deploy: 8025cec

latest/GenAIExamples/Translation/README.html

@@ -25,6 +25,8 @@
         <script src="../../_static/sphinx_highlight.js?v=dc90522c"></script>
         <script src="../../_static/opea-custom.js?v=22d49862"></script>
         <script src="../../_static/design-tabs.js?v=f930bc37"></script>
+        <script src="https://unpkg.com/mermaid@10.2.0/dist/mermaid.min.js"></script>
+        <script>mermaid.initialize({startOnLoad:true});</script>
     <script src="../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../genindex.html" />
     <link rel="search" title="Search" href="../../search.html" />
@@ -863,7 +865,46 @@ <h1>Translation Application<a class="headerlink" href="#translation-application"
 <p>Language Translation is the communication of the meaning of a source-language text by means of an equivalent target-language text.</p>
 <p>Translation architecture shows below:</p>
 <p><img alt="architecture" src="../../_images/translation_architecture.png" /></p>
-<p>This Translation use case performs Language Translation Inference across multiple platforms. Currently, we provide the example for <a class="reference external" href="https://www.intel.com/content/www/us/en/products/details/processors/ai-accelerators/gaudi-overview.html">Intel Gaudi2</a> and <a class="reference external" href="https://www.intel.com/content/www/us/en/products/details/processors/xeon.html">Intel Xeon Scalable Processors</a>, and we invite contributions from other hardware vendors to expand OPEA ecosystem.</p>
+<p>The Translation example is implemented using the component-level microservices defined in <a class="reference external" href="https://github.com/opea-project/GenAIComps">GenAIComps</a>. The flow chart below shows the information flow between different microservices for this example.</p>
+<div class="mermaid">
+            flowchart LR
+    %% Colors %%
+    classDef blue fill:#ADD8E6,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5
+    classDef orange fill:#FBAA60,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5
+    classDef orchid fill:#C26DBC,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5
+    classDef invisible fill:transparent,stroke:transparent;
+    style Translation-MegaService stroke:#000000
+
+    %% Subgraphs %%
+    subgraph Translation-MegaService[&quot;Translation MegaService &quot;]
+        direction LR
+        LLM([LLM MicroService]):::blue
+    end
+    subgraph UserInterface[&quot; User Interface &quot;]
+        direction LR
+        a([User Input Query]):::orchid
+        UI([UI server&lt;br&gt;]):::orchid
+    end
+
+
+    LLM_gen{{LLM Service &lt;br&gt;}}
+    GW([Translation GateWay&lt;br&gt;]):::orange
+    NG([Nginx MicroService]):::blue
+
+
+    %% Questions interaction
+    direction LR
+    a[User Input Query] --&gt; UI
+    a[User Input Query] --&gt; |Need Proxy Server|NG
+    NG --&gt; UI
+    UI --&gt; GW
+    GW &lt;==&gt; Translation-MegaService
+
+
+    %% Embedding service flow
+    direction LR
+    LLM &lt;-.-&gt; LLM_gen
+        </div><p>This Translation use case performs Language Translation Inference across multiple platforms. Currently, we provide the example for <a class="reference external" href="https://www.intel.com/content/www/us/en/products/details/processors/ai-accelerators/gaudi-overview.html">Intel Gaudi2</a> and <a class="reference external" href="https://www.intel.com/content/www/us/en/products/details/processors/xeon.html">Intel Xeon Scalable Processors</a>, and we invite contributions from other hardware vendors to expand OPEA ecosystem.</p>
 <section id="deploy-translation-service">
 <h2>Deploy Translation Service<a class="headerlink" href="#deploy-translation-service" title="Link to this heading">¶</a></h2>
 <p>The Translation service can be effortlessly deployed on either Intel Gaudi2 or Intel Xeon Scalable Processors.</p>

latest/_sources/GenAIExamples/Translation/README.md.txt

@@ -6,6 +6,58 @@ Translation architecture shows below:
 
 ![architecture](./assets/img/translation_architecture.png)
 
+The Translation example is implemented using the component-level microservices defined in [GenAIComps](https://github.com/opea-project/GenAIComps). The flow chart below shows the information flow between different microservices for this example.
+
+```mermaid
+---
+config:
+  flowchart:
+    nodeSpacing: 400
+    rankSpacing: 100
+    curve: linear
+  themeVariables:
+    fontSize: 50px
+---
+flowchart LR
+    %% Colors %%
+    classDef blue fill:#ADD8E6,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5
+    classDef orange fill:#FBAA60,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5
+    classDef orchid fill:#C26DBC,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5
+    classDef invisible fill:transparent,stroke:transparent;
+    style Translation-MegaService stroke:#000000
+
+    %% Subgraphs %%
+    subgraph Translation-MegaService["Translation MegaService "]
+        direction LR
+        LLM([LLM MicroService]):::blue
+    end
+    subgraph UserInterface[" User Interface "]
+        direction LR
+        a([User Input Query]):::orchid
+        UI([UI server<br>]):::orchid
+    end
+
+
+    LLM_gen{{LLM Service <br>}}
+    GW([Translation GateWay<br>]):::orange
+    NG([Nginx MicroService]):::blue
+
+
+    %% Questions interaction
+    direction LR
+    a[User Input Query] --> UI
+    a[User Input Query] --> |Need Proxy Server|NG
+    NG --> UI
+    UI --> GW
+    GW <==> Translation-MegaService
+
+
+    %% Embedding service flow
+    direction LR
+    LLM <-.-> LLM_gen
+
+```
+
 This Translation use case performs Language Translation Inference across multiple platforms. Currently, we provide the example for [Intel Gaudi2](https://www.intel.com/content/www/us/en/products/details/processors/ai-accelerators/gaudi-overview.html) and [Intel Xeon Scalable Processors](https://www.intel.com/content/www/us/en/products/details/processors/xeon.html), and we invite contributions from other hardware vendors to expand OPEA ecosystem.
 
 ## Deploy Translation Service