lzy/sci-gui-agent-benchmark
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add eval libreoffice writer compare table & equation

Browse Source
This commit is contained in:
tsuky_chen
2023-12-31 01:02:27 +08:00
parent 0fc81d951b
commit c937e31b18
7 changed files with 197 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
evaluation_examples/examples/libreoffice_writer/0810415c-bde4-4443-9047-d5f70165a697.json
View File

@@ -3,10 +3,40 @@
"snapshot": "libreoffice_writer",
"instruction": "Make the line spacing of first two paragraph into double line spacing",
"source": "https://www.youtube.com/watch?v=Q_AaL6ljudU",
"config": [],
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?export=download&id=1u7y8cUXqe-QzNX3YaPpZKYyphwv5IjHF_O5TjMnqvS4",
"path": "Desktop/Double_Line_Spacing.docx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "Desktop/Double_Line_Spacing.docx"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"libreoffice_writer"
],
"evaluator": "evaluation_dir"
}
"evaluator": {
"func": "compare_line_spacing",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?export=download&id=1D8_1WItMwyWkUPodohUKevIORE4pDw3C",
"dest": "Double_Line_Spacing_Gold.docx"
},
"result": {
"type": "vm_file",
"path": "Desktop/Double_Line_Spacing.docx",
"dest": "Double_Line_Spacing.docx"
}
}
}

36
evaluation_examples/examples/libreoffice_writer/663876c7-3471-43db-ba51-f410b13d9d7d.json
View File

@@ -3,10 +3,40 @@
"snapshot": "libreoffice_writer",
"instruction": "Insert the equation \"(a + b)^2 = a^2 + 2 a b + b^2\"",
"source": "https://askubuntu.com/questions/319593/how-to-type-science-equations-in-libre-office",
"config": [],
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://docs.google.com/document/d/1ui9Kerbgm4oT_8sE7C_t2DJN9F6_ovu2o3zvY0Ro56Q/edit?usp=drive_link",
"path": "Desktop/Insert_Equation.docx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "Desktop/Insert_Equation.docx"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"libreoffice_writer"
],
"evaluator": "evaluation_dir"
}
"evaluator": {
"func": "compare_insert_equation",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?export=download&id=1mbaglsw_xrVXJT8aNkuMQ9cTUh9Xhv9V",
"dest": "Insert_Equation_Gold.docx"
},
"result": {
"type": "vm_file",
"path": "Desktop/Insert_Equation.docx",
"dest": "Insert_Equation.docx"
}
}
}

36
evaluation_examples/examples/libreoffice_writer/66399b0d-8fda-4618-95c4-bfc6191617e9.json
View File

@@ -3,10 +3,40 @@
"snapshot": "libreoffice_writer",
"instruction": "Insert a 7*5 empty table",
"source": "https://www.youtube.com/watch?v=l25Evu4ohKg",
"config": [],
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?export=download&id=1fl11qfMJ3Z7TTY3leaTpofkOKY8FhoklkxOK_vIx_J0",
"path": "Desktop/Insert_Empty_Table.docx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "Desktop/Insert_Empty_Table.docx"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"libreoffice_writer"
],
"evaluator": "evaluation_dir"
}
"evaluator": {
"func": "compare_docx_tables",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?export=download&id=1i8WGOU1EM1NwoVPwFuLltoeS8uKn1j3bUVPeA4bwTO0",
"dest": "Insert_Empty_Table_Gold.docx"
},
"result": {
"type": "vm_file",
"path": "Desktop/Insert_Empty_Table.docx",
"dest": "Insert_Empty_Table.docx"
}
}
}

36
evaluation_examples/examples/libreoffice_writer/936321ce-5236-426a-9a20-e0e3c5dc536f.json
View File

@@ -3,10 +3,40 @@
"snapshot": "libreoffice_writer",
"instruction": "Convert the content seperated by commas to a table",
"source": "https://www.youtube.com/watch?v=l25Evu4ohKg",
"config": [],
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?export=download&id=1bLaEmCfVoHzi51-i66O-YRIJv0xW66irXf0pmyT5B8E",
"path": "Desktop/Convert_Text_To_Table.docx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "Desktop/Convert_Text_To_Table.docx"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"libreoffice_writer"
],
"evaluator": "evaluation_dir"
}
"evaluator": {
"func": "compare_docx_tables",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?export=download&id=1DY7J6xtnLCUa8lsAXjdY9VK1XxrbXE6G",
"dest": "Convert_Text_To_Table_Gold.docx"
},
"result": {
"type": "vm_file",
"path": "Desktop/Convert_Text_To_Table.docx",
"dest": "Convert_Text_To_Table.docx"
}
}
}

6
evaluation_examples/examples/libreoffice_writer/adf5e2c3-64c7-4644-b7b6-d2f0167927e7.json
View File

