🛠️ OpenAI Vision — 6

Next, in 🛠️ OpenAI Vision,

function runme() {
  local tag=2023-11-25-tag-v1

  @tag set x1 $tag
  @tag set x2 $tag
  @tag set x3 $tag
  @tag set x4 $tag
  @tag set x5 $tag
  @tag set x6 $tag
  
  @tag search $tag
}

runme

6 object(s): x1, x2, x3, x4, x5, x6

@tag search $tag

6 object(s): x6, x5, x4, x3, x2, x1

vanwatch list area=vancouver,ingest,published --log 0

2023–11–12–12–03–40–85851, 2023–11–19–15–08–01–41901, 2023–11–19–17–38–06–69168, vanwatch-process-dev-2023–11–11-v61

vanwatch list area=vancouver,ingest,published \
  --offset 1 \
  --count 1

@select $(vanwatch list area=vancouver,ingest,published \
  --offset 3 \
  --count 1 \
  --log 0) open

vanwatch vision \
    "name any of the following if you see them in any of the images: \
construction,festival,homelessness,accident" \
    area=vancouver,offset=3 \
    Davie,Bute

🤖 success: The images provided appear to be from surveillance cameras at various angles of an urban street setting. I do not see clear indicators of a festival, homelessness, accident, or construction in these images. Here’s what can be identified:

1. The first image shows a crosswalk painted with rainbow colors, which might suggest a neighborhood with a welcoming attitude towards the LGBTQ+ community. There’s a person crossing the street, but no signs of any of the specific situations you asked about.

2. The second image shows a different angle of the same street intersection, with several people walking and cars at the stoplight. Again, there is no indication of a festival, homelessness, an accident, or construction.

3. The third image features a stretch of storefronts with people walking by. It’s a regular city scene without any of the specific elements you mentioned.

4. The fourth image shows a straight-on view down the street with vehicles moving and parked. The scene appears to be normal city traffic, with no signs of an accident, construction, homelessness, or a festival.

vanwatch vision \
    "Name any of the following if you see them in any of the images: \
construction, festival, homelessness, and accident. Generate a short answer \
and do not explain your answer, only name the listed items if you see them." \
    area=vancouver,offset=3 \
    Davie,Bute

None of the listed items are visible in the images provided.

Arbutus16

vanwatch vision \
    "Generate a dictionary with the following keywords: construction, \
festival, homelessness, and accident, and assign them to True if you see them
in any of the images." \
    area=vancouver,offset=3 \
    Arbutus16

🤖 success: Based on the provided images, here is the dictionary with the keywords and their assigned boolean values indicating their presence in any of the images:

```python
{
“construction”: True,
“festival”: False,
“homelessness”: False,
“accident”: False
}
```

The “construction” keyword is set to True because the second and third images show signs of construction such as barriers, traffic cones, and construction fencing. The other keywords are set to False as there are no visible indications of a festival, homelessness, or an accident in the provided images.

{
 "construction": True,
 "festival": False,
 "homelessness": False,
 "accident": False
}

vanwatch vision \
    "Generate a dictionary with the following keywords: construction, \
festival, homelessness, and accident, and assign them to True if you see them \
in any of the images. Only return the dictionary in json notations and do not \
include any other text in the output." \
    area=vancouver,offset=3 \
    Arbutus16

🤖 success: ```json
{
  "construction": true,
  "festival": false,
  "homelessness": false,
  "accident": false
}
```

openai pytest

openai pytest list

openai pytest openai_cli/tests/test_vision.py

openai pytest

🔻 giza += openai.

giza update push

option::int