adrien/Jade
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Better welcome page

Browse Source
This commit is contained in:
Adrien Bouvais 2024-06-16 18:55:42 +02:00
parent b12c6d4ea4
commit 0355cf374e
4 changed files with 158 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.dockerignore
View File

@ -1,2 +1,3 @@
data data
wasm wasm
dbschema

4
Chat.go
View File

@ -346,6 +346,9 @@ func generateEnterKeyChatHTML() string {
<li>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.</li> <li>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 $0.005 for GPT-3.5 turbo.</li>
</ul> </ul>
<p>Remember, prices and token limits may vary depending on the provider and the specific LLM you're using.</p> <p>Remember, prices and token limits may vary depending on the provider and the specific LLM you're using.</p>
<h2>Start for free</h2>
<p>Groq and Google offer free messages per minutes, enough for a conversation. Allowing you to use their models with JADE for free.</p>
<p>OpenAI and Anthropic offer 5$ of free credits when creating an account. So you can try JADE with their models for free.</p>
<h2>Get a key</h2> <h2>Get a key</h2>
<p>To get a key and learn more about the different LLM providers and their offerings, check out their websites:</p> <p>To get a key and learn more about the different LLM providers and their offerings, check out their websites:</p>
<ul> <ul>
@ -355,6 +358,7 @@ func generateEnterKeyChatHTML() string {
<li><a href="https://console.mistral.ai/" target="https://console.mistral.ai/">Mistral AI</a></li> <li><a href="https://console.mistral.ai/" target="https://console.mistral.ai/">Mistral AI</a></li>
<li><a href="https://aistudio.google.com" target="https://aistudio.google.com">Google</a></li> <li><a href="https://aistudio.google.com" target="https://aistudio.google.com">Google</a></li>
<li><a href="https://www.perplexity.ai/" target="https://www.perplexity.ai/">Perplexity</a></li> <li><a href="https://www.perplexity.ai/" target="https://www.perplexity.ai/">Perplexity</a></li>
<li><a href="https://fireworks.ai/" target="https://fireworks.ai/">Fireworks AI</a></li>
</ul> </ul>
` `

2
views/partials/popover-usage.html
View File

@ -10,7 +10,7 @@
<div class="dropdown-item"> <div class="dropdown-item">
<!-- Placeholder for additional text --> <!-- Placeholder for additional text -->
<div class="content" id="usage-content" style="max-height: 30vh; overflow-y: auto;"> <div class="content" id="usage-content" style="max-height: 30vh; overflow-y: auto;">
<table class="table is-narrow is-fullwidth is-striped"> <table class="table is-narrow is-fullwidth is-striped" style="max-width: 200px;">
<tbody> <tbody>
{% for usage in usages %} {% for usage in usages %}
<tr> <tr>

