Files
Eric BuehlerandGitHub 0e027790f2 Add a web chat app! (#1362)
* Initial

* Markdown

* Copy code

* Add model loading sidebar

* Support vision models

* Tweak isq

* Links go to another page

* Clear when switch model

* Fix html tags

* Add image support!

* More then one images

* Fix

* Improved textarea

* Tab for switching between vision and text

* No paged attn for now

* Prettier format

* Multiple models at once

* Better switching, clearing ability

* Mobile support

* Inline markdown parser

* Update examples

* Typos

* Support specifying isq

* Fix mobile

* Fixes

* Fix button on mobile

* Image height is capped

* Thumbnail

* Fix rotating kv cache edge case

* Add drag and drop for images

* Small things

* Sidebar is frozen now

* Better listner

* Add readme

* Tweak readme
2025-05-23 15:27:13 -04:00

53 lines
1.4 KiB
Rust

use anyhow::Result;
use clap::Parser;
use mistralrs::{IsqType, TextMessageRole, VisionMessages, VisionModelBuilder};
use mistralrs_core::initialize_logging;
use tokio::task;
#[derive(Parser)]
#[command(version, about, long_about = None)]
struct Args {
#[arg(short, long, default_value = "Qwen/Qwen2.5-VL-3B-Instruct")]
model_id: String,
}
#[tokio::main]
async fn main() -> Result<()> {
initialize_logging();
let args = Args::parse();
let bytes = task::spawn_blocking(|| {
match reqwest::blocking::get(
"https://cdn.britannica.com/45/5645-050-B9EC0205/head-treasure-flower-disk-flowers-inflorescence-ray.jpg",
) {
Ok(http_resp) => Ok(http_resp.bytes()?.to_vec()),
Err(e) => anyhow::bail!(e),
}
}).await??;
let image = image::load_from_memory(&bytes)?;
let model = VisionModelBuilder::new(args.model_id)
.with_isq(IsqType::Q8_0)
.with_logging()
.build()
.await?;
let messages = VisionMessages::new().add_image_message(
TextMessageRole::User,
"What is depicted here?",
vec![image],
&model,
)?;
let response = model.send_chat_request(messages).await?;
println!("{}", response.choices[0].message.content.as_ref().unwrap());
dbg!(
response.usage.avg_prompt_tok_per_sec,
response.usage.avg_compl_tok_per_sec
);
Ok(())
}