document_loaders/parsers/docai.py
Unescape Escape View File

@ -5,6 +5,7 @@ pip install google-cloud-documentai
pip install google-cloud-documentai-toolbox
"""
import logging
import re
import time
from dataclasses import dataclass
from typing import TYPE_CHECKING, Iterator, List, Optional, Sequence
@ -65,13 +66,14 @@ class DocAIParser(BaseBlobParser):
"a client."
)
if processor_name and not processor_name.isalnum():
pattern = "projects\/[0-9]+\/locations\/[a-z\-0-9]+\/processors\/[a-z0-9]+"
if processor_name and not re.fullmatch(pattern, processor_name):
raise ValueError(
f"Processor name {processor_name} has a wrong format. Use only ID from"
"the `Basic information` section on the GCP console. E.g., if your "
f"Processor name {processor_name} has a wrong format. If your "
"prediction endpoint looks like https://us-documentai.googleapis.com"
"/v1/projects/PROJECT_ID/locations/us/processors/PROCESSOR_ID:process"
", use only PROCESSOR_ID part."
"/v1/projects/PROJECT_ID/locations/us/processors/PROCESSOR_ID:process,"
" use only projects/PROJECT_ID/locations/us/processors/PROCESSOR_ID "
"part."
)
self._gcs_output_path = gcs_output_path

114
libs/langchain/poetry.lock generated
Unescape Escape View File

@ -1841,8 +1841,8 @@ files = [
[package.dependencies]
aiohttp = ">=3.1.0"
grpcio = [
{version = ">=1.22.0", markers = "python_version < \"3.11\""},
{version = ">=1.49.1", markers = "python_version >= \"3.11\""},
{version = ">=1.22.0", markers = "python_version < \"3.11\""},
]
numpy = "*"
protobuf = ">=3.8.0,<4.0.0"
@ -2679,6 +2679,30 @@ gitdb = ">=4.0.1,<5"
[package.extras]
test = ["black", "coverage[toml]", "ddt (>=1.1.1,!=1.4.3)", "mock", "mypy", "pre-commit", "pytest", "pytest-cov", "pytest-instafail", "pytest-subtests", "pytest-sugar"]
[[package]]
name = "google-api-core"
version = "1.34.0"
description = "Google API client core library"
optional = true
python-versions = ">=3.7"
files = [
{file = "google-api-core-1.34.0.tar.gz", hash = "sha256:6fb380f49d19ee1d09a9722d0379042b7edb06c0112e4796c7a395078a043e71"},
{file = "google_api_core-1.34.0-py3-none-any.whl", hash = "sha256:7421474c39d396a74dfa317dddbc69188f2336835f526087c7648f91105e32ff"},
]
[package.dependencies]
google-auth = ">=1.25.0,<3.0dev"
googleapis-common-protos = ">=1.56.2,<2.0dev"
grpcio = {version = ">=1.33.2,<2.0dev", optional = true, markers = "extra == \"grpc\""}
grpcio-status = {version = ">=1.33.2,<2.0dev", optional = true, markers = "extra == \"grpc\""}
protobuf = ">=3.19.5,<3.20.0 || >3.20.0,<3.20.1 || >3.20.1,<4.0.0dev"
requests = ">=2.18.0,<3.0.0dev"
[package.extras]
grpc = ["grpcio (>=1.33.2,<2.0dev)", "grpcio-status (>=1.33.2,<2.0dev)"]
grpcgcp = ["grpcio-gcp (>=0.2.2,<1.0dev)"]
grpcio-gcp = ["grpcio-gcp (>=0.2.2,<1.0dev)"]
[[package]]
name = "google-api-core"
version = "2.12.0"
@ -2693,6 +2717,8 @@ files = [
[package.dependencies]
google-auth = ">=2.14.1,<3.0.dev0"
googleapis-common-protos = ">=1.56.2,<2.0.dev0"
grpcio = {version = ">=1.33.2,<2.0dev", optional = true, markers = "python_version < \"3.11\" and extra == \"grpc\""}
grpcio-status = {version = ">=1.33.2,<2.0.dev0", optional = true, markers = "python_version < \"3.11\" and extra == \"grpc\""}
protobuf = ">=3.19.5,<3.20.0 || >3.20.0,<3.20.1 || >3.20.1,<4.21.0 || >4.21.0,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4.21.3 || >4.21.3,<4.21.4 || >4.21.4,<4.21.5 || >4.21.5,<5.0.0.dev0"
