From a1e02c6d57fa0028cc1f900f98ccb735656fb9c7 Mon Sep 17 00:00:00 2001 From: David Chang Date: Thu, 1 Feb 2024 00:17:41 +0800 Subject: [PATCH 1/6] ver Jan31stv7 fixed an error in thunderbird evaluation --- .../thunderbird/030eeff7-b492-4218-b312-701ec99ee0cc.json | 2 +- main.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/evaluation_examples/examples/thunderbird/030eeff7-b492-4218-b312-701ec99ee0cc.json b/evaluation_examples/examples/thunderbird/030eeff7-b492-4218-b312-701ec99ee0cc.json index a419f69..b169b6b 100644 --- a/evaluation_examples/examples/thunderbird/030eeff7-b492-4218-b312-701ec99ee0cc.json +++ b/evaluation_examples/examples/thunderbird/030eeff7-b492-4218-b312-701ec99ee0cc.json @@ -68,7 +68,7 @@ "expected": { "type": "rule", "rules": { - "unexpect": { + "expect": { "mail.identity.id1.auto_quote": { "method": "eq", "ref": false diff --git a/main.py b/main.py index ce7ee30..543c851 100644 --- a/main.py +++ b/main.py @@ -47,7 +47,7 @@ def human_agent(): Runs the Gym environment with human input. """ - with open("evaluation_examples/examples/libreoffice_calc/4f07fbe9-70de-4927-a4d5-bb28bc12c52c.json", "r") as f: + with open("evaluation_examples/examples/thunderbird/030eeff7-b492-4218-b312-701ec99ee0cc.json", "r") as f: example = json.load(f) example["snapshot"] = "Snapshot 30" From 5d436a6b66f9230d64875ad8c1886f9ab9ced7ed Mon Sep 17 00:00:00 2001 From: David Chang Date: Thu, 1 Feb 2024 11:38:46 +0800 Subject: [PATCH 2/6] ver Feb1st human evaluation and SoM experiments on Thunderbird --- .../06fe7178-4491-4589-810f-2e2bc9502122.json | 2 +- .../2ad9387a-65d8-4e33-ad5b-7580065a27ca.json | 2 +- experiment_screenshot_som.py | 22 ++++++++++++++++--- main.py | 2 +- mm_agents/gpt_4v_agent.py | 19 ++++++++++------ 5 files changed, 34 insertions(+), 13 deletions(-) diff --git a/evaluation_examples/examples/thunderbird/06fe7178-4491-4589-810f-2e2bc9502122.json b/evaluation_examples/examples/thunderbird/06fe7178-4491-4589-810f-2e2bc9502122.json index 733a831..5a51bc8 100644 --- a/evaluation_examples/examples/thunderbird/06fe7178-4491-4589-810f-2e2bc9502122.json +++ b/evaluation_examples/examples/thunderbird/06fe7178-4491-4589-810f-2e2bc9502122.json @@ -1,7 +1,7 @@ { "id": "06fe7178-4491-4589-810f-2e2bc9502122", "snapshot": "thunderbird", - "instruction": "Could you help me back up all the email files in my profile to ~/emails.bak? Please save them separately in eml format.", + "instruction": "Could you help me back up all the email files in my inbox to ~/emails.bak? Please save them separately in eml format.", "source": "https://www.quora.com/How-do-I-backup-email-files-in-Mozilla-Thunderbird", "config": [ { diff --git a/evaluation_examples/examples/thunderbird/2ad9387a-65d8-4e33-ad5b-7580065a27ca.json b/evaluation_examples/examples/thunderbird/2ad9387a-65d8-4e33-ad5b-7580065a27ca.json index 6b89f31..f8e17ec 100644 --- a/evaluation_examples/examples/thunderbird/2ad9387a-65d8-4e33-ad5b-7580065a27ca.json +++ b/evaluation_examples/examples/thunderbird/2ad9387a-65d8-4e33-ad5b-7580065a27ca.json @@ -1,7 +1,7 @@ { "id": "2ad9387a-65d8-4e33-ad5b-7580065a27ca", "snapshot": "thunderbird", - "instruction": "Create two local folders for me: COMPANY and UNIVERSITY.", + "instruction": "Create two local folders in Thunderbird for me: COMPANY and UNIVERSITY.", "source": "https://support.mozilla.org/bm/questions/1027435", "config": [ { diff --git a/experiment_screenshot_som.py b/experiment_screenshot_som.py index 24f8fd7..5cddff7 100644 --- a/experiment_screenshot_som.py +++ b/experiment_screenshot_som.py @@ -46,7 +46,7 @@ logger = logging.getLogger("desktopenv.experiment") #PATH_TO_VM = r"C:\Users\tianbaox\Documents\Virtual Machines\Ubuntu\Ubuntu.vmx" -PATH_TO_VM = "../../../../大文件/镜像/Ubuntu-1218/Ubuntu/Ubuntu.vmx" +PATH_TO_VM = "/mnt/data1/david/os-images/Ubuntu-1218/Ubuntu.vmx" def run_one_example(example, agent, max_steps=10, example_trajectory_dir="exp_trajectory", recording=True): trajectory_recording_path = os.path.join(example_trajectory_dir, "trajectory.json") @@ -198,6 +198,22 @@ if __name__ == '__main__': , "aa3a8974-2e85-438b-b29e-a64df44deb4b" , "a01fbce3-2793-461f-ab86-43680ccbae25" , "4f07fbe9-70de-4927-a4d5-bb28bc12c52c" + # 42, ^ calc, v thunderbird + , "bb5e4c0d-f964-439c-97b6-bdb9747de3f4" + , "7b6c7e24-c58a-49fc-a5bb-d57b80e5b4c3" + , "12086550-11c0-466b-b367-1d9e75b3910e" + , "06fe7178-4491-4589-810f-2e2bc9502122" + , "6766f2b8-8a72-417f-a9e5-56fcaa735837" + , "e1e75309-3ddb-4d09-92ec-de869c928143" + , "3d1682a7-0fb0-49ae-a4dc-a73afd2d06d5" + , "35253b65-1c19-4304-8aa4-6884b8218fc0" + , "d088f539-cab4-4f9a-ac92-9999fc3a656e" + , "2ad9387a-65d8-4e33-ad5b-7580065a27ca" + , "480bcfea-d68f-4aaa-a0a9-2589ef319381" + , "030eeff7-b492-4218-b312-701ec99ee0cc" + , "94760984-3ff5-41ee-8347-cf1af709fea0" + , "99146c54-4f37-4ab8-9327-5f3291665e1e" + , "c9e7eaf2-b1a1-4efc-a982-721972fa9f02" ] - for example_id in xx_list[18:]: - main("libreoffice_calc", example_id) + for example_id in xx_list[42:]: + main("thunderbird", example_id) diff --git a/main.py b/main.py index 543c851..627ed5f 100644 --- a/main.py +++ b/main.py @@ -47,7 +47,7 @@ def human_agent(): Runs the Gym environment with human input. """ - with open("evaluation_examples/examples/thunderbird/030eeff7-b492-4218-b312-701ec99ee0cc.json", "r") as f: + with open("evaluation_examples/examples/thunderbird/c9e7eaf2-b1a1-4efc-a982-721972fa9f02.json", "r") as f: example = json.load(f) example["snapshot"] = "Snapshot 30" diff --git a/mm_agents/gpt_4v_agent.py b/mm_agents/gpt_4v_agent.py index 0dd15cf..9810eff 100644 --- a/mm_agents/gpt_4v_agent.py +++ b/mm_agents/gpt_4v_agent.py @@ -460,14 +460,18 @@ class GPT4v_Agent: with open("messages.json", "w") as f: f.write(json.dumps(messages, indent=4)) - response = self.call_llm({ - "model": self.model, - "messages": messages, - "max_tokens": self.max_tokens - }) + try: + response = self.call_llm({ + "model": self.model, + "messages": messages, + "max_tokens": self.max_tokens + }) + except: + response = "" logger.debug("RESPONSE: %s", response) + # {{{ if self.exp == "seeact": messages.append({ "role": "assistant", @@ -503,7 +507,7 @@ class GPT4v_Agent: except Exception as e: print("Failed to parse action from response", e) actions = None - self.thoughts.append("") + self.thoughts.append("") # }}} return actions @@ -516,7 +520,8 @@ class GPT4v_Agent: response = requests.post( "https://api.openai.com/v1/chat/completions", headers=self.headers, - json=payload + json=payload, + timeout=20 ) if response.status_code != 200: From ee851aeb543174ce791d1073daaf13d26f0440b7 Mon Sep 17 00:00:00 2001 From: tsuky_chen <91684733+chenjix@users.noreply.github.com> Date: Thu, 1 Feb 2024 16:09:24 +0800 Subject: [PATCH 3/6] Update 0cecd4f3-74de-457b-ba94-29ad6b5dafb6.json --- .../libreoffice_calc/0cecd4f3-74de-457b-ba94-29ad6b5dafb6.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/evaluation_examples/examples/libreoffice_calc/0cecd4f3-74de-457b-ba94-29ad6b5dafb6.json b/evaluation_examples/examples/libreoffice_calc/0cecd4f3-74de-457b-ba94-29ad6b5dafb6.json index 97ad2a1..56ba374 100644 --- a/evaluation_examples/examples/libreoffice_calc/0cecd4f3-74de-457b-ba94-29ad6b5dafb6.json +++ b/evaluation_examples/examples/libreoffice_calc/0cecd4f3-74de-457b-ba94-29ad6b5dafb6.json @@ -1,7 +1,7 @@ { "id": "0cecd4f3-74de-457b-ba94-29ad6b5dafb6", "snapshot": "libreoffice_calc", - "instruction": "Rename \"Sheet 1\" to \"LARS Resources\". Then make a copy of it. Place the copy before \"Sheet 2\" and rename it by appending a suffix \"(Backup)\", concatenated by a which space. And Also rename \"Sheet2\" by appending the suffix \"(Offline)\".", + "instruction": "Rename \"Sheet 1\" to \"LARS Resources\". Then make a copy of it. Place the copy before \"Sheet 2\" and rename it by appending a suffix \"(Backup)\", concatenated by a white space. And Also rename \"Sheet2\" by appending the suffix \"(Offline)\".", "source": "https://www.libreofficehelp.com/add-insert-delete-copy-move-rename-a-worksheet-in-libreoffice-calc/", "config": [ { From 62f50cdc26ceb67600806a38a0497f8a9c4eedaa Mon Sep 17 00:00:00 2001 From: tsuky_chen <91684733+chenjix@users.noreply.github.com> Date: Thu, 1 Feb 2024 16:10:47 +0800 Subject: [PATCH 4/6] Update 7a4e4bc8-922c-4c84-865c-25ba34136be1.json --- .../libreoffice_calc/7a4e4bc8-922c-4c84-865c-25ba34136be1.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/evaluation_examples/examples/libreoffice_calc/7a4e4bc8-922c-4c84-865c-25ba34136be1.json b/evaluation_examples/examples/libreoffice_calc/7a4e4bc8-922c-4c84-865c-25ba34136be1.json index 99133d0..58857fa 100644 --- a/evaluation_examples/examples/libreoffice_calc/7a4e4bc8-922c-4c84-865c-25ba34136be1.json +++ b/evaluation_examples/examples/libreoffice_calc/7a4e4bc8-922c-4c84-865c-25ba34136be1.json @@ -1,7 +1,7 @@ { "id": "7a4e4bc8-922c-4c84-865c-25ba34136be1", "snapshot": "libreoffice_calc", - "instruction": "Reorder the columns to be \"Data\", \"First Name\", \"Last Name\", \"Order ID\", \"Sales\"", + "instruction": "Reorder