Prodia: remove for now as the API keeps changing and is not a good default for our users - may put this back anytime (#786)

Author: enricoros

README.md

@@ -180,7 +180,7 @@ You can easily configure 100s of AI models in big-AGI:
 | Local Servers       | [LM Studio](https://lmstudio.ai/)                                                                                                                                                                                                                                                              |
 | Multimodal services | [Azure](https://azure.microsoft.com/en-us/products/ai-services/openai-service) · [Anthropic](https://anthropic.com) · [Google Gemini](https://ai.google.dev/) · [OpenAI](https://platform.openai.com/docs/overview)                                                                            |
 | Language services   | [Alibaba](https://www.alibabacloud.com/en/product/modelstudio) · [DeepSeek](https://deepseek.com) · [Groq](https://wow.groq.com/) · [Mistral](https://mistral.ai/) · [OpenRouter](https://openrouter.ai/) · [Perplexity](https://www.perplexity.ai/) · [Together AI](https://www.together.ai/) | 
-| Image services      | [Prodia](https://prodia.com/) (SDXL)                                                                                                                                                                                                                                                           | 
+| Image services      | OpenAI, ...                                                                                                                                                                                                                                                                                    | 
 | Speech services     | [ElevenLabs](https://elevenlabs.io) (Voice synthesis / cloning)                                                                                                                                                                                                                                | 
 
 Add extra functionality with these integrations:

docs/README.md

@@ -40,7 +40,7 @@ How to set up AI models and features in big-AGI.
 - **Enhanced AI Features**:
   - **[Web Browsing](config-feature-browse.md)**: Enable web page download through third-party services or your own cloud
   - **Web Search**: Google Search API (see '[Environment Variables](environment-variables.md)')
-  - **Image Generation**: GPT Image (gpt-image-1), DALL·E 3 and 2, or Prodia API for Stable Diffusion XL
+  - **Image Generation**: GPT Image (gpt-image-1), DALL·E 3 and 2
   - **Voice Synthesis**: ElevenLabs API for voice generation
 
 ## Deployment & Customization

docs/environment-variables.md

@@ -56,8 +56,6 @@ GOOGLE_CSE_ID=
 ELEVENLABS_API_KEY=
 ELEVENLABS_API_HOST=
 ELEVENLABS_VOICE_ID=
-# Text-To-Image: Prodia
-PRODIA_API_KEY=
 
 # Backend HTTP Basic Authentication (see `deploy-authentication.md` for turning on authentication)
 HTTP_BASIC_AUTH_USERNAME=
@@ -133,8 +131,6 @@ Enable the app to Talk, Draw, and Google things up.
 | `ELEVENLABS_API_KEY`       | ElevenLabs API Key - used for calls, etc.                                                                               |
 | `ELEVENLABS_API_HOST`      | Custom host for ElevenLabs                                                                                              |
 | `ELEVENLABS_VOICE_ID`      | Default voice ID for ElevenLabs                                                                                         |
-| **Text-To-Image**          | [Prodia](https://prodia.com/) is a reliable image generation service                                                    |
-| `PRODIA_API_KEY`           | Prodia API Key - used with '/imagine ...'                                                                               |
 | **Google Custom Search**   | [Google Programmable Search Engine](https://programmablesearchengine.google.com/about/)  produces links to pages        |
 | `GOOGLE_CLOUD_API_KEY`     | Google Cloud API Key, used with the '/react' command - [Link to GCP](https://console.cloud.google.com/apis/credentials) |
 | `GOOGLE_CSE_ID`            | Google Custom/Programmable Search Engine ID - [Link to PSE](https://programmablesearchengine.google.com/)               |

docs/k8s/env-secret.yaml

@@ -46,6 +46,3 @@ stringData:
   ELEVENLABS_API_KEY: ""
   ELEVENLABS_API_HOST: ""
   ELEVENLABS_VOICE_ID: ""
-
-  # Text-To-Image: Prodia
-  PRODIA_API_KEY: ""

src/apps/chat/components/message/ChatMessage.tsx

@@ -226,7 +226,7 @@ export function ChatMessage(props: {
   const handleHighlightSelText = useSelHighlighterMemo(messageId, selText, contentFragments, fromAssistant, props.onMessageFragmentReplace);
 
   const textSubject = selText ? selText : fragmentFlattenedText;
-  const isSpecialT2I = textSubject.startsWith('https://images.prodia.xyz/') || textSubject.startsWith('/draw ') || textSubject.startsWith('/imagine ') || textSubject.startsWith('/img ');
+  const isSpecialT2I = textSubject.startsWith('/draw ') || textSubject.startsWith('/imagine ') || textSubject.startsWith('/img ');
   const couldDiagram = textSubject.length >= 100 && !isSpecialT2I;
   const couldImagine = textSubject.length >= 3 && !isSpecialT2I;
   const couldSpeak = couldImagine;

src/apps/draw/create/ZeroDrawConfig.tsx

@@ -20,7 +20,7 @@ export function ZeroDrawConfig() {
       <CardContent>
         <Typography>
           <strong>AI Text-to-Image</strong> does not seem available.<br />
-          Please configure one service, such as an OpenAI LLM service, or the Prodia service.
+          Please configure one service, such as an OpenAI LLM service.
         </Typography>
       </CardContent>
       <CardActions buttonFlex='0'>

src/apps/news/news.data.tsx

@@ -278,7 +278,6 @@ export const NewsItems: NewsItem[] = [
       { text: <><B issue={194}>Text Tools</B> including highlight differences</> },
       { text: <><B href='https://mermaid.js.org/'>Mermaid</B> Diagramming Rendering</> },
       { text: <><B>OpenAI 1106</B> Chat Models</> },
-      { text: <><B>SDXL</B> support with Prodia</> },
       { text: <>Cloudflare OpenAI API Gateway</> },
       { text: <>Helicone for Anthropic</> },
     ],

src/common/chat-overlay/ConversationHandler.ts

@@ -138,7 +138,7 @@ export class ConversationHandler {
 
   /**
    * @param text assistant text
-   * @param generatorName LlmId or string, such as 'DALL·E' | 'Prodia' | 'react-...' | 'web'
+   * @param generatorName LlmId or string, such as 'GPT Image' | 'DALL·E' | 'react-...' | 'web'
    */
   messageAppendAssistantText(text: string, generatorName: Extract<DMessageGenerator, { mgt: 'named' }>['name']): void {
     const message = createDMessageTextContent('assistant', text);

src/common/components/useCapabilities.ts

@@ -40,7 +40,7 @@ export interface TextToImageProvider {
   vendor: TextToImageVendor;
   // UI attributes
   label: string;              // e.g. 'OpenAI #2'
-  painter: string;            // e.g. 'GPT Image', 'DALL·E' or 'Prodia'
+  painter: string;            // e.g. 'GPT Image', 'DALL·E', 'Grok', ...
   description: string;
   configured: boolean;
 }

src/modules/backend/backend.router.ts

@@ -68,7 +68,6 @@ export const backendRouter = createTRPCRouter({
         hasDB: (!!env.MDB_URI) || (!!env.POSTGRES_PRISMA_URL && !!env.POSTGRES_URL_NON_POOLING),
         hasBrowsing: !!env.PUPPETEER_WSS_ENDPOINT,
         hasGoogleCustomSearch: !!env.GOOGLE_CSE_ID && !!env.GOOGLE_CLOUD_API_KEY,
-        hasImagingProdia: !!env.PRODIA_API_KEY,
         hasVoiceElevenLabs: !!env.ELEVENLABS_API_KEY,
         // hashes
         hashLlmReconfig: generateLlmEnvConfigHash(env),