V4.8.20 feature (#3686)

* Aiproxy (#3649)

* model config

* feat: model config ui

* perf: rename variable

* feat: custom request url

* perf: model buffer

* perf: init model

* feat: json model config

* auto login

* fix: ts

* update packages

* package

* fix: dockerfile

* feat: usage filter & export & dashbord (#3538)

* feat: usage filter & export & dashbord

* adjust ui

* fix tmb scroll

* fix code & selecte all

* merge

* perf: usages list；perf: move components (#3654)

* perf: usages list

* team sub plan load

* perf: usage dashboard code

* perf: dashboard ui

* perf: move components

* add default model config (#3653)

* 4.8.20 test (#3656)

* provider

* perf: model config

* model perf (#3657)

* fix: model

* dataset quote

* perf: model config

* model tag

* doubao model config

* perf: config model

* feat: model test

* fix: POST 500 error on dingtalk bot (#3655)

* feat: default model (#3662)

* move model config

* feat: default model

* fix: false triggerd org selection (#3661)

* export usage csv i18n (#3660)

* export usage csv i18n

* fix build

* feat: markdown extension (#3663)

* feat: markdown extension

* media cros

* rerank test

* default price

* perf: default model

* fix: cannot custom provider

* fix: default model select

* update bg

* perf: default model selector

* fix: usage export

* i18n

* fix: rerank

* update init extension

* perf: ip limit check

* doubao model order

* web default modle

* perf: tts selector

* perf: tts error

* qrcode package

* reload buffer (#3665)

* reload buffer

* reload buffer

* tts selector

* fix: err tip (#3666)

* fix: err tip

* perf: training queue

* doc

* fix interactive edge (#3659)

* fix interactive edge

* fix

* comment

* add gemini model

* fix: chat model select

* perf: supplement assistant empty response (#3669)

* perf: supplement assistant empty response

* check array

* perf: max_token count;feat: support resoner output;fix: member scroll (#3681)

* perf: supplement assistant empty response

* check array

* perf: max_token count

* feat: support resoner output

* member scroll

* update provider order

* i18n

* fix: stream response (#3682)

* perf: supplement assistant empty response

* check array

* fix: stream response

* fix: model config cannot set to null

* fix: reasoning response (#3684)

* perf: supplement assistant empty response

* check array

* fix: reasoning response

* fix: reasoning response

* doc (#3685)

* perf: supplement assistant empty response

* check array

* doc

* lock

* animation

* update doc

* update compose

* doc

* doc

---------

Co-authored-by: heheer <heheer@sealos.io>
Co-authored-by: a.e. <49438478+I-Info@users.noreply.github.com>

packages/service/core/ai/utils.ts

@@ -2,32 +2,23 @@ import { LLMModelItemType } from '@fastgpt/global/core/ai/model.d';
 import {
   ChatCompletionCreateParamsNonStreaming,
   ChatCompletionCreateParamsStreaming,
-  ChatCompletionMessageParam
+  StreamChatType
 } from '@fastgpt/global/core/ai/type';
-import { countGptMessagesTokens } from '../../common/string/tiktoken';
 import { getLLMModel } from './model';
 
-export const computedMaxToken = async ({
+/* 
+  Count response max token
+*/
+export const computedMaxToken = ({
   maxToken,
-  model,
-  filterMessages = []
+  model
 }: {
   maxToken?: number;
   model: LLMModelItemType;
-  filterMessages: ChatCompletionMessageParam[];
 }) => {
   if (maxToken === undefined) return;
 
   maxToken = Math.min(maxToken, model.maxResponse);
-  const tokensLimit = model.maxContext;
-
-  /* count response max token */
-  const promptsToken = await countGptMessagesTokens(filterMessages);
-  maxToken = promptsToken + maxToken > tokensLimit ? tokensLimit - promptsToken : maxToken;
-
-  if (maxToken <= 0) {
-    maxToken = 200;
-  }
   return maxToken;
 };
 
@@ -39,6 +30,7 @@ export const computedTemperature = ({
   model: LLMModelItemType;
   temperature: number;
 }) => {
+  if (typeof model.maxTemperature !== 'number') return undefined;
   temperature = +(model.maxTemperature * (temperature / 10)).toFixed(2);
   temperature = Math.max(temperature, 0.01);
 
@@ -87,3 +79,12 @@ export const llmCompletionsBodyFormat = <T extends CompletionsBodyType>(
 
   return requestBody as InferCompletionsBody<T>;
 };
+
+export const llmStreamResponseToText = async (response: StreamChatType) => {
+  let answer = '';
+  for await (const part of response) {
+    const content = part.choices?.[0]?.delta?.content || '';
+    answer += content;
+  }
+  return answer;
+};