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

…2729)

* 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

.env.example

@@ -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.

api/app/clients/GoogleClient.js

@@ -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;
     }

api/server/utils/import/importers.js

@@ -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';
     }
 

client/src/components/Chat/Landing.tsx

@@ -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')}