fix
This commit is contained in:
parent
05495ea616
commit
e6bde72771
3
Chat.go
3
Chat.go
@ -359,7 +359,7 @@ func generateEnterKeyChatHTML() string {
|
|||||||
<h1>API keys</h1>
|
<h1>API keys</h1>
|
||||||
<p class="mt-2">JADE require at least one API key to work. Add one in the settings at the bottom right of the page.</p>
|
<p class="mt-2">JADE require at least one API key to work. Add one in the settings at the bottom right of the page.</p>
|
||||||
<p>API keys are unique codes that allow you to access and use different Large Language Model (LLM) providers.</p>
|
<p>API keys are unique codes that allow you to access and use different Large Language Model (LLM) providers.</p>
|
||||||
<p>Most providers offer free credits when you first sign up or per month, which means you have a balance in your account that you can use to generate messages.</p>
|
<p>Most providers offer free credits when you first sign up or per minute, which means you have a balance in your account that you can use to generate messages.</p>
|
||||||
<p><strong>You pay for the service based on the number of tokens input and generated.</strong> A token is a small unit of text, roughly equivalent to 3 characters. So, a small input and output text will cost very little.</p>
|
<p><strong>You pay for the service based on the number of tokens input and generated.</strong> A token is a small unit of text, roughly equivalent to 3 characters. So, a small input and output text will cost very little.</p>
|
||||||
<h2>Pricing Examples</h2>
|
<h2>Pricing Examples</h2>
|
||||||
<ul>
|
<ul>
|
||||||
@ -376,6 +376,7 @@ func generateEnterKeyChatHTML() string {
|
|||||||
<li><a href="https://console.groq.com/login" target="https://console.groq.com/login">Groq</a></li>
|
<li><a href="https://console.groq.com/login" target="https://console.groq.com/login">Groq</a></li>
|
||||||
<li><a href="https://console.mistral.ai/" target="https://console.mistral.ai/">MistralAI</a></li>
|
<li><a href="https://console.mistral.ai/" target="https://console.mistral.ai/">MistralAI</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>
|
||||||
</ul>
|
</ul>
|
||||||
`
|
`
|
||||||
|
|
||||||
|
|||||||
@ -43,12 +43,14 @@
|
|||||||
</span>
|
</span>
|
||||||
</button></h3>
|
</button></h3>
|
||||||
<p id="all-models-details" style="display:none;">With JADE, you can easily switch between models like GPT 3.5 or
|
<p id="all-models-details" style="display:none;">With JADE, you can easily switch between models like GPT 3.5 or
|
||||||
4o, Gemini, Llama, Mistral, Claude, and more. Even custom endpoint. This means you can choose the best model
|
4o, Gemini, Llama, Mistral, Claude, and more. Even custom endpoint.
|
||||||
for
|
<br><br>This means you can choose the best model for your specific needs, whether it's for general
|
||||||
for your specific needs, whether it's for general knowledge, creative writing, or technical expertise.
|
knowledge, creative writing, or technical expertise. Having access to multiple models allows you to take
|
||||||
Having access to multiple models allows you to take advantage of their unique strengths and weaknesses,
|
advantage of their unique strengths and
|
||||||
|
weaknesses,
|
||||||
ensuring you get the most accurate and relevant responses. (See all models available in the last
|
ensuring you get the most accurate and relevant responses. (See all models available in the last
|
||||||
section)<br><br></p>
|
section)<br><br>
|
||||||
|
</p>
|
||||||
</li>
|
</li>
|
||||||
<li>
|
<li>
|
||||||
<h3>Multiple models in a single conversation.<button class="button ml-2 is-small is-primary is-outlined"
|
<h3>Multiple models in a single conversation.<button class="button ml-2 is-small is-primary is-outlined"
|
||||||
@ -59,7 +61,8 @@
|
|||||||
</button></h3>
|
</button></h3>
|
||||||
<p id="multi-models-details" style="display:none;">You can ask a question and receive responses from several
|
<p id="multi-models-details" style="display:none;">You can ask a question and receive responses from several
|
||||||
models at once, enabling
|
models at once, enabling
|
||||||
you to compare their answers and choose the most suitable one. This feature is particularly useful for
|
you to compare their answers and choose the most suitable one. <br><br>This feature is particularly useful
