Andreas/LibreChat
1
0
Fork 0
mirror of https://github.com/danny-avila/LibreChat.git synced 2025-12-16 08:20:14 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

⚡ feat: Gemini-1.5 Flash, gpt-4o imports, modelSpec greeting fix (#2729)

Browse source 
* fix: Gemini Flash stream fix

* fix: correct `sender` field for gpt-4o imports from ChatGPT

* add flash model examples and fix vertex streaming

* style: modelSpec greeting fix
This commit is contained in:
Danny Avila 2024-05-15 09:02:48 -04:00 • committed by GitHub
parent 64bf0800a0
commit fc9368e0e7
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 13 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

4
.env.example
View file

@ -116,10 +116,10 @@ GOOGLE_KEY=user_provided
# GOOGLE_REVERSE_PROXY=
# Gemini API
# GOOGLE_MODELS=gemini-1.0-pro,gemini-1.0-pro-001,gemini-1.0-pro-latest,gemini-1.0-pro-vision-latest,gemini-1.5-pro-latest,gemini-pro,gemini-pro-vision
# GOOGLE_MODELS=gemini-1.5-flash-latest,gemini-1.0-pro,gemini-1.0-pro-001,gemini-1.0-pro-latest,gemini-1.0-pro-vision-latest,gemini-1.5-pro-latest,gemini-pro,gemini-pro-vision
# Vertex AI
# GOOGLE_MODELS=gemini-1.5-pro-preview-0409,gemini-1.0-pro-vision-001,gemini-pro,gemini-pro-vision,chat-bison,chat-bison-32k,codechat-bison,codechat-bison-32k,text-bison,text-bison-32k,text-unicorn,code-gecko,code-bison,code-bison-32k
# GOOGLE_MODELS=gemini-1.5-flash-preview-0514,gemini-1.5-pro-preview-0409,gemini-1.0-pro-vision-001,gemini-pro,gemini-pro-vision,chat-bison,chat-bison-32k,codechat-bison,codechat-bison-32k,text-bison,text-bison-32k,text-unicorn,code-gecko,code-bison,code-bison-32k
# Google Gemini Safety Settings
# NOTE (Vertex AI): You do not have access to the BLOCK_NONE setting by default.

13
api/app/clients/GoogleClient.js
View file

@ -683,11 +683,12 @@ class GoogleClient extends BaseClient {
const safetySettings = _payload.safetySettings;
requestOptions.safetySettings = safetySettings;
const delay = modelName.includes('flash') ? 8 : 14;
const result = await client.generateContentStream(requestOptions);
for await (const chunk of result.stream) {
const chunkText = chunk.text();
this.generateTextStream(chunkText, onProgress, {
delay: 12,
await this.generateTextStream(chunkText, onProgress, {
delay,
});
reply += chunkText;
}
@ -701,10 +702,14 @@ class GoogleClient extends BaseClient {
safetySettings: safetySettings,
});
let delay = this.isGenerativeModel ? 12 : 8;
if (modelName.includes('flash')) {
delay = 5;
}
for await (const chunk of stream) {
const chunkText = chunk?.content ?? chunk;
this.generateTextStream(chunkText, onProgress, {
delay: this.isGenerativeModel ? 12 : 8,
await this.generateTextStream(chunkText, onProgress, {
delay,
});
reply += chunkText;
}

2
api/server/utils/import/importers.js
View file

@ -202,7 +202,7 @@ function processConversation(conv, importBatchBuilder, requestUserId) {
const isCreatedByUser = role === 'user';
let sender = isCreatedByUser ? 'user' : 'GPT-3.5';
const model = mapping.message.metadata.model_slug || openAISettings.model.default;
if (model === 'gpt-4') {
if (model.includes('gpt-4')) {
sender = 'GPT-4';
}

2
client/src/components/Chat/Landing.tsx
View file

@ -76,7 +76,7 @@ export default function Landing({ Header }: { Header?: ReactNode }) {
</div> */}
</div>
) : (
<div className="mb-5 text-2xl font-medium dark:text-white">
<div className="mb-5 max-w-[75vh] px-12 text-center text-lg font-medium dark:text-white md:px-0 md:text-2xl">
{endpoint === EModelEndpoint.assistants
? conversation?.greeting ?? localize('com_nav_welcome_assistant')
: conversation?.greeting ?? localize('com_nav_welcome_message')}