tdpeuter/open-webui
tdpeuter/open-webui
1
Fork 0
forked from open-webui/open-webui
Code Issues Pull requests 1 Releases 2 Packages Activity Actions

feat: split large openai responses into smaller chunkers

Browse source
This commit is contained in:
Jun Siang Cheah 2024-04-20 20:03:52 +01:00
parent a4083f43cb
commit efa258c695
3 changed files with 90 additions and 55 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

65
src/lib/apis/streaming/index.ts Normal file
View file

@ -0,0 +1,65 @@
type TextStreamUpdate = {
done: boolean;
value: string;
};
// createOpenAITextStream takes a ReadableStreamDefaultReader from an SSE response,
// and returns an async generator that emits delta updates with large deltas chunked into random sized chunks
export async function createOpenAITextStream(
messageStream: ReadableStreamDefaultReader
): Promise<AsyncGenerator<TextStreamUpdate>> {
return streamLargeDeltasAsRandomChunks(openAIStreamToIterator(messageStream));
}
async function* openAIStreamToIterator(
reader: ReadableStreamDefaultReader
): AsyncGenerator<TextStreamUpdate> {
while (true) {
const { value, done } = await reader.read();
if (done) {
yield { done: true, value: '' };
break;
}
const lines = value.split('\n');
for (const line of lines) {
if (line !== '') {
console.log(line);
if (line === 'data: [DONE]') {
yield { done: true, value: '' };
} else {
const data = JSON.parse(line.replace(/^data: /, ''));
console.log(data);
yield { done: false, value: data.choices[0].delta.content ?? '' };
}
}
}
}
}
// streamLargeDeltasAsRandomChunks will chunk large deltas (length > 5) into random sized chunks between 1-3 characters
// This is to simulate a more fluid streaming, even though some providers may send large chunks of text at once
async function* streamLargeDeltasAsRandomChunks(
iterator: AsyncGenerator<TextStreamUpdate>
): AsyncGenerator<TextStreamUpdate> {
for await (const textStreamUpdate of iterator) {
if (textStreamUpdate.done) {
yield textStreamUpdate;
return;
}
let content = textStreamUpdate.value;
if (content.length < 5) {
yield { done: false, value: content };
continue;
}
while (content != '') {
const chunkSize = Math.min(Math.floor(Math.random() * 3) + 1, content.length);
const chunk = content.slice(0, chunkSize);
yield { done: false, value: chunk };
await sleep(5);
content = content.slice(chunkSize);
}
}
}
const sleep = (ms: number) => new Promise((resolve) => setTimeout(resolve, ms));

37
src/routes/(app)/+page.svelte
View file

@ -39,6 +39,7 @@
import { RAGTemplate } from '$lib/utils/rag';
import { LITELLM_API_BASE_URL, OLLAMA_API_BASE_URL, OPENAI_API_BASE_URL } from '$lib/constants';
import { WEBUI_BASE_URL } from '$lib/constants';
import { createOpenAITextStream } from '$lib/apis/streaming';
const i18n = getContext('i18n');
@ -599,38 +600,22 @@
.pipeThrough(splitStream('\n'))
.getReader();
while (true) {
const { value, done } = await reader.read();
const textStream = await createOpenAITextStream(reader);
console.log(textStream);
for await (const update of textStream) {
const { value, done } = update;
if (done || stopResponseFlag || _chatId !== $chatId) {
responseMessage.done = true;
messages = messages;
break;
}
try {
let lines = value.split('\n');
for (const line of lines) {
if (line !== '') {
console.log(line);
if (line === 'data: [DONE]') {
responseMessage.done = true;
messages = messages;
} else {
let data = JSON.parse(line.replace(/^data: /, ''));
console.log(data);
if (responseMessage.content == '' && data.choices[0].delta.content == '\n') {
continue;
} else {
responseMessage.content += data.choices[0].delta.content ?? '';
messages = messages;
}
}
}
}
} catch (error) {
console.log(error);
if (responseMessage.content == '' && value == '\n') {
continue;
} else {
responseMessage.content += value;
messages = messages;
}
if ($settings.notificationEnabled && !document.hasFocus()) {

43
src/routes/(app)/c/[id]/+page.svelte
View file

@ -42,6 +42,7 @@
OLLAMA_API_BASE_URL,
WEBUI_BASE_URL
} from '$lib/constants';
import { createOpenAITextStream } from '$lib/apis/streaming';
const i18n = getContext('i18n');
@ -551,9 +552,9 @@
messages: [
$settings.system
? {
role: 'system',
content: $settings.system
}
role: 'system',
content: $settings.system
}
: undefined,
...messages
]
@ -611,38 +612,22 @@
.pipeThrough(splitStream('\n'))
.getReader();
while (true) {
const { value, done } = await reader.read();
const textStream = await createOpenAITextStream(reader);
console.log(textStream);
for await (const update of textStream) {
const { value, done } = update;
if (done || stopResponseFlag || _chatId !== $chatId) {
responseMessage.done = true;
messages = messages;
break;
}
try {
let lines = value.split('\n');
for (const line of lines) {
if (line !== '') {
console.log(line);
if (line === 'data: [DONE]') {
responseMessage.done = true;
messages = messages;
} else {
let data = JSON.parse(line.replace(/^data: /, ''));
console.log(data);
if (responseMessage.content == '' && data.choices[0].delta.content == '\n') {
continue;
} else {
responseMessage.content += data.choices[0].delta.content ?? '';
messages = messages;
}
}
}
}
} catch (error) {
console.log(error);
if (responseMessage.content == '' && value == '\n') {
continue;
} else {
responseMessage.content += value;
messages = messages;
}
if ($settings.notificationEnabled && !document.hasFocus()) {