2025-08-26 - 2026-08-26
Overview
68 Releases published by 2 users
Published
llama-cloud-services-py@0.6.94
Published
llama_parse@0.6.94
Published
llama-cloud-services-py@0.6.93
Published
llama_parse@0.6.93
Published
llama-cloud-services-py@0.6.92
Published
llama-cloud-services@0.5.4
Published
llama_parse@0.6.92
Published
llama-cloud-services-py@0.6.91
Published
llama_parse@0.6.91
Published
llama-cloud-services-py@0.6.90
Published
llama_parse@0.6.90
Published
llama-cloud-services@0.5.3
Published
llama-cloud-services@0.5.2
Published
llama-cloud-services-py@0.6.89
Published
llama_parse@0.6.89
Published
llama-cloud-services@0.5.1
Published
llama-cloud-services-py@0.6.88
Published
llama-cloud-services@0.4.3
Published
llama_parse@0.6.88
Published
llama-cloud-services-py@0.6.87
Published
llama_parse@0.6.87
Published
llama-cloud-services-py@0.6.86
Published
llama_parse@0.6.86
Published
llama-cloud-services-py@0.6.85
Published
llama_parse@0.6.85
Published
llama-cloud-services-py@0.6.84
Published
llama_parse@0.6.84
Published
llama-cloud-services-py@0.6.83
Published
llama_parse@0.6.83
Published
llama-cloud-services-py@0.6.82
Published
llama-cloud-services@0.4.2
Published
llama_parse@0.6.82
Published
llama-cloud-services-py@0.6.81
Published
llama-cloud-services@0.4.1
Published
llama_parse@0.6.81
Published
llama-cloud-services-py@0.6.80
Published
llama_parse@0.6.80
Published
llama-cloud-services-py@0.6.79
Published
llama-cloud-services@0.4.0
Published
llama_parse@0.6.79
Published
llama-cloud-services-py@0.6.78
Published
llama_parse@0.6.78
Published
llama-cloud-services-py@0.6.77
Published
llama_parse@0.6.77
Published
llama-cloud-services@0.3.10
Published
llama-cloud-services@0.3.9
Published
llama-cloud-services-py@0.6.76
Published
llama_parse@0.6.76
Published
llama-cloud-services-py@0.6.75
Published
llama_parse@0.6.75
Published
llama-cloud-services-py@0.6.74
Published
llama_parse@0.6.74
Published
llama-cloud-services-py@0.6.73
Published
llama-cloud-services@0.3.8
Published
llama_parse@0.6.73
Published
llama-cloud-services-py@0.6.72
Published
llama_parse@0.6.72
Published
llama-cloud-services@0.3.7
Published
v0.6.69
Published
v0.6.68
Published
v0.6.67
Published
llama-cloud-services@0.3.6
Published
v0.6.66
Published
llama-cloud-services@0.3.5
Published
v0.6.65
Published
v0.6.64
Published
llama-cloud-services@0.3.4
Published
v0.6.63
734 Issues closed from 1 user
Closed
#1081 [PR #1111] [MERGED] more loudly deprecate ancient llama-parse package
Closed
#1082 [PR #1112] [MERGED] chore: version packages
Closed
#1083 [PR #1114] [MERGED] Allows xlsx files in the sdk for extract
Closed
#1084 [PR #1113] [CLOSED] Extract e2e confidence problem
Closed
#1085 [PR #1115] [MERGED] Bump up patch version
Closed
#1086 [PR #1116] [MERGED] chore: version packages
Closed
#1076 [PR #1095] [MERGED] Add retries to all extract sdk functions uniformly
Closed
#1077 [PR #1098] [MERGED] Use sonnet when testing premium mode in extract e2e
Closed
#1078 [PR #1101] [MERGED] Use unique filenames when running dist tests
Closed
#1079 [PR #1103] [MERGED] chore: version packages
Closed
#1080 [PR #1110] [MERGED] Lower frequency for e2e tests
Closed
#1070 [PR #1090] [MERGED] Force github reparse of the workflow
Closed
#1071 [PR #1092] [MERGED] build(deps): bump slackapi/slack-github-action from 1.27.0 to 2.1.1
Closed
#1072 [PR #1093] [MERGED] Try to reparse scheduled workflow
Closed
#1073 [PR #1094] [MERGED] Change cron schedule for hourly extract tests
Closed
#1074 [PR #1096] [MERGED] Fix verbose logging on slack channel
Closed
#1075 [PR #1097] [MERGED] Invalidate cache when running extract tests
Closed
#1064 [PR #1082] [CLOSED] chore: version packages
Closed
#1065 [PR #1081] [MERGED] Use error description in invalid extraction error
Closed
#1066 [PR #1085] [MERGED] Bump up minor version for python packages
Closed
#1067 [PR #1087] [MERGED] chore: version packages
Closed
#1069 [PR #1089] [MERGED] Run hourly extract tests to catch SDK schema drifts
Closed
#1061 [PR #1075] [MERGED] remove extension filter
Closed
#1062 [PR #1076] [MERGED] chore: version packages
Closed
#1063 [PR #1086] [MERGED] Bump up patch version for python packages
Closed
#1056 [PR #1069] [MERGED] Add bounding box type support to TS too
Closed
#1057 [PR #1070] [MERGED] forgot ts changeset
Closed
#1058 [PR #1071] [MERGED] chore: version packages
Closed
#1059 [PR #1073] [MERGED] chore: version packages
Closed
#1060 [PR #1074] [CLOSED] Pierre/allow not ext files
Closed
#1050 [PR #1057] [MERGED] Remove generate from build path to fix publishing
Closed
#1051 [PR #1058] [MERGED] chore: version packages
Closed
#1052 [PR #1065] [MERGED] add notice (don't merge until ready)
Closed
#1053 [PR #1067] [MERGED] Parse bounding boxes from extract jobs results in agent data
Closed
#1054 [PR #1066] [MERGED] fix: bug fix retry logic in Classify and Extract
Closed
#1055 [PR #1068] [MERGED] chore: version packages
Closed
#1044 [PR #1051] [MERGED] batch parse sctript with asyncio
Closed
#1045 [PR #1045] [MERGED] add tier/version to api
Closed
#1046 [PR #1046] [MERGED] chore: version packages
Closed
#1047 [PR #1053] [MERGED] improve parse ts polling
Closed
#1048 [PR #1054] [MERGED] chore: version packages
Closed
#1049 [PR #1056] [MERGED] docs: correct links in readme
Closed
#1042 [PR #1052] [MERGED] feat: support zod v4 & v3
Closed
#1043 [PR #1044] [MERGED] docs: Split Example Notebook
Closed
#1037 [PR #1041] [MERGED] chore: version packages
Closed
#1038 [PR #1039] [MERGED] chore: version packages
Closed
#1039 [PR #1040] [MERGED] Bump llama cloud services and parse versions
Closed
#1040 [PR #1042] [MERGED] Add new fields to SpreadsheetParsingConfig and update validation tests
Closed
#1041 [PR #1043] [MERGED] chore: version packages
Closed
#1031 [PR #1032] [MERGED] Fix sheets API client
Closed
#1032 [PR #1035] [MERGED] chore: version packages
Closed
#1033 [PR #1036] [MERGED] Dummy release
Closed
#1034 [PR #1034] [MERGED] No more presigned URLs by default
Closed
#1035 [PR #1037] [MERGED] chore: version packages
Closed
#1036 [PR #1038] [MERGED] line level bbox
Closed
#1025 [PR #1023] [MERGED] Implement test plan and create mocked tests
Closed
#1026 [PR #1024] [CLOSED] add fake llama cloud server
Closed
#1027 [PR #1027] [MERGED] Pierre/more parse parameters
Closed
#1028 [PR #1028] [MERGED] feat: add mocking for agent data
Closed
#1029 [PR #1025] [MERGED] chore: version packages
Closed
#1030 [PR #1031] [MERGED] Add timeouts to E2E GHA
Closed
#1017 [PR #1012] [MERGED] Add support for custom metadata in file upload methods
Closed
#1018 [PR #1014] [MERGED] chore: version packages
Closed
#1019 [PR #1013] [MERGED] chore: rename classifyclient and keep it backward compatible
Closed
#1020 [PR #1016] [MERGED] chore: version packages
Closed
#1021 [PR #1015] [MERGED] propagate retrieval metadata to retrieved nodes
Closed
#1022 [PR #1021] [CLOSED] Implement llama cloud testing utilities and tests
Closed
#1023 [PR #1017] [MERGED] Add notebook for tabular extraction
Closed
#1012 [PR #1009] [MERGED] docs: add batch parse directory example notebook
Closed
#1014 [PR #996] [MERGED] destructured keyword params for classify
Closed
#1015 [PR #998] [MERGED] fix version breaking
Closed
#1016 [PR #997] [MERGED] Remove organization id from classify
Closed
#1008 [PR #991] [MERGED] chore: version packages
Closed
#1009 [PR #992] [MERGED] beta sheets API
Closed
#1010 [PR #995] [MERGED] chore: version packages
Closed
#1011 [PR #994] [MERGED] Bump to version 0.6.78
Closed
#1013 [PR #999] [MERGED] chore: version packages
Closed
#1002 [PR #988] [MERGED] chore: version packages
Closed
#1004 [PR #986] [MERGED] Add common SourceText class for classify/extract text inputs
Closed
#1005 [PR #985] [MERGED] feat: add classify to ts sdk
Closed
#1006 [PR #989] [MERGED] docs: add llamaclassify demo
Closed
#1007 [PR #990] [MERGED] Fix: Return partial results on job failure
Closed
#997 [PR #980] [MERGED] Add agressive table extraction argument
Closed
#998 [PR #981] [MERGED] chore: version packages
Closed
#999 [PR #977] [MERGED] chore: version packages
Closed
#1000 [PR #982] [MERGED] chore: version packages
Closed
#1001 [PR #983] [MERGED] improve classify notebook
Closed
#992 [PR #975] [MERGED] fix default bbox values
Closed
#993 [PR #973] [MERGED] build(deps): bump github/codeql-action from 3 to 4
Closed
#994 [PR #969] [MERGED] Add ImageNode support in TypeScript
Closed
#995 [PR #976] [MERGED] safest types possible for parse
Closed
#996 [PR #974] [MERGED] build(deps): bump astral-sh/setup-uv from 6 to 7
Closed
#987 [PR #963] [MERGED] fix: re-enable js publishing
Closed
#988 [PR #961] [MERGED] build(deps): bump actions/checkout from 4 to 5
Closed
#989 [PR #962] [MERGED] loosen packaging requirements
Closed
#990 [PR #964] [MERGED] Only escape single dollar sign in notebook md
Closed
#991 [PR #965] [MERGED] chore: version packages
Closed
#982 [PR #955] [MERGED] Missed some things again with tag fixes
Closed
#983 [PR #956] [MERGED] chore: version packages
Closed
#984 [PR #959] [MERGED] build(deps): bump pnpm/action-setup from 3 to 4
Closed
#985 [PR #960] [MERGED] build(deps): bump actions/setup-python from 5 to 6
Closed
#986 [PR #958] [MERGED] build(deps): bump astral-sh/setup-uv from 3 to 6
Closed
#977 [PR #951] [MERGED] fix changeset harder
Closed
#978 [PR #952] [MERGED] chore: version packages
Closed
#979 [PR #950] [CLOSED] chore: version packages
Closed
#980 [PR #953] [MERGED] fixup tagging more better
Closed
#981 [PR #954] [MERGED] chore: version packages
Closed
#972 [PR #946] [MERGED] Disable npm release
Closed
#973 [PR #945] [MERGED] Escaping dollar signs in md output when running in a jupyter notebook
Closed
#974 [PR #947] [CLOSED] chore: version packages
Closed
#975 [PR #949] [MERGED] swap changesets
Closed
#976 [PR #948] [MERGED] fix: explicitly tag. I thought the action did this
Closed
#967 [PR #940] [MERGED] Update llama-cloud dep
Closed
#968 [PR #941] [MERGED] chore: version packages
Closed
#969 [PR #943] [MERGED] fix: theres just one publish token
Closed
#970 [PR #944] [MERGED] Fix more bugs in publishing
Closed
#971 [PR #942] [MERGED] ignore nvmrc
Closed
#962 [PR #928] [MERGED] Handle validation errors for agent data retrieval
Closed
#963 [PR #924] [MERGED] Support creating indexes in a specified project_id
Closed
#964 [PR #927] [CLOSED] Add failing test for citation field bug
Closed
#965 [PR #931] [MERGED] docs: parse -> classify -> extract
Closed
#966 [PR #929] [MERGED] Handle reasoning field conflict
Closed
#957 [PR #919] [MERGED] parse: expose spreadsheet_force_formula_computation option
Closed
#958 [PR #920] [MERGED] py: bump version to v.0.6.66
Closed
#959 [PR #921] [MERGED] Refactor agent fields in llama_cloud_services
Closed
#952 [PR #909] [MERGED] Bump actions/setup-node from 4 to 5
Closed
#953 [PR #911] [MERGED] update parse package
Closed
#955 [PR #906] [MERGED] Fix uv sync; remove poetry lock
Closed
#946 [PR #897] [MERGED] Update version script, and unify the linting so that prettier is more consistent
Closed
#947 [PR #898] [MERGED] fix: "v" prefix being added to js versions
Closed
#948 [PR #902] [MERGED] fix: make ts release beautiful again
Closed
#949 [PR #899] [MERGED] fix: v prefix goes deeper. Fix more
Closed
#950 [PR #905] [MERGED] Remove report generation related code from llama_cloud_services
Closed
#951 [PR #904] [MERGED] Bump version to 0.6.64
Closed
#941 [PR #891] [MERGED] getting started LlamaCloudIndex notebook
Closed
#942 [PR #892] [MERGED] Added "SourceText" to __init__.py
Closed
#943 [PR #894] [MERGED] Fix tag push command in CONTRIBUTING.md
Closed
#944 [PR #893] [MERGED] version bump to 0.6.63
Closed
#945 [PR #895] [MERGED] client unification
Closed
#934 [PR #879] [CLOSED] deprecate (a)load_data methods and split_by_page in constructor
Closed
#936 [PR #882] [MERGED] update all example notebooks
Closed
#937 [PR #887] [MERGED] add alternative builder method
Closed
#938 [PR #888] [MERGED] add file names in return values
Closed
#939 [PR #884] [CLOSED] Surface parse errors
Closed
#940 [PR #889] [MERGED] parse: expose page.slideSpeakerNotes
Closed
#932 [PR #878] [MERGED] add acreate_classify_job
Closed
#933 [PR #881] [MERGED] fix: Make env based api url overrideable
Closed
#935 [PR #883] [MERGED] fix preset notebook: give outputs in markdown
Closed
#927 [PR #873] [MERGED] fix composite retriever
Closed
#928 [PR #872] [CLOSED] Update llama-cloud-services
Closed
#929 [PR #874] [MERGED] add a starter notebook for llamaparse presets
Closed
#930 [PR #875] [MERGED] Bump actions/checkout from 4 to 5
Closed
#931 [PR #871] [MERGED] feat: support passing a pre-uploaded file directly
Closed
#920 [PR #855] [MERGED] chore: bump ts version for parse
Closed
#921 [PR #864] [MERGED] fix presigned urls + add very necessary test
Closed
#922 [PR #867] [MERGED] parallelize e2e tests
Closed
#923 [PR #865] [MERGED] Re-order extraction metadata union for better parsing
Closed
#924 [PR #868] [MERGED] feat: export ExtractedFieldMetadata and ExtractedFieldMetadataDict types
Closed
#925 [PR #869] [MERGED] citation can be null
Closed
#926 [PR #870] [MERGED] handle error field
Closed
#917 [PR #863] [MERGED] missing await
Closed
#918 [PR #859] [MERGED] support llama parse audio
Closed
#919 [PR #861] [MERGED] remove print
Closed
#912 [PR #849] [MERGED] version via changesets
Closed
#913 [PR #851] [MERGED] feat: add parse and getTables methods to LlamaParseReader
Closed
#914 [PR #850] [MERGED] parse: expose HTML output for result table items when possible
Closed
#915 [PR #852] [MERGED] Update docs for extract
Closed
#916 [PR #853] [MERGED] Bump version to 0.6.56
Closed
#906 [PR #842] [CLOSED] chore: add e2e tests and use monorepo for TS
Closed
#907 [PR #845] [MERGED] docs: move ts examples in their own top-level folder
Closed
#908 [PR #846] [MERGED] py: bump version to 0.6.55
Closed
#909 [PR #844] [MERGED] utils/parse: add method to check pypi for package updates
Closed
#910 [PR #848] [CLOSED] maybe?
