Eden AI
Access multiple AI providers for text generation, image creation, and OCR through Eden AI.
On this page
Connect
Auth type: API key (secret_text). Paste the API key (or token) from the provider's settings into the connect dialog. It is encrypted at rest and only decrypted on the server when an action runs.
- In the editor: Backend panel, Integrations tab, then Connect. This connects it for the project.
- For every project in a workspace: Workspace settings, Integrations.
- Owners and admins choose which integrations members may connect in the admin panel (Integrations tab), and can attach their own OAuth app there.
Call it from a workflow
Pass the action name and its input. The call resolves with { success, output, error? }; a missing connection resolves with success false and the reason. See ctx.integrations.invoke and ctx.integrations.call.
// .workflow.js (native ctx)
export async function run(ctx) {
const res = await ctx.integrations.invoke("eden_ai", "image_generation", {
"provider": "<provider>",
"text": "<prompt>",
"resolution": "<resolution>"
});
if (!res.success) throw new Error(res.error);
ctx.log.info("Eden AI answered", { output: res.output });
}// defineWorkflow module (@app/sdk ctx)
import { defineWorkflow } from "@app/sdk";
export default defineWorkflow({
id: "eden-ai-image-generation",
name: "Eden AI: Image Generation",
description: "Calls Eden AI when a row is created.",
trigger: { type: "entity_event", entity: "tickets", event: "created" },
async run(ctx, event) {
const res = await ctx.integrations.call("eden_ai", {
"action": "image_generation",
"provider": "<provider>",
"text": "<prompt>",
"resolution": "<resolution>"
}) as { success: boolean; error?: string };
if (!res.success) throw new Error(res.error);
},
});curl -X POST "$APP_ORIGIN/__appbricx/connector-proxy/eden_ai/image_generation" \
-H "Authorization: Bearer $APP_KEY" \
-H "content-type: application/json" \
-d '{"props":{"provider":"<provider>","text":"<prompt>","resolution":"<resolution>"}}'Actions
image_generationin catalog
Image Generation. Create images from text prompts using Eden AI. Supports multiple providers, models, and resolutions.
| Input | Type | Description |
|---|---|---|
providerrequired | id (picked from your account) | The AI provider to use for image generation. |
textrequired | long text | Description of the desired image(s). Be specific and descriptive for best results. |
resolutionrequired | id (picked from your account) | The image resolution (e.g., 512x512, 1024x1024). |
num_imagesoptional | number | Number of images to generate (1-10). |
modeloptional | id (picked from your account) | Specific model to use for image generation. Leave empty for provider default. |
fallback_providersoptional | ids (picked from your account) | Alternative providers to try if the main provider fails (up to 5). |
show_original_responseoptional | boolean | Include the raw provider response in the output for debugging. |
detect_language
Detect Language of Text. Detect the language used in a text using Eden AI. Supports multiple providers and models.
| Input | Type | Description |
|---|---|---|
providerrequired | id (picked from your account) | The AI provider to use for language detection. |
textrequired | long text | The text to detect language for. |
modeloptional | text | Specific model to use (e.g., gpt-4o, grok-2-latest). Leave empty for default. |
fallback_providersoptional | ids (picked from your account) | Alternative providers to try if the main provider fails (up to 5). |
show_original_responseoptional | boolean | Include the raw provider response in the output for debugging. |
extract_entities
Extract Named Entities in Text. Identify entities (names, places) in text using Eden AI. Supports multiple providers, languages, and models.
| Input | Type | Description |
|---|---|---|
providerrequired | id (picked from your account) | The AI provider to use for named entity recognition. |
textrequired | long text | The text to extract entities from. |
languageoptional | id (picked from your account) | The language of the input text. Choose "Auto Detection" if unsure. |
modeloptional | text | Specific model to use (e.g., gpt-4o, gemini-1.5-flash, grok-2-latest). Leave empty for default. |
fallback_providersoptional | ids (picked from your account) | Alternative providers to try if the main provider fails (up to 5). |
show_original_responseoptional | boolean | Include the raw provider response in the output for debugging. |
extract_keywords
Extract Keywords in Text. Identify important terms in a text using Eden AI. Supports multiple providers, languages, and models.
