diff --git a/Chat.go b/Chat.go
index 7fa6898..c93864e 100644
--- a/Chat.go
+++ b/Chat.go
@@ -282,7 +282,7 @@ func generateWelcomeChatHTML() string {
NextMessages := []TemplateMessage{}
nextMsg := TemplateMessage{
Icon: "icons/bouvai2.png", // Assuming Icon is a field you want to include from Message
- Content: " " + welcomeMessage,
+ Content: welcomeMessage,
Hidden: false, // Assuming Hidden is a field you want to include from Message
Id: "0",
Name: "JADE",
@@ -361,8 +361,8 @@ func generateEnterKeyChatHTML() string {
For 1 large text, like a PDF with 30,000 characters (60-120 pages), you would pay around $0.05 per message for GPT-4o or $0.005 for GPT-3.5 turbo.
Remember, prices and token limits may vary depending on the provider and the specific LLM you're using.
-
Learn More
-
To learn more about the different LLM providers and their offerings, check out their websites:
+
Get a key
+
To get a key and learn more about the different LLM providers and their offerings, check out their websites:
diff --git a/views/partials/popover-conversation.html b/views/partials/popover-conversation.html
index 8252d25..1d4026a 100644
--- a/views/partials/popover-conversation.html
+++ b/views/partials/popover-conversation.html
@@ -78,6 +78,7 @@
function toggleConversationSelection(element, name) {
const elements = Array.from(document.getElementsByClassName('icon-conv'));
+ document.getElementById('conversation-dropdown').classList.remove('is-active');
// If the conversation is already selected, keep it
if (element.classList.contains('unselected')) {
diff --git a/views/partials/welcome-chat.html b/views/partials/welcome-chat.html
index cc3ef8f..c3cae09 100644
--- a/views/partials/welcome-chat.html
+++ b/views/partials/welcome-chat.html
@@ -15,15 +15,13 @@
from GPT-4 can be used by Claude Haiku in the next interaction.
-
AI models sometimes generate information that is
- inaccurate or misleading, a phenomenon known as "hallucination." By using multiple models, JADE helps you
- cross-verify the information provided, significantly reducing the risk of such errors. This ensures that the
- responses you receive are more reliable and trustworthy, making JADE a more dependable tool for your
- conversational needs.
+ inaccurate or misleading, a phenomenon known as "hallucination." By using multiple models, JADE reduces each
+ model's bias. This ensures that the responses you receive are more reliable and trustworthy.