requests = ">=2.18.0,<3.0.0.dev0"
@ -2775,6 +2801,25 @@ requests-oauthlib = ">=0.7.0"
[package.extras]
tool = ["click (>=6.0.0)"]
[[package]]
name = "google-cloud-documentai"
version = "2.20.1"
description = "Google Cloud Documentai API client library"
optional = true
python-versions = ">=3.7"
files = [
{file = "google-cloud-documentai-2.20.1.tar.gz", hash = "sha256:eba90546c80177bab7ee8aa3f4b7b1f89cf3ce9752032e359a15d0fbf2225fb0"},
{file = "google_cloud_documentai-2.20.1-py2.py3-none-any.whl", hash = "sha256:793a2e59c425655c951055810635798b5ef56fed164e35b2bd521e5c30ab279e"},
]
[package.dependencies]
google-api-core = {version = ">=1.34.0,<2.0.dev0 || >=2.11.dev0,<3.0.0dev", extras = ["grpc"]}
proto-plus = [
{version = ">=1.22.2,<2.0.0dev", markers = "python_version >= \"3.11\""},
{version = ">=1.22.0,<2.0.0dev", markers = "python_version < \"3.11\""},
]
protobuf = ">=3.19.5,<3.20.0 || >3.20.0,<3.20.1 || >3.20.1,<4.21.0 || >4.21.0,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4.21.3 || >4.21.3,<4.21.4 || >4.21.4,<4.21.5 || >4.21.5,<5.0.0dev"
[[package]]
name = "google-pasta"
version = "0.2.0"
@ -3014,6 +3059,22 @@ files = [
[package.extras]
protobuf = ["grpcio-tools (>=1.59.0)"]
[[package]]
name = "grpcio-status"
version = "1.48.2"
description = "Status proto mapping for gRPC"
optional = true
python-versions = ">=3.6"
files = [
{file = "grpcio-status-1.48.2.tar.gz", hash = "sha256:53695f45da07437b7c344ee4ef60d370fd2850179f5a28bb26d8e2aa1102ec11"},
{file = "grpcio_status-1.48.2-py3-none-any.whl", hash = "sha256:2c33bbdbe20188b2953f46f31af669263b6ee2a9b2d38fa0d36ee091532e21bf"},
]
[package.dependencies]
googleapis-common-protos = ">=1.5.5"
grpcio = ">=1.48.2"
protobuf = ">=3.12.0"
[[package]]
name = "grpcio-tools"
version = "1.48.2"
@ -3729,6 +3790,7 @@ optional = false
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*, !=3.6.*"
files = [
{file = "jsonpointer-2.4-py2.py3-none-any.whl", hash = "sha256:15d51bba20eea3165644553647711d150376234112651b4f1811022aecad7d7a"},
{file = "jsonpointer-2.4.tar.gz", hash = "sha256:585cee82b70211fa9e6043b7bb89db6e1aa49524340dde8ad6b63206ea689d88"},
]
[[package]]
@ -4536,6 +4598,16 @@ files = [
{file = "MarkupSafe-2.1.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:5bbe06f8eeafd38e5d0a4894ffec89378b6c6a625ff57e3028921f8ff59318ac"},
{file = "MarkupSafe-2.1.3-cp311-cp311-win32.whl", hash = "sha256:dd15ff04ffd7e05ffcb7fe79f1b98041b8ea30ae9234aed2a9168b5797c3effb"},
{file = "MarkupSafe-2.1.3-cp311-cp311-win_amd64.whl", hash = "sha256:134da1eca9ec0ae528110ccc9e48041e0828d79f24121a1a146161103c76e686"},
{file = "MarkupSafe-2.1.3-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:f698de3fd0c4e6972b92290a45bd9b1536bffe8c6759c62471efaa8acb4c37bc"},
{file = "MarkupSafe-2.1.3-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:aa57bd9cf8ae831a362185ee444e15a93ecb2e344c8e52e4d721ea3ab6ef1823"},
{file = "MarkupSafe-2.1.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ffcc3f7c66b5f5b7931a5aa68fc9cecc51e685ef90282f4a82f0f5e9b704ad11"},
{file = "MarkupSafe-2.1.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:47d4f1c5f80fc62fdd7777d0d40a2e9dda0a05883ab11374334f6c4de38adffd"},
{file = "MarkupSafe-2.1.3-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1f67c7038d560d92149c060157d623c542173016c4babc0c1913cca0564b9939"},