|
||||||
|
for
|
||||||
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>
|
||||||
@ -69,9 +72,10 @@
|
|||||||
<i class="fa-solid fa-info"></i>
|
<i class="fa-solid fa-info"></i>
|
||||||
</span>
|
</span>
|
||||||
</button></h3>
|
</button></h3>
|
||||||
<p id="same-models-details" style="display:none;">Hoz JADE work is that you can create custom bot. Each bot have
|
<p id="same-models-details" style="display:none;">The core feature of JADE are the bots. Each bot have
|
||||||
a name, model,
|
a name, model,
|
||||||
temperature and system prompt. You can create as many bot as you want and select as many to answer each
|
temperature and system prompt. <br><br>You can create as many bot as you want and select as many to answer
|
||||||
|
each
|
||||||
question. An example is creating the same model that reponse in different language.<br><br></p>
|
question. An example is creating the same model that reponse in different language.<br><br></p>
|
||||||
</li>
|
</li>
|
||||||
<li>
|
<li>
|
||||||
@ -81,7 +85,8 @@
|
|||||||
</span>
|
</span>
|
||||||
</button></h3>
|
</button></h3>
|
||||||
<p id="reduce-hallucination-details" style="display:none;">AI models sometimes generate information that is
|
<p id="reduce-hallucination-details" style="display:none;">AI models sometimes generate information that is
|
||||||
inaccurate or misleading, a phenomenon known as "hallucination." By using multiple models, JADE reduces each
|
inaccurate or misleading, a phenomenon known as "hallucination." <br><br>By using multiple models, JADE
|
||||||
|
reduces each
|
||||||
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>
|
||||||
@ -100,7 +105,7 @@
|
|||||||
example.<br><br></p>
|
example.<br><br></p>
|
||||||
</li>
|
</li>
|
||||||
<li>
|
<li>
|
||||||
<h3>All providers.<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"
|
||||||
onclick="toggleDetails('provider-details')">
|
onclick="toggleDetails('provider-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>
|
||||||
@ -109,181 +114,159 @@
|
|||||||
<div id="provider-details" style="display:none; overflow-x: hidden;">
|
<div id="provider-details" style="display:none; overflow-x: hidden;">
|
||||||
<div class="columns">
|
<div class="columns">
|
||||||
<div class="column is-two-thirds">
|
<div class="column is-two-thirds">
|
||||||
<strong>Providers available:</strong>
|
<strong>OpenAI</strong> - OpenAI offer 5$ credits when creating an API account.
|
||||||
|
Around 10 000 small question to GPT-4 Omni or 100 000 to GPT-3.5 Turbo.
|
||||||
</div>
|
</div>
|
||||||
<div class="column">
|
<div class="column">
|
||||||
<strong>Models available:</strong>
|
<ul>
|
||||||
|
<li>
|
||||||
|
<strong>GPT 4 Omni</strong>
|
||||||
|
</li>
|
||||||
|
<li>
|
||||||
|
<strong>GPT 4 Turbo</strong>
|
||||||
|
</li>
|
||||||
|
<li>
|
||||||
|
<strong>GPT 4</strong>
|
||||||
|
</li>
|
||||||
|
<li>
|
||||||
|
<strong>GPT 3.5 Turbo</strong>
|
||||||
|
</li>
|
||||||
|
</ul>
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
<ul>
|
<br>
|
||||||
<li>
|
<div class="columns">
|
||||||
<div class="columns">
|
<div class="column is-two-thirds">
|
||||||
<div class="column is-two-thirds">
|
<strong>Anthropic</strong> - Anthropic offer 5$ credits when creating an API
|
||||||
<strong>OpenAI</strong> - OpenAI offer 5$ credits when creating an API account.
|
account. Around 2 000 small question to Claude 3 Opus or 120 000 to Claude Haiku.
|
||||||
Around 10 000 small question to GPT-4 Omni or 100 000 to GPT-3.5 Turbo.
|
</div>
|
||||||
</div>
|
<div class="column">
|
||||||
<div class="column">
|
<ul>
|
||||||
<ul>
|
<li>
|
||||||
<li>
|
<strong>Claude 3 Opus</strong>
|
||||||
<strong>GPT 4 Omni</strong>
|
</li>
|
||||||
</li>
|
<li>
|
||||||
<li>
|
<strong>Claude 3 Sonnet</strong>
|
||||||
<strong>GPT 4 Turbo</strong>
|
</li>
|
||||||
</li>
|
<li>
|
||||||
<li>
|
<strong>Claude 3 Haiku</strong>
|
||||||
<strong>GPT 4</strong>
|
</li>
|
||||||
</li>
|
</ul>
|
||||||
<li>
|
</div>
|
||||||
<strong>GPT 3.5 Turbo</strong>
|
</div>
|
||||||
</li>
|
<br>
|
||||||
</ul>
|
<div class="columns">
|
||||||
</div>
|
<div class="column is-two-thirds">
|
||||||
</div>
|
<strong>Mistral</strong> - Mistral do not offer free credits.