Closed
#911 [PR #847] [CLOSED] feat: implement changesets
Closed
#900 [PR #834] [MERGED] fix: Fix bugs in ExtractedFieldMetadata parser
Closed
#901 [PR #838] [MERGED] fix: run e2e only on 3.12
Closed
#902 [PR #839] [MERGED] wip: implementing Extract in TS
Closed
#903 [PR #841] [MERGED] Add claude code workflow with restricted access
Closed
#904 [PR #840] [MERGED] Update Extract with stateless API
Closed
#905 [PR #843] [MERGED] chore: build before releaes
Closed
#896 [PR #831] [CLOSED] feat: restructure docs/examples
Closed
#897 [PR #835] [CLOSED] Re-enabling this test
Closed
#898 [PR #836] [MERGED] add files client
Closed
#899 [PR #837] [MERGED] Classifier SDK
Closed
#892 [PR #828] [MERGED] fix: add symlink to avoid breaking links
Closed
#893 [PR #830] [MERGED] delete examples
Closed
#894 [PR #832] [MERGED] Copy extracted citations to the new repo
Closed
#895 [PR #829] [MERGED] Example Notebooks
Closed
#887 [PR #822] [MERGED] feat: add ts examples (clean)
Closed
#888 [PR #824] [MERGED] Update README.md
Closed
#889 [PR #823] [MERGED] fix: no git checks on pnpm publish
Closed
#890 [PR #827] [CLOSED] feat: add changesets
Closed
#891 [PR #826] [MERGED] chore: remove llamaindex dep
Closed
#882 [PR #817] [MERGED] feat: add index to llama-cloud-services
Closed
#883 [PR #820] [MERGED] docs(readme): update hyperlinks to correct targets
Closed
#884 [PR #819] [MERGED] fix: add release to NPM
Closed
#885 [PR #821] [MERGED] Merge index into main
Closed
#886 [PR #818] [CLOSED] Add examples for TypeScript
Closed
#877 [PR #809] [MERGED] Fixes to multimodal report generation
Closed
#878 [PR #815] [MERGED] Adding support for page citations, and refactor the confidence into the field metadata
Closed
#879 [PR #814] [MERGED] Bump llama-cloud version
Closed
#880 [PR #810] [CLOSED] wip: monorepo changes
Closed
#881 [PR #811] [MERGED] Adding TS llama-cloud-services and moving llama-parse to uv
Closed
#873 [PR #806] [MERGED] parse: expose preserve_very_small_text option
Closed
#874 [PR #802] [MERGED] bump version to v0.6.50
Closed
#875 [PR #801] [MERGED] parse: expose functionality to get raw job results
Closed
#876 [PR #803] [MERGED] feat: default to _public agent data
Closed
#869 [PR #800] [CLOSED] push get_markdown up a level to get_result to include result and full md in one
Closed
#870 [PR #794] [MERGED] chore: vbump to 0.6.47 and example notebook
Closed
#871 [PR #797] [MERGED] Bump v0.6.49
Closed
#872 [PR #808] [MERGED] Make versioning a little easier, and fix llama_parse version
Closed
#864 [PR #793] [MERGED] feat: add table extraction for LlamaParse as CSV files
Closed
#865 [PR #784] [MERGED] relax pydantic job object
Closed
#867 [PR #795] [MERGED] Update to version 0.6.48
Closed
#868 [PR #796] [MERGED] Add new method to fetch the full, non-paginated markdown
Closed
#860 [PR #783] [MERGED] Bump up version to 0.6.42
Closed
#861 [PR #772] [MERGED] Bump to version 0.6.39
Closed
#862 [PR #785] [MERGED] Improve Agent Data interface, and add file related fields to extracted data for file tracking
Closed
#863 [PR #786] [MERGED] merge_tables_across_pages_in_markdown parse parameter
Closed
#852 [PR #766] [MERGED] Manage extract agent lifecycle in pytest
Closed
#853 [PR #769] [MERGED] Relax tenacity version; bump up version to 0.6.37
Closed
#854 [PR #764] [MERGED] Make job fetching more robust to connection errors
Closed
#855 [PR #770] [CLOSED] Update parse client to handle Remote Protocol Error
Closed
#856 [PR #771] [MERGED] except one more error type
Closed
#857 [PR #775] [MERGED] header footer control in llamaparse
Closed
#858 [PR #776] [MERGED] parse: loosen PageItem.rows type hint (v0.6.41)
Closed
#859 [PR #782] [MERGED] Add nicer hand-written agent data interface
Closed
#850 [PR #757] [MERGED] add high_res_ocr to the package
Closed
#851 [PR #763] [MERGED] Bump up version to 0.6.36
Closed
#842 [PR #751] [MERGED] v0.6.31
Closed
#843 [PR #750] [MERGED] Fix colab broken links
Closed
#844 [PR #754] [MERGED] Bump requests from 2.32.3 to 2.32.4 in /llama_parse
Closed
#845 [PR #753] [MERGED] Bump tornado from 6.4.2 to 6.5.1 in /llama_parse
Closed
#846 [PR #752] [MERGED] Bump h11 from 0.14.0 to 0.16.0 in /llama_parse
Closed
#847 [PR #758] [MERGED] fix partition
Closed
#848 [PR #755] [MERGED] 6.32 warning on unused parameters
Closed
#849 [PR #762] [MERGED] Bump version to 0.6.35
Closed
#838 [PR #741] [MERGED] 0.6.28: fix job result format after partitioning changes
Closed
#839 [PR #743] [MERGED] Directly pass None project_id
Closed
#840 [PR #747] [MERGED] more optional types marked
Closed
#841 [PR #748] [MERGED] Bump to version 0.6.30
Closed
#834 [PR #740] [MERGED] v0.6.26
Closed
#835 [PR #737] [MERGED] parse: fix the "model" parameter mismatch between playground and Python client
Closed
#836 [PR #739] [MERGED] add multi-fund analysis notebook
Closed
#837 [PR #745] [MERGED] 0.6.29: Standerdize the parsing input format for both .aget_json() and .aload_data()
Closed
#830 [PR #731] [MERGED] Add notebook for Form 4 extraction
Closed
#831 [PR #729] [MERGED] Bump to version 0.6.23
Closed
#832 [PR #732] [MERGED] v0.6.24
Closed
#833 [PR #736] [MERGED] 0.6.25 outlined_table_extraction
Closed
#822 [PR #708] [MERGED] parse: fix num_workers/parse job batching
Closed
#823 [PR #707] [MERGED] v0.6.20
Closed
#824 [PR #711] [MERGED] even more optional
Closed
#825 [PR #709] [MERGED] parse: support partitioning files before parsing (v0.6.27)
Closed
#826 [PR #716] [MERGED] Adding example for extracting with citations
Closed
#827 [PR #720] [MERGED] Remove credits from parse metadata
Closed
#828 [PR #726] [MERGED] Pass through verify and timeout config to the extraction agent
Closed
#829 [PR #718] [MERGED] v0.6.22
Closed
#817 [PR #703] [MERGED] add support for presets
Closed
#818 [PR #704] [MERGED] add auto_mode_configuration_jon for llamaParse
Closed
#819 [PR #706] [MERGED] v0.6.19
Closed
#820 [PR #702] [MERGED] make original height + width optional in the parse result
Closed
#821 [PR #701] [MERGED] Bump actions/setup-python from 4 to 5
Closed
#812 [PR #696] [MERGED] Update to latest version of llama-cloud
Closed
#813 [PR #698] [MERGED] Dependabot configuration to update actions in workflow
Closed
#814 [PR #697] [MERGED] Bump to v0.6.16
Closed
#815 [PR #699] [MERGED] Refactor CodeQL workflow
Closed
#816 [PR #700] [MERGED] Bump actions/checkout from 3 to 4
Closed
#807 [PR #683] [MERGED] Add markdown_table_multiline_header_separator support
Closed
#808 [PR #692] [MERGED] skip llama-report tests in cicd
Closed
#809 [PR #682] [MERGED] Use unique filename to avoid db collisions later
Closed
#810 [PR #693] [MERGED] small enum nit for FailedPageMode
Closed
#811 [PR #691] [MERGED] Page error parameters
Closed
#802 [PR #678] [MERGED] Bump version to v0.6.11
Closed
#803 [PR #679] [MERGED] Update docs for LlamaExtract
Closed
#804 [PR #680] [MERGED] v0.6.12
Closed
#805 [PR #677] [MERGED] v0.6.10
Closed
#806 [PR #681] [MERGED] parse readme nits
Closed
#794 [PR #671] [MERGED] Update extract.md
Closed
#795 [PR #668] [MERGED] Rename test endpoint to match functionality
Closed
#796 [PR #667] [MERGED] solar panel extraction workflow
Closed
#797 [PR #673] [MERGED] Fix bytes input for LlamaExtract
Closed
#798 [PR #672] [MERGED] Add layout agent mode visual citation demo notebook
Closed
#799 [PR #674] [MERGED] Better connection management on llamaextract client
Closed
#800 [PR #675] [MERGED] Add compact_markdown_table parameter
Closed
#801 [PR #676] [MERGED] Support text as input directly in the SDK
Closed
#789 [PR #663] [MERGED] Bump to version 0.6.9
Closed
#790 [PR #664] [MERGED] create llamaextract demo with lm317 datasheet
Closed
#791 [PR #665] [MERGED] fix notebook
Closed
#792 [PR #666] [MERGED] chore: add base url documentation
Closed
#793 [PR #670] [MERGED] add due diligence notebook
Closed
#782 [PR #656] [MERGED] Bump to version 0.6.7
Closed
#783 [PR #655] [MERGED] Add xfail for timeout errors in report gen
Closed
#784 [PR #654] [MERGED] Add provision for custom httpx client for LlamaExtract
Closed
#785 [PR #657] [MERGED] Revert httpx_client as argument
Closed
#786 [PR #658] [MERGED] Update notebook for extract
Closed
#787 [PR #662] [CLOSED] Bump to version 0.6.8
Closed
#788 [PR #660] [MERGED] Add new parameter, fix parse_mode
Closed
#777 [PR #648] [MERGED] fix:Add retry handling to parse and backoff patterns - catching 5XX errors and HTTP errors
Closed
#778 [PR #647] [MERGED] Typos and removing staging URL
Closed
#779 [PR #650] [MERGED] new result object
Closed
#780 [PR #651] [MERGED] Update llama cloud for extract endpoints
Closed
#781 [PR #652] [MERGED] Bump up version for release
Closed
#772 [PR #636] [MERGED] Bump version to v0.6.3
Closed
#773 [PR #638] [MERGED] Add adaptive_long_table option
Closed
#774 [PR #635] [MERGED] Update README.md
Closed
#775 [PR #646] [MERGED] Add notebook for extraction from SEC 10-K/Q filings
Closed
#776 [PR #645] [MERGED] Bump to version 0.6.5 (updating llama-cloud dependency)
Closed
#767 [PR #617] [MERGED] fix publish flow
Closed
#768 [PR #622] [MERGED] add new parsing mode and prompt parameters
Closed
#769 [PR #632] [MERGED] v0.6.2
Closed
#770 [PR #616] [MERGED] add organization id and project id as args
Closed
#771 [PR #628] [MERGED] Add LlamaExtract to llama-cloud-services
Closed
#763 [PR #606] [MERGED] add gemini2 flash notebook
Closed
#764 [PR #592] [MERGED] fix release pipeline no-dev issue
Closed
#765 [PR #611] [MERGED] fixing colab links
Closed
#766 [PR #597] [MERGED] Refactor into llama-cloud-services
Closed
#757 [PR #557] [MERGED] Extract layout, audio files
Closed
#758 [PR #551] [MERGED] Fix docstring for aget_xlsx method
Closed
#759 [PR #568] [MERGED] Stoli/feat/connection handling
Closed
#760 [PR #569] [MERGED] v0.5.19
Closed
#761 [PR #582] [MERGED] add new formatting instruction parameters
Closed
#762 [PR #603] [MERGED] v0.6.0
Closed
#752 [PR #544] [MERGED] Expanding auto mode notebook with strings and regex triggers
Closed
#753 [PR #545] [MERGED] update auto-mode
Closed
#754 [PR #542] [MERGED] Add get charts function
Closed
#755 [PR #548] [MERGED] Update cache parameter
Closed
#756 [PR #550] [MERGED] Add cookbook for parsing instructions
Closed
#748 [PR #525] [MERGED] Add more parameters
Closed
#750 [PR #529] [MERGED] Add demo videos notebooks
Closed
#751 [PR #540] [MERGED] auto-mode notebook
Closed
#744 [PR #484] [MERGED] dynamic section retrieval nb
Closed
#745 [PR #506] [MERGED] add test for downloading images
Closed
#746 [PR #475] [MERGED] add input url and http_proxy
Closed
#747 [PR #531] [MERGED] JSON mode tour notebook
Closed
#749 [PR #532] [MERGED] Add support for html_remove_navigation_elements.
Closed
#737 [PR #455] [MERGED] fix RFP example
Closed
#738 [PR #460] [MERGED] Add continuous_mode
Closed
#739 [PR #457] [MERGED] Update issue templates
Closed
#740 [PR #464] [MERGED] Add PurePosixPath to list of allowed file-paths
Closed
#741 [PR #461] [MERGED] multimodal report generation image
Closed
#742 [PR #472] [MERGED] add xlsx support
Closed
#743 [PR #468] [CLOSED] Pierre/new params
Closed
#732 [PR #438] [MERGED] Add RFP Response generation workflow
Closed
#733 [PR #441] [MERGED] Add missing parameters
Closed
#734 [PR #446] [MERGED] Release is_formatting_instruction parameter
Closed
#735 [PR #454] [CLOSED] feat: Add Greek supported language
Closed
#736 [PR #448] [CLOSED] add annotate link option
Closed
#725 [PR #409] [MERGED] Compare Excel RAG with o1 models
Closed
#726 [PR #414] [MERGED] nit: move o1 excel notebook
Closed
#727 [PR #415] [MERGED] Update excel rag with o1 notebook
Closed
#728 [PR #417] [MERGED] Update README.md to convey need to specify extra_info["file_name"]
Closed
#729 [PR #416] [MERGED] fix excel notebook
Closed
#730 [PR #429] [MERGED] add multimodal RAG pipeline with contextual retrieval
Closed
#731 [PR #426] [MERGED] improve error handling for jobs
Closed
#717 [PR #378] [MERGED] Add timeout to the image request using httpx
Closed
#718 [PR #384] [MERGED] allow custom httpx client
Closed
#719 [PR #386] [MERGED] update README
Closed
#720 [PR #388] [MERGED] bump to 0.5.3
Closed
#721 [PR #394] [MERGED] do not attach a filepath when a stram of bytes is passed
Closed
#722 [PR #400] [MERGED] Remove JSON from valid result types
Closed
#723 [PR #406] [MERGED] add premium mode support
Closed
#724 [PR #402] [MERGED] fix multimodal RAG over slide deck
Closed
#712 [PR #351] [CLOSED] Resolved dependency conflicts
Closed
#714 [PR #349] [MERGED] add report generation agent
Closed
#715 [PR #363] [MERGED] CLI Testing Tool for Parsing Results to Standard Output
Closed
#716 [PR #372] [MERGED] Support take_screenshot
Closed
#706 [PR #329] [CLOSED] start one httpx per parser, async get images
Closed
#707 [PR #340] [MERGED] add report generation example
Closed
#708 [PR #342] [MERGED] small edits
Closed
#709 [PR #330] [MERGED] Adds more use case notebooks to multimodal parsing
Closed
#702 [PR #297] [MERGED] Pierre/fix page separator
Closed
#703 [PR #302] [CLOSED] check if chunk is not just whitespace
Closed
#704 [PR #316] [MERGED] add gpt-4o-mini example
Closed
#705 [PR #292] [MERGED] nit fix multimodal
Closed
#692 [PR #259] [MERGED] allow for bytes or buffer as input
Closed
#694 [PR #254] [MERGED] Modify _get_sub_docs to use Custom Separator
Closed
#695 [PR #271] [MERGED] fix file_input type issue
Closed
#696 [PR #273] [CLOSED] Handle file_path as either str or PosixPath.