| Input | Type | Description |
|---|---|---|
providerrequired | id (picked from your account) | The AI provider to use for keyword extraction. |
textrequired | long text | The text to extract keywords from. |
languageoptional | id (picked from your account) | The language of the input text. Choose "Auto Detection" if unsure. |
modeloptional | text | Specific model to use (e.g., gpt-4o, gpt-4, grok-2-latest). Leave empty for default. |
fallback_providersoptional | ids (picked from your account) | Alternative providers to try if the main provider fails (up to 5). |
show_original_responseoptional | boolean | Include the raw provider response in the output for debugging. |
generate_text
Generate Text. Generate text completions using various AI providers through Eden AI chat endpoint.
| Input | Type | Description |
|---|---|---|
providerrequired | id (picked from your account) | The AI provider to use for text generation. |
promptrequired | long text | The main prompt or question you want the AI to respond to. |
system_promptoptional | long text | System message to set the behavior and context for the AI assistant (e.g., "You are a helpful coding assistant"). |
modeloptional | text | Specific model to use (e.g., gpt-4o, claude-3-sonnet-latest, gemini-2.0-flash). Leave empty for provider-specific defaults. |
temperatureoptional | number | Controls randomness (0.0-2.0). Higher values make output more creative. |
max_completion_tokensoptional | number | Maximum number of tokens to generate in the response. |
reasoning_effortoptional | id (picked from your account) | Level of reasoning depth for the response. |
fallback_providersoptional | ids (picked from your account) | Alternative providers to try if the main provider fails. |
include_imageoptional | boolean | Include an image in your prompt (for vision-capable models). |
image_urloptional | text | URL of the image to include in the prompt (only used if "Include Image" is enabled). |
invoice_parser
Invoice Parser. Extract structured invoice data from files using Eden AI. Supports multiple providers, languages, and document types.
| Input | Type | Description |
|---|---|---|
providerrequired | id (picked from your account) | The AI provider to use for financial document parsing. |
filerequired | file | Provide the financial document file (PDF, image, etc). |
document_typeoptional | id (picked from your account) | The type of financial document to parse. |
languageoptional | id (picked from your account) | The language of the document. Choose "Auto Detection" if unsure. |
modeloptional | text | Specific model to use (e.g., gpt-4o, gpt-4o-mini, gpt-4-turbo). Leave empty for default. |
file_passwordoptional | text | Password for protected PDF files (if applicable). |
convert_to_pdfoptional | boolean | Convert DOC/DOCX files to PDF format for better compatibility. |
fallback_providersoptional | ids (picked from your account) | Alternative providers to try if the main provider fails (up to 5). |
show_original_responseoptional | boolean | Include the raw provider response in the output for debugging. |
moderate_text
Moderate Text. Detect explicit or policy-violating text using Eden AI. Supports multiple providers, languages, and models.
| Input | Type | Description |
|---|---|---|
providerrequired | id (picked from your account) | The AI provider to use for text moderation. |
textrequired | long text | The text to analyze for explicit or policy-violating content. |
languageoptional | id (picked from your account) | The language of the input text. Choose "Auto Detection" if unsure. |
modeloptional | text | Specific model to use (e.g., text-moderation-latest, text-moderation-stable). Leave empty for default. |
fallback_providersoptional | ids (picked from your account) | Alternative providers to try if the main provider fails (up to 5). |
show_original_responseoptional | boolean | Include the raw provider response in the output for debugging. |
ocr_image
Extract Text in Image (OCR). Extract text from images (OCR) using Eden AI. Supports multiple providers, languages, and bounding box coordinates.
| Input | Type | Description |
|---|---|---|
providerrequired | id (picked from your account) | The AI provider to use for text extraction. |
file_urlrequired | text | Public URL to the image or document file. |
languageoptional | id (picked from your account) | The language of the text in the image. Choose "Auto Detection" if unsure. |
file_passwordoptional | text | Password for protected PDF files (if applicable). |
attributes_as_listoptional | boolean | Return extracted data with each attribute as a list instead of list of objects. |
fallback_providersoptional | ids (picked from your account) | Alternative providers to try if the main provider fails (up to 5). |
show_original_responseoptional | boolean | Include the raw provider response in the output for debugging. |
receipt_parser
Receipt Parser. Extract structured data from receipts and documents using Eden AI. Supports general data extraction with bounding boxes.
