From: shamoon <4887959+shamoon@users.noreply.github.com> Date: Sat, 2 Aug 2025 03:51:50 +0000 (-0400) Subject: Merge branch 'dev' into feature-ai X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=refs%2Fheads%2Ffeature-ai;p=thirdparty%2Fpaperless-ngx.git Merge branch 'dev' into feature-ai --- b52412d7763c7ef81652931d234e7179421d5f91 diff --cc docs/index.md index 3e9f835912,c1c06eb2b9..fd1473b717 --- a/docs/index.md +++ b/docs/index.md @@@ -30,8 -30,7 +30,8 @@@ physical documents into a searchable on - Utilizes the open-source Tesseract engine to recognize more than 100 languages. - Documents are saved as PDF/A format which is designed for long term storage, alongside the unaltered originals. - Uses machine-learning to automatically add tags, correspondents and document types to your documents. +- **New**: Paperless-ngx can now leverage AI (Large Language Models or LLMs) for document suggestions. This is an optional feature that can be enabled (and is disabled by default). - - Supports PDF documents, images, plain text files, Office documents (Word, Excel, Powerpoint, and LibreOffice equivalents)[^1] and more. + - Supports PDF documents, images, plain text files, Office documents (Word, Excel, PowerPoint, and LibreOffice equivalents)[^1] and more. - Paperless stores your documents plain on disk. Filenames and folders are managed by paperless and their format can be configured freely with different configurations assigned to different documents. - **Beautiful, modern web application** that features: - Customizable dashboard with statistics. diff --cc pyproject.toml index 6fcfcb0174,1a98266b7f..8e2d38a9a3 --- a/pyproject.toml +++ b/pyproject.toml @@@ -248,7 -239,7 +248,8 @@@ testpaths = "src/paperless_mail/tests/", "src/paperless_tesseract/tests/", "src/paperless_tika/tests", + "src/paperless_text/tests/", + "src/paperless_ai/tests", ] addopts = [ "--pythonwarnings=all", diff --cc src-ui/src/app/components/document-detail/document-detail.component.ts index 8d2f32ac98,55b8ade397..3c018188c1 --- a/src-ui/src/app/components/document-detail/document-detail.component.ts +++ b/src-ui/src/app/components/document-detail/document-detail.component.ts @@@ -73,8 -73,8 +73,9 @@@ import { CorrespondentService } from 's import { CustomFieldsService } from 'src/app/services/rest/custom-fields.service' import { DocumentTypeService } from 'src/app/services/rest/document-type.service' import { DocumentService } from 'src/app/services/rest/document.service' + import { SavedViewService } from 'src/app/services/rest/saved-view.service' import { StoragePathService } from 'src/app/services/rest/storage-path.service' +import { TagService } from 'src/app/services/rest/tag.service' import { UserService } from 'src/app/services/rest/user.service' import { SettingsService } from 'src/app/services/settings.service' import { ToastService } from 'src/app/services/toast.service' diff --cc src/documents/views.py index 74249ed1ad,b84267d75e..40aa20db7f --- a/src/documents/views.py +++ b/src/documents/views.py @@@ -1174,55 -1093,16 +1174,62 @@@ class DocumentViewSet ) +@method_decorator( + [ + ensure_csrf_cookie, + login_required, + cache_control(no_cache=True), + ], + name="dispatch", +) +class ChatStreamingView(View): + def post(self, request): + request.compress_exempt = True + ai_config = AIConfig() + if not ai_config.ai_enabled: + return HttpResponseBadRequest("AI is required for this feature") + + try: + data = json.loads(request.body) + question = data["q"] + doc_id = data.get("document_id", None) + except (KeyError, json.JSONDecodeError): + return