Halaman ini masih berbahasa Inggris.
Lens
Read research PDFs, annotate passages, and ask questions across your documents.
Jalaran Lens is a research reading workspace where you read PDFs, annotate passages, and ask questions answered from one paper or across your whole collection.
Who Lens is for
For researchers holding forty papers on one topic who need to know which of them said the thing they half-remember. Cross-document question answering is the feature that turns a folder of PDFs into something you can interrogate.
What Lens does
Upload research PDFs and Lens extracts and embeds the text, then lets you read each one in the browser and save annotations against specific passages. Questions can be scoped to a single paper or asked across the whole collection, with answers grounded in retrieved passages rather than in the model’s general knowledge, so the answer points at where it came from and you can check it. That checkability is the entire point when the material is research you intend to cite.
- In-browser PDF reading with passage annotation
- Single-document and cross-document question answering
- Answers grounded in retrieved passages you can verify
- Text extracted and embedded on upload
How Lens works
Upload your PDFs
Text is extracted and embedded so passages can be retrieved by meaning rather than by keyword.
Read and annotate
Read in the browser and save annotations against specific excerpts, so a passage and your reaction to it stay together.
Ask one paper a question
Scoped to a single document when you know which one you need.
Ask the whole collection
Cross-document questions answered from retrieved passages, which is how you find the paper you half-remember.
What Lens does not do
Lens reads PDFs with an extractable text layer. A scanned image with no text layer will not work, because there is no OCR: a real limit for older papers. It does not fetch papers for you and has no publisher integration, so you supply the files. Answers are grounded in retrieved passages, which means a passage that retrieval misses is a passage the answer will not reflect; verify before citing.
Common questions
- Does it work with scanned PDFs?
- No. There is no OCR, so a scan with no text layer cannot be read or embedded. Papers digitised properly work; photographs of pages do not.
- Can I trust the answers enough to cite them?
- Verify first. Answers are grounded in retrieved passages and point at their source so you can check, but retrieval can miss a relevant passage. Use it to find the paper, then read the paper.
- Does it find and download papers?
- No. You supply the PDFs. There is no publisher, arXiv or library integration.
Works well with
All modules in Study and write
Link atomic notes with [[backlinks]] into a concept graph: a Zettelkasten second brain.
Look up papers by DOI, manage references, and export APA 7 or IEEE bibliographies.
Structured long-form writing for theses, papers and reports, with per-section goals and AI critique.
Track what you are reading and watching, and synthesise across your own notes.
Run scholarship, grant and conference submissions through a seven-stage pipeline.
Pull the entities out of raw text and turn them into already-linked Vault notes.