Merge pull request #858 from cbcoutinho/feat/tiered-doc-processor-b2-tier1
feat: tiered PDF processor — pypdfium2 fast path (deprecate pymupdf4llm)
This commit is contained in:
@@ -2215,6 +2215,7 @@ dependencies = [
|
||||
{ name = "pyjwt", extra = ["crypto"] },
|
||||
{ name = "pymupdf" },
|
||||
{ name = "pymupdf4llm" },
|
||||
{ name = "pypdfium2" },
|
||||
{ name = "python-json-logger" },
|
||||
{ name = "pythonvcard4" },
|
||||
{ name = "qdrant-client" },
|
||||
@@ -2283,6 +2284,7 @@ requires-dist = [
|
||||
{ name = "pyjwt", extras = ["crypto"], specifier = ">=2.8.0" },
|
||||
{ name = "pymupdf", specifier = ">=1.26.6" },
|
||||
{ name = "pymupdf4llm", specifier = ">=0.2.2" },
|
||||
{ name = "pypdfium2", specifier = ">=5.9.0" },
|
||||
{ name = "python-json-logger", specifier = ">=3.2.0" },
|
||||
{ name = "pythonvcard4", specifier = ">=0.2.0" },
|
||||
{ name = "qdrant-client", specifier = ">=1.17.0" },
|
||||
@@ -3455,6 +3457,35 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/c0/1e/5fae75a5dc478e376ab95253c2f611665a4d9e2249667387a975e00fbbcb/pymupdf4llm-0.2.7-py3-none-any.whl", hash = "sha256:3ac6b0344c8bade2c97c3d7ea5eb354c71383a8d1ca177fafc3519dd564273b7", size = 66905, upload-time = "2025-12-07T20:43:12.447Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pypdfium2"
|
||||
version = "5.9.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/b0/98/6b44bf82ddb3c7a3e0249203772aad8981b4491d6227f182685f310faeff/pypdfium2-5.9.0.tar.gz", hash = "sha256:db1274bd27844db6fda17ef1dbcd0026c47d357437058d838e98060c0da9e92e", size = 272455, upload-time = "2026-06-01T15:43:38.08Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/8b/d9/59630cb40e5f37e7712e6ea65e9cac633f4195e8b737bb3a46054aa63340/pypdfium2-5.9.0-py3-none-android_23_arm64_v8a.whl", hash = "sha256:91914837c4a4285b3e0724a84eca8079363db7475acbcab405933d1807785664", size = 3407817, upload-time = "2026-06-01T15:42:58.426Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/0f/3d/e205708835a3730d5242652b6577ac06ad4721e6fcef77cc7c9d3541c686/pypdfium2-5.9.0-py3-none-android_23_armeabi_v7a.whl", hash = "sha256:90610d352f050b065b703f3a46602a852fce7dd8787300c8c7a472485b644d8f", size = 2862706, upload-time = "2026-06-01T15:43:00.581Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/01/47/e843fb895a891438b3f8c6d834fdc9c19183cd60980fc9325429d5c01505/pypdfium2-5.9.0-py3-none-macosx_11_0_arm64.whl", hash = "sha256:6c4fbe3a7190b329c526358fb2855d797f7b74b5ecfc61d19657ef20bcebc108", size = 3489945, upload-time = "2026-06-01T15:43:02.542Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/35/bd/f5e6afd556f97fcaa2bec4cb04669664c166028fc2a059bd65447c852b43/pypdfium2-5.9.0-py3-none-macosx_11_0_x86_64.whl", hash = "sha256:e93f0cf440169a3e445e6fbd06c803877e7418f3e13254287875cb67f208bb5a", size = 3674186, upload-time = "2026-06-01T15:43:04.496Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/6d/4d/5286812216a292d51dfba8e7bff276da198f126508f8c2afa3630bf701dc/pypdfium2-5.9.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1d902e03dff5efd51d93cd23d3e55bde53802fa6207bcd0e455239518859a069", size = 3669571, upload-time = "2026-06-01T15:43:06.571Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ac/c8/822db2c89baa13e6cee321d587fcd42df463a1fc2f7520b3f6814768bc71/pypdfium2-5.9.0-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:6cf38d7ad3575947b82384869f2ab69ba345eb21d83118d25db3e83f967b0421", size = 3400412, upload-time = "2026-06-01T15:43:08.35Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/1a/dd/7d09d8cdc28383df13f739a97ac4f1215a704a97a29506dee2bf89d8a350/pypdfium2-5.9.0-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:77f7479a28b43aa658735e3ce79cfd1fccd5d42db035c21bb4c26e8bd7e280e5", size = 3803326, upload-time = "2026-06-01T15:43:10.054Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/99/58/3f4e04ffe1ae62b437de07a96da672091cef62b619d0dc78207c1af442e6/pypdfium2-5.9.0-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:07e6ba170d577eabf60dbba701d051c64318dd029d38ca5907d83ae1a66fe779", size = 4216890, upload-time = "2026-06-01T15:43:11.701Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/1d/f6/2dde4656750c4a6da99e1f070ca09d2b5a9d68186b42e711a1a3e5b1cb32/pypdfium2-5.9.