Closed
#697 [PR #277] [MERGED] Make File Extension Check Case-Insensitive
Closed
#698 [PR #285] [MERGED] New parameters
Closed
#699 [PR #284] [MERGED] create multi-modal RAG notebook
Closed
#700 [PR #288] [MERGED] nit: slide deck fix
Closed
#701 [PR #289] [MERGED] [WIP] add sonnet cookbook + llamaparse fixes
Closed
#687 [PR #243] [CLOSED] Make Split to Page Default = False
Closed
#688 [PR #231] [MERGED] rewrite advanced example
Closed
#689 [PR #234] [MERGED] add baseline to dcf excel RAG
Closed
#690 [PR #250] [MERGED] add target_pages and bounding_box parameters
Closed
#691 [PR #251] [MERGED] v0.4.5
Closed
#693 [PR #258] [MERGED] llama-parse with elasticsearch vector database example notebook
Closed
#682 [PR #212] [MERGED] add split by page mode
Closed
#683 [PR #211] [MERGED] add KG agent
Closed
#684 [PR #221] [MERGED] Fix Typo in description of invalidate_cache argument of LlamaParse constructor
Closed
#685 [PR #215] [MERGED] add simple excel notebook (with dcf)
Closed
#686 [PR #216] [MERGED] Pierre/new options
Closed
#677 [PR #201] [MERGED] bump version, add image support
Closed
#678 [PR #198] [MERGED] Bump requests from 2.31.0 to 2.32.2
Closed
#679 [PR #197] [MERGED] Bump tqdm from 4.66.2 to 4.66.3
Closed
#680 [PR #204] [MERGED] Add Excel spreadsheet example with llamaparse
Closed
#681 [PR #203] [MERGED] Add spreadsheet extensions
Closed
#672 [PR #186] [MERGED] fix colab badge
Closed
#673 [PR #193] [MERGED] nit: add caltrain weekend doc
Closed
#674 [PR #192] [MERGED] clean up gpt4o notebook
Closed
#675 [PR #195] [MERGED] allow for .jpg images
Closed
#676 [PR #196] [CLOSED] Add the fast mode flag
Closed
#666 [PR #159] [MERGED] Ensure image extensions, vbump
Closed
#667 [PR #178] [MERGED] New option skip diagonal text and invalidate cache
Closed
#668 [PR #180] [MERGED] gpt4o notebook over tesla impact docs
Closed
#669 [PR #179] [MERGED] add new mode and params for openai
Closed
#670 [PR #181] [MERGED] Add example for Weaviate
Closed
#671 [PR #185] [MERGED] llamaparse example over caltrain schedule
Closed
#658 [PR #136] [MERGED] Fixing paths of data in example notebook
Closed
#660 [PR #139] [MERGED] docs: update readme with link to llamacloud
Closed
#661 [PR #140] [MERGED] QoL Changes
Closed
#662 [PR #141] [MERGED] v0.4.1
Closed
#663 [PR #142] [MERGED] Skip tests if CICD doesn't populate the secrets
Closed
#664 [PR #148] [MERGED] some notebook updates
Closed
#665 [PR #154] [MERGED] add html support
Closed
#652 [PR #107] [MERGED] Add mongodb llamaparse example
Closed
#653 [PR #109] [MERGED] nit: add colab badge to mongodb notebook
Closed
#654 [PR #98] [MERGED] fix advanced RAG notebook title
Closed
#655 [PR #110] [MERGED] Extend supported formats
Closed
#656 [PR #111] [MERGED] vbump
Closed
#657 [PR #128] [CLOSED] Logging file path when creating job
Closed
#659 [PR #117] [MERGED] Enable support for custom filesystem
Closed
#647 [PR #93] [MERGED] Init LlamaParseJsonNodeParser example
Closed
#648 [PR #89] [MERGED] nit: fix grammar in insurance cookbook
Closed
#649 [PR #91] [MERGED] Added utils files
Closed
#650 [PR #96] [CLOSED] Add Qdrant demonstration
Closed
#651 [PR #97] [MERGED] fixes to insurance demo
Closed
#642 [PR #78] [MERGED] add financial powerpoint cookbook
Closed
#643 [PR #82] [MERGED] Adding parsing instructions demo
Closed
#644 [PR #88] [MERGED] add agent demo
Closed
#645 [PR #86] [MERGED] Update demo_parsing_instructions.ipynb
Closed
#646 [PR #84] [MERGED] demo insurance + parsing instructions
Closed
#637 [PR #68] [MERGED] fix to json bug
Closed
#638 [PR #64] [MERGED] add json cookbook
Closed
#639 [PR #62] [MERGED] Pierre/json images
Closed
#640 [PR #74] [MERGED] let client support more file types
Closed
#641 [PR #75] [MERGED] add basic ppt demo
Closed
#627 [PR #23] [MERGED] add advanced rag example for astra
Closed
#628 [PR #26] [MERGED] Astra DB vector store imports from newly-named package
Closed
#629 [PR #27] [MERGED] Astra DB notebooks allow optional namespace specification
Closed
#630 [PR #24] [MERGED] Update demo_advanced.ipynb
Closed
#631 [PR #37] [MERGED] ADD: Support for language parameter in the package
Closed
#632 [PR #48] [MERGED] add language cookbook
Closed
#633 [PR #49] [MERGED] [version] bump version to 0.3.5
Closed
#634 [PR #53] [MERGED] fix(base): add file_path to exception msg
Closed
#635 [PR #55] [MERGED] add table copmarisons cookbook
Closed
#636 [PR #60] [MERGED] fix language
Closed
#625 [PR #22] [MERGED] Astra DB Example Notebook updated for 0.10.x, remove ServiceContext
Closed
#626 [PR #21] [CLOSED] fix astra example (make compatible with v10)
Closed
#619 [PR #15] [MERGED] Logan/update docs
Closed
#620 [PR #13] [MERGED] Refactor demo structure
Closed
#621 [PR #16] [MERGED] nit: fix README instructions for v0.10 compatibility
Closed
#622 [PR #20] [MERGED] QoL improvements
Closed
#623 [PR #18] [MERGED] upd demo results
Closed
#624 [PR #17] [MERGED] clean up notebook baseline method
Closed
#617 [PR #11] [CLOSED] New Llama parser Demo
Closed
#618 [PR #12] [MERGED] New Llama Parser Demo
Closed
#612 [PR #7] [MERGED] Add an example for Astra DB Integration
Closed
#613 [PR #6] [MERGED] change demo
Closed
#614 [PR #8] [MERGED] Fix readme typos
Closed
#615 [PR #10] [MERGED] Bump version
Closed
#616 [PR #9] [MERGED] Handle error from API
Closed
#610 [PR #5] [MERGED] add print statement to print job_id for easier debugging
Closed
#611 [PR #4] [MERGED] upd examples
Closed
#607 [PR #1] [CLOSED] upd demo
Closed
#608 [PR #2] [MERGED] Add pdf reader as baseline
Closed
#609 [PR #3] [MERGED] slight nits, rename to LlamaParser
Closed
#605 New dashboard usage page shows $ when referring to credits
Closed
#598 Nothing to show
Closed
#602 Broken Notion link in LlamaAgent launch blog
Closed
#596 webapp: Button to upload files to index is gone, preventing uploads
Closed
#592 Unable to delete files: 409 Conflict
Closed
#587 v2 parse api not working.
Closed
#580 LaamaParse: v2 documentation is all wrong
Closed
#557 Bounding box error with Llamaparse
Closed
#554 No screenshot/figure node retrieval in typescript
Closed
#533 ImportError: cannot import name 'ClassifyJobWithStatus' from 'llama_cloud.types'
Closed
#519 LlamaParse through TS failing with unclear error log
Closed
#507 Issue with get_tables() method - files written to wrong location
Closed
#500 Option to Force Image Conversion to Prevent White Fonting
Closed
#497 Unable to Use "PREMIUM" Extraction Mode via SDK (Only Available in UI)
Closed
#498 Prompts Not Applied via API When Parsing
Closed
#489 Can't "Contact Sales" from billing
Closed
#491 Help -> Chat with Us is broken
Closed
#494 Getting a 401 in the playground
Closed
#484 LlamaParse - .aget_json not taking in bytes
Closed
#485 [Bug]: LlamaParse.parse() not able to parse CSVs
Closed
#482 Is the cloud service down?
Closed
#483 doNotCache and invalidateCache set to true, but cached result still returned
Closed
#466 LlamaParse timing out on XLSX files. XLS versions work
Closed
#469 LlamaParse -- Import Error: cannot import name 'Secret' from 'pydantic'
Closed
#470 LlamaParse dependency issue
Closed
#461 pydantic validation error of JobResult calling LlamaParse.parser.parse()
Closed
#463 Issue with LlamaParse ...
Closed
#464 which python version are you supporting?
Closed
#455 Error while parsing the file '<bytes/buffer>': Event loop is closed
Closed
#456 Vendor API key are only supported for parse mode parse_page_with_lvm!
Closed
#457 Issue with LlamaParse ...
Closed
#451 parsemode with lvm results in parsemode with llm
Closed
#452 [Bug]:
Closed
#447 REST API documentation
Closed
#449 LlamaCloudServices doesn't support 'preserve_layout_alignment_across_pages' flag for LlamaParse
Closed
#444 Llama Parse is taking full screenshot instead of just an image from page
Closed
#446 Issue with LlamaParse ...
Closed
#431 Issue with LlamaParse content_guideline_instruction
Closed
#421 Support ".dotx" file type
Closed
#422 NO_CONTENT_HERE - LLamaParse has STOPPED working with SCANNED PDFs
Closed
#426 Python api's parameters are not applied
Closed
#429 Problems with Parsing Instruction
Closed
#412 Target pages param does not work properly
Closed
#415 load_data errors out with "The error "Error while parsing the file '<bytes/buffer>': file_name must be provided in extra_info when passing bytes"
Closed
#417 [URGENT] - Please help - Llama webhook is not being called
Closed
#408 Issue with LlamaParse ...Page 1 [error] - FONT_ERROR : Fail to identify 120 glyphs on page 1 from font : Type3
Closed
#401 python lib doesn't raise exception is incase of limit exceeded
Closed
#394 TypeError: Plain typing.TypeAlias is not valid as type argument
Closed
#396 ERROR_DURING_PROCESSING: An unknown error occurred during processing.
Closed
#398 Parsing with "auto_mode=true" scanned PDFs returns "NO_CONTENT_HERE" on every page
Closed
#385 Webhooks never get sent
Closed
#389 An unknown error occurred during processing. Job id: 80ebb07e-6996-4891-9293-a989d377bc4c
Closed
#390 struggling to understand llama parse node based parser's benefits
Closed
#391 Issue with LlamaParse ...
Closed
#393 Misuse of httpx Client creating unnecessary overhead.
Closed
#379 Put download button for json
Closed
#383 Import Issue : cannot import name 'LLM' from 'llama_index.core.llms'
Closed
#384 Premium mode is summarizing my documents instead of parsing them using API
Closed
#376 Is it possible to get source for the query response?
Closed
#377 Not go through the full file
Closed
#378 What's the default mode in the API?
Closed
#367 Add a Download Button for JSON File Output
Closed
#364 Webhook never get send when parsing xlsx files
Closed
#355 Issue with LlamaParse ...
Closed
#358 Module Not Found: Cannot Resolve '@llamaindex/readers/obsidian' in Next.js Build
Closed
#361 Error while parsing the PDF files.
Closed
#353 How to create query engine with webhook response?
Closed
#346 dynamic_section_retrieval.ipynb example not running
Closed
#348 Slower than usual.
Closed
#349 Issue with LlamaParse ...
Closed
#350 Problem with parsing PDFs with multi-level columns
Closed
#344 Unable to import Llama parse
Closed
#339 Issue with LlamaParse ...
Closed
#328 Issue with LlamaParse ...
Closed
#324 Llamaparse Interface return Forbidden on all files
Closed
#325 Issue with LlamaParse
Closed
#326 How can I use the input_url parameter?
Closed
#327 Alternative Methods for Report Generation Using LLMs Without LlamaParse or LlamaCloud?
Closed
#319 Unable to use AzureOpenAI llm model
Closed
#323 Similarity score not available (Knowledge graph)
Closed
#316 Error jobs with UNSUPPORTED_FILE_TYPE do not appear in the history
Closed
#318 UNSUPPORTED_FILE_TYPE when providing .doc Word Document
Closed
#307 Issue with LlamaParse
Closed
#308 Issue with LlamaParse ...System is Down
Closed
#311 Issue with LlamaParse ...Chinese Parsing of an English Doc
Closed
#312 Extremely slow processing and timeouts
Closed
#313 Unknow Error Occured while parsing It is coming for all the PDF - e9749617-ea3d-4946-8a63-20a83b2fbc85
Closed
#314 Issue with Llamaparse - Incompatibility with Certain Excel Documents
Closed
#315 parsing_instruction
Closed
#302 Llama Parse import Issue
Closed
#304 Failed to load the Excel document
Closed
#306 Parsing does not work with files with no extensions (but a correct MIME type)
Closed
#297 Unable to parse Excel sheets
Closed
#299 LlamaParse is working weird with prompt - multimodal
Closed
#300 When llama-parse converts table-like sections to tables, the bBox property seems to use a default value which is not useful
Closed
#303 Issue with LlamaParse: Hallucinations on Bank Statements
Closed
#290 TS SDK - Error parsing MSFT DOCX and PPTX File Types - I suspect LlamaParseReader is applying wrong MIME Type
Closed
#291 Issue with LlamaParse ...i have a pdf document that is a mix of structured, searchable pages combined with scanned pages. When parsed via llamaparse, I only receive the structured pages as output
Closed
#292 PPTX, DOCS parsing not working with Python SDK but works when I use the UI due to mime type=None
Closed
#282 Good working script processing api, now returns "markdown": "NO_CONTENT_HERE"
Closed
#284 Llamparse within SimpledirectoryReader doesn't accept PurePosixPath
Closed
#285 get_nodes_and_objects
Closed
#286 Issue with LlamaParse chokes if I try to specifically access page 0 (the cover) of a pdf
Closed
#287 premium mode code example
Closed
#288 Parsing Instructions passed not getting executed
Closed
#274 Issue with LlamaParse ...
Closed
#276 Webhook JSON is wrong
Closed
#278 LlamaParse returns incomprehensible output
Closed
#269 Error parsing HTML
Closed
#272 API does will not parse text in PDF image
Closed
#273 LlamaParse returns more pages than original document
Closed
#265 Issue with sending the Webhook
Closed
#266 Web UI Displays Time of Job in "Created At Column"
Closed
#267 page separator not working on current llama parser version on python.
Closed
#259 Llama Parse is down but the Status page doesn't reflect this
Closed
#260 Issue with LlamaParse ...no response from Llamaparse...2:49EST, 9/9/2024
Closed
#262 Not extracting full text from pdf
Closed
#263 LlamaParse not processing PDFs. Possible rate limit?
Closed
#264 LlamaParse not Processing PDFs (2024-09-09)
Closed
#255 upload api timesout when sending second request from same lambda
Closed
#256 Error while parsing the file 'filename.pdf': 'json'
Closed
#257 Version solving failed on windows
Closed
#258 LlamaParse not Processing PDFs (2024-09-05)
Closed
#245 In RAG notebook, Parse error
Closed
#238 Issue to get the parsing result when i use the API
Closed
#239 Document Too large, max page is undefined
Closed
#229 Parse .pdf that contains images what build from small pieace of images
Closed
#230 Can I remove headers and footers when parsing a PDF?
Closed
#231 How can I use LlamaParse under FastAPI? (event loop error)
Closed
#232 '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed:
Closed
#233 Documents do not finish processing or fail/time out.
Closed
#234 the extraction is not working properly
Closed
#220 Azure GPT 4o API key support?
Closed
#221 How force the latest version in my project?
Closed
#222 500 error
Closed
#223 Number Parsing PVSyst Diagrams
Closed
#224 Accessing active parsing jobs
Closed
#225 Not able to retrieve full extract of the parsed pdf
Closed
#226 Only the half of my docs are parsed correctly, the rest shows 0 pages
Closed
#228 Can't run the BASIC of Basics
Closed
#214 All error with vendor multimodal and fast_mode
Closed
#215 target_pages parameter not affecting llama_parse behavior
Closed
#216 TypeError while importing llamaparse
Closed
#212 Retrieval of completed job
Closed
#213 custom page break separator with new lines doesn't respect \n in frontend
Closed
#208 Result not found even the job status is 'SUCCESS'
Closed
#210 can not extract the images from pdf pages
Closed
#199 Cannot process same PDF file twice
Closed
#200 Request Ability to Download Historical Job Results From Web UI
Closed
#201 413 Request Entity Too Large
Closed
#202 Python couldn't get the same results as those from web UI's preview tab
Closed
#204 Cetain Excel file returns empty result in both Web UI and API
Closed
#194 Automatic Chunking of PDF with LlamaParse
Closed
#195 Bounding Box not working
Closed
#198 Use of GPT 4o mini with Llama Parse
Closed
#187 Word-Level Modifications In High Entropy Documents if GPT-4o Enabled
Closed
#189 Support for understanding tables spanning multiple pages
Closed
#190 Show parsed markdown for a file in console view
Closed
#178 job return : Result not found. Check job status to see if it has completed.