|
||||||
</li>
|
</div>
|
||||||
<br>
|
<div class="column">
|
||||||
<li>
|
<ul>
|
||||||
<div class="columns">
|
<li>
|
||||||
<div class="column is-two-thirds">
|
<strong>Mixtral 8x22b</strong>
|
||||||
<strong>Anthropic</strong> - Anthropic offer 5$ credits when creating an API
|
</li>
|
||||||
account. Around 2 000 small question to Claude 3 Opus or 120 000 to Claude Haiku.
|
<li>
|
||||||
</div>
|
<strong>Mixtral 8x7b</strong>
|
||||||
<div class="column">
|
</li>
|
||||||
<ul>
|
<li>
|
||||||
<li>
|
<strong>Mistral 7b</strong>
|
||||||
<strong>Claude 3 Opus</strong>
|
</li>
|
||||||
</li>
|
<li>
|
||||||
<li>
|
<strong>Mistral Large</strong>
|
||||||
<strong>Claude 3 Sonnet</strong>
|
</li>
|
||||||
</li>
|
<li>
|
||||||
<li>
|
<strong>Mistral Small</strong>
|
||||||
<strong>Claude 3 Haiku</strong>
|
</li>
|
||||||
</li>
|
<li>
|
||||||
</ul>
|
<strong>Codestral</strong>
|
||||||
</div>
|
</li>
|
||||||
</div>
|
</ul>
|
||||||
</li>
|
</div>
|
||||||
<br>
|
</div>
|
||||||
<li>
|
<br>
|
||||||
<div class="columns">
|
<div class="columns">
|
||||||
<div class="column is-two-thirds">
|
<div class="column is-two-thirds">
|
||||||
<strong>Mistral</strong> - Mistral do not offer free credits.
|
<strong>Groq</strong> - Groq offer a free tier with limit of tokens and request per minutes.
|
||||||
</div>
|
The rate is plenty for a chatbot. 30 messages and between 6 000 and 30 000 tokens per
|
||||||
<div class="column">
|
minute. Per tokens coming soon.
|
||||||
<ul>
|
</div>
|
||||||
<li>
|
<div class="column">
|
||||||
<strong>Mixtral 8x22b</strong>
|
<ul>
|
||||||
</li>
|
<li>
|
||||||
<li>
|
<strong>Llama 3 70b</strong>
|
||||||
<strong>Mixtral 8x7b</strong>
|
</li>
|
||||||
</li>
|
<li>
|
||||||
<li>
|
<strong>Llama 3 8b</strong>
|
||||||
<strong>Mistral 7b</strong>
|
</li>
|
||||||
</li>
|
<li>
|
||||||
<li>
|
<strong>Mixtral 8x7b</strong>
|
||||||
<strong>Mistral Large</strong>
|
</li>
|
||||||
</li>
|
<li>
|
||||||
<li>
|
<strong>Gemma 7b</strong>
|
||||||
<strong>Mistral Small</strong>
|
</li>
|
||||||
</li>
|
</ul>
|
||||||
<li>
|
</div>
|
||||||
<strong>Codestral</strong>
|
</div>
|
||||||
</li>
|
<br>
|
||||||
</ul>
|
<div class="columns">
|
||||||
</div>
|
<div class="column is-two-thirds">
|
||||||
</div>
|
<strong>Google</strong> - Like Groq, Google offer a free tier with limit of tokens and
|
||||||
</li>
|
request per minutes. The rate is plenty for a chatbot. 15 messages and 1 000 000
|
||||||
<br>
|
tokens per minute. Per tokens also available.
|
||||||
<li>
|
</div>
|
||||||
<div class="columns">
|
<div class="column">
|
||||||
<div class="column is-two-thirds">
|
<ul>
|
||||||
<strong>Groq</strong> - Groq offer a free tier with limit of tokens and request per minutes.
|
<li>
|
||||||
The rate is plenty for a chatbot. 30 messages and between 6 000 and 30 000 tokens per
|
<strong>Gemini 1.5 pro</strong>
|
||||||
minute. Per tokens coming soon.
