NextNeural/LUNA

LUNA - Latent Understanding & Narrative Assembly

LUNA is the file-synthesis tool of Next Neural Labs. Drop up to 100 files of any type (documents, spreadsheets, code, images, audio, video) into a task, tell LUNA what to build (e.g. "Everything about climate change in Italy"), and it returns one structured Note - Title, Agenda, themed Body, and a Sources section that credits every file it actually used.

How it works

1. 1.Categorize - each upload is sorted by type (text / document / image / audio / video / spreadsheet / code / …).
2. 2.Extract in parallel - content is pulled from every file concurrently to keep cost and latency low: documents/sheets/code are parsed to text, images are read by a vision-language model (description + on-screen text), audio/video are transcribed with Whisper.
3. 3.Map (extract + grade) - a fast model reads each file, always extracts its content, and grades how well it serves your prompt (high / medium / low / none). The grade is advisory and the extraction is never thrown away, so a shaky per-file call can't silently lose a file's content.
4. 4.Reduce (synthesis) - a strong model sees every file's extraction together and is the final judge of what to use. It fuses the relevant material into the Note (in the language of your prompt). If your prompt targets one thing (e.g. "what's on the video"), it answers from that and sets the unrelated uploads aside instead of summarizing them "just in case". A file is either used (in the body + Sources) or not used (one short line) - never both.

The front-end lives at https://app.nnlabs.pl/luna; this Space exposes the build API the website drives. Uploaded files are processed and then purged - only the generated Note is stored (in the website's database).