{file = "MarkupSafe-2.1.3-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:9aad3c1755095ce347e26488214ef77e0485a3c34a50c5a5e2471dff60b9dd9c"},
{file = "MarkupSafe-2.1.3-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:14ff806850827afd6b07a5f32bd917fb7f45b046ba40c57abdb636674a8b559c"},
{file = "MarkupSafe-2.1.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8f9293864fe09b8149f0cc42ce56e3f0e54de883a9de90cd427f191c346eb2e1"},
{file = "MarkupSafe-2.1.3-cp312-cp312-win32.whl", hash = "sha256:715d3562f79d540f251b99ebd6d8baa547118974341db04f5ad06d5ea3eb8007"},
{file = "MarkupSafe-2.1.3-cp312-cp312-win_amd64.whl", hash = "sha256:1b8dd8c3fd14349433c79fa8abeb573a55fc0fdd769133baac1f5e07abf54aeb"},
{file = "MarkupSafe-2.1.3-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:8e254ae696c88d98da6555f5ace2279cf7cd5b3f52be2b5cf97feafe883b58d2"},
{file = "MarkupSafe-2.1.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cb0932dc158471523c9637e807d9bfb93e06a95cbf010f1a38b98623b929ef2b"},
{file = "MarkupSafe-2.1.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9402b03f1a1b4dc4c19845e5c749e3ab82d5078d16a2a4c2cd2df62d57bb0707"},
@ -5778,12 +5850,12 @@ files = [
[package.dependencies]
numpy = [
{version = ">=1.23.5", markers = "python_version >= \"3.11\""},
{version = ">=1.21.0", markers = "python_version <= \"3.9\" and platform_system == \"Darwin\" and platform_machine == \"arm64\" and python_version >= \"3.8\""},
{version = ">=1.19.3", markers = "platform_system == \"Linux\" and platform_machine == \"aarch64\" and python_version >= \"3.8\" and python_version < \"3.10\" or python_version > \"3.9\" and python_version < \"3.10\" or python_version >= \"3.9\" and platform_system != \"Darwin\" and python_version < \"3.10\" or python_version >= \"3.9\" and platform_machine != \"arm64\" and python_version < \"3.10\""},
{version = ">=1.17.3", markers = "(platform_system != \"Darwin\" and platform_system != \"Linux\") and python_version >= \"3.8\" and python_version < \"3.9\" or platform_system != \"Darwin\" and python_version >= \"3.8\" and python_version < \"3.9\" and platform_machine != \"aarch64\" or platform_machine != \"arm64\" and python_version >= \"3.8\" and python_version < \"3.9\" and platform_system != \"Linux\" or (platform_machine != \"arm64\" and platform_machine != \"aarch64\") and python_version >= \"3.8\" and python_version < \"3.9\""},
{version = ">=1.21.4", markers = "python_version >= \"3.10\" and platform_system == \"Darwin\" and python_version < \"3.11\""},
{version = ">=1.21.2", markers = "platform_system != \"Darwin\" and python_version >= \"3.10\" and python_version < \"3.11\""},
{version = ">=1.23.5", markers = "python_version >= \"3.11\""},
]
[[package]]
@ -5959,9 +6031,9 @@ files = [
[package.dependencies]
numpy = [
{version = ">=1.23.2", markers = "python_version >= \"3.11\""},
{version = ">=1.20.3", markers = "python_version < \"3.10\""},
{version = ">=1.21.0", markers = "python_version >= \"3.10\" and python_version < \"3.11\""},
{version = ">=1.23.2", markers = "python_version >= \"3.11\""},
]
python-dateutil = ">=2.8.2"
pytz = ">=2020.1"
@ -6379,6 +6451,23 @@ files = [
[package.dependencies]
wcwidth = "*"
[[package]]
name = "proto-plus"
version = "1.22.3"
description = "Beautiful, Pythonic protocol buffers."
