Dataset Viewer
Auto-converted to Parquet Duplicate
conversations
listlengths
2
16
images
listlengths
1
3
system
stringclasses
1 value
tools
stringclasses
1 value
id
stringlengths
10
10
[ { "from": "human", "value": "<image>Where is the lake outflow to?" }, { "from": "gpt", "value": "<think>\nThe user is asking about where the lake in the image flows to (its outflow). This is a scenic photograph showing a lake surrounded by dramatic mountains with a golden sunset sky. To answer t...
[ "images/0a/0a9c56ce6af00f62d9980a299bee75fc00b57a8c2131f81f2e36fa00a9f7ba2b.jpg" ]
You are an advanced **Single-Image Visual Investigation Agent**. Your input is one image (handle ``img_1``; occasionally more than one independent ``img_*``) plus a question that requires **web-verifiable** facts. **INPUT FORMAT** - There is **no video handle** and no frame grid. - **Do NOT** call ``select_timespan``...
[ { "type": "function", "function": { "name": "crop", "description": "Crop a rectangular region from an image before image_search. Use this for logos, faces, signs, jersey numbers, scoreboard regions, and other small visual cues.\n\nPREFER bbox_1000 (normalized coordinates) over pixel x/y/w/h: you...
sft-073363
[ { "from": "human", "value": "<image>Which organization released the 2025 economic outlook report for the area shown in the image?" }, { "from": "gpt", "value": "<think>\nThe user is asking about which organization released a 2025 economic outlook report for the area shown in the image. The image...
[ "images/cc/cce48341872d577072246a244851bbec6baa88ef30aff1bac5385e26e54b398f.jpg" ]
You are an advanced **Single-Image Visual Investigation Agent**. Your input is one image (handle ``img_1``; occasionally more than one independent ``img_*``) plus a question that requires **web-verifiable** facts. **INPUT FORMAT** - There is **no video handle** and no frame grid. - **Do NOT** call ``select_timespan``...
[ { "type": "function", "function": { "name": "crop", "description": "Crop a rectangular region from an image before image_search. Use this for logos, faces, signs, jersey numbers, scoreboard regions, and other small visual cues.\n\nPREFER bbox_1000 (normalized coordinates) over pixel x/y/w/h: you...
sft-073364
[ { "from": "human", "value": "<image>What is this type of stone monument called?" }, { "from": "gpt", "value": "<think>\nThe user is asking about the type of stone monument shown in the image. I can see a carved stone monument with decorative elements at the top (including what appears to be a wh...
[ "images/75/7505fd81a811ac57400cae5470cdfc57ffc879723f460364dbd6ae9cb9986668.jpg" ]
You are an advanced **Single-Image Visual Investigation Agent**. Your input is one image (handle ``img_1``; occasionally more than one independent ``img_*``) plus a question that requires **web-verifiable** facts. **INPUT FORMAT** - There is **no video handle** and no frame grid. - **Do NOT** call ``select_timespan``...
[ { "type": "function", "function": { "name": "crop", "description": "Crop a rectangular region from an image before image_search. Use this for logos, faces, signs, jersey numbers, scoreboard regions, and other small visual cues.\n\nPREFER bbox_1000 (normalized coordinates) over pixel x/y/w/h: you...
sft-073365
[ { "from": "human", "value": "<image>Who or what maintains this facility?" }, { "from": "gpt", "value": "<think>\nThe user is asking about who or what maintains this facility. Looking at the image, I can see what appears to be a historic cemetery or necropolis on a hill with various monuments, to...
[ "images/07/07877cbeaedfcd73aea102dac1e930fc139f30be28e745d18f2c0ca82435777b.jpg" ]
You are an advanced **Single-Image Visual Investigation Agent**. Your input is one image (handle ``img_1``; occasionally more than one independent ``img_*``) plus a question that requires **web-verifiable** facts. **INPUT FORMAT** - There is **no video handle** and no frame grid. - **Do NOT** call ``select_timespan``...
