Skip to main content

Jina AI

Shanone’s Jina AI integration gives your agent 4 tools for turning the web into LLM-ready content — search with inline extraction, single-URL reading, multi-step deep research, and relevance reranking.

Getting Started

1

Get your Jina API Key

Generate a key from the Jina AI API page.
2

Add it to Shanone

Open Integrations in the Shanone dashboard, select Jina AI, and paste in your API Key.
3

Retry your request

Once saved, shanone_execute_tool calls for jina_* tools will succeed.

Available Tools

Shanone provides 4 tools for Jina AI, organized into these categories:
jina_search — web search that automatically fetches and returns the top 5 results’ content in LLM-friendly markdown, optionally restricted to specific sites
jina_read — convert any URL (web page, PDF, or MS Office document) to clean markdown, HTML, text, or a screenshot
jina_deep_search — an agent that reasons, searches, and iterates through multiple steps to answer complex questions with cited sources
jina_rerank — score and reorder a set of documents by relevance to a query using a cross-encoder model

Common Use Cases

Grounded answers

Use jina_search to pull current information into a response instead of relying on stale knowledge

Clean content extraction

Read a specific article or PDF with jina_read and get clean markdown without ads or navigation

Complex research

Hand off a multi-part research question to jina_deep_search and get a synthesized, cited answer

RAG quality improvement

Rerank retrieved documents with jina_rerank before feeding the top results to an LLM

Troubleshooting

Double-check the API Key saved in the Integrations page — Jina’s free tier keys and paid keys both work, but an expired or mistyped key will fail every request.
This is expected — DeepSearch reasons and searches iteratively, averaging around 56.7 seconds per query. Don’t treat a long wait as a failure; only retry if it actually times out or errors.
Documents must be separated with the ||| delimiter in a single string — check that your documents don’t contain that delimiter as part of their content, which would split them unexpectedly.