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7ce3a3dd23ec0adaa079d8be54565ba2aa2f6060e76a4989cd42dabc163d74ee", size = 3728830, upload-time = "2026-06-01T15:43:13.329Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/d0/ca/f2ff8b9200c7dfc5aee85126edc856eb93c7056085da2454a75ef1e4dbc4/pypdfium2-5.9.0-py3-none-manylinux_2_27_s390x.manylinux_2_28_s390x.whl", hash = "sha256:ae177938f5cf95a275db25a4f8553e2ebd954ecda2f9bc84848ba4b027ce438f", size = 4063322, upload-time = "2026-06-01T15:43:15.158Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/64/88/0b587de03c873c28adc59f6ac959de4032d3f3bc946094523b14a192d9c3/pypdfium2-5.9.0-py3-none-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:ffe49edde2ac86f28ca7e58f565255a442f38a7508fff31b79a55f508f25a31e", size = 4039738, upload-time = "2026-06-01T15:43:16.975Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/83/4c/fa627f00a954e66465e929077cf43bd012595091fff82758d989486e7bdc/pypdfium2-5.9.0-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:b7b760bc2957ecf73c274af6ed8b168a2dcb328ac0a0f7ed6123cd92f6e7c9c9", size = 4997259, upload-time = "2026-06-01T15:43:18.915Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/32/f0/1736d80c5d12d931f74ca6b4213b006ee016ec33c6325fad870234cc240c/pypdfium2-5.9.0-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:7cdc8e5d2f8d82add1e4f70a4fbe5f3b33c17f301ebde38c669fd7f78a7d032c", size = 4537061, upload-time = "2026-06-01T15:43:20.879Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/01/00/aa8890dfd385b2e7365034231987029cff15cc7eb4f06e8380da5608738a/pypdfium2-5.9.0-py3-none-musllinux_1_2_i686.whl", hash = "sha256:38a058dbd4929acaf0ab9171179eb86c24d8c6655a6836006796105a9f200890", size = 5232786, upload-time = "2026-06-01T15:43:23.73Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/65/12/8f45ea698781a0bed96ac4fbde440060790863273943461f0f160a993d52/pypdfium2-5.9.0-py3-none-musllinux_1_2_ppc64le.whl", hash = "sha256:1894511a0e862e7ec5679f3a6dc43ac72c4ef92c7ca438357203913e8634a643", size = 5170121, upload-time = "2026-06-01T15:43:25.858Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/25/bd/9bb6ba375796e1de1d6c1af8d8303dd1781190346871c81a94d4e09eddfd/pypdfium2-5.9.0-py3-none-musllinux_1_2_riscv64.whl", hash = "sha256:040f5513b808db705d4878f57e2bf0b9dc6e6a0ad8d765c36cf62febf3933b28", size = 4663540, upload-time = "2026-06-01T15:43:27.677Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/d2/4a/fd103bac197f22038bf70be1f7507ced7519f1214ea0dae137f37803ab8a/pypdfium2-5.9.0-py3-none-musllinux_1_2_s390x.whl", hash = "sha256:f4991ae39bcea757552579bba4aebfaedb71c96dd35c2292f957b8ac9132f1ff", size = 5090619, upload-time = "2026-06-01T15:43:29.522Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/22/89/9531fa1e6e004fe522cdca0cd945cd6a9d7338e7125e6b0734d632d31fa6/pypdfium2-5.9.0-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:25ff1a5abd08ff9e87f62e5dac114ea95647c257fbbdbe029be8db71a6d7650b", size = 5050806, upload-time = "2026-06-01T15:43:31.322Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/fc/d0/e53c68555ff128b2470e4a468762b320d9c6ae2c914decea3487d923982f/pypdfium2-5.9.0-py3-none-win32.whl", hash = "sha256:b0057dc8c2033584dc3e61afb5f23a135dab52b081695b435e27f9b7b074c605", size = 3670966, upload-time = "2026-06-01T15:43:32.991Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/da/0c/22e5fc035ad1594b44f265bc0a59ae34d377bc2ea74a92793e7a674bf96d/pypdfium2-5.9.0-py3-none-win_amd64.whl", hash = "sha256:06508c33b9772cf3878e48364c6e14c70cefc18a3abd6983ac9f338da9305275", size = 3800959, upload-time = "2026-06-01T15:43:34.536Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/11/e3/cf1711add7add22a17f7c7633cd795edc92f17ab7bdf1930493ae0f56680/pypdfium2-5.9.0-py3-none-win_arm64.whl", hash = "sha256:565ddfc98795fd2f6054b544ee9791d7b9032f9cf77a57891b6e501fafd0ef3f", size = 3585718, upload-time = "2026-06-01T15:43:36.521Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pyreadline3"
|
||||
version = "3.5.4"
|
||||
|
||||
Reference in New Issue
Block a user