[PR #47] [MERGED] feat: add multiple images (or in-context learning) conversation example #72

New issue

Closed

opened 2026-10-26 21:09:23 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-26 21:09:23 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/DeepSeek-VL/pull/47
Author: @StevenLiuWen
Created: 4/16/2024
Status: ✅ Merged
Merged: 4/16/2024
Merged by: @Benjamin-eecs

Base: main ← Head: main

📝 Commits (4)

dd980e3 add multiple images (or in-context learning) conversation example
523211b Update inference.py
85a1bd7 chore: add github action
40cf0a9 fix: github action

📊 Changes

8 files changed (+121 additions, -5 deletions)

View changed files

➕ .github/workflows/lint.yml (+68 -0)
📝 README.md (+21 -5)
➕ images/dog_a.png (+0 -0)
➕ images/dog_b.png (+0 -0)
➕ images/dog_c.png (+0 -0)
➕ images/dog_d.png (+0 -0)
📝 inference.py (+18 -0)
📝 pyproject.toml (+14 -0)

📄 Description

conversation = [
    {
        "role": "User",
        "content": "<image_placeholder>A dog wearing nothing in the foreground, "
                   "<image_placeholder>a dog wearing a santa hat, "
                   "<image_placeholder>a dog wearing a wizard outfit, and "
                   "<image_placeholder>what's the dog wearing?",
        "images": [
            "images/dog_a.png",
            "images/dog_b.png",
            "images/dog_c.png",
            "images/dog_d.png",
        ],
    },
    {"role": "Assistant", "content": ""}
]

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/deepseek-ai/DeepSeek-VL/pull/47 **Author:** [@StevenLiuWen](https://github.com/StevenLiuWen) **Created:** 4/16/2024 **Status:** ✅ Merged **Merged:** 4/16/2024 **Merged by:** [@Benjamin-eecs](https://github.com/Benjamin-eecs) **Base:** `main` ← **Head:** `main` --- ### 📝 Commits (4) - [`dd980e3`](https://github.com/deepseek-ai/DeepSeek-VL/commit/dd980e342907990620d3bbfb715dea242e0a1d55) add multiple images (or in-context learning) conversation example - [`523211b`](https://github.com/deepseek-ai/DeepSeek-VL/commit/523211bc23112ea6f5df94e119e42555f0a1da01) Update inference.py - [`85a1bd7`](https://github.com/deepseek-ai/DeepSeek-VL/commit/85a1bd7c12f8e28603e5a6ed5252ebc141868e3d) chore: add github action - [`40cf0a9`](https://github.com/deepseek-ai/DeepSeek-VL/commit/40cf0a949cbfa491d4a7606f0fa76851ded0c1eb) fix: github action ### 📊 Changes **8 files changed** (+121 additions, -5 deletions) <details> <summary>View changed files</summary> ➕ `.github/workflows/lint.yml` (+68 -0) 📝 `README.md` (+21 -5) ➕ `images/dog_a.png` (+0 -0) ➕ `images/dog_b.png` (+0 -0) ➕ `images/dog_c.png` (+0 -0) ➕ `images/dog_d.png` (+0 -0) 📝 `inference.py` (+18 -0) 📝 `pyproject.toml` (+14 -0) </details> ### 📄 Description ```python conversation = [ { "role": "User", "content": "<image_placeholder>A dog wearing nothing in the foreground, " "<image_placeholder>a dog wearing a santa hat, " "<image_placeholder>a dog wearing a wizard outfit, and " "<image_placeholder>what's the dog wearing?", "images": [ "images/dog_a.png", "images/dog_b.png", "images/dog_c.png", "images/dog_d.png", ], }, {"role": "Assistant", "content": ""} ] ``` --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-26 21:09:23 +00:00

closed this issue
added the
pull-request
label

No labels

enhancement

environment

pull-request

No milestone

No project

No assignees

1 participant

Notifications

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference

deepseek-ai/DeepSeek-VL#72

No description provided.

Rows
Columns