@@ -1,7 +1,7 @@
{
"id": "adf5e2c3-64c7-4644-b7b6-d2f0167927e7",
"snapshot": "libreoffice_writer",
"instruction": "Helping me adding CITATION_TEXT to my reference list, and add a cross reference after the word \"WHERE_WE_ADD_REFERENCE\"",
"instruction": "Helping me adding CITATION_TEXT:\"C. Luo and M. J. Carey, \"LSM-based storage techniques: a survey,\" The VLDB Journal, vol. 29, no. 1, pp. 393–418, 2020.\" to my reference list, and add a cross reference after the word \"WHERE_WE_ADD_REFERENCE\"",
"source": "https://seekstar.github.io/2022/04/11/libreoffice%E5%BC%95%E7%94%A8%E6%96%87%E7%8C%AE/",
"config": [
{
@@ -9,7 +9,7 @@
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?export=download&id=1boNZ3JuqUx2apMqExL3UX9A4Sopi77ke7yKnIO3cpbg",
"url": "https://doc-00-20-docstext.googleusercontent.com/export/hglu5spf1pl3kjo47q5hl516lk/fm9rfictm643s722v6huocv1t8/1703936520000/108888117743638485671/108888117743638485671/1boNZ3JuqUx2apMqExL3UX9A4Sopi77ke7yKnIO3cpbg?format=docx&dat=AOBvIb0aOSBJsn7KXrdM4-kYvBzstZwFeJ04cq3PPIlMtRwz8ONEDNFmGVQ6yTj9QF89iCgMY5Nrtyqmuh1DgCncJKWadsXRe0pwDkP-LFXnU3sQ4j4h1Cx-DscnonNv53syeLZLiKiQI2BeqxQ8_3dji3UDwAqoSue5xteFhWh4D8yNWdfAYDP8frGmEUm92DegHuvzRaLLJt2HWSvyTt9ZhZfX_0ome1hqdE89bYpdzS2Z9K7Cke2YushT1KPR0BO51ZX5MXyuppdS6uJ5ZX0S6yoJ5XUIXl2uQgUeV0DKvMBhelGrLAs9YdzAw6UvStH5B5Sd91JhFL9LN_1ttWuBYyddJldgf85tYJFRjtQ_sTnfTEC4KZ1eUjU7pFKRVGFJ78jY_BzYYHG-UWL7lkuwtroRp55Fv40sn7ynCUuTgsmiki678_xOGU9_LpP6UU567_29W3KJVfqFBBES3Y3_fIGyLrO081jG8076QNsF4UULcz2u7Q1Jnps1--4XRDa1hIZvGHTUWA6FM9bCWd8Cd9_RFlklYwKa38-PSGdRa5_b8Jz07o1xKyPjfQ6CeMZ5rZ1wzwREc4ZdL4ae7eWUHZsyK9Gd2tLnCfLjeP2sCTGUrFKHtS9k6Vtd-SlorajknLK8V48npAlWzESxDIQcGqHQqfJJKljaH5q2IBKsOPvH8xxfzAEkkI3Kmqasx8NE2BXr8X-f1AXbAb1PvjDOO9TJnhfbgcVm4_5fGl5D0ODoOQZ_g48KpJglaWV3qyBHMFBVEW3Xtr5gRQg5IEVK8zmdMwjmXDDhySOKHCNZDUutKzj0G57cxPVW5TOr93M9zVNh7zeh3iIyyDYAzKw3SnXYGubxFKY6ezcEmNaGfhPSRooKvxgcKBJYFAk",
"path": "Desktop/Add_Citation_Cross_Reference.docx"
}
]
@@ -30,7 +30,7 @@
"func": "compare_docx_files",
"expected": {
"type": "cloud_file",
"path": "https://doc-14-20-docstext.googleusercontent.com/export/hglu5spf1pl3kjo47q5hl516lk/erhjsu6vpod00o7ruf95hlnqkk/1703931360000/108888117743638485671/108888117743638485671/1tiN6A9-zQ2gfDPTWAYK5mv5JbUe2Y_PqPIyuvsu7PgA?format=docx&dat=AOBvIb1uRgycIK4pNup7ZrnJqwNjYOgTUlrhxAc8DnBWzUt9zDxLm3e4s0KQytzQ1qvFZaBr8-ymrVv7Mmb7ovpVk4k8sgS_2MRD1m-tMUDiUEGFtoxrECd4Xoaspuwb-BZttyU1cCdY3U12qcNWy5Cts_uys6ouKZok01Z7s1J233udfrMbXvDt_X-HeNo_7e6Bh64ZC4ohHOKZddsuayKYxPTKpgnho_8FPuWXqZDKyfYRDoTXxGWv-WrZSVqRSHP6GMtBdWc1-QBuWzH_iRTM64joeveSDppMjMeB5bjdJQ7EXf-EjA8MjSxtvQQGBmun7PoZ-W7fLmQ1E3fZKJ5BwQDOIJHDCBar83iHHoXOUJ1Q5UbkKcCS0nJ_pprCzRYXLSeVfN0_bdGuY2lSE8GhX-yGlyGIjAIZK-YulOFXwV0--4aD10rh43A5GLmSLeNZe6maUU33j1V-zUtp1qPgRk3SnPJENNOXf-sOYAvQqSgROSBvAwElqgHUMD_ROK692M7_7OtFe4sjs0eVnBzROEHy-ZznXqdSXJj6-2vloXHWfswPfE-Mq5kc7F1zX4CY6H1kQ-zgHzeLX-qQA6YmgZPJ0pLzFkAkBiMAjPigA_2dy7jk-niePSbZ9DcgYoX6iv6MkJ0y6JE_HQF7Gr6kDBiOjOyDp7gFoMj35F41Fac1wpSJmoiUEGLg0qGRBZ6BPc54m-AAFuy-2s4BUUtPgk-FlTD1jSpHDXLbJ-VQFglx1CYpfqFAnmIE8yseQPh3GqQYyCtCfD-zzO-CRTT9A-XOQVuH27npfk2gMDKtGwJr7XhNL8lL9b8540uTjt9nFnmNfDZCFK01VULdHZesSBedqM4iApgVVnjok8nmYw14e9WSgJOdjeiYAwI",
"path": "https://drive.google.com/uc?export=download&id=1eJSr8J2eiGr6K5n59MGOwY-8dgCPIjYh",
"dest": "Add_Citation_Cross_Reference_Gold.docx"
},
"result": {