Will.qiu: Created page with " = Introduction = GenAI Chatbot - v1.0.1 is a next-generation conversational AI assistant built on the [https://lemonade-server.ai/ Le..."

2025-09-02T05:40:46Z

Created page with " = Introduction = <span style="font-size:larger;">GenAI Chatbot - v1.0.1 is a next-generation conversational AI assistant built on the [https://lemonade-server.ai/ Le..."

New page

 

= Introduction =

<span style="font-size:larger;">GenAI Chatbot - v1.0.1 is a next-generation conversational AI assistant built on the [https://lemonade-server.ai/ Lemonade] architecture, supporting all models compatible with [https://lemonade-server.ai/docs/server/server_models/#model-management-gui Lemonade-Model-Management]. Designed for seamless integration with [https://genai-studio.gitbook.io/docs GenAI Studio], it allows users to directly import models that have been fine-tuned within [https://genai-studio.gitbook.io/docs GenAI Studio], enabling easy deployment and immediate use of custom models in the chatbot. At its core, GenAI Chatbot utilizes efficient Small Language Models (SLMs) to provide natural, context-aware interactions. The chatbot features advanced capabilities, including audio processing (Speech-to-Text [STT], Text-to-Speech [TTS]), Retrieval-Augmented Generation (RAG), and an embedded vector database (VectorDB), all within a flexible configuration suitable for diverse application scenarios. It is currently optimized for embedded platforms such as `Ryzen AI 8000` and `Ryzen AI 300 (STX/KRK)` .</span>

= How To =

== Download Models from Lemonade ==
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Ollama-1.png|none|900x600px|Ollama-1.png]]
</div>
*<span style="font-size:larger;">Go to the page https://www.ollama.com/search and click on the "Models" tab as shown in Icon 1.</span>
*<span style="font-size:larger;">Use the search bar shown in Icon 2 to find the model you want to download.</span>
*<span style="font-size:larger;">In Icon 3, locate the name of the model.</span>

 
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
 
</div> <div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Ollama-2.png|none|900x600px|Ollama-2.png]]
</div>
*<span style="font-size:larger;">After clicking in, you'll see the name and version of the model you need to download.</span>
*<span style="font-size:larger;">Please note that the model size depends on your hardware resources.</span>
*<span style="font-size:larger;">Make sure your hardware matches the specifications shown in [[#Platforms|the table above]].</span>

 
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
 
</div> <div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Ollama-3.png|none|900x600px|Ollama-3.png]]
</div>
*<span style="font-size:larger;">Go back to GenAI-Chatbot and create new chat window, as shown in Icon 1.</span>
*<span style="font-size:larger;">Enter the model name you just saw into the search bar in the chat window, as shown in Icon 2.</span>
*<span style="font-size:larger;">Then, click the download button at the location marked in Icon 3.</span>

 
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
 
</div> <div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Ollama-4.png|none|900x600px|Ollama-4.png]]
</div>
*<span style="font-size:larger;">After clicking the download button, a notification will pop up.</span>

 
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
 
</div> <div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Ollama-5.png|none|900x600px|Ollama-5.png]]
</div>
*<span style="font-size:larger;">After the download is complete, a notification will appear confirming the completion.</span>

 
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
 
</div> <div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Ollama-6.png|none|900x600px|Ollama-6.png]]
</div>
*<span style="font-size:larger;">Next, you'll be able to find the model you downloaded in the model selection menu.</span>

== Download SLM Models from GenAI Studio ==
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Genai-studio-1.png|none|900x600px|Genai-studio-1.png]]
</div>
*<span style="font-size:larger;">Click GenAI Studio Hub from the left menu.</span>
*<span style="font-size:larger;">Enter the URL of your GenAI Studio.</span>
*<span style="font-size:larger;">Click the "Save" </span>
*<span style="font-size:larger;">Once the configuration is successful, a notification will appear as shown at icon 4.</span>
*<span style="font-size:larger;">Displays a list of all models supported by GenAI Studio.</span>
*<span style="font-size:larger;">Click on icon 6 to download the desired model.</span>

 
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
 
</div> <div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Genai-studio-3.png|none|900x600px|Genai-studio-3.png]]
</div>
*<span style="font-size:larger;">After the download is complete, a notification will appear, and the icon will change to a completion icon.</span>

 
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Genai-studio-4.png|none|900x600px|Genai-studio-4.png]]
</div>
*<span style="font-size:larger;">After the model has downloaded, you can select this LLM Model in new Chat </span>

 

== Delete model ==

== Using mcp tools ==

== Add new mcp server on genai-chatbot ==

== Using GenAI Agent ==

== Create a new Knowledge ==
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Rag-1.png|none|900x600px|Rag-1.png]]
</div>
*<span style="font-size:larger;">Client the Workspace from the left menu.</span>
*<span style="font-size:larger;">Go to the Knowledge.</span>
*<span style="font-size:larger;">Click the + icon to add a new knowledge.</span>