[ { "type": "function", "function": { "name": "crop", "description": "Crop a rectangular region from an image before image_search. Use this for logos, faces, signs, jersey numbers, scoreboard regions, and other small visual cues.\n\nPREFER bbox_1000 (normalized coordinates) over pixel x/y/w/h: you...
sft-073366
[ { "from": "human", "value": "<image>Is the population of Egypt in the figure greater than it was in 1990? Answer with “now” or “1990”." }, { "from": "gpt", "value": "<think>\nThe user is asking whether Egypt's population in the figure (2025) is greater than it was in 1990. From the image, I can ...
[ "images/d2/d241034ac4cc16efd62b33f46cbd24c27c6d54853378e042ce435498245b15eb.jpg" ]
You are an advanced **Single-Image Visual Investigation Agent**. Your input is one image (handle ``img_1``; occasionally more than one independent ``img_*``) plus a question that requires **web-verifiable** facts. **INPUT FORMAT** - There is **no video handle** and no frame grid. - **Do NOT** call ``select_timespan``...
[ { "type": "function", "function": { "name": "crop", "description": "Crop a rectangular region from an image before image_search. Use this for logos, faces, signs, jersey numbers, scoreboard regions, and other small visual cues.\n\nPREFER bbox_1000 (normalized coordinates) over pixel x/y/w/h: you...
sft-073367
[{"from":"human","value":"<image>Who is the group in the image known for their influence in culture (...TRUNCATED)
[ "images/5d/5db4d354e79ef631a01bff0029d499e3092dc15066bd9954887cfbc2a0f21a8e.jpg" ]
"\nYou are an advanced **Single-Image Visual Investigation Agent**. Your input is one image\n(handle(...TRUNCATED)
"[\n {\n \"type\": \"function\",\n \"function\": {\n \"name\": \"crop\",\n \"descri(...TRUNCATED)
sft-073368
[{"from":"human","value":"<image>Which organization is holding this conference?"},{"from":"gpt","val(...TRUNCATED)
[ "images/ef/eff3868b9fbb97895c52e4b4151adeeadac5b827bdde787c100888c126025d98.jpg" ]
"\nYou are an advanced **Single-Image Visual Investigation Agent**. Your input is one image\n(handle(...TRUNCATED)
"[\n {\n \"type\": \"function\",\n \"function\": {\n \"name\": \"crop\",\n \"descri(...TRUNCATED)
sft-073369
[{"from":"human","value":"<image>At least how many people were killed by the small plane collision i(...TRUNCATED)
[ "images/46/46632a3e4fac349d7f890db3f9057e7195a18003afdd09aa7f5e4831d2104c9f.jpg" ]
"\nYou are an advanced **Single-Image Visual Investigation Agent**. Your input is one image\n(handle(...TRUNCATED)
"[\n {\n \"type\": \"function\",\n \"function\": {\n \"name\": \"crop\",\n \"descri(...TRUNCATED)
sft-073370
[{"from":"human","value":"<image>Which city or region does this building locate in?"},{"from":"gpt",(...TRUNCATED)
[ "images/da/daf60797a283002e616fbeaf0ea480e517add8f44fe92307ac33f1d384ede828.jpg" ]
"\nYou are an advanced **Single-Image Visual Investigation Agent**. Your input is one image\n(handle(...TRUNCATED)
"[\n {\n \"type\": \"function\",\n \"function\": {\n \"name\": \"crop\",\n \"descri(...TRUNCATED)
sft-073371
[{"from":"human","value":"<image>Who is the manufacturer of this aircraft?"},{"from":"gpt","value":"(...TRUNCATED)
[ "images/c7/c7f8f69dcded550dbec2a80ac1f9fac1f643fd114575e5de45b4fed501667ded.jpg" ]
"\nYou are an advanced **Single-Image Visual Investigation Agent**. Your input is one image\n(handle(...TRUNCATED)
"[\n {\n \"type\": \"function\",\n \"function\": {\n \"name\": \"crop\",\n \"descri(...TRUNCATED)
sft-073372
End of preview. Expand in Data Studio
README.md exists but content is empty.
Downloads last month
-