Closed
#180 Unable to parse scanned image pdf
Closed
#182 Error while parsing the file
Closed
#184 Tracing using Langfuse
Closed
#185 Error while parsing the file 'file_path': 'markdown'
Closed
#173 The target_page parameter does not work correctly
Closed
#166 respect pageSeperator in LlamaParseReader
Closed
#168 Error while parsing the file
Closed
#169 Unable to parse any pdf
Closed
#158 Feature Request: result_type='markdown' return page number
Closed
#159 Allow Claude as precise mode (similar to GPT-4o)
Closed
#160 [Question] LlamaParse as open source
Closed
#161 FastMode not available via API
Closed
#148 I want to use fast mode, when will it be released?
Closed
#150 It's not extracting images from a textbook excerpt I uploaded / tried with python SDK
Closed
#155 Same code working fine, but when rerunning now I got the following error
Closed
#144 Issue with PDF page boundaries
Closed
#145 Getting Error while Using FlagEmbeddingReranker i.e AttributeError: 'Dispatcher' object has no attribute 'get_dispatch_event'
Closed
#147 CERTIFICATE ERROR
Closed
#137 Job not found
Closed
#138 Page seperator
Closed
#139 time out
Closed
#140 Very slow responses and timeouts
Closed
#141 Bug
Closed
#127 [Errno -2] Name or service not known
Closed
#129 Assistance with Parsed Document Content
Closed
#130 Usage count is wrong (GPT4-o)
Closed
#131 Use ChatGPT 4o from API call?
Closed
#121 Add Support for XML, CSV, and XLSX File Types
Closed
#123 Where can I find my cached documents?
Closed
#125 XLSX parsing not working
Closed
#112 i love Llama_parse
Closed
#113 V1
Closed
#111 Server disconnected without sending a response
Closed
#103 table
Closed
#104 New feature request
Closed
#107 EU-based Data Hosting
Closed
#109 Private cloud and on-prem hosting
Closed
#99 AssertionError when attempting to query nodes parsed via llama-parse
Closed
#100 Getting 404/405 when using curl
Closed
#101 Typo in LlamaParse Documentation
Closed
#91 I want to save the result md files to my disk
Closed
#95 Images from PDF do not download properly.
Closed
#96 File extension throws parsing error - not issue
Closed
#88 Parsing table with empty columns not optimal. result_type='text' produces better table formatting.
Closed
#89 LLamaParse has STOPPED working with SCANNED PDFs
Closed
#90 Sample PDF link does not work
Closed
#81 SSLCertVerificationError when using LlamaParse
Closed
#82 'ascii' codec can't encode character '\u201c' in position 7: ordinal not in range(128)
Closed
#83 404 Not Found Error
Closed
#85 CORS issue when trying to upgrade llamaparse plan
Closed
#87 Return Error parsing PDF
Closed
#74 File extension case sensitive throws parsing error
Closed
#75 Is the service down?
Closed
#78 Is there a way to ingest an URL of a PDF (supposedly from a cloud storage), rather than taking the document from directory ?
Closed
#67 LlamaParse demo notebook issue when using node parser
Closed
#68 LLama_Parse Returns a bunch of Undefined for my PDF
Closed
#69 Llama parse returning undefined for basic PDF
Closed
#70 Unresponsive API call
Closed
#72 [BUG] 413 Request Entity Too Large
Closed
#64 New FS not supported by llama-parse
Closed
#58 Integration of llama_parse in nodejs
Closed
#60 Timed Out Session/ Not getting result.
Closed
#61 'th' changing to 'p'
Closed
#62 Integration of LlamaParse as the default PDF loader in AzStorageBlobReader
Closed
#63 llama-parse install not working due to version compatibility issue w/ llama-index
Closed
#51 No result (NO_CONTENT_HERE)
Closed
#53 Missing table column after parsing
Closed
#54 Inconsistent table parsing behavior
Closed
#56 Table parsing issue with multiple tables in close proximity
Closed
#46 Tables Not Parsing Properly
Closed
#47 Where is the md file stored?
Closed
#48 FlagEmbeddingReranker OSError
Closed
#49 Textract result in blog post
Closed
#40 Not Support to .doc extension
Closed
#41 llama_parse import error
Closed
#42 ImportError: circular import?
Closed
#37 Error while parsing the PDF file: Job failed: PDF_TOO_LARGE
Closed
#39 Invalid authentication token. Even with newly generated cloud API key.
Closed
#31 Missing values from table
Closed
#32 ValueError: Could not extract json string from output
Closed
#33 AttributeError: 'dict' object has no attribute 'json'
Closed
#34 AttributeError: 'dict' object has no attribute 'json'
Closed
#36 Error while parsing the PDF file <file_name>: 'dict' object has no attribute 'json'
Closed
#28 Error while parsing the PDF file: Failed to parse the PDF file
Closed
#29 Plan to Opensource llama_parse
Closed
#30 Error while parsing the PDF file:
Closed
#22 Failed to parse the PDF file: Job failed: PDF_IS_PROTECTED
Closed
#23 tests
Closed
#24 Information for source file name ...
Closed
#25 Could not extract json string from output error
Closed
#26 Page numbers returned in response
Closed
#27 Figure parsing issue
Closed
#16 markdown table needs <br> rather than newline
Closed
#18 would be nice to remove header\footer from pdf
Closed
#19 Error parsing markdown (Parse -> Try demo)
Closed
#20 UI: "This is an early preview..." banner overflows horizontally on the trailing edge of the window
Closed
#7 Multilingual support?
Closed
#8 Data in Columns in the Markdown is not correct.
Closed
#10 Extracting tables and text information separately using parser
Closed
#13 Return positional information
Closed
#14 some information incorrectly presented as tables
Closed
#15 Issue with Parsing and No Error/Timeout
Closed
#4 Error while parsing the PDF file: Failed to parse the PDF file: Internal Server Error
Closed
#6 AttributeError on colab notebook?
Closed
#1 PDF too large error
Closed
#2 Metrics
1086 Issues created by 1 user
Opened
#1 PDF too large error
Opened
#2 Metrics
Opened
#3 A chunk of text is missing in the output
Opened
#4 Error while parsing the PDF file: Failed to parse the PDF file: Internal Server Error
Opened
#5 Accept S3 type bucket links of PDFs?
Opened
#6 AttributeError on colab notebook?
Opened
#7 Multilingual support?
Opened
#8 Data in Columns in the Markdown is not correct.
Opened
#9 Auto Rotation of Pages with horizontal content
Opened
#10 Extracting tables and text information separately using parser
Opened
#11 Issue in getting data from tables spanning across pages with footer text
Opened
#12 Column parsing errors
Opened
#13 Return positional information
Opened
#14 some information incorrectly presented as tables
Opened
#15 Issue with Parsing and No Error/Timeout
Opened
#16 markdown table needs <br> rather than newline
Opened
#17 bad ocr
Opened
#18 would be nice to remove header\footer from pdf
Opened
#19 Error parsing markdown (Parse -> Try demo)
Opened
#20 UI: "This is an early preview..." banner overflows horizontally on the trailing edge of the window
Opened
#21 Reading order is messed up
Opened
#22 Failed to parse the PDF file: Job failed: PDF_IS_PROTECTED
Opened
#23 tests
Opened
#24 Information for source file name ...
Opened
#25 Could not extract json string from output error
Opened
#26 Page numbers returned in response
Opened
#27 Figure parsing issue
Opened
#28 Error while parsing the PDF file: Failed to parse the PDF file
Opened
#29 Plan to Opensource llama_parse
Opened
#30 Error while parsing the PDF file:
Opened
#31 Missing values from table
Opened
#32 ValueError: Could not extract json string from output
Opened
#33 AttributeError: 'dict' object has no attribute 'json'
Opened
#34 AttributeError: 'dict' object has no attribute 'json'
Opened
#35 binding parameter 0
Opened
#36 Error while parsing the PDF file <file_name>: 'dict' object has no attribute 'json'
Opened
#37 Error while parsing the PDF file: Job failed: PDF_TOO_LARGE
Opened
#38 Not getting result
Opened
#39 Invalid authentication token. Even with newly generated cloud API key.
Opened
#40 Not Support to .doc extension
Opened
#41 llama_parse import error
Opened
#42 ImportError: circular import?
Opened
#43 Wait long time but no result return
Opened
#44 Formulas are not parsed correctly
Opened
#45 Type Annotation Issue in get_images Method inside llama_parse -> base.py
Opened
#46 Tables Not Parsing Properly
Opened
#47 Where is the md file stored?
Opened
#48 FlagEmbeddingReranker OSError
Opened
#49 Textract result in blog post
Opened
#50 SSLCertVerificationError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: self signed certificate (_ssl.c:1129)
Opened
#51 No result (NO_CONTENT_HERE)
Opened
#52 Parser does not recognise superscript or subscript characters
Opened
#53 Missing table column after parsing
Opened
#54 Inconsistent table parsing behavior
Opened
#55 Parsing 2 page PDF file taking a long time.
Opened
#56 Table parsing issue with multiple tables in close proximity
Opened
#57 Multilanguage support in the same document
Opened
#58 Integration of llama_parse in nodejs
Opened
#59 Academic Papers
Opened
#60 Timed Out Session/ Not getting result.
Opened
#61 'th' changing to 'p'
Opened
#62 Integration of LlamaParse as the default PDF loader in AzStorageBlobReader
Opened
#63 llama-parse install not working due to version compatibility issue w/ llama-index
Opened
#64 New FS not supported by llama-parse
Opened
#65 Stacked table headers seen as separate headers
Opened
#66 Missing text when parsing
Opened
#67 LlamaParse demo notebook issue when using node parser
Opened
#68 LLama_Parse Returns a bunch of Undefined for my PDF
Opened
#69 Llama parse returning undefined for basic PDF
Opened
#70 Unresponsive API call
Opened
#71 Example of bad parsing of pdf tables with misleading results
Opened
#72 [BUG] 413 Request Entity Too Large
Opened
#73 Usage of ref_doc_id of Node parsed
Opened
#74 File extension case sensitive throws parsing error
Opened
#75 Is the service down?
Opened
#76 [Table Parsing Issue] Multiline content in single cell but detected as multiple rows instead
Opened
#77 RateLimitError - OPENAI while using get_nodes_from_documents
Opened
#78 Is there a way to ingest an URL of a PDF (supposedly from a cloud storage), rather than taking the document from directory ?
Opened
#79 Reading a scanned image in pdf , returning "NO_CONTENT_HERE"
Opened
#80 Poor Parse From Basic Form
Opened
#81 SSLCertVerificationError when using LlamaParse
Opened
#82 'ascii' codec can't encode character '\u201c' in position 7: ordinal not in range(128)
Opened
#83 404 Not Found Error
Opened
#84 llama_parse freezed when parsing word files (doc & docx)
Opened
#85 CORS issue when trying to upgrade llamaparse plan
Opened
#86 LlamaParse messes up ordering of two-column PDFs
Opened
#87 Return Error parsing PDF
Opened
#88 Parsing table with empty columns not optimal. result_type='text' produces better table formatting.
Opened
#89 LLamaParse has STOPPED working with SCANNED PDFs
Opened
#90 Sample PDF link does not work
Opened
#91 I want to save the result md files to my disk
Opened
#92 unable to extract tablular data thats within an image
Opened
#93 Tables with nested columns (almost right)
Opened
#94 RuntimeError: Event loop is closed
Opened
#95 Images from PDF do not download properly.
Opened
#96 File extension throws parsing error - not issue
Opened
#97 Silent Failure from API
Opened
#98 PDF only partially parsed
Opened
#99 AssertionError when attempting to query nodes parsed via llama-parse
Opened
#100 Getting 404/405 when using curl
Opened
#101 Typo in LlamaParse Documentation
Opened
#102 Struture not correctly detected with this pdf
Opened
#103 table
Opened
#104 New feature request
Opened
#105 markdown output for table in pdf is incorrect
Opened
#106 Issue with handling tables in a 2-column pdf
Opened
#107 EU-based Data Hosting
Opened
#108 Not able to extract data from Table data
Opened
#109 Private cloud and on-prem hosting
Opened
#110 Server error time out
Opened
#111 Server disconnected without sending a response
Opened
#112 i love Llama_parse
Opened
#113 V1
Opened
#114 Server issues
Opened
#115 Incompatability of nest_asyncio and uvloop
Opened
#116 Does Llama Parse skip reprocessing already parsed documents? T
Opened
#117 not working for this pdf
Opened
#118 Parsing process debugging options
Opened
#119 No mention of privacy
Opened
#120 Images
Opened
#121 Add Support for XML, CSV, and XLSX File Types
Opened
#122 My API Key suddenly disappeared from my dashboard
Opened
#123 Where can I find my cached documents?
Opened
#124 Mistakes parsing data from table using LlamaParse and gpt4o
Opened
#125 XLSX parsing not working
Opened
#126 Example demo_advanced.ipynb fails
Opened
#127 [Errno -2] Name or service not known
Opened
#128 API key Revocation
Opened
#129 Assistance with Parsed Document Content
Opened
#130 Usage count is wrong (GPT4-o)
Opened
#131 Use ChatGPT 4o from API call?
Opened
#132 In the processing of grey text with white background of the PDF will appear a large number of recognition errors in the messy code.
Opened
#133 LlamaParse ReadTimeOut error
Opened
#134 No metadata for async aload_data runs
Opened
#135 Icelandic - is_ on platform but is in LlamaParse?
Opened
#136 ImportError: cannot import name 'DocxReader' from 'llama_index.readers.file' (unknown location)
Opened
#137 Job not found
Opened
#138 Page seperator
Opened
#139 time out
Opened
#140 Very slow responses and timeouts
Opened
#141 Bug
Opened
#142 APIConnectionError
Opened
#143 Parsing complex pdfs and outcomes
Opened
#144 Issue with PDF page boundaries
Opened
#145 Getting Error while Using FlagEmbeddingReranker i.e AttributeError: 'Dispatcher' object has no attribute 'get_dispatch_event'
Opened
#146 Unable to parse big single page pdf to md
Opened
#147 CERTIFICATE ERROR
Opened
#148 I want to use fast mode, when will it be released?
Opened
#149 GPT-4o Enablement Can Result in Hyperlink Hallucinations
Opened
#150 It's not extracting images from a textbook excerpt I uploaded / tried with python SDK
Opened
#151 Problem with tables next to each other
Opened
#152 md either misses text/words or formats wrong at times
Opened
#153 Typescript examples
Opened
#154 Complex Pages Sometimes Lost When GPT-4o Enabled
Opened
#155 Same code working fine, but when rerunning now I got the following error
Opened
#156 Feature Request: Multi-lingual support for code usage
Opened
#157 Trying advanced llamaparse + weaviate store example, script hangs on importing FlagEmbeddingReranker
Opened
#158 Feature Request: result_type='markdown' return page number
Opened
#159 Allow Claude as precise mode (similar to GPT-4o)
Opened
#160 [Question] LlamaParse as open source
Opened
#161 FastMode not available via API
Opened
#162 Error when creating a project
Opened
#163 How to exclude strikethrough text?
Opened
#164 RTL issue
Opened
#165 Llamaparse-Results-to-csv
Opened
#166 respect pageSeperator in LlamaParseReader
Opened
#167 Error parsing books in other language even if the language parameter is set in LlamaParse
Opened
#168 Error while parsing the file
Opened
#169 Unable to parse any pdf
Opened
#170 not able to parse PDF properly
Opened
#171 Unable to run with GPT40
Opened
#172 Unable to parse PDF from directory
Opened
#173 The target_page parameter does not work correctly
Opened
#174 Differences in text and markdown output for pdf. Markdown is missing some text on page boundaries
Opened
#175 Failed to interpret bar charts correctly
Opened
#176 [Bug]: LlamaParse - Inconsistent number of documents being produced after parsing with gpt-4o enabled
Opened
#177 Parse images and drawing in Excel documents.
Opened
#178 job return : Result not found. Check job status to see if it has completed.