<span style="font-size:larger;">Here are sample files:</span>
<span style="font-size:larger;">* PDF: [[Media:10_Essential_Q&As_About_Over-the-Counter_(OTC)_Medication_Use.pdf|tial_Q&As_About_Over-the-Counter_(OTC)_Medication_Use.pdf]] ,</span>
<span style="font-size:larger;">* Text: '''[[Media:10_Essential_Q&As_About_Over-the-Counter_(OTC)_Medication_Use.txt|10_Essential_Q&As_About_Over-the-Counter_(OTC)_Medication_Use.txt]]'''  </span>

 
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Rag-2.png|none|900x600px|Rag-2.png]]
</div>
*<span style="font-size:larger;">Enter the title.</span>
*<span style="font-size:larger;">Enter the goal or description.</span>
*<span style="font-size:larger;">Click the "Create Knowledge" button to finish.</span>

 
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Rag-4.png|none|900x600px|Rag-4.png]]
</div>
*<span style="font-size:larger;">Click the "+" icon.</span>
*<span style="font-size:larger;">Click the "Upload files" to upload files.</span>

 
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Rag-5.png|none|900x600px|Rag-5.png]]
</div>
*<span style="font-size:larger;">Select the files you want to use.</span>

 
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Rag-6.png|none|900x600px|Rag-6.png]]
</div>
*<span style="font-size:larger;">After the upload, the files will be displayed and a success notification will appear.</span>

 
== Create a Chatbot Assistant with RAG ( Knowledge ) ==

<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Rag-7.png|none|900x600px|Rag-7.png]]
</div>
*<span style="font-size:larger;">Go to the Models tab.</span>
*<span style="font-size:larger;">Click the "+" icon, to add a new model.</span>

 
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Rag-8.png|none|900x600px|Rag-8.png]]
</div>
*<span style="font-size:larger;">On the add new model page, fill in and select the required fields shown in the red box:</span>
**<span style="font-size:larger;">Click the "+" icon, to add a new model.</span>
**<span style="font-size:larger;"> * Title, * Subtitle, * Base Model, and * System Prompt.</span>

 
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Rag-9.png|none|900x600px|Rag-9.png]]
</div>
<span style="font-size:larger;">Continuing from the previous page,</span>
*<span style="font-size:larger;">Click the "Select Knowledge" to select the Knowledge you just created,</span>
*<span style="font-size:larger;">Click the "Save & Create" to save and create.</span>

 
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Rag-10.png|none|900x600px|Rag-10.png]]
</div>
*<span style="font-size:larger;">After successful creation, a notification will appear at icon 1.</span>
*<span style="font-size:larger;">Then, click on the model ( icon 2 ) to enter the model chat. Start the Assistant chat.</span>

 
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Rag-11.png|none|900x600px|Rag-11.png]]
</div>
*<span style="font-size:larger;">The chat window will display that the model in use is the Knowledge model you created.</span>

 
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Rag-12.png|none|900x600px|Rag-12.png]]
</div>
*<span style="font-size:larger;">After starting the conversation, you will see that the model retrieves information from the Knowledge you created in its responses.</span>

 

== Configuring TTS with Azure AI Speech API ==

=== Create an Account on Azure AI Speech API ===

<span style="font-size:larger;">'''1. [https://learn.microsoft.com/en-us/dotnet/azure/create-azure-account#option-2-sign-up-for-a-free-azure-account Create an Azure account]'''</span>
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Azure-1.png|none|800x400px|Azure-1.png]]
</div>
*<span style="font-size:larger;">''Get started with Azure’s free account: new users receive $200 credit for 30 days and free access to popular services.''</span>
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Azure-2.png|none|600x400px|Azure-2.png]]
</div>
*<span style="font-size:larger;">''AI Speech – Text-to-Speech: 500,000 neural characters per month for free accounts''</span>

