# VLM Demo

> *VLM Demo*: Lightweight repo for chatting with models loaded into *VLM Bench*.

---

## Installation

This repository can be installed as follows:

```bash
git clone git@github.com:TRI-ML/vlm-demo.git
cd vlm-demo
pip install -e .
```

This repository also requires that the `vlm-bench` package (`vlbench`) and 
`prismatic-vlms` package (`prisma`) are installed in the current environment.
These can both be installed from source from the following git repos:

+ `vlm-bench`: `https://github.com/TRI-ML/vlm-bench`
+ `prismatic-vlms`: `https://github.com/TRI-ML/prismatic-vlms`

## Usage

The main script to run is `interactive_demo.py`, while the implementation of 
the Gradio Controller (`serve/gradio_controller.py`) and Gradio Web Server
(`serve/gradio_web_server.py`) are within `serve`. All of this code is heavily
adapted from the [LLaVA Github Repo:](https://github.com/haotian-liu/LLaVA/blob/main/llava/serve/).
More details on how this code was modified from the original LLaVA repo is provided in the 
relevant source files.

To run the demo, run the following commands:

+ Start Gradio Controller: `python -m serve.controller --host 0.0.0.0 --port 10000`
+ Start Gradio Web Server: `python -m serve.gradio_web_server --controller http://localhost:10000 --model-list-mode reload --share`
+ Run interactive demo: `CUDA_VISIBLE_DEVICES=0 python -m interactive_demo  --port 40000  --model_dir <PATH TO MODEL CKPT>`

When running the demo, the following parameters are adjustable:
+ Temperature
+ Max output tokens

The default interaction mode is Chat, which is the main way to use our models. However, we also support a number of other 
interaction modes for more specific use cases:
+ Captioning: Here, you can simply upload an image with no provided prompt and the selected model will output a caption. Even if a prompt
is input by the user, it will not be used in producing the caption.
+ Bounding Box Prediction: After uploading an image, simply specify a portion of the image for which bounding box coordinates are desired
in the prompt and the selected model will output corresponding coordinates.
+ Visual Question Answering: Selecting this option is best when the user wants short, succint answers to a specific question provided in the
prompt.
+ True/False Question Answering: Selecting this option is best when the user wants a True/False answer to a specific question provided in the 
prompt.


## Contributing

Before committing to the repository, *make sure to set up your dev environment!*

Here are the basic development environment setup guidelines:

+ Fork/clone the repository, performing an editable installation. Make sure to install with the development dependencies
  (e.g., `pip install -e ".[dev]"`); this will install `black`, `ruff`, and `pre-commit`.

+ Install `pre-commit` hooks (`pre-commit install`).

+ Branch for the specific feature/issue, issuing PR against the upstream repository for review.