optional = true
python-versions = ">=3.6"
files = [
{file = "proto-plus-1.22.3.tar.gz", hash = "sha256:fdcd09713cbd42480740d2fe29c990f7fbd885a67efc328aa8be6ee3e9f76a6b"},
{file = "proto_plus-1.22.3-py3-none-any.whl", hash = "sha256:a49cd903bc0b6ab41f76bf65510439d56ca76f868adf0274e738bfdd096894df"},
]
[package.dependencies]
protobuf = ">=3.19.0,<5.0.0dev"
[package.extras]
testing = ["google-api-core[grpc] (>=1.31.5)"]
[[package]]
name = "protobuf"
version = "3.19.6"
@ -7639,6 +7728,7 @@ files = [
{file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:69b023b2b4daa7548bcfbd4aa3da05b3a74b772db9e23b982788168117739938"},
{file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:81e0b275a9ecc9c0c0c07b4b90ba548307583c125f54d5b6946cfee6360c733d"},
{file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ba336e390cd8e4d1739f42dfe9bb83a3cc2e80f567d8805e11b46f4a943f5515"},
{file = "PyYAML-6.0.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:326c013efe8048858a6d312ddd31d56e468118ad4cdeda36c719bf5bb6192290"},
{file = "PyYAML-6.0.1-cp310-cp310-win32.whl", hash = "sha256:bd4af7373a854424dabd882decdc5579653d7868b8fb26dc7d0e99f823aa5924"},
{file = "PyYAML-6.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:fd1592b3fdf65fff2ad0004b5e363300ef59ced41c2e6b3a99d4089fa8c5435d"},
{file = "PyYAML-6.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6965a7bc3cf88e5a1c3bd2e0b5c22f8d677dc88a455344035f03399034eb3007"},
@ -7646,8 +7736,15 @@ files = [
{file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42f8152b8dbc4fe7d96729ec2b99c7097d656dc1213a3229ca5383f973a5ed6d"},
{file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:062582fca9fabdd2c8b54a3ef1c978d786e0f6b3a1510e0ac93ef59e0ddae2bc"},
{file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d2b04aac4d386b172d5b9692e2d2da8de7bfb6c387fa4f801fbf6fb2e6ba4673"},
{file = "PyYAML-6.0.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e7d73685e87afe9f3b36c799222440d6cf362062f78be1013661b00c5c6f678b"},
{file = "PyYAML-6.0.1-cp311-cp311-win32.whl", hash = "sha256:1635fd110e8d85d55237ab316b5b011de701ea0f29d07611174a1b42f1444741"},
{file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"},
{file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"},
{file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"},
{file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"},
{file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"},
{file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"},
{file = "PyYAML-6.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:0d3304d8c0adc42be59c5f8a4d9e3d7379e6955ad754aa9d6ab7a398b59dd1df"},
{file = "PyYAML-6.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:50550eb667afee136e9a77d6dc71ae76a44df8b3e51e41b77f6de2932bfe0f47"},
{file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1fe35611261b29bd1de0070f0b2f47cb6ff71fa6595c077e42bd0c419fa27b98"},
{file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:704219a11b772aea0d8ecd7058d0082713c3562b4e271b849ad7dc4a5c90c13c"},
@ -7664,6 +7761,7 @@ files = [
{file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a0cd17c15d3bb3fa06978b4e8958dcdc6e0174ccea823003a106c7d4d7899ac5"},
{file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:28c119d996beec18c05208a8bd78cbe4007878c6dd15091efb73a30e90539696"},
{file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7e07cbde391ba96ab58e532ff4803f79c4129397514e1413a7dc761ccd755735"},