Opened
#179 LlamaParse marks plain text as header if the text is at the beginning of the page
Opened
#180 Unable to parse scanned image pdf
Opened
#181 ValueError: Could not extract json string from output (with correct output)
Opened
#182 Error while parsing the file
Opened
#183 return raw table/image information
Opened
#184 Tracing using Langfuse
Opened
#185 Error while parsing the file 'file_path': 'markdown'
Opened
#186 Better header footer representation
Opened
#187 Word-Level Modifications In High Entropy Documents if GPT-4o Enabled
Opened
#188 gpt4o_mode=True parse output is showing unrelated context
Opened
#189 Support for understanding tables spanning multiple pages
Opened
#190 Show parsed markdown for a file in console view
Opened
#191 Text converted to curves ignored completely in the output
Opened
#192 unable to read vertical orientated chinese traditional words
Opened
#193 Columnar Text Shuffled in OCR Mode
Opened
#194 Automatic Chunking of PDF with LlamaParse
Opened
#195 Bounding Box not working
Opened
#196 Missing pages in PDF extraction
Opened
#197 LlamaParse OCR poorly on numbers, auto calculates instead of doing OCR, inconsistent parsing results between UI and Python (gpt-4o enabled)
Opened
#198 Use of GPT 4o mini with Llama Parse
Opened
#199 Cannot process same PDF file twice
Opened
#200 Request Ability to Download Historical Job Results From Web UI
Opened
#201 413 Request Entity Too Large
Opened
#202 Python couldn't get the same results as those from web UI's preview tab
Opened
#203 Allow bounding_boxes and/or dpi settings for multimodal parsing with large pdf page
Opened
#204 Cetain Excel file returns empty result in both Web UI and API
Opened
#205 Python API does not allow setting multiple languages but doc says one can.
Opened
#206 Error Parsing Normal PDF File
Opened
#207 async def aget_json does not work with bytes
Opened
#208 Result not found even the job status is 'SUCCESS'
Opened
#209 Add Documentation for JSON Results
Opened
#210 can not extract the images from pdf pages
Opened
#211 parsing glossary across pages in pdf breaks up definition
Opened
#212 Retrieval of completed job
Opened
#213 custom page break separator with new lines doesn't respect \n in frontend
Opened
#214 All error with vendor multimodal and fast_mode
Opened
#215 target_pages parameter not affecting llama_parse behavior
Opened
#216 TypeError while importing llamaparse
Opened
#217 Poor performance on scanned PDFs with improperly rotated content
Opened
#218 Section of pdf document not parsed via API
Opened
#219 dont know how to visualise/view chunking of pdf
Opened
#220 Azure GPT 4o API key support?
Opened
#221 How force the latest version in my project?
Opened
#222 500 error
Opened
#223 Number Parsing PVSyst Diagrams
Opened
#224 Accessing active parsing jobs
Opened
#225 Not able to retrieve full extract of the parsed pdf
Opened
#226 Only the half of my docs are parsed correctly, the rest shows 0 pages
Opened
#227 Unable to parse application forms having square boxes to fill in letters
Opened
#228 Can't run the BASIC of Basics
Opened
#229 Parse .pdf that contains images what build from small pieace of images
Opened
#230 Can I remove headers and footers when parsing a PDF?
Opened
#231 How can I use LlamaParse under FastAPI? (event loop error)
Opened
#232 '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed:
Opened
#233 Documents do not finish processing or fail/time out.
Opened
#234 the extraction is not working properly
Opened
#235 Llamaparse sometimes translates non-English text to English in Markdown output
Opened
#236 include "notes" from powerpoint when parsing
Opened
#237 bad parsing results
Opened
#238 Issue to get the parsing result when i use the API
Opened
#239 Document Too large, max page is undefined
Opened
#240 Issues with Extracted Text Output Using Llama Parse : Incorrect OCR Results
Opened
#241 NameError with llama Parse
Opened
#242 Error with import LlamaParse
Opened
#243 Tables parsed contains many empty rows and very long parsing time
Opened
#244 Getting user doesnt have access to create a project in LLamacloud
Opened
#245 In RAG notebook, Parse error
Opened
#246 OCR perform badly in Chinese content
Opened
#247 Issue with LlamaParse : bBox hight is not correct
Opened
#248 Gemini Flash 1.5 in multimodal vendor
Opened
#249 Llama parse basic demo fails on run on Colab Enterprise
Opened
#250 Extracted sub-images as different file instead of single image it supposed to be
Opened
#251 use_vendor_multimodal_model
Opened
#252 Issue with LlamaParse ...
Opened
#253 Q&A questions for a PDF document with images.
Opened
#254 LlamaParse feature take_screenshot does not work with AzStorageBlobReader
Opened
#255 upload api timesout when sending second request from same lambda
Opened
#256 Error while parsing the file 'filename.pdf': 'json'
Opened
#257 Version solving failed on windows
Opened
#258 LlamaParse not Processing PDFs (2024-09-05)
Opened
#259 Llama Parse is down but the Status page doesn't reflect this
Opened
#260 Issue with LlamaParse ...no response from Llamaparse...2:49EST, 9/9/2024
Opened
#261 Request Field for Logging User-Specified Job-Level metadata
Opened
#262 Not extracting full text from pdf
Opened
#263 LlamaParse not processing PDFs. Possible rate limit?
Opened
#264 LlamaParse not Processing PDFs (2024-09-09)
Opened
#265 Issue with sending the Webhook
Opened
#266 Web UI Displays Time of Job in "Created At Column"
Opened
#267 page separator not working on current llama parser version on python.
Opened
#268 LLAMA_PARSE PERFORM BADLY IN THAI LANGUAGE!? or it's my mistake?
Opened
#269 Error parsing HTML
Opened
#270 Disable text warping in output text
Opened
#271 Issue with Parsing Field Inputs in Fillable PDF Forms Using Llama Parse
Opened
#272 API does will not parse text in PDF image
Opened
#273 LlamaParse returns more pages than original document
Opened
#274 Issue with LlamaParse ...
Opened
#275 Link images in markdown
Opened
#276 Webhook JSON is wrong
Opened
#277 Something went wrong when reconstruction page X
Opened
#278 LlamaParse returns incomprehensible output
Opened
#279 parameter vendor_multimodal_api_base for inital LlamaParse
Opened
#280 401: Invalid API Key when requesting job results
Opened
#281 The reader self creates data out of thin air?
Opened
#282 Good working script processing api, now returns "markdown": "NO_CONTENT_HERE"
Opened
#283 Markdownelement node parser
Opened
#284 Llamparse within SimpledirectoryReader doesn't accept PurePosixPath
Opened
#285 get_nodes_and_objects
Opened
#286 Issue with LlamaParse chokes if I try to specifically access page 0 (the cover) of a pdf
Opened
#287 premium mode code example
Opened
#288 Parsing Instructions passed not getting executed
Opened
#289 Issue with LlamaParse ... The json result file does not identiy heading levels, returning always 1. Tried with PDF and HTML
Opened
#290 TS SDK - Error parsing MSFT DOCX and PPTX File Types - I suspect LlamaParseReader is applying wrong MIME Type
Opened
#291 Issue with LlamaParse ...i have a pdf document that is a mix of structured, searchable pages combined with scanned pages. When parsed via llamaparse, I only receive the structured pages as output
Opened
#292 PPTX, DOCS parsing not working with Python SDK but works when I use the UI due to mime type=None
Opened
#293 The result of the RAG example based on LlamaPaser and MongoDB is “Empty Response”
Opened
#294 Issue with LlamaParse ...
Opened
#295 Webhooks don't return data for CSVs
Opened
#296 Issue with LlamaParse ...
Opened
#297 Unable to parse Excel sheets
Opened
#298 Issue with LlamaParse ...
Opened
#299 LlamaParse is working weird with prompt - multimodal
Opened
#300 When llama-parse converts table-like sections to tables, the bBox property seems to use a default value which is not useful
Opened
#301 Output RLF template missing
Opened
#302 Llama Parse import Issue
Opened
#303 Issue with LlamaParse: Hallucinations on Bank Statements
Opened
#304 Failed to load the Excel document
Opened
#305 Greek (EL) OCR support
Opened
#306 Parsing does not work with files with no extensions (but a correct MIME type)
Opened
#307 Issue with LlamaParse
Opened
#308 Issue with LlamaParse ...System is Down
Opened
#309 Annotation layer of PDF not being included in parsed output
Opened
#310 Issue with LlamaParse ... An unknown error occurred during processing. Job id: e7207b3d-aff5-48f5-8dbc-eaa69c8b1c87
Opened
#311 Issue with LlamaParse ...Chinese Parsing of an English Doc
Opened
#312 Extremely slow processing and timeouts
Opened
#313 Unknow Error Occured while parsing It is coming for all the PDF - e9749617-ea3d-4946-8a63-20a83b2fbc85
Opened
#314 Issue with Llamaparse - Incompatibility with Certain Excel Documents
Opened
#315 parsing_instruction
Opened
#316 Error jobs with UNSUPPORTED_FILE_TYPE do not appear in the history
Opened
#317 LLamaparse can not parse content of scanned pages, if scanned page orientation changes and when there are two pages scanned in one page
Opened
#318 UNSUPPORTED_FILE_TYPE when providing .doc Word Document
Opened
#319 Unable to use AzureOpenAI llm model
Opened
#320 Incorrect tabular data extraction for handwritten docs when submitted as PDF while correctly extracting accurate data when submitted as an image.
Opened
#321 "continuing this pattern" in output, instead of full data
Opened
#322 Process Time Inconsistent
Opened
#323 Similarity score not available (Knowledge graph)
Opened
#324 Llamaparse Interface return Forbidden on all files
Opened
#325 Issue with LlamaParse
Opened
#326 How can I use the input_url parameter?
Opened
#327 Alternative Methods for Report Generation Using LLMs Without LlamaParse or LlamaCloud?
Opened
#328 Issue with LlamaParse ...
Opened
#329 Issue with LlamaParse ...
Opened
#330 Issue with LlamaParse ...
Opened
#331 Excel: Multiline text in a cell breaks the output table
Opened
#332 Issue with LlamaParse ...Endless Loading During Parsing
Opened
#333 Couldn't use Azure OpenAI deployed model for Llama Parse
Opened
#334 lvl does not always start at 1
Opened
#335 OCR_ERROR : OCR failed on image / Details: socket hang up (hosted version)
Opened
#336 Please add the option to include extra info in async batch processing
Opened
#337 Error while parsing the file '<bytes/buffer>'
Opened
#338 Issue with LlamaParse "Parse" tool from the dashboard
Opened
#339 Issue with LlamaParse ...
Opened
#340 Issue with llama parse
Opened
#341 Issue with LlamaParse ...
Opened
#342 Issue with LlamaParse ...
Opened
#343 Error while downloading images from parsed result
Opened
#344 Unable to import Llama parse
Opened
#345 Quality of Screenshots
Opened
#346 dynamic_section_retrieval.ipynb example not running
Opened
#347 Additional metadata for parsed pages like page_separator
Opened
#348 Slower than usual.
Opened
#349 Issue with LlamaParse ...
Opened
#350 Problem with parsing PDFs with multi-level columns
Opened
#351 Images in uploaded pdfs are not recognized
Opened
#352 How to send a llama_parse job in python async?
Opened
#353 How to create query engine with webhook response?
Opened
#354 Parsing Stopped on PENDING state
Opened
#355 Issue with LlamaParse ...
Opened
#356 Multimodal Report Generation
Opened
#357 advanced dynamic section retrieval for mistral
Opened
#358 Module Not Found: Cannot Resolve '@llamaindex/readers/obsidian' in Next.js Build
Opened
#359 Llama parse OCR question
Opened
#360 Hebrew Language Support
Opened
#361 Error while parsing the PDF files.
Opened
#362 can't get data in form of json
Opened
#363 How to construct a table of contents of a book?
Opened
#364 Webhook never get send when parsing xlsx files
Opened
#365 Issue with LlamaParse ... Image/PDF parsing was not right - OCR issues
Opened
#366 LLamaparse could not extract figures from one pdf file despite good pdf quality (edge-case)
Opened
#367 Add a Download Button for JSON File Output
Opened
#368 "I'm sorry, but I can't assist with that." markdown response when using is_formatting_instructions=True for PDFs
Opened
#369 Issue with LlamaParse ...how can I pars all the pages of the file at once ?
Opened
#370 The page separator parameter is not working in the llamaparse api
Opened
#371 Webhook not being triggered
Opened
#372 REST API - Upload File error via C#
Opened
#373 There are frequent cases where one cannot distinguish between '6' and '8'.
Opened
#374 Unable To create Project and Organization in LLama Cloud
Opened
#375 Support bytes and BytesIO like object for the aget_json methods
Opened
#376 Is it possible to get source for the query response?
Opened
#377 Not go through the full file
Opened
#378 What's the default mode in the API?
Opened
#379 Put download button for json
Opened
#380 Ability to set chunk size for pdf-to-markdown conversion
Opened
#381 Parsing error on API but not frontend
Opened
#382 llama parse summarize the information of a paragraph in the pdf file
Opened
#383 Import Issue : cannot import name 'LLM' from 'llama_index.core.llms'
Opened
#384 Premium mode is summarizing my documents instead of parsing them using API
Opened
#385 Webhooks never get sent
Opened
#386 New Error: Error message: Something went wrong while extracting the markdown.
Opened
#387 Issue with LlamaParse ...
Opened
#388 HTML Support for parsing.
Opened
#389 An unknown error occurred during processing. Job id: 80ebb07e-6996-4891-9293-a989d377bc4c
Opened
#390 struggling to understand llama parse node based parser's benefits
Opened
#391 Issue with LlamaParse ...
Opened
#392 LLamaparse is missing chunks of text when parsing PDF / How Do You Ensure Your Parser Fully Parses a Document Without Missing Content (Text/Tables/Information)?
Opened
#393 Misuse of httpx Client creating unnecessary overhead.
Opened
#394 TypeError: Plain typing.TypeAlias is not valid as type argument
Opened
#395 use_vendor_multimodal_model=True is returning "NO_CONTENT"
Opened
#396 ERROR_DURING_PROCESSING: An unknown error occurred during processing.
Opened
#397 Retrieving job_id from the job
Opened
#398 Parsing with "auto_mode=true" scanned PDFs returns "NO_CONTENT_HERE" on every page
Opened
#399 Some jobs report UNSUPPORTED_FILE_TYPE Exception but by Status is Good According to API
Opened
#400 Issue with creating projects in my LlamaParse organization
Opened
#401 python lib doesn't raise exception is incase of limit exceeded
Opened
#402 Getting an error: "An unknown error occurred during processing." when using input_url from firebase storage
Opened
#403 Issue with LlamaParse ... api xlsx endpoint it does not decode and when i download it, i find a error file
Opened
#404 in json mode using vendor_multimodal_model is not working
Opened
#405 Issue with LlamaParse : Error 500 with AWS S3 Presigned URL
Opened
#406 Issue with LlamaParse ...The API is suddently extremely slow in terms of responding to documents. Initially, my website used to get a response in seconds. Anyone felt the same? Thanks
Opened
#407 LlamaParse closes connection unexpectedly
Opened
#408 Issue with LlamaParse ...Page 1 [error] - FONT_ERROR : Fail to identify 120 glyphs on page 1 from font : Type3
Opened
#409 get_json_result when used to parse a pdf file, always returns markdown headers at level 1. Does not return header hierarchy. Please refer to the attached pdf and md files
Opened
#410 Llama Parse Slowness and Variation in Output Using Parsing instruction
Opened
#411 Font Parsing Error in Llama Parse API Causing Garbled Output
Opened
#412 Target pages param does not work properly
Opened
#413 Some PDFs Fail with "Unsupported Type" Error & Successfully Parsed PDFs Not Loading
Opened
#414 Issue with LlamaParse Vendor Model Gemini 1.5 Pro
Opened
#415 load_data errors out with "The error "Error while parsing the file '<bytes/buffer>': file_name must be provided in extra_info when passing bytes"
Opened
#416 Issue with LlamaParse - no feedback when pressing [Parse]
Opened
#417 [URGENT] - Please help - Llama webhook is not being called
Opened
#418 Job stuck at "in progress"
Opened
#419 Issue with LlamaParse ... Yesterday, I launched a job in premium mode with a simple PDF containing an image, and today it is still in progress.
Opened
#420 REST API Fetch Request not working - CORS issue even with Authorization Bearer API Key
Opened
#421 Support ".dotx" file type
Opened
#422 NO_CONTENT_HERE - LLamaParse has STOPPED working with SCANNED PDFs
Opened
#423 Issue with LlamaParse ...- Jobs disappear
Opened
#424 Job Records from parsing/history missing Job Durations
Opened
#425 when pdf's sent in batch in non json mode, getting wrong responses
Opened
#426 Python api's parameters are not applied
Opened
#427 Questions about handwritings in document
Opened
#428 3rd Party multi-modal model gemini-2.0-flash-001 responds with MANY '-' and whitespaces in tables causing >1000 chunks for 1 page
Opened
#429 Problems with Parsing Instruction
Opened
#430 Missing text using Type 1 (CID) font in markdown result
Opened
#431 Issue with LlamaParse content_guideline_instruction
Opened
#432 Issue with LlamaParse ...