HttpResponseBadRequest("Invalid request") + + if doc_id: + try: + document = Document.objects.get(id=doc_id) + except Document.DoesNotExist: + return HttpResponseBadRequest("Document not found") + + if not has_perms_owner_aware(request.user, "view_document", document): + return HttpResponseForbidden("Insufficient permissions") + + documents = [document] + else: + documents = get_objects_for_user_owner_aware( + request.user, + "view_document", + Document, + ) + + response = StreamingHttpResponse( + stream_chat_with_documents(query_str=question, documents=documents), + content_type="text/event-stream", + ) + return response + + @extend_schema_view( list=extend_schema( + description="Document views including search", parameters=[ + OpenApiParameter( + name="query", + type=OpenApiTypes.STR, + location=OpenApiParameter.QUERY, + description="Advanced search query string", + ), OpenApiParameter( name="full_perms", type=OpenApiTypes.BOOL, diff --cc uv.lock index c6e144ecaa,79e73b6c73..db57301a58 --- a/uv.lock +++ b/uv.lock @@@ -4097,49 -3102,29 +4099,49 @@@ wheels = [[package]] name = "ruff" - version = "0.12.2" + version = "0.12.7" source = { registry = "https://pypi.org/simple" } - sdist = { url = "https://files.pythonhosted.org/packages/6c/3d/d9a195676f25d00dbfcf3cf95fdd4c685c497fcfa7e862a44ac5e4e96480/ruff-0.12.2.tar.gz", hash = "sha256:d7b4f55cd6f325cb7621244f19c873c565a08aff5a4ba9c69aa7355f3f7afd3e", size = 4432239, upload-time = "2025-07-03T16:40:19.566Z" } + sdist = { url = "https://files.pythonhosted.org/packages/a1/81/0bd3594fa0f690466e41bd033bdcdf86cba8288345ac77ad4afbe5ec743a/ruff-0.12.7.tar.gz", hash = "sha256:1fc3193f238bc2d7968772c82831a4ff69252f673be371fb49663f0068b7ec71", size = 5197814, upload-time = "2025-07-29T22:32:35.877Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/74/b6/2098d0126d2d3318fd5bec3ad40d06c25d377d95749f7a0c5af17129b3b1/ruff-0.12.2-py3-none-linux_armv6l.whl", hash = "sha256:093ea2b221df1d2b8e7ad92fc6ffdca40a2cb10d8564477a987b44fd4008a7be", size = 10369761, upload-time = "2025-07-03T16:39:38.847Z" }, - { url = "https://files.pythonhosted.org/packages/b1/4b/5da0142033dbe155dc598cfb99262d8ee2449d76920ea92c4eeb9547c208/ruff-0.12.2-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:09e4cf27cc10f96b1708100fa851e0daf21767e9709e1649175355280e0d950e", size = 11155659, upload-time = "2025-07-03T16:39:42.294Z" }, - { url = "https://files.pythonhosted.org/packages/3e/21/967b82550a503d7c5c5c127d11c935344b35e8c521f52915fc858fb3e473/ruff-0.12.2-py3-none-macosx_11_0_arm64.whl", hash = "sha256:8ae64755b22f4ff85e9c52d1f82644abd0b6b6b6deedceb74bd71f35c24044cc", size = 10537769, upload-time = "2025-07-03T16:39:44.75Z" }, - { url = "https://files.pythonhosted.org/packages/33/91/00cff7102e2ec71a4890fb7ba1803f2cdb122d82787c7d7cf8041fe8cbc1/ruff-0.12.2-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3eb3a6b2db4d6e2c77e682f0b988d4d61aff06860158fdb413118ca133d57922", size = 10717602, upload-time = "2025-07-03T16:39:47.652Z" }, - { url = "https://files.pythonhosted.org/packages/9b/eb/928814daec4e1ba9115858adcda44a637fb9010618721937491e4e2283b8/ruff-0.12.2-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:73448de992d05517170fc37169cbca857dfeaeaa8c2b9be494d7bcb0d36c8f4b", size = 10198772, upload-time = "2025-07-03T16:39:49.641Z" }, - { url = "https://files.pythonhosted.org/packages/50/fa/f15089bc20c40f4f72334f9145dde55ab2b680e51afb3b55422effbf2fb6/ruff-0.12.2-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3b8b94317cbc2ae4a2771af641739f933934b03555e51515e6e021c64441532d", size = 11845173, upload-time = "2025-07-03T16:39:52.069Z" }, - { url = "https://files.pythonhosted.org/packages/43/9f/1f6f98f39f2b9302acc161a4a2187b1e3a97634fe918a8e731e591841cf4/ruff-0.12.2-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:45fc42c3bf1d30d2008023a0a9a0cfb06bf9835b147f11fe0679f21ae86d34b1", size = 12553002, upload-time = "2025-07-03T16:39:54.551Z" }, - { url = "https://files.pythonhosted.org/packages/d8/70/08991ac46e38ddd231c8f4fd05ef189b1b94be8883e8c0c146a025c20a19/ruff-0.12.2-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ce48f675c394c37e958bf229fb5c1e843e20945a6d962cf3ea20b7a107dcd9f4", size = 12171330, upload-time = "2025-07-03T16:39:57.55Z" }, - { url = "https://files.pythonhosted.org/packages/88/a9/5a55266fec474acfd0a1c73285f19dd22461d95a538f29bba02edd07a5d9/ruff-0.12.2-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:793d8859445ea47591272021a81391350205a4af65a9392401f418a95dfb75c9", size = 11774717, upload-time = "2025-07-03T16:39:59.78Z" }, - { url = "https://files.pythonhosted.org/packages/87/e5/0c270e458fc73c46c0d0f7cf970bb14786e5fdb88c87b5e423a4bd65232b/ruff-0.12.2-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6932323db80484dda89153da3d8e58164d01d6da86857c79f1961934354992da", size = 11646659, upload-time = "2025-07-03T16:40:01.934Z" }, - { url = "https://files.pythonhosted.org/packages/b7/b6/45ab96070c9752af37f0be364d849ed70e9ccede07675b0ec4e3ef76b63b/ruff-0.12.2-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:6aa7e623a3a11538108f61e859ebf016c4f14a7e6e4eba1980190cacb57714ce", size = 10604012, upload-time = "2025-07-03T16:40:04.363Z" }, - { url = "https://files.pythonhosted.org/packages/86/91/26a6e6a424eb147cc7627eebae095cfa0b4b337a7c1c413c447c9ebb72fd/ruff-0.12.2-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:2a4a20aeed74671b2def096bdf2eac610c7d8ffcbf4fb0e627c06947a1d7078d", size = 10176799, upload-time = "2025-07-03T16:40:06.514Z" }, - { url = "https://files.pythonhosted.org/packages/f5/0c/9f344583465a61c8918a7cda604226e77b2c548daf8ef7c2bfccf2b37200/ruff-0.12.2-py3-none-musllinux_1_2_i686.whl", hash = "sha256:71a4c550195612f486c9d1f2b045a600aeba851b298c667807ae933478fcef04", size = 11241507, upload-time = "2025-07-03T16:40:08.708Z" }, - { url = "https://files.pythonhosted.org/packages/1c/b7/99c34ded8fb5f86c0280278fa89a0066c3760edc326e935ce0b1550d315d/ruff-0.12.2-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:4987b8f4ceadf597c927beee65a5eaf994c6e2b631df963f86d8ad1bdea99342", size = 11717609, upload-time = "2025-07-03T16:40:10.836Z" }, + { url = "https://files.pythonhosted.org/packages/e1/d2/6cb35e9c85e7a91e8d22ab32ae07ac39cc34a71f1009a6f9e4a2a019e602/ruff-0.12.7-py3-none-linux_armv6l.whl", hash = "sha256:76e4f31529899b8c434c3c1dede98c4483b89590e15fb49f2d46183801565303", size = 11852189, upload-time = "2025-07-29T22:31:41.281Z" }, + { url = "https://files.pythonhosted.org/packages/63/5b/a4136b9921aa84638f1a6be7fb086f8cad0fde538ba76bda3682f2599a2f/ruff-0.12.7-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:789b7a03e72507c54fb3ba6209e4bb36517b90f1a3569ea17084e3fd295500fb", size = 12519389, upload-time = "2025-07-29T22:31:54.265Z" }, + { url = "https://files.pythonhosted.org/packages/a8/c9/3e24a8472484269b6b1821794141f879c54645a111ded4b6f58f9ab0705f/ruff-0.12.7-py3-none-macosx_11_0_arm64.whl", hash = "sha256:2e1c2a3b8626339bb6369116e7030a4cf194ea48f49b64bb505732a7fce4f4e3", size = 11743384, upload-time = "2025-07-29T22:31:59.575Z" }, + { url = "https://files.pythonhosted.org/packages/26/7c/458dd25deeb3452c43eaee853c0b17a1e84169f8021a26d500ead77964fd/ruff-0.12.7-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:32dec41817623d388e645612ec70d5757a6d9c035f3744a52c7b195a57e03860", size = 11943759, upload-time = "2025-07-29T22:32:01.95Z" }, + { url = "https://files.pythonhosted.org/packages/7f/8b/658798472ef260ca050e400ab96ef7e85c366c39cf3dfbef4d0a46a528b6/ruff-0.12.7-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:47ef751f722053a5df5fa48d412dbb54d41ab9b17875c6840a58ec63ff0c247c", size = 11654028, upload-time = "2025-07-29T22:32:04.367Z" }, + { url = "https://files.pythonhosted.org/packages/a8/86/9c2336f13b2a3326d06d39178fd3448dcc7025f82514d1b15816fe42bfe8/ruff-0.12.7-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a828a5fc25a3efd3e1ff7b241fd392686c9386f20e5ac90aa9234a5faa12c423", size = 13225209, upload-time = "2025-07-29T22:32:06.952Z" }, + { url = "https://files.pythonhosted.org/packages/76/69/df73f65f53d6c463b19b6b312fd2391dc36425d926ec237a7ed028a90fc1/ruff-0.12.7-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:5726f59b171111fa6a69d82aef48f00b56598b03a22f0f4170664ff4d8298efb", size = 14182353, upload-time = "2025-07-29T22:32:10.053Z" }, + { url = "https://files.pythonhosted.org/packages/58/1e/de6cda406d99fea84b66811c189b5ea139814b98125b052424b55d28a41c/ruff-0.12.7-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:74e6f5c04c4dd4aba223f4fe6e7104f79e0eebf7d307e4f9b18c18362124bccd", size = 13631555, upload-time = "2025-07-29T22:32:12.644Z" }, + { url = "https://files.pythonhosted.org/packages/6f/ae/625d46d5164a6cc9261945a5e89df24457dc8262539ace3ac36c40f0b51e/ruff-0.12.7-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5d0bfe4e77fba61bf2ccadf8cf005d6133e3ce08793bbe870dd1c734f2699a3e", size = 12667556, upload-time = "2025-07-29T22:32:15.312Z" }, + { url = "https://files.pythonhosted.org/packages/55/bf/9cb1ea5e3066779e42ade8d0cd3d3b0582a5720a814ae1586f85014656b6/ruff-0.12.7-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:06bfb01e1623bf7f59ea749a841da56f8f653d641bfd046edee32ede7ff6c606", size = 12939784, upload-time = "2025-07-29T22:32:17.69Z" }, + { url = "https://files.pythonhosted.org/packages/55/7f/7ead2663be5627c04be83754c4f3096603bf5e99ed856c7cd29618c691bd/ruff-0.12.7-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:e41df94a957d50083fd09b916d6e89e497246698c3f3d5c681c8b3e7b9bb4ac8", size = 11771356, upload-time = "2025-07-29T22:32:20.134Z" }, + { url = "https://files.pythonhosted.org/packages/17/40/a95352ea16edf78cd3a938085dccc55df692a4d8ba1b3af7accbe2c806b0/ruff-0.12.7-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:4000623300563c709458d0ce170c3d0d788c23a058912f28bbadc6f905d67afa", size = 11612124, upload-time = "2025-07-29T22:32:22.645Z" }, + { url = "https://files.pythonhosted.org/packages/4d/74/633b04871c669e23b8917877e812376827c06df866e1677f15abfadc95cb/ruff-0.12.7-py3-none-musllinux_1_2_i686.whl", hash = "sha256:69ffe0e5f9b2cf2b8e289a3f8945b402a1b19eff24ec389f45f23c42a3dd6fb5", size = 12479945, upload-time = "2025-07-29T22:32:24.765Z" }, + { url = "https://files.pythonhosted.org/packages/be/34/c3ef2d7799c9778b835a76189c6f53c179d3bdebc8c65288c29032e03613/ruff-0.12.7-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:a07a5c8ffa2611a52732bdc67bf88e243abd84fe2d7f6daef3826b59abbfeda4", size = 12998677, upload-time = "2025-07-29T22:32:27.022Z" }, ] +[[package]] +name = "safetensors" +version = "0.5.3" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/71/7e/2d5d6ee7b40c0682315367ec7475693d110f512922d582fef1bd4a63adc3/safetensors-0.5.3.tar.gz", hash = "sha256:b6b0d6ecacec39a4fdd99cc19f4576f5219ce858e6fd8dbe7609df0b8dc56965", size = 67210 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/18/ae/88f6c49dbd0cc4da0e08610019a3c78a7d390879a919411a410a1876d03a/safetensors-0.5.3-cp38-abi3-macosx_10_12_x86_64.whl", hash = "sha256:bd20eb133db8ed15b40110b7c00c6df51655a2998132193de2f75f72d99c7073", size = 436917 }, + { url = "https://files.pythonhosted.org/packages/b8/3b/11f1b4a2f5d2ab7da34ecc062b0bc301f2be024d110a6466726bec8c055c/safetensors-0.5.3-cp38-abi3-macosx_11_0_arm64.whl", hash = "sha256:21d01c14ff6c415c485616b8b0bf961c46b3b343ca59110d38d744e577f9cce7", size = 418419 }, + { url = "https://files.pythonhosted.org/packages/5d/9a/add3e6fef267658075c5a41573c26d42d80c935cdc992384dfae435feaef/safetensors-0.5.3-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:11bce6164887cd491ca75c2326a113ba934be596e22b28b1742ce27b1d076467", size = 459493 }, + { url = "https://files.pythonhosted.org/packages/df/5c/bf2cae92222513cc23b3ff85c4a1bb2811a2c3583ac0f8e8d502751de934/safetensors-0.5.3-cp38-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:4a243be3590bc3301c821da7a18d87224ef35cbd3e5f5727e4e0728b8172411e", size = 472400 }, + { url = "https://files.pythonhosted.org/packages/58/11/7456afb740bd45782d0f4c8e8e1bb9e572f1bf82899fb6ace58af47b4282/safetensors-0.5.3-cp38-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8bd84b12b1670a6f8e50f01e28156422a2bc07fb16fc4e98bded13039d688a0d", size = 522891 }, + { url = "https://files.pythonhosted.org/packages/57/3d/fe73a9d2ace487e7285f6e157afee2383bd1ddb911b7cb44a55cf812eae3/safetensors-0.5.3-cp38-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:391ac8cab7c829452175f871fcaf414aa1e292b5448bd02620f675a7f3e7abb9", size = 537694 }, + { url = "https://files.pythonhosted.org/packages/a6/f8/dae3421624fcc87a89d42e1898a798bc7ff72c61f38973a65d60df8f124c/safetensors-0.5.3-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cead1fa41fc54b1e61089fa57452e8834f798cb1dc7a09ba3524f1eb08e0317a", size = 471642 }, + { url = "https://files.pythonhosted.org/packages/ce/20/1fbe16f9b815f6c5a672f5b760951e20e17e43f67f231428f871909a37f6/safetensors-0.5.3-cp38-abi3-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:1077f3e94182d72618357b04b5ced540ceb71c8a813d3319f1aba448e68a770d", size = 502241 }, + { url = "https://files.pythonhosted.org/packages/5f/18/8e108846b506487aa4629fe4116b27db65c3dde922de2c8e0cc1133f3f29/safetensors-0.5.3-cp38-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:799021e78287bac619c7b3f3606730a22da4cda27759ddf55d37c8db7511c74b", size = 638001 }, + { url = "https://files.pythonhosted.org/packages/82/5a/c116111d8291af6c8c8a8b40628fe833b9db97d8141c2a82359d14d9e078/safetensors-0.5.3-cp38-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:df26da01aaac504334644e1b7642fa000bfec820e7cef83aeac4e355e03195ff", size = 734013 }, + { url = "https://files.pythonhosted.org/packages/7d/ff/41fcc4d3b7de837963622e8610d998710705bbde9a8a17221d85e5d0baad/safetensors-0.5.3-cp38-abi3-musllinux_1_2_i686.whl", hash = "sha256:32c3ef2d7af8b9f52ff685ed0bc43913cdcde135089ae322ee576de93eae5135", size = 670687 }, + { url = "https://files.pythonhosted.org/packages/40/ad/2b113098e69c985a3d8fbda4b902778eae4a35b7d5188859b4a63d30c161/safetensors-0.5.3-cp38-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:37f1521be045e56fc2b54c606d4455573e717b2d887c579ee1dbba5f868ece04", size = 643147 }, +] + [[package]] name = "scikit-learn" - version = "1.7.0" + version = "1.7.1" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "joblib", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },