Who it is forA graduate student or researcher with a folder of PDFs who needs quick, sourced answers to questions about their reading list.
The problemSearching many PDFs by hand for one claim or method is slow, and chat answers without sources are hard to trust.
The outcomeA running local workspace where each answer cites a passage, and clicking the citation opens the highlighted spot in the PDF.
What you need first
- Docker, or Python 3.11+ and Node.js 20+ for the local setup
- An OpenAI API key for chat
- A contact email for the EMAIL setting used by citation lookup
- A TypeSafe API key only if you want the Compare feature
Steps
- Run
cp backend/.env.example backend/.envand set OPENAI_API_KEY and EMAIL in backend/.env. - Run
docker compose up --buildfrom the repo root and wait for the first build to finish. - Open http://127.0.0.1:5000 in a browser and upload one or more PDFs to the library.
- Ask a question in chat, then click a citation to jump to the highlighted passage in the preview.
- Run
docker compose downwhen you are done. Your papers and chat history stay in the thesys-data volume.
Prompt for your agent
Use the Sreehari05055/thesys-core repo to set up a local research workspace with Docker, set OPENAI_API_KEY and EMAIL in backend/.env, and upload the PDFs in <path-to-pdf-folder>. Report the chat answer to the question <your question> and the citation it links to. Verify that clicking the citation opens the highlighted passage in the PDF preview.
Caveat. The first ingest downloads Hugging Face weights inside the container, and chat needs an OpenAI API key, so the answers are not fully offline.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page