<span style="font-size:larger;">'''2. Set Up the Azure Speech Service'''</span>
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Azure-speech-1.png|none|900x600px|Azure-speech-1.png]]
</div>
*<span style="font-size:larger;">''In the [https://portal.azure.com/#home Azure Portal], click on "Create a resource".''</span>
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Azure-speech-2.png|none|900x600px|Azure-speech-2.png]]
</div>
*<span style="font-size:larger;">''Click on icon 1: "AI + Machine Learning"''</span>
*<span style="font-size:larger;">''Then, click on icon 2: "Speech"''</span>
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Azure-speech-3.png|none|900x600px|Azure-speech-3.png]]
</div>
*<span style="font-size:larger;">''Click on “Start” at the position marked by the red box.''</span>
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Azure-speech-4.png|none|900x600px|Azure-speech-4.png]]
</div>
*<span style="font-size:larger;">''Click "Create" and fill in the necessary details:''</span>
**<span style="font-size:larger;">''Subscription: Choose your Azure subscription.''</span>
**<span style="font-size:larger;">''Resource Group: Select an existing group or create a new one.''</span>
**<span style="font-size:larger;">''Region: Choose a region close to your location.''</span>
**<span style="font-size:larger;">''Name: Provide a unique name for your Speech resource.''</span>
**<span style="font-size:larger;">''Pricing Tier: Select Free F0.''</span>
**<span style="font-size:larger;">''Click on icon 2: "Review + create"''</span>
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Azure-speech-5.png|none|900x600px|Azure-speech-5.png]]
</div>
*<span style="font-size:larger;">''After confirming the information, click the “Create” button.''</span>
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Azure-speech-6.png|none|900x600px|Azure-speech-6.png]]
</div>
*<span style="font-size:larger;">''After entering the overview page, click on the name link of the resource you created under "Resource."''</span>
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Azure-speech-7.png|none|900x600px|Azure-speech-7.png]]
</div>
*<span style="font-size:larger;">''In the left-hand menu, click on "Keys and Endpoint".''</span>
*<span style="font-size:larger;">''Note down the Key1 or Key2 and the Endpoint URL; you'll need these to authenticate your API requests.''</span>

 

=== <span style="font-size:larger;">Setup the Azue Text-to-Speec in GenAI Chatbot</span> ===
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Stt-tts-1.png|none|900x600px|Stt-tts-1.png]]
</div>
*<span style="font-size:larger;">Click the"Admin Panel."</span>

 
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Stt-tts-2.png|none|900x600px|Stt-tts-2.png]]
</div>
*<span style="font-size:larger;">Click the Audio</span>
*<span style="font-size:larger;">Select the "Text-to-Speech Engine" with "Azure AI Speech".</span>

 
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Stt-tts-3.png|none|900x600px|Stt-tts-3.png]]
</div>
*<span style="font-size:larger;">Enter the Azure AI Speech API token in API Key.</span>
*<span style="font-size:larger;">Click the "Save" icon.</span>
*<span style="font-size:larger;">Finally, you will see a success notification.</span>

== Evaluate the Benchmark of Each Chatbot Response ==
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">
[[File:Chatbot-benchmark.png|none|900x600px|Chatbot-benchmark.png]]
</div>
*<span style="font-size:larger;">''An information button is provided next to each response. Clicking it reveals detailed performance and inference statistics for that response, including token counts, processing speed, and computation time. This allows developers to monitor and optimize system performance in real time.''</span>

 

= Example =

== Creating an Audio + RAG Chatbot for Medication Assistant ==
<div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">[[File:EAS-GenAI DevKit.jpg|none|800x400px|GenAI Chatbot DevKit]]</div>
=== <span style="font-size:large;">1. Configuring TTS with Azure AI Speech API</span> ===
<div style="margin-left: 2em;"><span style="font-size:large;">[[#Create_an_Account_on_Azure_AI_Speech_API|(1). Create an Account on Azure AI Speech API]]</span></div> <div style="margin-left: 2em;"><span style="font-size:larger;">[[#Setup_the_Azue_Text-to-Speec_in.C2.A0GenAI_Chatbot|(2). Setting Up on GenAI Chatbot]]</span></div> <div style="margin-left: 2em;"> </div>
=== <span style="font-size:large;">2. [[#Create_a_new_Knowledge|Create a Knowledge]]</span> ===

 

=== <span style="font-size:large;">3. [[#Create_a_Chatbot_Assistant_with_RAG_.28_Knowledge_.29|Create a Chatbot Assistant with RAG ( Knowledge )]]</span> ===

 

=== <span style="font-size:large;">4. </span>Start a voice chatbot assistant with RAG ===
<div style="margin-left: 2em;">
 
</div> <div style="margin-left: 2em;"><div style="display:inline-block; box-shadow:0 4px 16px rgba(0,0,0,0.15); border-radius:12px;">[[File:Rag-stt-tts-4.png|none|900x600px|Rag-stt-tts-4.png]]</div>
<span style="font-size: 15.6px;">1. Make sure the select model is the RAG model.</span><br/> <span style="font-size:larger;">2. Click the mic icon to start voice mode.</span><br/> <span style="font-size:larger;">3. While speaking, the system will show a listening status.</span><br/> <span style="font-size:larger;">4. After speaking, your question will appear as text.</span><br/> <span style="font-size:larger;">5. The Medical Chatbot Assistant will response and play the answer with audio.</span>
</div>

Edge AI SDK/GenAIChatbot/v1.0.1 - Revision history

Will.qiu: Created page with " = Introduction = GenAI Chatbot - v1.0.1 is a next-generation conversational AI assistant built on the [https://lemonade-server.ai/ Le..."