Find the shot of Earth through a station window
0:47CC-BY-SA-4.0 · مصطفى ملو (Wikimedia Commons user)
Proof frames
Tool calls
build_visual_index
Arguments
{
"source": "$CLIP"
}
Result
{
"ok": true,
"data": {
"status": "queued",
"message": "Repeat the same tool call to poll progress."
}
}
build_visual_index
Arguments
{
"source": "$CLIP"
}
Result
{
"ok": true,
"data": {
"status": "running",
"indexed_until_sec": 0,
"duration_sec": 47,
"frames_indexed": 0,
"progress": 0,
"model": "openai/clip-vit-base-patch32",
"model_revision": "3d74acf9a28c67741b2f4f2ea7635f0aaf6f0268"
}
}
build_visual_index
Arguments
{
"source": "$CLIP"
}
Result
{
"ok": true,
"data": {
"status": "running",
"indexed_until_sec": 0,
"duration_sec": 47,
"frames_indexed": 0,
"progress": 0,
"model": "openai/clip-vit-base-patch32",
"model_revision": "3d74acf9a28c67741b2f4f2ea7635f0aaf6f0268"
}
}
build_visual_index
Arguments
{
"source": "$CLIP"
}
Result
{
"ok": true,
"data": {
"status": "complete",
"indexed_until_sec": 47,
"duration_sec": 47,
"frames_indexed": 47,
"progress": 1,
"model": "openai/clip-vit-base-patch32",
"model_revision": "3d74acf9a28c67741b2f4f2ea7635f0aaf6f0268"
}
}
search_visual
Arguments
{
"source": "$CLIP",
"query": "blue Earth seen through a round window in a space station",
"top_k": 5
}
Result
{
"ok": true,
"data": {
"status": "queued",
"message": "Repeat the same tool call to poll progress."
}
}
search_visual
Arguments
{
"source": "$CLIP",
"query": "blue Earth seen through a round window in a space station",
"top_k": 5
}
Result
{
"ok": true,
"data": {
"status": "complete",
"hits": [
{
"rank": 1,
"timestamp_sec": 30.5,
"timecode": "00:00:30.500",
"score": 0.29230737686157227,
"frame_badge": "#1",
"timestamp_kind": "sample_target",
"decoded_timestamp": null
},
{
"rank": 2,
"timestamp_sec": 31.5,
"timecode": "00:00:31.500",
"score": 0.27490898966789246,
"frame_badge": "#2",
"timestamp_kind": "sample_target",
"decoded_timestamp": null
},
{
"rank": 3,
"timestamp_sec": 32.5,
"timecode": "00:00:32.500",
"score": 0.25770601630210876,
"frame_badge": "#3",
"timestamp_kind": "sample_target",
"decoded_timestamp": null
},
{
"rank": 4,
"timestamp_sec": 10,
"timecode": "00:00:10.000",
"score": 0.15969303250312805,
"frame_badge": "#4",
"timestamp_kind": "sample_target",
"decoded_timestamp": null
},
{
"rank": 5,
"timestamp_sec": 23,
"timecode": "00:00:23.000",
"score": 0.15874408185482025,
"frame_badge": "#5",
"timestamp_kind": "sample_target",
"decoded_timestamp": null
}
],
"intervals": [
{
"start_sec": 10,
"end_sec": 11,
"last_sample_sec": 10,
"score": 0.15969303250312805,
"ranks": [
4
]
},
{
"start_sec": 23,
"end_sec": 24,
"last_sample_sec": 23,
"score": 0.15874408185482025,
"ranks": [
5
]
},
{
"start_sec": 24.5,
"end_sec": 39.5,
"last_sample_sec": 32.5,
"score": 0.29230737686157227,
"ranks": [
1,
2,
3
]
}
],
"contact_sheet": {
"file_path": "<cache>/02aba353e34587bfcbc3/contact_sheets/visual_62fe3b0e08f5ade4e9a5.jpg",
"sample_count": 5,
"rows": 2,
"cols": 4,
"start_sec": 30.5,
"end_sec": 23,
"timestamps": [
30.5,
31.5,
32.5,
10,
23
],
"frame_width": 224,
"frame_height": 126,
"tool_file": {
"_tag": "ToolFile",
"name": "visual_62fe3b0e08f5ade4e9a5.jpg",
"mimeType": "image/jpeg",
"encoding": "base64",
"data": "<68664 base64 chars dropped>",
"byteLength": 51498
}
},
"index_status": "complete",
"index_complete": true,
"indexed_until_sec": 47,
"duration_sec": 47,
"frames_indexed": 47,
"progress": 1,
"model": "openai/clip-vit-base-patch32",
"model_revision": "3d74acf9a28c67741b2f4f2ea7635f0aaf6f0268",
"note": "Cosine similarity is not confidence. Sample-based intervals are approximate; the interval holding rank 1 is at least 15 s long (or the whole searched range if shorter). Verify badges and inspect_window. Empty results do not establish absence."
}
}
Question and answer
- Question
- Where is the shot of blue Earth seen through a space station window?
- Answer
- The top search match runs from 24.5 s to 39.5 s.
Check passedIoU 0.20, minimum 0.15
How it was checked
- Truth from
- constructed
- Fixed at
Planted by this recipe: ffmpeg joined host footage from 14 s to 44.5 s, the public-domain NASA shot from 16 s to 19 s, and host footage from 44.5 s to 58 s, so the shot is at 30.5 s to 33.5 s of the clip. Minimum IoU 0.15: search_visual's rank-1 interval is at least 15 s, so a 3 s shot it fully covers scores 0.2, and one up to 20 s long still passes.
A script spliced a 3 s public-domain NASA shot into this cooking clip at a planted time and removed its sound, and the search reports intervals at least 15 s long, so the answer is wider than the shot.
Try it yourself
Use agentic-video to build the visual index of my video, then search it for "blue Earth seen through a round window in a space station" and tell me the start and end of the top match. Use my own file.
- Get the .mcpb file and open it in Claude Desktop.
- Or:
pip install agentic-video
Clip and licence
- Licence
- CC-BY-SA-4.0
- Author
- مصطفى ملو (Wikimedia Commons user)
- Source
- commons.wikimedia.org
This file is licensed under the Creative Commons Attribution-Share Alike 4.0 International license.
Also uses (insert 1)
- Licence
- PD
- Author
- NASA
- Source
- commons.wikimedia.org
This file is in the public domain in the United States because it was solely created by NASA.