Jina AI
Jina AI Search Foundation — Reader, web search, embeddings, reranker and classifier on one API key.
OCNORA ships 12 typed Jina AI operations. Each node has a schema-driven form, input and output tables beside its settings, and is pre-flighted by Workflow Health before your first real run. Endpoints not covered by a typed node are called at https://api.jina.ai through the HTTP node with the same credential.
Before you connect Jina AI
- Authentication
- Bearer token
- Credential
- the API key, or {"api_key": "…"}
- Connection test
- Available: the stored credential can be checked against the provider when you add it. This is not a record that a test was run or passed.
What you can do with Jina AI
Operations, grouped by what they do to your data.
Create and send 2
Delete and cancel 1
Other operations 3
A sample Jina AI workflow
- 1A core triggerStart the run from a chat, form, manual, schedule, webhook, workflow trigger — no Jina AI trigger is needed.
- 2Get Batch Jobjina.get_batchPoll one batch embedding job and report its state and per-line completed and failed counts.
- 3Cancel Batch Jobjina.cancel_batchCancel a batch embedding job that is still running.
An outline built from this provider’s node contracts, not a recorded run. Each step’s output fields are available to the next in the field picker.
Every node below has a reference page: what it does, the connection it needs, its config fields with types, constraints and examples, and the shapes it emits.
Operations 12
- Cancel Batch JobCancel a batch embedding job that is still running.jina.cancel_batch
- Classify TextClassify inputs zero-shot against candidate labels, or with a classifier previously trained on this account.jina.classify
- Start Batch Embedding JobSubmit an asynchronous batch embedding job for a large corpus and return the job id and its starting status, not the vectors.jina.create_batch_embedding
- Create EmbeddingsTurn text, images or code into embedding vectors with a Jina embedding model, for semantic search or clustering.jina.embed
- Get Batch JobPoll one batch embedding job and report its state and per-line completed and failed counts.jina.get_batch
- Get ModelFetch one model's metadata: modalities, context length, pricing and the datacenters that serve it.jina.get_model
- List Batch JobsList the batch embedding jobs this API key has submitted.jina.list_batches
- List ModelsList the models this API serves, with their modalities, context length and pricing.jina.list_models
- Read URLFetch one web page through the Jina Reader and return it as LLM-ready markdown, HTML, plain text or a screenshot URL.jina.read_url
- Rerank DocumentsScore a list of documents against a query with a Jina reranker and return them ordered by relevance.jina.rerank
- Search the WebRun a web search and return the results already read into LLM-ready content, in search-engine results page order.jina.search
- Train ClassifierTrain a few-shot classifier from labelled examples, or add more examples to a classifier that already exists.jina.train_classifier
Jina AI questions
- How does OCNORA authenticate with Jina AI?
- With a stored Bearer token credential, shaped the API key, or {"api_key": "…"}. A connection test can check it when you add it.
- What can I automate with Jina AI?
- 12 typed operations, each with a reference page listing its config fields and the shapes it emits.
- What if the Jina AI operation I need is not listed?
- Call https://api.jina.ai from the HTTP node with the same credential, or describe the step to the AI builder, which asks our team for a typed node when one is missing.
- Are there templates that use Jina AI?
- Not yet. Start from a blank workflow, or describe the workflow to Build with AI.
- How are Jina AI calls controlled?
- Every call and every run step is audited, runs count against the tenant’s token and USD budgets, and Workflow Health pre-flights the workflow when you save it.
More in AI & models
See your first Jina AI workflow run.
Book a technical demo. We add the connection, pick a template or describe the workflow to Build with AI, and Workflow Health checks it before it runs.