158
views/partials/welcome-chat.html
View File

@ -36,7 +36,7 @@
<h2>More information</h2> <h2>More information</h2>
<ul> <ul>
<li> <li>
<h3>Variety of AI models from different providers.<button class="button ml-2 is-small is-primary is-outlined" <h3>Get access to all models.<button class="button ml-2 is-small is-primary is-outlined"
onclick="toggleDetails('all-models-details')"> onclick="toggleDetails('all-models-details')">
<span class="icon is-small"> <span class="icon is-small">
<i class="fa-solid fa-info"></i> <i class="fa-solid fa-info"></i>
@ -53,7 +53,7 @@
</p> </p>
</li> </li>
<li> <li>
<h3>Multiple models in a single conversation.<button class="button ml-2 is-small is-primary is-outlined" <h3>Get the best answer from multiple models.<button class="button ml-2 is-small is-primary is-outlined"
onclick="toggleDetails('multi-models-details')"> onclick="toggleDetails('multi-models-details')">
<span class="icon is-small"> <span class="icon is-small">
<i class="fa-solid fa-info"></i> <i class="fa-solid fa-info"></i>
@ -66,7 +66,7 @@
complex queries where different models might offer unique insights or solutions.<br><br></p> complex queries where different models might offer unique insights or solutions.<br><br></p>
</li> </li>
<li> <li>
<h3>Duplicate models in a single conversation.<button class="button ml-2 is-small is-primary is-outlined" <h3>Even from the same model.<button class="button ml-2 is-small is-primary is-outlined"
onclick="toggleDetails('same-models-details')"> onclick="toggleDetails('same-models-details')">
<span class="icon is-small"> <span class="icon is-small">
<i class="fa-solid fa-info"></i> <i class="fa-solid fa-info"></i>
@ -90,7 +90,7 @@
model's bias. This ensures that the responses you receive are more reliable and trustworthy.<br><br></p> model's bias. This ensures that the responses you receive are more reliable and trustworthy.<br><br></p>
</li> </li>
<li> <li>
<h3>Pay only for what you use.<button class="button ml-2 is-small is-primary is-outlined" <h3>Pay only for what you use or not at all.<button class="button ml-2 is-small is-primary is-outlined"
onclick="toggleDetails('flexible-pricing-details')"> onclick="toggleDetails('flexible-pricing-details')">
<span class="icon is-small"> <span class="icon is-small">
<i class="fa-solid fa-info"></i> <i class="fa-solid fa-info"></i>
@ -99,10 +99,9 @@
<p id="flexible-pricing-details" style="display:none;">JADE use API, so you get access to free credits or tiers <p id="flexible-pricing-details" style="display:none;">JADE use API, so you get access to free credits or tiers
depending of the provider (see next section). This is particularly beneficial for users who may not need to depending of the provider (see next section). This is particularly beneficial for users who may not need to
use the chatbot extensively. Once the free credit use, you pay based on the length of you message and the use the chatbot extensively. Once the free credit use, you pay based on the length of you message and the
response generated in tokens (a token is around 3 characters). <br><br>JADE starts with a response generated in tokens (a token is around 3 characters). Groq and Google also offer free tiers that
free tier that allows you to send up to 200 messages a month. For more intensive use, you can upgrade for are enough for conversation. <br><br>JADE starts with a free tier that allows you to send up to 200 messages
just $0.95/month. So you can use Llama 70b for free forever if using JADE with a Groq Cloud account for a month. For more intensive use, you can upgrade for just $0.95/month.<br><br></p>
example.<br><br></p>
</li> </li>
<li> <li>
<h3>All providers and models.<button class="button ml-2 is-small is-primary is-outlined" <h3>All providers and models.<button class="button ml-2 is-small is-primary is-outlined"
@ -261,6 +260,149 @@
</div> </div>
</div> </div>
<br> <br>
<div class="columns">
<div class="column is-two-thirds">
<strong>Fireworks</strong> - Fireworks AI offer 1$ of free credits when creating an account.
Firework AI have a lot of open source models. I may add fine tuned models in the future.
</div>
<div class="column">
<ul>
<li>
<strong>FireLLaVA-13B</strong>
</li>
<li>
<strong>Mixtral MoE 8x7B Instruct</strong>
</li>
<li>
<strong>Mixtral MoE 8x22B Instruct</strong>
</li>
<li>
<strong>Llama 3 70B Instruct</strong>
</li>
<li>
<strong>Bleat</strong>
</li>
<li>
<strong>Chinese Llama 2 LoRA 7B</strong>
</li>
<li>
<strong>DBRX Instruct</strong>
</li>
<li>
<strong>Gemma 7B Instruct</strong>
</li>
<li>
<strong>Hermes 2 Pro Mistral 7b</strong>
</li>
<li>
<strong>Japanese StableLM Instruct Beta 70B</strong>
</li>
<li>
<strong>Japanese Stable LM Instruct Gamma 7B</strong>
</li>
<li>
<strong>Llama 2 13B French</strong>
</li>
<li>
<strong>Llama2 13B Guanaco QLoRA GGML</strong>
</li>
<li>
<strong>Llama 7B Summarize</strong>
</li>
<li>
<strong>Llama 2 13B</strong>
</li>
<li>
<strong>Llama 2 13B Chat</strong>
</li>
<li>
<strong>Llama 2 70B Chat</strong>
</li>
<li>
<strong>Llama 2 7B</strong>
</li>
<li>
<strong>Llama 2 7B Chat</strong>
</li>
<li>
<strong>Llama 3 70B Instruct (HF version)</strong>
</li>
<li>
<strong>Llama 3 8B (HF version)</strong>
</li>
<li>
<strong>Llama 3 8B Instruct</strong>
</li>
<li>
<strong>Llama 3 8B Instruct (HF version)</strong>
</li>
<li>
<strong>LLaVA V1.6 Yi 34B</strong>
</li>
<li>
<strong>Mistral 7B</strong>
</li>
<li>
<strong>Mistral 7B Instruct</strong>
</li>
<li>
<strong>Mistral 7B Instruct v0.2</strong>
</li>
<li>
<strong>Mistral 7B Instruct v0p3</strong>
</li>
<li>
<strong>Mixtral MoE 8x22B</strong>
</li>
<li>
<strong>Mixtral MoE 8x22B Instruct (HF version)</strong>
</li>
<li>
<strong>Mixtral MoE 8x7B</strong>
</li>
<li>
<strong>Mixtral MoE 8x7B Instruct (HF version)</strong>
</li>
<li>
<strong>MythoMax L2 13b</strong>
</li>
<li>
<strong>Nous Hermes 2 - Mixtral 8x7B - DPO (fp8)</strong>
</li>
<li>
<strong>Phi 3 Mini 128K Instruct</strong>
</li>
<li>
<strong>Phi 3 Vision 128K Instruct</strong>
</li>
<li>
<strong>Qwen1.5 72B Chat</strong>
</li>
<li>
<strong>StableLM 2 Zephyr 1.6B</strong>
</li>
<li>
<strong>StableLM Zephyr 3B</strong>
</li>
<li>
<strong>StarCoder 15.5B</strong>
</li>
<li>
<strong>StarCoder 7B</strong>
</li>
<li>
<strong>Traditional Chinese Llama2</strong>
</li>
<li>
<strong>Capybara 34B</strong>
</li>
<li>
<strong>Yi Large</strong>
</li>
</ul>
</div>
</div>
<br>
<strong>Hugging face</strong> - You can also use custom endpoints. I only tested hugging face but in <strong>Hugging face</strong> - You can also use custom endpoints. I only tested hugging face but in
theory, as long as the key is valid and it use the openai api, it should work. This part need some theory, as long as the key is valid and it use the openai api, it should work. This part need some
testing and improvement. testing and improvement.