{file = "PyYAML-6.0.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:49a183be227561de579b4a36efbb21b3eab9651dd81b1858589f796549873dd6"},
{file = "PyYAML-6.0.1-cp38-cp38-win32.whl", hash = "sha256:184c5108a2aca3c5b3d3bf9395d50893a7ab82a38004c8f61c258d4428e80206"},
{file = "PyYAML-6.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:1e2722cc9fbb45d9b87631ac70924c11d3a401b2d7f410cc0e3bbf249f2dca62"},
{file = "PyYAML-6.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9eb6caa9a297fc2c2fb8862bc5370d0303ddba53ba97e71f08023b6cd73d16a8"},
@ -7671,6 +7769,7 @@ files = [
{file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5773183b6446b2c99bb77e77595dd486303b4faab2b086e7b17bc6bef28865f6"},
{file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b786eecbdf8499b9ca1d697215862083bd6d2a99965554781d0d8d1ad31e13a0"},
{file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bc1bf2925a1ecd43da378f4db9e4f799775d6367bdb94671027b73b393a7c42c"},
{file = "PyYAML-6.0.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:04ac92ad1925b2cff1db0cfebffb6ffc43457495c9b3c39d3fcae417d7125dc5"},
{file = "PyYAML-6.0.1-cp39-cp39-win32.whl", hash = "sha256:faca3bdcf85b2fc05d06ff3fbc1f83e1391b3e724afa3feba7d13eeab355484c"},
{file = "PyYAML-6.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:510c9deebc5c0225e8c96813043e62b680ba2f9c50a08d3724c7f28a747d1486"},
{file = "PyYAML-6.0.1.tar.gz", hash = "sha256:bfdf460b1736c775f2ba9f6a92bca30bc2095067b8a9d77876d1fad6cc3b4a43"},
@ -8634,6 +8733,11 @@ files = [
{file = "scikit_learn-1.3.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f66eddfda9d45dd6cadcd706b65669ce1df84b8549875691b1f403730bdef217"},
{file = "scikit_learn-1.3.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c6448c37741145b241eeac617028ba6ec2119e1339b1385c9720dae31367f2be"},
{file = "scikit_learn-1.3.1-cp311-cp311-win_amd64.whl", hash = "sha256:c413c2c850241998168bbb3bd1bb59ff03b1195a53864f0b80ab092071af6028"},
{file = "scikit_learn-1.3.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:ef540e09873e31569bc8b02c8a9f745ee04d8e1263255a15c9969f6f5caa627f"},
{file = "scikit_learn-1.3.1-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:9147a3a4df4d401e618713880be023e36109c85d8569b3bf5377e6cd3fecdeac"},
{file = "scikit_learn-1.3.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d2cd3634695ad192bf71645702b3df498bd1e246fc2d529effdb45a06ab028b4"},
{file = "scikit_learn-1.3.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0c275a06c5190c5ce00af0acbb61c06374087949f643ef32d355ece12c4db043"},
{file = "scikit_learn-1.3.1-cp312-cp312-win_amd64.whl", hash = "sha256:0e1aa8f206d0de814b81b41d60c1ce31f7f2c7354597af38fae46d9c47c45122"},
{file = "scikit_learn-1.3.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:52b77cc08bd555969ec5150788ed50276f5ef83abb72e6f469c5b91a0009bbca"},
{file = "scikit_learn-1.3.1-cp38-cp38-macosx_12_0_arm64.whl", hash = "sha256:a683394bc3f80b7c312c27f9b14ebea7766b1f0a34faf1a2e9158d80e860ec26"},
{file = "scikit_learn-1.3.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a15d964d9eb181c79c190d3dbc2fff7338786bf017e9039571418a1d53dab236"},
@ -10937,7 +11041,7 @@ cli = ["typer"]
cohere = ["cohere"]
docarray = ["docarray"]
embeddings = ["sentence-transformers"]