Opened
#433 Unexpected LlamaParse Behavior in v0.6.1 – Extracting Raw OCR Instead of Analyzing Page Content
Opened
#434 PDF -> JSON parsing issue with LlamaParse
Opened
#435 Job still in progress after more than 48 hours
Opened
#436 Too Many Request Issue - System is Not Processing multiple Request
Opened
#437 Issue with LlamaParse ...
Opened
#438 Llama Parse accuracy issue on scanned PDF with rotated pages
Opened
#439 Issue with LlamaParse ...
Opened
#440 parsing a table from a pdf file into a markdown format is no longer showing table column header bounaries
Opened
#441 output_tables_as_HTML option not working for xlsx file
Opened
#442 Parsing performance degraded
Opened
#443 Degraded Performance
Opened
#444 Llama Parse is taking full screenshot instead of just an image from page
Opened
#445 Webhook improvements
Opened
#446 Issue with LlamaParse ...
Opened
#447 REST API documentation
Opened
#448 job with a given ID returns SUCCESS in my job history but at the same time the Python API call fails
Opened
#449 LlamaCloudServices doesn't support 'preserve_layout_alignment_across_pages' flag for LlamaParse
Opened
#450 Default parser is not "Accurate" anymore. JSON instructions update.
Opened
#451 parsemode with lvm results in parsemode with llm
Opened
#452 [Bug]:
Opened
#453 Missing Data When Parsing in Auto Mode
Opened
#454 Text-To-SQL Report
Opened
#455 Error while parsing the file '<bytes/buffer>': Event loop is closed
Opened
#456 Vendor API key are only supported for parse mode parse_page_with_lvm!
Opened
#457 Issue with LlamaParse ...
Opened
#458 Issue with LlamaParse ...
Opened
#459 getting the error job took more than 30 minutes or Something went wrong while extracting the markdown.
Opened
#460 Bach processing fails and aborts the whole job
Opened
#461 pydantic validation error of JobResult calling LlamaParse.parser.parse()
Opened
#462 When parsing a PDF with markdown, some parts of text are getting lost.
Opened
#463 Issue with LlamaParse ...
Opened
#464 which python version are you supporting?
Opened
#465 PDF file parse failure
Opened
#466 LlamaParse timing out on XLSX files. XLS versions work
Opened
#467 Issue with get_file_page_screenshot() in Python library
Opened
#468 Apple Pages parsing not working
Opened
#469 LlamaParse -- Import Error: cannot import name 'Secret' from 'pydantic'
Opened
#470 LlamaParse dependency issue
Opened
#471 [BUG] page_separator {pageNumber} placeholder not replaced in python
Opened
#472 Academic papers (two-column format) not parsed correctly.
Opened
#473 Support Finnish language
Opened
#474 Parsing is not extracting data that was filled in a PDF form.
Opened
#475 Pydantic JobResult Validation Error for Audio Files with result_type="text" Due to Missing pages/job_metadata
Opened
#476 Issue with LlamaParse - Something went wrong while extracting the markdown.
Opened
#477 Agent functions never complete when using the python SDK inside Google Cloud functions.
Opened
#478 llama_cloud_services Support for Custom Embedding Endpoints？
Opened
#479 Parse Document with Agent - cross-page tables not merged
Opened
#480 .tif File Extension Not Recognized as Valid TIFF – Returns "Unsupported file type" Error
Opened
#481 LlamaParse parsing letter "a" as Infinity symbol
Opened
#482 Is the cloud service down?
Opened
#483 doNotCache and invalidateCache set to true, but cached result still returned
Opened
#484 LlamaParse - .aget_json not taking in bytes
Opened
#485 [Bug]: LlamaParse.parse() not able to parse CSVs
Opened
#486 Custom Metadata Update Triggers File Parse Failure in LlamaCloud UI
Opened
#487 Tables in markdowns are getting skewed
Opened
#488 Spreadsheet ingested, but then system hung
Opened
#489 Can't "Contact Sales" from billing
Opened
#490 S3 bucket with HTML files not syncing with Llama Index
Opened
#491 Help -> Chat with Us is broken
Opened
#492 Can not create a datasource for Sharepoint sub folder
Opened
#493 Can't end Starter plan subscription
Opened
#494 Getting a 401 in the playground
Opened
#495 Unique table parsing Issue
Opened
#496 MultiModalVectorStoreIndex retriever index out of bounds
Opened
#497 Unable to Use "PREMIUM" Extraction Mode via SDK (Only Available in UI)
Opened
#498 Prompts Not Applied via API When Parsing
Opened
#499 "How can I top up for credits without a subscription? The option isn’t visible."
Opened
#500 Option to Force Image Conversion to Prevent White Fonting
Opened
#501 Gemini LVM Bug
Opened
#502 Deprecation notice to Llama-Parse
Opened
#503 Some modes treats input file text as prompt instructions, causing unintended translations
Opened
#504 [Feature Request]: Allow retrieval of parsing job ID or parsed content after adding file to pipeline
Opened
#505 LlamaParse: hide_header and hide_footer are NOT working for pdf
Opened
#506 get_tables() method writes files to incorrect locations
Opened
#507 Issue with get_tables() method - files written to wrong location
Opened
#508 Extraction is working when uploading pdf on Platform but not with api .
Opened
#509 OCR_ERROR : OCR failed
Opened
#510 [Feature Request]: Webhook when the job is completed
Opened
#511 use changeset for versioning
Opened
#512 **From Flawless to Failure: Premium OCR Suddenly Can’t Read Images**
Opened
#513 Manage metadata in the UI
Opened
#514 RECONSTRUCTION_ERROR when parsing with parse_mode="parse_document_with_agent"
Opened
#515 Extraction job webhooks not delivered to automation platform Make.com endpoint
Opened
#516 Error 409 during deletion of file
Opened
#517 playground_index_creditfail
Opened
#518 Parsing URLs with expandable sections
Opened
#519 LlamaParse through TS failing with unclear error log
Opened
#520 Getting consistent "HTTP 429 Too Many Requests" for LlamaParse API
Opened
#521 Extract Job Creation Throttle
Opened
#522 Extract Job timed out (need help in investigation is the only file that fail)
Opened
#523 charge me more then 1 credits for byok models
Opened
#524 Confusing Async Behavior and Webhook Usage in LlamaParse Python SDK
Opened
#525 TS Type error for 'llama-cloud-services'
Opened
#526 MULTIMODAL_ERROR when using GPT-5 from Azure OpenAI
Opened
#527 Document Size Limitation Error - Need Higher Page Limit for parse_page_with_agent Mode
Opened
#528 Dont work
Opened
#529 Need help to migrate from self-hosted Supabase on AWS to Supabase SaaS
Opened
#530 Not working parse and download in PDF
Opened
#531 parse is failing
Opened
#532 Unknown Error Failed to fetch Try again
Opened
#533 ImportError: cannot import name 'ClassifyJobWithStatus' from 'llama_cloud.types'
Opened
#534 Fatal 500 error on custom raw json schema on llamaextract
Opened
#535 Parsing failed RECONSTRUCTION_ERROR on parse_page_with_agent_mode, job_timeout was also not being respected
Opened
#536 Slow parsing (~10 min) and missing editable field content in ‘Parse page with agent - GPT 4.1 Mini - v2’ mode
Opened
#537 Delete parsed job data
Opened
#538 Pro plan refund
Opened
#539 Cant make an API key: Something went wrong with generating your new key.
Opened
#540 Any plans to add 3rd party vendors to the list of models for Llamaparse?
Opened
#541 Support max_completion_tokens Parameter for Azure GPT-5 Models in LlamaParse
Opened
#542 Free 10,000 Credits deducted from the new package I just bought
Opened
#543 [Bug]: Item bBoxes are not accurate
Opened
#544 Same PDF was parsed correctly on September 5, but not longer on September 9
Opened
#545 LlamaParse JSON Output for an XLSX File contains null elements in the table
Opened
#546 LlamaIndex Cloud Bug Report: Intermittent PDF Processing Failure (Non-Deterministic)
Opened
#547 Provide a reason why an extraction job failed.
Opened
#548 "Parse document with LLM" listed cost is inconsistent
Opened
#549 Inaccurate page count and credit usage in parse API response
Opened
#550 Verify email header on free account has a verify link that is not a hyperlink.
Opened
#551 Extraction quality <-> Chunk size
Opened
#552 Deleting an index does not stop the index
Opened
#553 Playground downloads files when uploading + clicking parse
Opened
#554 No screenshot/figure node retrieval in typescript
Opened
#555 ExtractConfig Documentation shows ChunkMode when in reality its DocumentChunkMode
Opened
#556 Jobs appear to hang as in progress
Opened
#557 Bounding box error with Llamaparse
Opened
#558 Cannot access enterprise account
Opened
#559 Google Cloud Storage (GCS) support as Data Source
Opened
#560 unsupported file type: xlsx
Opened
#561 LlamaParse is not working from this package and the web dashboard
Opened
#562 remove contents from chunk
Opened
#563 Expose credits_used / job_credits_usage fields in JobResult.job_metadata (Python SDK)
Opened
#564 Credit limit for this month
Opened
#565 Inconsistent Record Extraction
Opened
#566 Content from previous pdf page duplicated in the next page items (python lib)
Opened
#567 Different heading levels for siblings, missing heading (parse with python lib)
Opened
#568 We couldn't fetch your invoices at this time. Please try refreshing the page or contact support if the problem persists.
Opened
#569 Issue Parsing Tables Across Multiple Pages in PDF Documents
Opened
#570 anthropic-sonnet-4.5 always fails with extract
Opened
#571 Unable to extract a line from a well constructed structured PDF
Opened
#572 [CSV] Bank Statement on a .csv file giving an error on extraction
Opened
#573 The RAW json edition on extract agents changed to read only.
Opened
#574 V2 Parse API: poor system prompt, user_prompt & system_prompt_append not sent to LLM when using parse_with_external_provider
Opened
#575 invoices
Opened
#576 Llama Extract Models
Opened
#577 Question About Extract Scheme
Opened
#578 I can't see my api key
Opened
#579 Confidence score not returning in the Llama Extract Response
Opened
#580 LaamaParse: v2 documentation is all wrong
Opened
#581 Parse document: Markdown output widely differs when used via code vs the Web UI
Opened
#582 TS Version uses requires and throws an error with ES2020/NodeNext
Opened
#583 api/parsing/job 500 error
Opened
#584 How many Extract Agents can we create?
Opened
#585 Bug when using Extract API
Opened
#586 Please Add a .tif,.tiff file support in llama Extraction.
Opened
#587 v2 parse api not working.
Opened
#588 Error querying data sink: 400 Client Error
Opened
#589 fail to parse hebrew document
Opened
#590 extract_stateless does not support docx
Opened
#591 Checkboxes working in the UI but not programmatically
Opened
#592 Unable to delete files: 409 Conflict
Opened
#593 Asking for package version of llama_cloud_services
Opened
#594 validation error in JobResult - pydantic
Opened
#595 [TypeScript SDK] Add partition_pages support for large document parallel processing
Opened
#596 webapp: Button to upload files to index is gone, preventing uploads
Opened
#597 Parsing tier with Python:
Opened
#598 Nothing to show
Opened
#599 Flowise Llamaindex modules with pinecone retreiving
Opened
#600 Extract Stateless API Error
Opened
#601 auto_mode_configuration accepted by v2 API but triggered_auto_mode is always false — is auto_mode actually implemented in v2?
Opened
#602 Broken Notion link in LlamaAgent launch blog
Opened
#603 Unable to process and showing 0 credit balance (I upgraded my plan about an hour ago)
Opened
#604 All records are not being extracted on Paid Plan - Why?
Opened
#605 New dashboard usage page shows $ when referring to credits
Opened
#606 Multiple failed extraction jobs
Opened
#607 [PR #1] [CLOSED] upd demo
Opened
#608 [PR #2] [MERGED] Add pdf reader as baseline
Opened
#609 [PR #3] [MERGED] slight nits, rename to LlamaParser
Opened
#610 [PR #5] [MERGED] add print statement to print job_id for easier debugging
Opened
#611 [PR #4] [MERGED] upd examples
Opened
#612 [PR #7] [MERGED] Add an example for Astra DB Integration
Opened
#613 [PR #6] [MERGED] change demo
Opened
#614 [PR #8] [MERGED] Fix readme typos
Opened
#615 [PR #10] [MERGED] Bump version
Opened
#616 [PR #9] [MERGED] Handle error from API
Opened
#617 [PR #11] [CLOSED] New Llama parser Demo
Opened
#618 [PR #12] [MERGED] New Llama Parser Demo
Opened
#619 [PR #15] [MERGED] Logan/update docs
Opened
#620 [PR #13] [MERGED] Refactor demo structure
Opened
#621 [PR #16] [MERGED] nit: fix README instructions for v0.10 compatibility
Opened
#622 [PR #20] [MERGED] QoL improvements
Opened
#623 [PR #18] [MERGED] upd demo results
Opened
#624 [PR #17] [MERGED] clean up notebook baseline method
Opened
#625 [PR #22] [MERGED] Astra DB Example Notebook updated for 0.10.x, remove ServiceContext
Opened
#626 [PR #21] [CLOSED] fix astra example (make compatible with v10)
Opened
#627 [PR #23] [MERGED] add advanced rag example for astra
Opened
#628 [PR #26] [MERGED] Astra DB vector store imports from newly-named package
Opened
#629 [PR #27] [MERGED] Astra DB notebooks allow optional namespace specification
Opened
#630 [PR #24] [MERGED] Update demo_advanced.ipynb
Opened
#631 [PR #37] [MERGED] ADD: Support for language parameter in the package
Opened
#632 [PR #48] [MERGED] add language cookbook
Opened
#633 [PR #49] [MERGED] [version] bump version to 0.3.5
Opened
#634 [PR #53] [MERGED] fix(base): add file_path to exception msg
Opened
#635 [PR #55] [MERGED] add table copmarisons cookbook
Opened
#636 [PR #60] [MERGED] fix language
Opened
#637 [PR #68] [MERGED] fix to json bug
Opened
#638 [PR #64] [MERGED] add json cookbook
Opened
#639 [PR #62] [MERGED] Pierre/json images
Opened
#640 [PR #74] [MERGED] let client support more file types
Opened
#641 [PR #75] [MERGED] add basic ppt demo
Opened
#642 [PR #78] [MERGED] add financial powerpoint cookbook
Opened
#643 [PR #82] [MERGED] Adding parsing instructions demo
Opened
#644 [PR #88] [MERGED] add agent demo
Opened
#645 [PR #86] [MERGED] Update demo_parsing_instructions.ipynb
Opened
#646 [PR #84] [MERGED] demo insurance + parsing instructions
Opened
#647 [PR #93] [MERGED] Init LlamaParseJsonNodeParser example
Opened
#648 [PR #89] [MERGED] nit: fix grammar in insurance cookbook
Opened
#649 [PR #91] [MERGED] Added utils files
Opened
#650 [PR #96] [CLOSED] Add Qdrant demonstration
Opened
#651 [PR #97] [MERGED] fixes to insurance demo
Opened
#652 [PR #107] [MERGED] Add mongodb llamaparse example
Opened
#653 [PR #109] [MERGED] nit: add colab badge to mongodb notebook
Opened
#654 [PR #98] [MERGED] fix advanced RAG notebook title
Opened
#655 [PR #110] [MERGED] Extend supported formats
Opened
#656 [PR #111] [MERGED] vbump
Opened
#657 [PR #128] [CLOSED] Logging file path when creating job
Opened
#658 [PR #136] [MERGED] Fixing paths of data in example notebook
Opened
#659 [PR #117] [MERGED] Enable support for custom filesystem
Opened
#660 [PR #139] [MERGED] docs: update readme with link to llamacloud
Opened
#661 [PR #140] [MERGED] QoL Changes
Opened
#662 [PR #141] [MERGED] v0.4.1
Opened
#663 [PR #142] [MERGED] Skip tests if CICD doesn't populate the secrets
Opened
#664 [PR #148] [MERGED] some notebook updates
Opened
#665 [PR #154] [MERGED] add html support
Opened
#666 [PR #159] [MERGED] Ensure image extensions, vbump
Opened
#667 [PR #178] [MERGED] New option skip diagonal text and invalidate cache
Opened
#668 [PR #180] [MERGED] gpt4o notebook over tesla impact docs
Opened
#669 [PR #179] [MERGED] add new mode and params for openai
Opened
#670 [PR #181] [MERGED] Add example for Weaviate
Opened
#671 [PR #185] [MERGED] llamaparse example over caltrain schedule
Opened
#672 [PR #186] [MERGED] fix colab badge
Opened
#673 [PR #193] [MERGED] nit: add caltrain weekend doc
Opened
#674 [PR #192] [MERGED] clean up gpt4o notebook
Opened
#675 [PR #195] [MERGED] allow for .jpg images
Opened
#676 [PR #196] [CLOSED] Add the fast mode flag
Opened
#677 [PR #201] [MERGED] bump version, add image support
Opened
#678 [PR #198] [MERGED] Bump requests from 2.31.0 to 2.32.2
Opened
#679 [PR #197] [MERGED] Bump tqdm from 4.66.2 to 4.66.3
Opened
#680 [PR #204] [MERGED] Add Excel spreadsheet example with llamaparse
Opened
#681 [PR #203] [MERGED] Add spreadsheet extensions
Opened
#682 [PR #212] [MERGED] add split by page mode
Opened
#683 [PR #211] [MERGED] add KG agent
Opened
#684 [PR #221] [MERGED] Fix Typo in description of invalidate_cache argument of LlamaParse constructor
Opened
#685 [PR #215] [MERGED] add simple excel notebook (with dcf)
Opened
#686 [PR #216] [MERGED] Pierre/new options
Opened
#687 [PR #243] [CLOSED] Make Split to Page Default = False
Opened
#688 [PR #231] [MERGED] rewrite advanced example
Opened
#689 [PR #234] [MERGED] add baseline to dcf excel RAG
Opened
#690 [PR #250] [MERGED] add target_pages and bounding_box parameters
Opened
#691 [PR #251] [MERGED] v0.4.5
Opened
#692 [PR #259] [MERGED] allow for bytes or buffer as input
Opened
#693 [PR #258] [MERGED] llama-parse with elasticsearch vector database example notebook
Opened
#694 [PR #254] [MERGED] Modify _get_sub_docs to use Custom Separator
Opened
#695 [PR #271] [MERGED] fix file_input type issue
Opened
#696 [PR #273] [CLOSED] Handle file_path as either str or PosixPath.