| Input | Type | Description |
|---|---|---|
providerrequired | id (picked from your account) | The AI provider to use for data extraction. |
file_urlrequired | text | Public URL to the document file (PDF, image, etc). |
file_passwordoptional | text | Password for protected PDF files (if applicable). |
convert_to_pdfoptional | boolean | Convert DOC/DOCX files to PDF format for better compatibility. |
attributes_as_listoptional | boolean | Return extracted data with each attribute as a list instead of list of objects. |
fallback_providersoptional | ids (picked from your account) | Alternative providers to try if the main provider fails (up to 5). |
show_original_responseoptional | boolean | Include the raw provider response in the output for debugging. |
spell_check
Spell Check. Identify and correct spelling or grammar errors using Eden AI. Supports multiple providers, languages, and models.
| Input | Type | Description |
|---|---|---|
providerrequired | id (picked from your account) | The AI provider to use for spell checking and grammar correction. |
textrequired | long text | The text to check for spelling or grammar errors. |
languageoptional | id (picked from your account) | The language of the input text. Choose "Auto Detection" if unsure. |
modeloptional | text | Specific model to use (e.g., gpt-4o, gpt-4, grok-2-latest, command). Leave empty for default. |
fallback_providersoptional | ids (picked from your account) | Alternative providers to try if the main provider fails (up to 5). |
show_original_responseoptional | boolean | Include the raw provider response in the output for debugging. |
summarize_text
Summarize Text. Extract key sentences and create summaries from long text passages using various AI providers.
| Input | Type | Description |
|---|---|---|
providerrequired | id (picked from your account) | The AI provider to use for text summarization. |
textrequired | long text | The text content you want to summarize. Can be articles, documents, or any long-form text. |
output_sentencesoptional | number | How many sentences should the summary contain (1-20). |
languageoptional | id (picked from your account) | The language of the input text. Choose "Auto Detection" if unsure. |
modeloptional | text | Specific model to use (e.g., gpt-4, gpt-4o, summarize-xlarge). Leave empty for default. |
fallback_providersoptional | ids (picked from your account) | Alternative providers to try if the main provider fails (up to 5). |
show_original_responseoptional | boolean | Include the raw provider response in the output for debugging. |
text_to_speech
Generate Audio From Text. Convert text to spoken audio using Eden AI. Supports multiple providers, languages, and voice customization.
| Input | Type | Description |
|---|---|---|
providerrequired | id (picked from your account) | The AI provider to use for text-to-speech synthesis. |
textrequired | long text | The text to convert to speech. |
languageoptional | id (picked from your account) | The language and locale for the speech synthesis (defaults to en-US if not specified). |
optionoptional | id (picked from your account) | Choose the voice gender for speech synthesis (defaults to Female if not specified). |
rateoptional | number | Adjust speaking rate (-100 to 100, where 0 is normal speed). |
pitchoptional | number | Adjust voice pitch (-100 to 100, where 0 is normal pitch). |
volumeoptional | number | Adjust audio volume (-100 to 100, where 0 is normal volume). |
audio_formatoptional | id (picked from your account) | The audio format for the generated speech (default: MP3). |
sampling_rateoptional | number | Audio sampling rate in Hz (0-200000, 0 for provider default). |
fallback_providersoptional | ids (picked from your account) | Alternative providers to try if the main provider fails (up to 5). |
show_original_responseoptional | boolean | Include the raw provider response in the output for debugging. |
translate_text
Translate Text. Translate text into different languages using Eden AI. Supports multiple providers, languages, and models.
| Input | Type | Description |
|---|---|---|
providerrequired | id (picked from your account) | The AI provider to use for text translation. |
textrequired | long text | The text to translate. |
source_languageoptional | id (picked from your account) | The language of the input text. Choose "Auto Detection" to automatically detect the language. |
target_languagerequired | id (picked from your account) | The language to translate the text into. |
modeloptional | text | Specific model to use (e.g., gpt-4o, grok-2-latest). Leave empty for default. |
fallback_providersoptional | ids (picked from your account) | Alternative providers to try if the main provider fails (up to 5). |
show_original_responseoptional | boolean | Include the raw provider response in the output for debugging. |
Details
- Id
eden_ai- Category
- AI and ML
- Tags
- ai, aggregator, text, image, ocr
- Package
@activepieces/piece-eden-ai@0.2.0- Tier
- Community