extended-testing = ["aiosqlite", "amazon-textract-caller", "anthropic", "arxiv", "assemblyai", "atlassian-python-api", "beautifulsoup4", "bibtexparser", "cassio", "chardet", "dashvector", "esprima", "faiss-cpu", "feedparser", "geopandas", "gitpython", "gql", "html2text", "jinja2", "jq", "lxml", "markdownify", "motor", "mwparserfromhell", "mwxml", "newspaper3k", "numexpr", "openai", "openai", "openapi-pydantic", "pandas", "pdfminer-six", "pgvector", "psychicapi", "py-trello", "pymupdf", "pypdf", "pypdfium2", "pyspark", "rank-bm25", "rapidfuzz", "rapidocr-onnxruntime", "requests-toolbelt", "rspace_client", "scikit-learn", "sqlite-vss", "streamlit", "sympy", "telethon", "timescale-vector", "tqdm", "upstash-redis", "xata", "xmltodict"]
extended-testing = ["aiosqlite", "amazon-textract-caller", "anthropic", "arxiv", "assemblyai", "atlassian-python-api", "beautifulsoup4", "bibtexparser", "cassio", "chardet", "dashvector", "esprima", "faiss-cpu", "feedparser", "geopandas", "gitpython", "google-cloud-documentai", "gql", "html2text", "jinja2", "jq", "lxml", "markdownify", "motor", "mwparserfromhell", "mwxml", "newspaper3k", "numexpr", "openai", "openai", "openapi-pydantic", "pandas", "pdfminer-six", "pgvector", "psychicapi", "py-trello", "pymupdf", "pypdf", "pypdfium2", "pyspark", "rank-bm25", "rapidfuzz", "rapidocr-onnxruntime", "requests-toolbelt", "rspace_client", "scikit-learn", "sqlite-vss", "streamlit", "sympy", "telethon", "timescale-vector", "tqdm", "upstash-redis", "xata", "xmltodict"]
javascript = ["esprima"]
llms = ["clarifai", "cohere", "huggingface_hub", "manifest-ml", "nlpcloud", "openai", "openlm", "torch", "transformers"]
openai = ["openai", "tiktoken"]
@ -10947,4 +11051,4 @@ text-helpers = ["chardet"]
[metadata]
lock-version = "2.0"
python-versions = ">=3.8.1,<4.0"
content-hash = "36c742f7330bc9670d998bdc3ec6bf4babd4fe4712191afc9fa12b2bd71ccbf9"
content-hash = "6bf06e81190f228675452f1a7581614898c983d27f2d56ae9ddd92119c114b03"

2
libs/langchain/pyproject.toml
Unescape Escape View File

@ -139,6 +139,7 @@ anthropic = {version = "^0.3.11", optional = true}
aiosqlite = {version = "^0.19.0", optional = true}
rspace_client = {version = "^2.5.0", optional = true}
upstash-redis = {version = "^0.15.0", optional = true}
google-cloud-documentai = {version = "^2.20.1", optional = true}
[tool.poetry.group.test.dependencies]
@ -322,6 +323,7 @@ extended_testing = [
"bibtexparser",
"cassio",
"chardet",
"google-cloud-documentai",
"esprima",
"jq",
"pdfminer-six",

26
libs/langchain/tests/unit_tests/document_loaders/parsers/test_docai.py
Unescape Escape View File

@ -0,0 +1,26 @@
"""Tests for the Google Cloud DocAI parser."""
from unittest.mock import ANY, patch
import pytest
from langchain.document_loaders.parsers import DocAIParser
@pytest.mark.requires("google.cloud", "google.cloud.documentai")
def test_docai_parser_valid_processor_name() -> None:
processor_name = "projects/123456/locations/us-central1/processors/ab123dfg"
with patch("google.cloud.documentai.DocumentProcessorServiceClient") as test_client:
parser = DocAIParser(processor_name=processor_name, location="us")
test_client.assert_called_once_with(client_options=ANY, client_info=ANY)
assert parser._processor_name == processor_name
@pytest.mark.requires("google.cloud", "google.cloud.documentai")
@pytest.mark.parametrize(
"processor_name",
["projects/123456/locations/us-central1/processors/ab123dfg:publish", "ab123dfg"],
)
def test_docai_parser_invalid_processor_name(processor_name: str) -> None:
with patch("google.cloud.documentai.DocumentProcessorServiceClient"):
with pytest.raises(ValueError):
_ = DocAIParser(processor_name=processor_name, location="us")
Write Preview
Loading…
Cancel
Save