Opened
#697 [PR #277] [MERGED] Make File Extension Check Case-Insensitive
Opened
#698 [PR #285] [MERGED] New parameters
Opened
#699 [PR #284] [MERGED] create multi-modal RAG notebook
Opened
#700 [PR #288] [MERGED] nit: slide deck fix
Opened
#701 [PR #289] [MERGED] [WIP] add sonnet cookbook + llamaparse fixes
Opened
#702 [PR #297] [MERGED] Pierre/fix page separator
Opened
#703 [PR #302] [CLOSED] check if chunk is not just whitespace
Opened
#704 [PR #316] [MERGED] add gpt-4o-mini example
Opened
#705 [PR #292] [MERGED] nit fix multimodal
Opened
#706 [PR #329] [CLOSED] start one httpx per parser, async get images
Opened
#707 [PR #340] [MERGED] add report generation example
Opened
#708 [PR #342] [MERGED] small edits
Opened
#709 [PR #330] [MERGED] Adds more use case notebooks to multimodal parsing
Opened
#710 [PR #343] Improve multimodal report generation notebook
Opened
#711 [PR #345] Fix text nodes creation and improve agent handling
Opened
#712 [PR #351] [CLOSED] Resolved dependency conflicts
Opened
#713 [PR #353] Enhance readability and usability of demo_basic notebook
Opened
#714 [PR #349] [MERGED] add report generation agent
Opened
#715 [PR #363] [MERGED] CLI Testing Tool for Parsing Results to Standard Output
Opened
#716 [PR #372] [MERGED] Support take_screenshot
Opened
#717 [PR #378] [MERGED] Add timeout to the image request using httpx
Opened
#718 [PR #384] [MERGED] allow custom httpx client
Opened
#719 [PR #386] [MERGED] update README
Opened
#720 [PR #388] [MERGED] bump to 0.5.3
Opened
#721 [PR #394] [MERGED] do not attach a filepath when a stram of bytes is passed
Opened
#722 [PR #400] [MERGED] Remove JSON from valid result types
Opened
#723 [PR #406] [MERGED] add premium mode support
Opened
#724 [PR #402] [MERGED] fix multimodal RAG over slide deck
Opened
#725 [PR #409] [MERGED] Compare Excel RAG with o1 models
Opened
#726 [PR #414] [MERGED] nit: move o1 excel notebook
Opened
#727 [PR #415] [MERGED] Update excel rag with o1 notebook
Opened
#728 [PR #417] [MERGED] Update README.md to convey need to specify extra_info["file_name"]
Opened
#729 [PR #416] [MERGED] fix excel notebook
Opened
#730 [PR #429] [MERGED] add multimodal RAG pipeline with contextual retrieval
Opened
#731 [PR #426] [MERGED] improve error handling for jobs
Opened
#732 [PR #438] [MERGED] Add RFP Response generation workflow
Opened
#733 [PR #441] [MERGED] Add missing parameters
Opened
#734 [PR #446] [MERGED] Release is_formatting_instruction parameter
Opened
#735 [PR #454] [CLOSED] feat: Add Greek supported language
Opened
#736 [PR #448] [CLOSED] add annotate link option
Opened
#737 [PR #455] [MERGED] fix RFP example
Opened
#738 [PR #460] [MERGED] Add continuous_mode
Opened
#739 [PR #457] [MERGED] Update issue templates
Opened
#740 [PR #464] [MERGED] Add PurePosixPath to list of allowed file-paths
Opened
#741 [PR #461] [MERGED] multimodal report generation image
Opened
#742 [PR #472] [MERGED] add xlsx support
Opened
#743 [PR #468] [CLOSED] Pierre/new params
Opened
#744 [PR #484] [MERGED] dynamic section retrieval nb
Opened
#745 [PR #506] [MERGED] add test for downloading images
Opened
#746 [PR #475] [MERGED] add input url and http_proxy
Opened
#747 [PR #531] [MERGED] JSON mode tour notebook
Opened
#748 [PR #525] [MERGED] Add more parameters
Opened
#749 [PR #532] [MERGED] Add support for html_remove_navigation_elements.
Opened
#750 [PR #529] [MERGED] Add demo videos notebooks
Opened
#751 [PR #540] [MERGED] auto-mode notebook
Opened
#752 [PR #544] [MERGED] Expanding auto mode notebook with strings and regex triggers
Opened
#753 [PR #545] [MERGED] update auto-mode
Opened
#754 [PR #542] [MERGED] Add get charts function
Opened
#755 [PR #548] [MERGED] Update cache parameter
Opened
#756 [PR #550] [MERGED] Add cookbook for parsing instructions
Opened
#757 [PR #557] [MERGED] Extract layout, audio files
Opened
#758 [PR #551] [MERGED] Fix docstring for aget_xlsx method
Opened
#759 [PR #568] [MERGED] Stoli/feat/connection handling
Opened
#760 [PR #569] [MERGED] v0.5.19
Opened
#761 [PR #582] [MERGED] add new formatting instruction parameters
Opened
#762 [PR #603] [MERGED] v0.6.0
Opened
#763 [PR #606] [MERGED] add gemini2 flash notebook
Opened
#764 [PR #592] [MERGED] fix release pipeline no-dev issue
Opened
#765 [PR #611] [MERGED] fixing colab links
Opened
#766 [PR #597] [MERGED] Refactor into llama-cloud-services
Opened
#767 [PR #617] [MERGED] fix publish flow
Opened
#768 [PR #622] [MERGED] add new parsing mode and prompt parameters
Opened
#769 [PR #632] [MERGED] v0.6.2
Opened
#770 [PR #616] [MERGED] add organization id and project id as args
Opened
#771 [PR #628] [MERGED] Add LlamaExtract to llama-cloud-services
Opened
#772 [PR #636] [MERGED] Bump version to v0.6.3
Opened
#773 [PR #638] [MERGED] Add adaptive_long_table option
Opened
#774 [PR #635] [MERGED] Update README.md
Opened
#775 [PR #646] [MERGED] Add notebook for extraction from SEC 10-K/Q filings
Opened
#776 [PR #645] [MERGED] Bump to version 0.6.5 (updating llama-cloud dependency)
Opened
#777 [PR #648] [MERGED] fix:Add retry handling to parse and backoff patterns - catching 5XX errors and HTTP errors
Opened
#778 [PR #647] [MERGED] Typos and removing staging URL
Opened
#779 [PR #650] [MERGED] new result object
Opened
#780 [PR #651] [MERGED] Update llama cloud for extract endpoints
Opened
#781 [PR #652] [MERGED] Bump up version for release
Opened
#782 [PR #656] [MERGED] Bump to version 0.6.7
Opened
#783 [PR #655] [MERGED] Add xfail for timeout errors in report gen
Opened
#784 [PR #654] [MERGED] Add provision for custom httpx client for LlamaExtract
Opened
#785 [PR #657] [MERGED] Revert httpx_client as argument
Opened
#786 [PR #658] [MERGED] Update notebook for extract
Opened
#787 [PR #662] [CLOSED] Bump to version 0.6.8
Opened
#788 [PR #660] [MERGED] Add new parameter, fix parse_mode
Opened
#789 [PR #663] [MERGED] Bump to version 0.6.9
Opened
#790 [PR #664] [MERGED] create llamaextract demo with lm317 datasheet
Opened
#791 [PR #665] [MERGED] fix notebook
Opened
#792 [PR #666] [MERGED] chore: add base url documentation
Opened
#793 [PR #670] [MERGED] add due diligence notebook
Opened
#794 [PR #671] [MERGED] Update extract.md
Opened
#795 [PR #668] [MERGED] Rename test endpoint to match functionality
Opened
#796 [PR #667] [MERGED] solar panel extraction workflow
Opened
#797 [PR #673] [MERGED] Fix bytes input for LlamaExtract
Opened
#798 [PR #672] [MERGED] Add layout agent mode visual citation demo notebook
Opened
#799 [PR #674] [MERGED] Better connection management on llamaextract client
Opened
#800 [PR #675] [MERGED] Add compact_markdown_table parameter
Opened
#801 [PR #676] [MERGED] Support text as input directly in the SDK
Opened
#802 [PR #678] [MERGED] Bump version to v0.6.11
Opened
#803 [PR #679] [MERGED] Update docs for LlamaExtract
Opened
#804 [PR #680] [MERGED] v0.6.12
Opened
#805 [PR #677] [MERGED] v0.6.10
Opened
#806 [PR #681] [MERGED] parse readme nits
Opened
#807 [PR #683] [MERGED] Add markdown_table_multiline_header_separator support
Opened
#808 [PR #692] [MERGED] skip llama-report tests in cicd
Opened
#809 [PR #682] [MERGED] Use unique filename to avoid db collisions later
Opened
#810 [PR #693] [MERGED] small enum nit for FailedPageMode
Opened
#811 [PR #691] [MERGED] Page error parameters
Opened
#812 [PR #696] [MERGED] Update to latest version of llama-cloud
Opened
#813 [PR #698] [MERGED] Dependabot configuration to update actions in workflow
Opened
#814 [PR #697] [MERGED] Bump to v0.6.16
Opened
#815 [PR #699] [MERGED] Refactor CodeQL workflow
Opened
#816 [PR #700] [MERGED] Bump actions/checkout from 3 to 4
Opened
#817 [PR #703] [MERGED] add support for presets
Opened
#818 [PR #704] [MERGED] add auto_mode_configuration_jon for llamaParse
Opened
#819 [PR #706] [MERGED] v0.6.19
Opened
#820 [PR #702] [MERGED] make original height + width optional in the parse result
Opened
#821 [PR #701] [MERGED] Bump actions/setup-python from 4 to 5
Opened
#822 [PR #708] [MERGED] parse: fix num_workers/parse job batching
Opened
#823 [PR #707] [MERGED] v0.6.20
Opened
#824 [PR #711] [MERGED] even more optional
Opened
#825 [PR #709] [MERGED] parse: support partitioning files before parsing (v0.6.27)
Opened
#826 [PR #716] [MERGED] Adding example for extracting with citations
Opened
#827 [PR #720] [MERGED] Remove credits from parse metadata
Opened
#828 [PR #726] [MERGED] Pass through verify and timeout config to the extraction agent
Opened
#829 [PR #718] [MERGED] v0.6.22
Opened
#830 [PR #731] [MERGED] Add notebook for Form 4 extraction
Opened
#831 [PR #729] [MERGED] Bump to version 0.6.23
Opened
#832 [PR #732] [MERGED] v0.6.24
Opened
#833 [PR #736] [MERGED] 0.6.25 outlined_table_extraction
Opened
#834 [PR #740] [MERGED] v0.6.26
Opened
#835 [PR #737] [MERGED] parse: fix the "model" parameter mismatch between playground and Python client
Opened
#836 [PR #739] [MERGED] add multi-fund analysis notebook
Opened
#837 [PR #745] [MERGED] 0.6.29: Standerdize the parsing input format for both .aget_json() and .aload_data()
Opened
#838 [PR #741] [MERGED] 0.6.28: fix job result format after partitioning changes
Opened
#839 [PR #743] [MERGED] Directly pass None project_id
Opened
#840 [PR #747] [MERGED] more optional types marked
Opened
#841 [PR #748] [MERGED] Bump to version 0.6.30
Opened
#842 [PR #751] [MERGED] v0.6.31
Opened
#843 [PR #750] [MERGED] Fix colab broken links
Opened
#844 [PR #754] [MERGED] Bump requests from 2.32.3 to 2.32.4 in /llama_parse
Opened
#845 [PR #753] [MERGED] Bump tornado from 6.4.2 to 6.5.1 in /llama_parse
Opened
#846 [PR #752] [MERGED] Bump h11 from 0.14.0 to 0.16.0 in /llama_parse
Opened
#847 [PR #758] [MERGED] fix partition
Opened
#848 [PR #755] [MERGED] 6.32 warning on unused parameters
Opened
#849 [PR #762] [MERGED] Bump version to 0.6.35
Opened
#850 [PR #757] [MERGED] add high_res_ocr to the package
Opened
#851 [PR #763] [MERGED] Bump up version to 0.6.36
Opened
#852 [PR #766] [MERGED] Manage extract agent lifecycle in pytest
Opened
#853 [PR #769] [MERGED] Relax tenacity version; bump up version to 0.6.37
Opened
#854 [PR #764] [MERGED] Make job fetching more robust to connection errors
Opened
#855 [PR #770] [CLOSED] Update parse client to handle Remote Protocol Error
Opened
#856 [PR #771] [MERGED] except one more error type
Opened
#857 [PR #775] [MERGED] header footer control in llamaparse
Opened
#858 [PR #776] [MERGED] parse: loosen PageItem.rows type hint (v0.6.41)
Opened
#859 [PR #782] [MERGED] Add nicer hand-written agent data interface
Opened
#860 [PR #783] [MERGED] Bump up version to 0.6.42
Opened
#861 [PR #772] [MERGED] Bump to version 0.6.39
Opened
#862 [PR #785] [MERGED] Improve Agent Data interface, and add file related fields to extracted data for file tracking
Opened
#863 [PR #786] [MERGED] merge_tables_across_pages_in_markdown parse parameter
Opened
#864 [PR #793] [MERGED] feat: add table extraction for LlamaParse as CSV files
Opened
#865 [PR #784] [MERGED] relax pydantic job object
Opened
#866 [PR #790] adding deprecation notice to llama-parse
Opened
#867 [PR #795] [MERGED] Update to version 0.6.48
Opened
#868 [PR #796] [MERGED] Add new method to fetch the full, non-paginated markdown
Opened
#869 [PR #800] [CLOSED] push get_markdown up a level to get_result to include result and full md in one
Opened
#870 [PR #794] [MERGED] chore: vbump to 0.6.47 and example notebook
Opened
#871 [PR #797] [MERGED] Bump v0.6.49
Opened
#872 [PR #808] [MERGED] Make versioning a little easier, and fix llama_parse version
Opened
#873 [PR #806] [MERGED] parse: expose preserve_very_small_text option
Opened
#874 [PR #802] [MERGED] bump version to v0.6.50
Opened
#875 [PR #801] [MERGED] parse: expose functionality to get raw job results
Opened
#876 [PR #803] [MERGED] feat: default to _public agent data
Opened
#877 [PR #809] [MERGED] Fixes to multimodal report generation
Opened
#878 [PR #815] [MERGED] Adding support for page citations, and refactor the confidence into the field metadata
Opened
#879 [PR #814] [MERGED] Bump llama-cloud version
Opened
#880 [PR #810] [CLOSED] wip: monorepo changes
Opened
#881 [PR #811] [MERGED] Adding TS llama-cloud-services and moving llama-parse to uv
Opened
#882 [PR #817] [MERGED] feat: add index to llama-cloud-services
Opened
#883 [PR #820] [MERGED] docs(readme): update hyperlinks to correct targets
Opened
#884 [PR #819] [MERGED] fix: add release to NPM
Opened
#885 [PR #821] [MERGED] Merge index into main
Opened
#886 [PR #818] [CLOSED] Add examples for TypeScript
Opened
#887 [PR #822] [MERGED] feat: add ts examples (clean)
Opened
#888 [PR #824] [MERGED] Update README.md
Opened
#889 [PR #823] [MERGED] fix: no git checks on pnpm publish
Opened
#890 [PR #827] [CLOSED] feat: add changesets
Opened
#891 [PR #826] [MERGED] chore: remove llamaindex dep
Opened
#892 [PR #828] [MERGED] fix: add symlink to avoid breaking links
Opened
#893 [PR #830] [MERGED] delete examples
Opened
#894 [PR #832] [MERGED] Copy extracted citations to the new repo
Opened
#895 [PR #829] [MERGED] Example Notebooks
Opened
#896 [PR #831] [CLOSED] feat: restructure docs/examples
Opened
#897 [PR #835] [CLOSED] Re-enabling this test
Opened
#898 [PR #836] [MERGED] add files client
Opened
#899 [PR #837] [MERGED] Classifier SDK
Opened
#900 [PR #834] [MERGED] fix: Fix bugs in ExtractedFieldMetadata parser
Opened
#901 [PR #838] [MERGED] fix: run e2e only on 3.12
Opened
#902 [PR #839] [MERGED] wip: implementing Extract in TS
Opened
#903 [PR #841] [MERGED] Add claude code workflow with restricted access
Opened
#904 [PR #840] [MERGED] Update Extract with stateless API
Opened
#905 [PR #843] [MERGED] chore: build before releaes
Opened
#906 [PR #842] [CLOSED] chore: add e2e tests and use monorepo for TS
Opened
#907 [PR #845] [MERGED] docs: move ts examples in their own top-level folder
Opened
#908 [PR #846] [MERGED] py: bump version to 0.6.55
Opened
#909 [PR #844] [MERGED] utils/parse: add method to check pypi for package updates
Opened
#910 [PR #848] [CLOSED] maybe?
Opened
#911 [PR #847] [CLOSED] feat: implement changesets
Opened
#912 [PR #849] [MERGED] version via changesets
Opened
#913 [PR #851] [MERGED] feat: add parse and getTables methods to LlamaParseReader
Opened
#914 [PR #850] [MERGED] parse: expose HTML output for result table items when possible
Opened
#915 [PR #852] [MERGED] Update docs for extract
Opened
#916 [PR #853] [MERGED] Bump version to 0.6.56
Opened
#917 [PR #863] [MERGED] missing await
Opened
#918 [PR #859] [MERGED] support llama parse audio
Opened
#919 [PR #861] [MERGED] remove print
Opened
#920 [PR #855] [MERGED] chore: bump ts version for parse
Opened
#921 [PR #864] [MERGED] fix presigned urls + add very necessary test
Opened
#922 [PR #867] [MERGED] parallelize e2e tests
Opened
#923 [PR #865] [MERGED] Re-order extraction metadata union for better parsing
Opened
#924 [PR #868] [MERGED] feat: export ExtractedFieldMetadata and ExtractedFieldMetadataDict types
Opened
#925 [PR #869] [MERGED] citation can be null
Opened
#926 [PR #870] [MERGED] handle error field
Opened
#927 [PR #873] [MERGED] fix composite retriever
Opened
#928 [PR #872] [CLOSED] Update llama-cloud-services
Opened
#929 [PR #874] [MERGED] add a starter notebook for llamaparse presets
Opened
#930 [PR #875] [MERGED] Bump actions/checkout from 4 to 5
Opened
#931 [PR #871] [MERGED] feat: support passing a pre-uploaded file directly
Opened
#932 [PR #878] [MERGED] add acreate_classify_job
Opened
#933 [PR #881] [MERGED] fix: Make env based api url overrideable
Opened
#934 [PR #879] [CLOSED] deprecate (a)load_data methods and split_by_page in constructor
Opened
#935 [PR #883] [MERGED] fix preset notebook: give outputs in markdown
Opened
#936 [PR #882] [MERGED] update all example notebooks
Opened
#937 [PR #887] [MERGED] add alternative builder method
Opened
#938 [PR #888] [MERGED] add file names in return values
Opened
#939 [PR #884] [CLOSED] Surface parse errors
Opened
#940 [PR #889] [MERGED] parse: expose page.slideSpeakerNotes
Opened
#941 [PR #891] [MERGED] getting started LlamaCloudIndex notebook
Opened
#942 [PR #892] [MERGED] Added "SourceText" to __init__.py
Opened
#943 [PR #894] [MERGED] Fix tag push command in CONTRIBUTING.md
Opened
#944 [PR #893] [MERGED] version bump to 0.6.63
Opened
#945 [PR #895] [MERGED] client unification
Opened
#946 [PR #897] [MERGED] Update version script, and unify the linting so that prettier is more consistent
Opened
#947 [PR #898] [MERGED] fix: "v" prefix being added to js versions
Opened
#948 [PR #902] [MERGED] fix: make ts release beautiful again
Opened
#949 [PR #899] [MERGED] fix: v prefix goes deeper. Fix more
Opened
#950 [PR #905] [MERGED] Remove report generation related code from llama_cloud_services
Opened
#951 [PR #904] [MERGED] Bump version to 0.6.64
Opened
#952 [PR #909] [MERGED] Bump actions/setup-node from 4 to 5
Opened
#953 [PR #911] [MERGED] update parse package
Opened
#954 [PR #907] docs: streaming citation
Opened
#955 [PR #906] [MERGED] Fix uv sync; remove poetry lock
Opened
#956 [PR #913] add classify+extract notebook
Opened
#957 [PR #919] [MERGED] parse: expose spreadsheet_force_formula_computation option
Opened
#958 [PR #920] [MERGED] py: bump version to v.0.6.66
Opened
#959 [PR #921] [MERGED] Refactor agent fields in llama_cloud_services
Opened
#960 [PR #923] docs: index multimodal
Opened
#961 [PR #918] Support better Parse error handling
Opened
#962 [PR #928] [MERGED] Handle validation errors for agent data retrieval
Opened
#963 [PR #924] [MERGED] Support creating indexes in a specified project_id
Opened
#964 [PR #927] [CLOSED] Add failing test for citation field bug
Opened
#965 [PR #931] [MERGED] docs: parse -> classify -> extract
Opened
#966 [PR #929] [MERGED] Handle reasoning field conflict
Opened
#967 [PR #940] [MERGED] Update llama-cloud dep
Opened
#968 [PR #941] [MERGED] chore: version packages
Opened
#969 [PR #943] [MERGED] fix: theres just one publish token
Opened
#970 [PR #944] [MERGED] Fix more bugs in publishing
Opened
#971 [PR #942] [MERGED] ignore nvmrc
Opened
#972 [PR #946] [MERGED] Disable npm release
Opened
#973 [PR #945] [MERGED] Escaping dollar signs in md output when running in a jupyter notebook
Opened
#974 [PR #947] [CLOSED] chore: version packages
Opened
#975 [PR #949] [MERGED] swap changesets
Opened
#976 [PR #948] [MERGED] fix: explicitly tag. I thought the action did this
Opened
#977 [PR #951] [MERGED] fix changeset harder
Opened
#978 [PR #952] [MERGED] chore: version packages
Opened
#979 [PR #950] [CLOSED] chore: version packages
Opened
#980 [PR #953] [MERGED] fixup tagging more better
Opened
#981 [PR #954] [MERGED] chore: version packages
Opened
#982 [PR #955] [MERGED] Missed some things again with tag fixes
Opened
#983 [PR #956] [MERGED] chore: version packages
Opened
#984 [PR #959] [MERGED] build(deps): bump pnpm/action-setup from 3 to 4
Opened
#985 [PR #960] [MERGED] build(deps): bump actions/setup-python from 5 to 6
Opened
#986 [PR #958] [MERGED] build(deps): bump astral-sh/setup-uv from 3 to 6
Opened
#987 [PR #963] [MERGED] fix: re-enable js publishing
Opened
#988 [PR #961] [MERGED] build(deps): bump actions/checkout from 4 to 5
Opened
#989 [PR #962] [MERGED] loosen packaging requirements
Opened
#990 [PR #964] [MERGED] Only escape single dollar sign in notebook md
Opened
#991 [PR #965] [MERGED] chore: version packages
Opened
#992 [PR #975] [MERGED] fix default bbox values
Opened
#993 [PR #973] [MERGED] build(deps): bump github/codeql-action from 3 to 4
Opened
#994 [PR #969] [MERGED] Add ImageNode support in TypeScript
Opened
#995 [PR #976] [MERGED] safest types possible for parse
Opened
#996 [PR #974] [MERGED] build(deps): bump astral-sh/setup-uv from 6 to 7
Opened
#997 [PR #980] [MERGED] Add agressive table extraction argument
Opened
#998 [PR #981] [MERGED] chore: version packages
Opened
#999 [PR #977] [MERGED] chore: version packages
Opened
#1000 [PR #982] [MERGED] chore: version packages
Opened
#1001 [PR #983] [MERGED] improve classify notebook
Opened
#1002 [PR #988] [MERGED] chore: version packages
Opened
#1003 [PR #984] build(deps): bump actions/setup-node from 5 to 6
Opened
#1004 [PR #986] [MERGED] Add common SourceText class for classify/extract text inputs
Opened
#1005 [PR #985] [MERGED] feat: add classify to ts sdk
Opened
#1006 [PR #989] [MERGED] docs: add llamaclassify demo
Opened
#1007 [PR #990] [MERGED] Fix: Return partial results on job failure
Opened
#1008 [PR #991] [MERGED] chore: version packages
Opened
#1009 [PR #992] [MERGED] beta sheets API
Opened
#1010 [PR #995] [MERGED] chore: version packages
Opened
#1011 [PR #994] [MERGED] Bump to version 0.6.78
Opened
#1012 [PR #1009] [MERGED] docs: add batch parse directory example notebook
Opened
#1013 [PR #999] [MERGED] chore: version packages
Opened
#1014 [PR #996] [MERGED] destructured keyword params for classify
Opened
#1015 [PR #998] [MERGED] fix version breaking
Opened
#1016 [PR #997] [MERGED] Remove organization id from classify
Opened
#1017 [PR #1012] [MERGED] Add support for custom metadata in file upload methods
Opened
#1018 [PR #1014] [MERGED] chore: version packages
Opened
#1019 [PR #1013] [MERGED] chore: rename classifyclient and keep it backward compatible
Opened
#1020 [PR #1016] [MERGED] chore: version packages
Opened
#1021 [PR #1015] [MERGED] propagate retrieval metadata to retrieved nodes
Opened
#1022 [PR #1021] [CLOSED] Implement llama cloud testing utilities and tests
Opened
#1023 [PR #1017] [MERGED] Add notebook for tabular extraction
Opened
#1024 [PR #1022] build(deps): bump actions/checkout from 5 to 6
Opened
#1025 [PR #1023] [MERGED] Implement test plan and create mocked tests
Opened
#1026 [PR #1024] [CLOSED] add fake llama cloud server
Opened
#1027 [PR #1027] [MERGED] Pierre/more parse parameters
Opened
#1028 [PR #1028] [MERGED] feat: add mocking for agent data
Opened
#1029 [PR #1025] [MERGED] chore: version packages
Opened
#1030 [PR #1031] [MERGED] Add timeouts to E2E GHA
Opened
#1031 [PR #1032] [MERGED] Fix sheets API client
Opened
#1032 [PR #1035] [MERGED] chore: version packages
Opened
#1033 [PR #1036] [MERGED] Dummy release
Opened
#1034 [PR #1034] [MERGED] No more presigned URLs by default
Opened
#1035 [PR #1037] [MERGED] chore: version packages
Opened
#1036 [PR #1038] [MERGED] line level bbox
Opened
#1037 [PR #1041] [MERGED] chore: version packages
Opened
#1038 [PR #1039] [MERGED] chore: version packages
Opened
#1039 [PR #1040] [MERGED] Bump llama cloud services and parse versions
Opened
#1040 [PR #1042] [MERGED] Add new fields to SpreadsheetParsingConfig and update validation tests
Opened
#1041 [PR #1043] [MERGED] chore: version packages
Opened
#1042 [PR #1052] [MERGED] feat: support zod v4 & v3
Opened
#1043 [PR #1044] [MERGED] docs: Split Example Notebook
Opened
#1044 [PR #1051] [MERGED] batch parse sctript with asyncio
Opened
#1045 [PR #1045] [MERGED] add tier/version to api
Opened
#1046 [PR #1046] [MERGED] chore: version packages
Opened
#1047 [PR #1053] [MERGED] improve parse ts polling
Opened
#1048 [PR #1054] [MERGED] chore: version packages
Opened
#1049 [PR #1056] [MERGED] docs: correct links in readme
Opened
#1050 [PR #1057] [MERGED] Remove generate from build path to fix publishing
Opened
#1051 [PR #1058] [MERGED] chore: version packages
Opened
#1052 [PR #1065] [MERGED] add notice (don't merge until ready)
Opened
#1053 [PR #1067] [MERGED] Parse bounding boxes from extract jobs results in agent data
Opened
#1054 [PR #1066] [MERGED] fix: bug fix retry logic in Classify and Extract
Opened
#1055 [PR #1068] [MERGED] chore: version packages
Opened
#1056 [PR #1069] [MERGED] Add bounding box type support to TS too
Opened
#1057 [PR #1070] [MERGED] forgot ts changeset
Opened
#1058 [PR #1071] [MERGED] chore: version packages
Opened
#1059 [PR #1073] [MERGED] chore: version packages
Opened
#1060 [PR #1074] [CLOSED] Pierre/allow not ext files
Opened
#1061 [PR #1075] [MERGED] remove extension filter
Opened
#1062 [PR #1076] [MERGED] chore: version packages
Opened
#1063 [PR #1086] [MERGED] Bump up patch version for python packages
Opened
#1064 [PR #1082] [CLOSED] chore: version packages
Opened
#1065 [PR #1081] [MERGED] Use error description in invalid extraction error
Opened
#1066 [PR #1085] [MERGED] Bump up minor version for python packages
Opened
#1067 [PR #1087] [MERGED] chore: version packages
Opened
#1068 [PR #1088] fix: change ImageItem original_width/height type from int to float
Opened
#1069 [PR #1089] [MERGED] Run hourly extract tests to catch SDK schema drifts
Opened
#1070 [PR #1090] [MERGED] Force github reparse of the workflow
Opened
#1071 [PR #1092] [MERGED] build(deps): bump slackapi/slack-github-action from 1.27.0 to 2.1.1
Opened
#1072 [PR #1093] [MERGED] Try to reparse scheduled workflow
Opened
#1073 [PR #1094] [MERGED] Change cron schedule for hourly extract tests
Opened
#1074 [PR #1096] [MERGED] Fix verbose logging on slack channel
Opened
#1075 [PR #1097] [MERGED] Invalidate cache when running extract tests
Opened
#1076 [PR #1095] [MERGED] Add retries to all extract sdk functions uniformly
Opened
#1077 [PR #1098] [MERGED] Use sonnet when testing premium mode in extract e2e
Opened
#1078 [PR #1101] [MERGED] Use unique filenames when running dist tests
Opened
#1079 [PR #1103] [MERGED] chore: version packages
Opened
#1080 [PR #1110] [MERGED] Lower frequency for e2e tests
Opened
#1081 [PR #1111] [MERGED] more loudly deprecate ancient llama-parse package
Opened
#1082 [PR #1112] [MERGED] chore: version packages
Opened
#1083 [PR #1114] [MERGED] Allows xlsx files in the sdk for extract
Opened
#1084 [PR #1113] [CLOSED] Extract e2e confidence problem
Opened
#1085 [PR #1115] [MERGED] Bump up patch version
Opened
#1086 [PR #1116] [MERGED] chore: version packages