vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

server : revamp chat UI with vuejs and daisyui (#10175)

Browse source 
* server : simple chat UI with vuejs and daisyui

* move old files to legacy folder

* embed deps into binary

* basic markdown support

* add conversation history, save to localStorage

* fix bg-base classes

* save theme preferences

* fix tests

* regenerate, edit, copy buttons

* small fixes

* docs: how to use legacy ui

* better error handling

* make CORS preflight more explicit

* add GET method for CORS

* fix tests

* clean up a bit

* better auto scroll

* small fixes

* use collapse-arrow

* fix closeAndSaveConfigDialog

* small fix

* remove console.log

* fix style for <pre> element

* lighter bubble color (less distract when reading)
This commit is contained in:
Xuan Son Nguyen 2024-11-07 17:31:10 -04:00 • committed by GitHub
parent eec4d71737
commit a71d81cf8c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
33 changed files with 28884 additions and 1369 deletions
Download patch file Download diff file Expand all files Collapse all files

29
examples/server/public/completion.js
View file

@ -1,12 +1,16 @@
const paramDefaults = {
stream: true,
n_predict: 500,
temperature: 0.2,
stop: ["</s>"]
};
let generation_settings = null;
export class CompletionError extends Error {
constructor(message, name, data) {
super(message);
this.name = name;
}
};
// Completes the prompt as a generator. Recommended for most use cases.
//
@ -29,7 +33,7 @@ export async function* llama(prompt, params = {}, config = {}) {
const completionParams = { ...paramDefaults, ...params, prompt };
const response = await fetch(`${api_url}/completion`, {
const response = await fetch(`${api_url}${config.endpoint || '/completion'}`, {
method: 'POST',
body: JSON.stringify(completionParams),
headers: {
@ -41,6 +45,18 @@ export async function* llama(prompt, params = {}, config = {}) {
signal: controller.signal,
});
const status = response.status;
if (status !== 200) {
try {
const body = await response.json();
if (body && body.error && body.error.message) {
throw new CompletionError(body.error.message, 'ServerError');
}
} catch (err) {
throw new CompletionError(err.message, 'ServerError');
}
}
const reader = response.body.getReader();
const decoder = new TextDecoder();
@ -78,7 +94,12 @@ export async function* llama(prompt, params = {}, config = {}) {
for (const line of lines) {
const match = regex.exec(line);
if (match) {
result[match[1]] = match[2]
result[match[1]] = match[2];
if (result.data === '[DONE]') {
cont = false;
break;
}
// since we know this is llama.cpp, let's just decode the json in data
if (result.data) {
result.data = JSON.parse(result.data);