Back to directory

jina-cli

A Unix command-line wrapper over Jina AI's search, read, embedding, and reranking APIs, designed so an AI agent with shell access can call one consistent tool instead of many separate API integrations.

jina-cli

jina-cli exposes Jina AI's hosted APIs as ordinary Unix commands, built for both human use and for AI agents that already have shell access. Its commands cover reading a web page as clean Markdown, web search, including academic search through arXiv and SSRN, generating embeddings, reranking a set of documents by relevance to a query, classifying text into given labels, deduplicating text, capturing a screenshot of a URL, searching bibliographic citations, expanding a query into related queries, extracting figures and tables from a PDF, and guessing a page's publish date.

Every command reads from standard input and writes to standard output, so commands chain together with ordinary pipes, for example piping a search result into the rerank command. The project's stated reasoning is that an agent needs only one shell command with self-discovering help output, instead of many separate tool definitions for the same API surface. It installs from PyPI and requires a Jina API key set as an environment variable.

More in RAG

See all 540
  • ai·rete·rag

    ai-rete-rag.com

    A platform that pairs a Rete rule engine with retrieval-augmented generation, so deterministic rules decide an outcome and grounded retrieval explains the decision in plain language.

  • Xtriever

    github.com

    A hybrid retrieval engine for retrieval-augmented generation, written in Rust to run on-device on a phone or a laptop, combining lexical BM25 search, dense embedding search, reciprocal-rank fusion and cross-encoder re-ranking with no server.

  • FileFlux

    github.com

    A .NET library that turns PDF, DOCX, HWP and other documents into optimized chunks for RAG systems, through a five-stage pipeline built on high-performance Rust FFI readers.