|
</li>
|
||||||
</div>
|
<li>
|
||||||
<div class="column">
|
<strong>Gemini 1.5 flash</strong>
|
||||||
<ul>
|
</li>
|
||||||
<li>
|
<li>
|
||||||
<strong>Llama 3 70b</strong>
|
<strong>Gemini 1.0 pro</strong>
|
||||||
</li>
|
</li>
|
||||||
<li>
|
</ul>
|
||||||
<strong>Llama 3 8b</strong>
|
</div>
|
||||||
</li>
|
</div>
|
||||||
<li>
|
<br>
|
||||||
<strong>Mixtral 8x7b</strong>
|
<div class="columns">
|
||||||
</li>
|
<div class="column is-two-thirds">
|
||||||
<li>
|
<strong>Perplexity</strong> - Perplexity do not offer a free tier or credits. Perplexity
|
||||||
<strong>Gemma 7b</strong>
|
offer what they call 'online' models that can search online. So you can ask for the current
|
||||||
</li>
|
weather for example. Those models have additional cost of 5$ per 1 000 requests.
|
||||||
</ul>
|
</div>
|
||||||
</div>
|
<div class="column">
|
||||||
</div>
|
<ul>
|
||||||
</li>
|
<li>
|
||||||
<br>
|
<strong>Sonar Large</strong>
|
||||||
<li>
|
</li>
|
||||||
<div class="columns">
|
<li>
|
||||||
<div class="column is-two-thirds">
|
<strong>Sonar Large Online</strong>
|
||||||
<strong>Google</strong> - Like Groq, Google offer a free tier with limit of tokens and
|
</li>
|
||||||
request per minutes. The rate is plenty for a chatbot. 15 messages and 1 000 000
|
<li>
|
||||||
tokens per minute. Per tokens also available.
|
<strong>Sonar Small</strong>
|
||||||
</div>
|
</li>
|
||||||
<div class="column">
|
<li>
|
||||||
<ul>
|
<strong>Sonar Small Online</strong>
|
||||||
<li>
|
</li>
|
||||||
<strong>Gemini 1.5 pro</strong>
|
<li>
|
||||||
</li>
|
<strong>Llama 70b</strong>
|
||||||
<li>
|
</li>
|
||||||
<strong>Gemini 1.5 flash</strong>
|
<li>
|
||||||
</li>
|
<strong>Llama 7b</strong>
|
||||||
<li>
|
</li>
|
||||||
<strong>Gemini 1.0 pro</strong>
|
<li>
|
||||||
</li>
|
<strong>Mixtral 8x7b</strong>
|
||||||
</ul>
|
</li>
|
||||||
</div>
|
</ul>
|
||||||
</div>
|
</div>
|
||||||
</li>
|
</div>
|
||||||
<br>
|
<br>
|
||||||
<li>
|
<strong>Hugging face</strong> - You can also use custom endpoints. I only tested hugging face but in
|
||||||
<div class="columns">
|
theory, as long as the key is valid and it use the openai api, it should work. This part need some
|
||||||
<div class="column is-two-thirds">
|
testing and improvement.
|
||||||
<strong>Perplexity</strong> - Perplexity do not offer a free tier or credits. Perplexity
|
<br>
|
||||||
offer what they call 'online' models that can search online. So you can ask for the current
|
<strong>Goose AI</strong> - Chat API will be available soon.
|
||||||
weather for example. Those models have additional cost of 5$ per 1 000 requests.
|
<br>
|
||||||
</div>
|
|
||||||
<div class="column">
|
|
||||||
<ul>
|
|
||||||
<li>
|
|
||||||
<strong>Sonar Large</strong>
|
|
||||||
</li>
|
|
||||||
<li>
|
|
||||||
<strong>Sonar Large Online</strong>
|
|
||||||
</li>
|
|
||||||
<li>
|
|
||||||
<strong>Sonar Small</strong>
|
|
||||||
</li>
|
|
||||||
<li>
|
|
||||||
<strong>Sonar Small Online</strong>
|
|
||||||
</li>
|
|
||||||
<li>
|
|
||||||
<strong>Llama 70b</strong>
|
|
||||||
</li>
|
|
||||||
<li>
|
|
||||||
<strong>Llama 7b</strong>
|
|
||||||
</li>
|
|
||||||
<li>
|
|
||||||
<strong>Mixtral 8x7b</strong>
|
|
||||||
</li>
|
|
||||||
</ul>
|
|
||||||
</div>
|
|
||||||
</div>
|
|
||||||
</li>
|
|
||||||
<br>
|
|
||||||
<li>
|
|
||||||
<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
|
|
||||||
testing and improvement.
|
|
||||||
</li>
|
|
||||||
<br>
|
|
||||||
</ul>
|
|
||||||
</div>
|
</div>
|
||||||
</li>
|
</li>
|
||||||
</ul>
|
</ul>
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user