the columns to be \"Date\", \"First Name\", \"Last Name\", \"Order ID\", \"Sales\"", "source": "https://www.youtube.com/shorts/bvUhr1AHs44", "config": [ { From 660cbe908153a40876bd611547eedc6b1f3c29b7 Mon Sep 17 00:00:00 2001 From: rhythmcao Date: Thu, 1 Feb 2024 16:21:19 +0800 Subject: [PATCH 5/6] expert human test for multi-app finished, fix some small issues --- .../46407397-a7d5-4c6b-92c6-dbe038b1457b.json | 2 +- .../897e3b53-5d4d-444b-85cb-2cdc8a97d903.json | 2 +- .../b52b40a5-ad70-4c53-b5b0-5650a8387052.json | 14 +++++++------- .../settings/googledrive/credentials.json | 2 +- 4 files changed, 10 insertions(+), 10 deletions(-) diff --git a/evaluation_examples/examples/multi_apps/46407397-a7d5-4c6b-92c6-dbe038b1457b.json b/evaluation_examples/examples/multi_apps/46407397-a7d5-4c6b-92c6-dbe038b1457b.json index f4fd1bf..db41601 100644 --- a/evaluation_examples/examples/multi_apps/46407397-a7d5-4c6b-92c6-dbe038b1457b.json +++ b/evaluation_examples/examples/multi_apps/46407397-a7d5-4c6b-92c6-dbe038b1457b.json @@ -68,7 +68,7 @@ "parameters": { "command": [ "tar", - "-xzv", + "-xz", "--recursive-unlink", "-f", "/home/user/thunderbird-profile.tar.gz", diff --git a/evaluation_examples/examples/multi_apps/897e3b53-5d4d-444b-85cb-2cdc8a97d903.json b/evaluation_examples/examples/multi_apps/897e3b53-5d4d-444b-85cb-2cdc8a97d903.json index 9da5cc0..6417237 100644 --- a/evaluation_examples/examples/multi_apps/897e3b53-5d4d-444b-85cb-2cdc8a97d903.json +++ b/evaluation_examples/examples/multi_apps/897e3b53-5d4d-444b-85cb-2cdc8a97d903.json @@ -1,7 +1,7 @@ { "id": "897e3b53-5d4d-444b-85cb-2cdc8a97d903", "snapshot": "chrome", - "instruction": "I have a LibreOffice Writer file form.docx on the desktop. Help me convert it to PDF format and store it in the forms/ folder in my Google Drive.", + "instruction": "I have a LibreOffice Writer file form.docx on the desktop. Help me convert it to PDF format and store the PDF in the forms/ folder in my Google Drive.", "source": "https://marketplace.uipath.com/listings/convert-word-file-to-pdf-and-store-in-onedrive", "config": [ { diff --git a/evaluation_examples/examples/multi_apps/b52b40a5-ad70-4c53-b5b0-5650a8387052.json b/evaluation_examples/examples/multi_apps/b52b40a5-ad70-4c53-b5b0-5650a8387052.json index 25b9024..e9e879d 100644 --- a/evaluation_examples/examples/multi_apps/b52b40a5-ad70-4c53-b5b0-5650a8387052.json +++ b/evaluation_examples/examples/multi_apps/b52b40a5-ad70-4c53-b5b0-5650a8387052.json @@ -68,13 +68,13 @@ "type": "execute", "parameters": { "command": [ - "tar", - "-xzv", - "--recursive-unlink", - "-f", - "/home/user/thunderbird-profile.tar.gz", - "-C", - "/home/user/" + "tar", + "-xz", + "--recursive-unlink", + "-f", + "/home/user/thunderbird-profile.tar.gz", + "-C", + "/home/user/" ] } }, diff --git a/evaluation_examples/settings/googledrive/credentials.json b/evaluation_examples/settings/googledrive/credentials.json index 1be4912..34d7be4 100644 --- a/evaluation_examples/settings/googledrive/credentials.json +++ b/evaluation_examples/settings/googledrive/credentials.json @@ -1 +1 @@ -{"access_token": "ya29.a0AfB_byAZmDTDsYds_iatV8a30PUPWcDHVW4Cyg71pTlD0f3eBBwAjV4WpVL8LdAle8sT4j_rX4rWH8iCt3QI2YdrQLFPlaVdBk0zRGGtAEcebIDuQy_VKD6j5c3IGxok9PDON-Mft0ZVJjUVEopgLYA4fYwctbQZ8nyl4AaCgYKAX4SARISFQHGX2Mim-LRNXCfACmecJH94-D09A0173", "client_id": "786888752612-rgng5v9hcq4as7pn0b40gt9r5lekmht9.apps.googleusercontent.com", "client_secret": "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", "refresh_token": "1//0ehtafHmucszRCgYIARAAGA4SNwF-L9IrpDBsnzdHKAlRfrkvzNFw1cpdnRY8rhM5gy4flsPYdysMav27yHamJx39BBGq-LLw40s", "token_expiry": "2024-01-31T14:41:25Z", "token_uri": "https://oauth2.googleapis.com/token", "user_agent": null, "revoke_uri": "https://oauth2.googleapis.com/revoke", "id_token": null, "id_token_jwt": null, "token_response": {"access_token": "ya29.a0AfB_byAZmDTDsYds_iatV8a30PUPWcDHVW4Cyg71pTlD0f3eBBwAjV4WpVL8LdAle8sT4j_rX4rWH8iCt3QI2YdrQLFPlaVdBk0zRGGtAEcebIDuQy_VKD6j5c3IGxok9PDON-Mft0ZVJjUVEopgLYA4fYwctbQZ8nyl4AaCgYKAX4SARISFQHGX2Mim-LRNXCfACmecJH94-D09A0173", "expires_in": 3599, "scope": "https://www.googleapis.com/auth/drive", "token_type": "Bearer"}, "scopes": ["https://www.googleapis.com/auth/drive"], "token_info_uri": "https://oauth2.googleapis.com/tokeninfo", "invalid": false, "_class": "OAuth2Credentials", "_module": "oauth2client.client"} \ No newline at end of file +{"access_token": "ya29.a0AfB_byD2_A8RPm6KzfjaNifjfgZ2M-D9G16GAPIj1ANxM3AMq4DLUXxj76CalsByOsqTUgEvADd-FEKL0FkBBc4ow-EuaLUEOm4yw2LNEOFMhVD_k4PvEIf4767fYU5o__GtyrGt5pNJy0MaBukDY2ui7GQwDuFFGt2q_AaCgYKAYMSARISFQHGX2MidvFUuBpNsy4fkC5DP2k8Aw0173", "client_id": "786888752612-rgng5v9hcq4as7pn0b40gt9r5lekmht9.apps.googleusercontent.com", "client_secret": "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", "refresh_token": "1//0ehtafHmucszRCgYIARAAGA4SNwF-L9IrpDBsnzdHKAlRfrkvzNFw1cpdnRY8rhM5gy4flsPYdysMav27yHamJx39BBGq-LLw40s", "token_expiry": "2024-02-01T08:29:08Z", "token_uri": "https://oauth2.googleapis.com/token", "user_agent": null, "revoke_uri": "https://oauth2.googleapis.com/revoke", "id_token": null, "id_token_jwt": null, "token_response": {"access_token": "ya29.a0AfB_byD2_A8RPm6KzfjaNifjfgZ2M-D9G16GAPIj1ANxM3AMq4DLUXxj76CalsByOsqTUgEvADd-FEKL0FkBBc4ow-EuaLUEOm4yw2LNEOFMhVD_k4PvEIf4767fYU5o__GtyrGt5pNJy0MaBukDY2ui7GQwDuFFGt2q_AaCgYKAYMSARISFQHGX2MidvFUuBpNsy4fkC5DP2k8Aw0173", "expires_in": 3599, "scope": "https://www.googleapis.com/auth/drive", "token_type": "Bearer"}, "scopes": ["https://www.googleapis.com/auth/drive"], "token_info_uri": "https://oauth2.googleapis.com/tokeninfo", "invalid": false, "_class": "OAuth2Credentials", "_module": "oauth2client.client"} \ No newline at end of file From fe21c4753390ebbbdde8bbec084ed228e5ea657e Mon Sep 17 00:00:00 2001 From: BlankCheng <913501223@qq.com> Date: Thu, 1 Feb 2024 16:27:24 +0800 Subject: [PATCH 6/6] Fix samples of Impress and OS --- .../21760ecb-8f62-40d2-8d85-0cee5725cb72.json | 2 +- .../5d901039-a89c-4bfb-967b-bf66f4df075e.json | 2 +- .../9ec204e4-f0a3-42f8-8458-b772a6797cab.json | 2 +- .../af23762e-2bfd-4a1d-aada-20fa8de9ce07.json | 4 ++-- .../examples/os/7688b85f-87a4-4e4a-b2f8-f3d6c3f29b82.json | 2 +- .../examples/os/bedcedc4-4d72-425e-ad62-21960b11fe0d.json | 2 +- 6 files changed, 7 insertions(+), 7 deletions(-) diff --git a/evaluation_examples/examples/libreoffice_impress/21760ecb-8f62-40d2-8d85-0cee5725cb72.json b/evaluation_examples/examples/libreoffice_impress/21760ecb-8f62-40d2-8d85-0cee5725cb72.json index 70bd696..173c5ac 100644 --- a/evaluation_examples/examples/libreoffice_impress/21760ecb-8f62-40d2-8d85-0cee5725cb72.json +++ b/evaluation_examples/examples/libreoffice_impress/21760ecb-8f62-40d2-8d85-0cee5725cb72.json @@ -1,7 +1,7 @@ { "id": "21760ecb-8f62-40d2-8d85-0cee5725cb72", "snapshot": "libreoffice_impress", - "instruction": "Could you help me add silde transition \"dissolve\" to my first page?", + "instruction": "Could you help me add slide transition \"dissolve\" to my first page?", "source": "https://www.libreofficehelp.com/add-animations-transitions-libreoffice-impress-slides/", "config": [ { diff --git a/evaluation_examples/examples/libreoffice_impress/5d901039-a89c-4bfb-967b-bf66f4df075e.json b/evaluation_examples/examples/libreoffice_impress/5d901039-a89c-4bfb-967b-bf66f4df075e.json index 03daf6c..9c4f050 100644 --- a/evaluation_examples/examples/libreoffice_impress/5d901039-a89c-4bfb-967b-bf66f4df075e.json +++ b/evaluation_examples/examples/libreoffice_impress/5d901039-a89c-4bfb-967b-bf66f4df075e.json @@ -1,7 +1,7 @@ { "id": "5d901039-a89c-4bfb-967b-bf66f4df075e", "snapshot": "libreoffice_impress", - "instruction": "I want to make this page my cover page. Could you help me stretch this image to fill the entire page, keeping its proportion and centering the image.", + "instruction": "I want to turn the rectangular image of Columbus on the first page into a cover page. Could you help me stretch this image to fill the entire page, keeping its proportion and centering the image?", "source": "https://superuser.com/questions/986776/how-can-i-stretch-an-image-in-a-libreoffice-impress-presentation-to-fill-the-pag", "config": [ { diff --git a/evaluation_examples/examples/libreoffice_impress/9ec204e4-f0a3-42f8-8458-b772a6797cab.json b/evaluation_examples/examples/libreoffice_impress/9ec204e4-f0a3-42f8-8458-b772a6797cab.json index 7c85a91..07be4b5 100644 --- a/evaluation_examples/examples/libreoffice_impress/9ec204e4-f0a3-42f8-8458-b772a6797cab.json +++ b/evaluation_examples/examples/libreoffice_impress/9ec204e4-f0a3-42f8-8458-b772a6797cab.json @@ -62,7 +62,7 @@ "expected": { "type": "cloud_file", "path": "https://drive.usercontent.google.com/download?id=1otbzscpOZ0tCXMvsMC0MmNWUC7Pv71of&export=download&authuser=0&confirm=t&uuid=faa0b0c1-6b14-4bce-a1fd-ccf824ee1e60&at=APZUnTXw6TlBOlrPPZ2OhfGnNPf0:1705338135842", - "dest": "MLA_Workshop_061X_Works_Cited_Gold.docx" + "dest": "MLA_Workshop_061X_Works_Cited_Gold.pptx" }, "result": { "type": "vm_file", diff --git a/evaluation_examples/examples/libreoffice_impress/af23762e-2bfd-4a1d-aada-20fa8de9ce07.json b/evaluation_examples/examples/libreoffice_impress/af23762e-2bfd-4a1d-aada-20fa8de9ce07.json index 8ca8792..e93015a 100644 --- a/evaluation_examples/examples/libreoffice_impress/af23762e-2bfd-4a1d-aada-20fa8de9ce07.json +++ b/evaluation_examples/examples/libreoffice_impress/af23762e-2bfd-4a1d-aada-20fa8de9ce07.json @@ -2,7 +2,7 @@ "id": "af23762e-2bfd-4a1d-aada-20fa8de9ce07", "snapshot": "libreoffice_impress", "instruction": "I am making PPT on LibreOffice Impress for presentation tomorrow. I need to summarize contents on one slide use Impress \"Summary Slide\" feature. Could you make that for me?", - "source": "https://www.libreofficehelp.com/export-libreoffice-impress-slides-images/#:~:text=Exporting%20a%20single%20slide%20as.jpg%2C.png%2C%20etc%20image%20is,on%20the%20checkbox%20Selection.%20Provide%20jpg%20quality%20options.", + "source": "https://superuser.com/questions/1059080/how-to-make-a-summary-slide-in-impress-listing-the-titles-of-all-slides-autom", "config": [ { "type": "download", @@ -62,7 +62,7 @@ "expected": { "type": "cloud_file", "path": "https://drive.usercontent.google.com/download?id=1nRwmFgYdskv3EiriZZFoT8TzM9CsG5B0&export=download&authuser=0&confirm=t&uuid=f2f919df-2867-4bc3-8bb9-dabd51108ebb&at=APZUnTWzw9LJWWXvH0cvdaWL-Ij-:1705319339474", - "dest": "Forests_Gold.docx" + "dest": "Forests_Gold.pptx" }, "result": { "type": "vm_file", diff --git a/evaluation_examples/examples/os/7688b85f-87a4-4e4a-b2f8-f3d6c3f29b82.json b/evaluation_examples/examples/os/7688b85f-87a4-4e4a-b2f8-f3d6c3f29b82.json index da8f5c4..2c0d1d1 100644 --- a/evaluation_examples/examples/os/7688b85f-87a4-4e4a-b2f8-f3d6c3f29b82.json +++ b/evaluation_examples/examples/os/7688b85f-87a4-4e4a-b2f8-f3d6c3f29b82.json @@ -1,7 +1,7 @@ { "id": "7688b85f-87a4-4e4a-b2f8-f3d6c3f29b82", "snapshot": "os", - "instruction": "Can you move the file with the path 'todo.txt' on the Desktop to the directory with the path 'done' on the Desktop?", + "instruction": "Can you move the file 'todo.txt' on the Desktop to the directory 'done/' on the Desktop?", "source": "https://ubuntu.com/tutorials/command-line-for-beginners#5-moving-and-manipulating-files", "config": [ { diff --git a/evaluation_examples/examples/os/bedcedc4-4d72-425e-ad62-21960b11fe0d.json b/evaluation_examples/examples/os/bedcedc4-4d72-425e-ad62-21960b11fe0d.json index 6c67c0c..97e8545 100644 --- a/evaluation_examples/examples/os/bedcedc4-4d72-425e-ad62-21960b11fe0d.json +++ b/evaluation_examples/examples/os/bedcedc4-4d72-425e-ad62-21960b11fe0d.json @@ -1,7 +1,7 @@ { "id": "bedcedc4-4d72-425e-ad62-21960b11fe0d", "snapshot": "os", - "instruction": "Could you set the 'Dim screen when inactive' to on in setting?", + "instruction": "Could you set the 'Dim screen when inactive' to off in setting?", "source": "https://www.youtube.com/watch?v=D4WyNjt_hbQ&t=2s", "trajectory": "trajectories/", "config": [