diff --git a/.dockerignore b/.dockerignore
index 869a94c..d4beccb 100644
--- a/.dockerignore
+++ b/.dockerignore
@@ -1,2 +1,3 @@
data
-wasm
\ No newline at end of file
+wasm
+dbschema
\ No newline at end of file
diff --git a/Chat.go b/Chat.go
index a0d6a29..166719c 100644
--- a/Chat.go
+++ b/Chat.go
@@ -346,15 +346,19 @@ 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 $0.005 for GPT-3.5 turbo.
Remember, prices and token limits may vary depending on the provider and the specific LLM you're using.
+ Start for free
+ Groq and Google offer free messages per minutes, enough for a conversation. Allowing you to use their models with JADE for free.
+ OpenAI and Anthropic offer 5$ of free credits when creating an account. So you can try JADE with their models for free.
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-usage.html b/views/partials/popover-usage.html
index 052fe62..919d99b 100644
--- a/views/partials/popover-usage.html
+++ b/views/partials/popover-usage.html
@@ -10,7 +10,7 @@
-
+
{% for usage in usages %}
diff --git a/views/partials/welcome-chat.html b/views/partials/welcome-chat.html
index d16e651..dbbe9b0 100644
--- a/views/partials/welcome-chat.html
+++ b/views/partials/welcome-chat.html
@@ -36,7 +36,7 @@
More information
- Variety of AI models from different providers.Get access to all models.
- Multiple models in a single conversation.Get the best answer from multiple models.
- Duplicate models in a single conversation.Even from the same model.
- Pay only for what you use.Pay only for what you use or not at all.
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
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).
+ response generated in tokens (a token is around 3 characters). Groq and Google also offer free tiers that
+ are enough for conversation.
All providers and models.
+
+ Fireworks - 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.
+
+
+
+
+ FireLLaVA-13B
+
+
+ Mixtral MoE 8x7B Instruct
+
+
+ Mixtral MoE 8x22B Instruct
+
+
+ Llama 3 70B Instruct
+
+
+ Bleat
+
+
+ Chinese Llama 2 LoRA 7B
+
+
+ DBRX Instruct
+
+
+ Gemma 7B Instruct
+
+
+ Hermes 2 Pro Mistral 7b
+
+
+ Japanese StableLM Instruct Beta 70B
+
+
+ Japanese Stable LM Instruct Gamma 7B
+
+
+ Llama 2 13B French
+
+
+ Llama2 13B Guanaco QLoRA GGML
+
+
+ Llama 7B Summarize
+
+
+ Llama 2 13B
+
+
+ Llama 2 13B Chat
+
+
+ Llama 2 70B Chat
+
+
+ Llama 2 7B
+
+
+ Llama 2 7B Chat
+
+
+ Llama 3 70B Instruct (HF version)
+
+
+ Llama 3 8B (HF version)
+
+
+ Llama 3 8B Instruct
+
+
+ Llama 3 8B Instruct (HF version)
+
+
+ LLaVA V1.6 Yi 34B
+
+
+ Mistral 7B
+
+
+ Mistral 7B Instruct
+
+
+ Mistral 7B Instruct v0.2
+
+
+ Mistral 7B Instruct v0p3
+
+
+ Mixtral MoE 8x22B
+
+
+ Mixtral MoE 8x22B Instruct (HF version)
+
+
+ Mixtral MoE 8x7B
+
+
+ Mixtral MoE 8x7B Instruct (HF version)
+
+
+ MythoMax L2 13b
+
+
+ Nous Hermes 2 - Mixtral 8x7B - DPO (fp8)
+
+
+ Phi 3 Mini 128K Instruct
+
+
+ Phi 3 Vision 128K Instruct
+
+
+ Qwen1.5 72B Chat
+
+
+ StableLM 2 Zephyr 1.6B
+
+
+ StableLM Zephyr 3B
+
+
+ StarCoder 15.5B
+
+
+ StarCoder 7B
+
+
+ Traditional Chinese Llama2
+
+
+ Capybara 34B
+
+
+ Yi Large
+
+
+
+
Hugging face - 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.