Jina AI
Create embeddings, rerank search results, and perform neural search with Jina AI. In Appbricx, your workflows and server functions call it by name once it is connected.
What you can do
5 actions, each one call from a workflow or a server function. Triggers come from your app: a row changing, a schedule or a webhook.
- Classify Text or ImageAssign categories to text or images using the Classifier API (zero-shot/few-shot).
classify_content - DeepSearch QueryAnswer complex questions through iterative search, reading, and reasoning with the DeepSearch API.
deepsearch_query - Extract Webpage ContentConvert a URL into clean, LLM-friendly Markdown using the Reader API.
extract_webpage_content - Train Custom ClassifierFine-tune a classifier with labeled examples for domain-specific tasks.
train_custom_classifier - Web Search SummarizationPerform a web search and retrieve summarized results using the Reader API.
web_search_summarization
Set it up
About two minutes, once per project or once for the whole workspace.
- Open Integrations in the builder
Backend panel, Integrations tab, then Jina AI. To connect it for every project, use Workspace settings, Integrations.
- Add your credentials
An API key (or token) from your Jina AI account, pasted once. It is stored encrypted and only read on the server when an action runs.
- API key From Jina AI's settings
- Call an action
From a workflow, by integration id and action name. The call answers with success, output and, when it fails, the reason.
Workflow // .workflow.js (native ctx) export async function run(ctx) { const res = await ctx.integrations.invoke("jina_ai", "classify_content", { "model": "jina-clip-v2", "input": "<text>", "labels": [] }); if (!res.success) throw new Error(res.error); ctx.log.info("Jina AI answered", { output: res.output }); }
More in AI and ML
Jina AI and its logo are trademarks of their owner, shown only to identify the service this integration connects to. Their use does not imply endorsement by, or affiliation with, that company.