Knowledge Base

The Sources Behind Every Default

AiMolSim Knowledge holds the papers, books and data the engine is built from, and your own Knowledge Base keeps your reports searchable on your server.

Get Started Request a Demo

A small research team in a library-style room, one person pointing at a wall display of connected document cards and a search bar

Walkthrough

From Source to Result

How a method traces back to its paper, its equations and a printed check.

Space or K plays and pauses, the arrow keys step. With reduced motion every step is shown at once.

Knowledge-backed scienceReal citations from the engine

S1 Peer-reviewed papers
S2 Academic textbooks
S3 Benchmark data sets
S4 Experimental reference data
S5 Curated databases
S6 Numerical analysis
S7 Standards and specifications
S8 Basis-set and parameter libraries
S9 Research monographs
S10 V and V studies
S11 Technical reports

1. Eleven source classes Every formula, parameter and number cites the highest class that carries it.

Eleven Source Classes, Ranked

Every formula, parameter and number cites the highest class that carries it. Each library item is tagged with its class.

Peer-reviewed journal articles, with their Supporting Information and errata
Academic textbooks from university or major scientific publishers
Computational benchmark data sets, published and versioned
Experimental reference data, critically evaluated (for example CODATA)
Curated reference databases (for example NIST CCCBDB)
Numerical analysis literature
Standards and specifications (IUPAC, file formats)
Basis-set and parameter libraries, data only, never program code
Research monographs
Verification and validation studies
Technical research reports, only when free to use for business

Not accepted as ground truth: lecture notes, blogs, wikis, software manuals, or other programs' code and output. Preprints count only alongside their published version.

Hybrid Search

Keyword matching, including Chinese characters, fused with semantic vectors by reciprocal rank fusion, with an optional rerank. Live

Vectors on Your Server

Qdrant runs on your own AI server and is the single search store. Install needs Internet access once. Live

Public and Private

Organisation documents and personal ones, with Projects as tags. Names are renamable per organisation.

AI Tags

A summary, type and tags for every document, so folders stay searchable.

Folder Upload

A desktop app uploads whole folders with subfolders, and a vision model reads scanned drawings.

Chemistry Lab Feeds It

Study Reports are saved to Public, Reports, Lab in the Knowledge Base
Verified sources keep their DOI, tier and retraction status
File storage can be a server, an S3-compatible store or the web server
Computation files from a Study are kept in a per-organisation store with a typed-confirmation purge

An engineer in a clean server room with racks of GPU servers holding a tablet that shows a dashboard of server tiles

Knowledge Questions

How does search work?

Documents are split into 1200-character chunks and embedded. Qdrant, running on your own AI server, stores the vectors. Search combines keyword matching with semantic vectors using reciprocal rank fusion, with an optional rerank, and rights are checked twice.

Who can see a document?

Public documents belong to the organisation and Private documents belong to one person. Projects tag folders and documents, and access rights are enforced on every search.

Can it read drawings and scanned PDFs?

Yes. A vision model can read PDFs that have no text layer. A desktop Knowledge Base app uploads whole folders with their subfolders.

Where are my files stored?

On a paired server, an S3-compatible store (AWS S3, Cloudflare R2, Backblaze B2, Wasabi, MinIO) or the web server, as you choose. Cloud vector databases have been retired; Qdrant on your own server is the single store for search.

Run Your Next Molecule Through AiMolSim

Describe a molecule and your question; the assistant drafts the plan and you approve it. Or see it first in a 30 minute demo.