⚙️ feat: Adjust Rate of Stream Progress (#3244)

* chore: bump data-provider and add MESSAGES CacheKey

* refactor: avoid saving messages while streaming, save partial text to cache instead

* fix(ci): processChunks

* chore: logging aborted request to debug

* feat: set stream rate for token processing

* chore: specify default stream rate

* fix(ci): Update AppService.js to use optional chaining for endpointLocals assignment

* refactor: abstract the error handler

* feat: streamRate for assistants; refactor: update default rate for token

* refactor: update error handling in assistants/errors.js

* refactor: update error handling in assistants/errors.js
This commit is contained in:
Danny Avila 2024-07-17 10:47:17 -04:00 committed by GitHub
parent 1c282d1517
commit 5d40d0a37a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
29 changed files with 661 additions and 309 deletions

View file

@ -1,7 +1,9 @@
const { z } = require('zod');
const axios = require('axios');
const { Ollama } = require('ollama');
const { Constants } = require('librechat-data-provider');
const { deriveBaseURL } = require('~/utils');
const { sleep } = require('~/server/utils');
const { logger } = require('~/config');
const ollamaPayloadSchema = z.object({
@ -40,6 +42,7 @@ const getValidBase64 = (imageUrl) => {
class OllamaClient {
constructor(options = {}) {
const host = deriveBaseURL(options.baseURL ?? 'http://localhost:11434');
this.streamRate = options.streamRate ?? Constants.DEFAULT_STREAM_RATE;
/** @type {Ollama} */
this.client = new Ollama({ host });
}
@ -136,6 +139,8 @@ class OllamaClient {
stream.controller.abort();
break;
}
await sleep(this.streamRate);
}
}
// TODO: regular completion