DocsCatalogPricing
Sign inStart research

Start

Docs homeGetting started

Product

WorkspaceLibrary filesAbstractsPresentationsDashboards

Admin

OrganizationsSecurity & privacy

Developers

Developer APIMCP serverIntegrationsTool catalog

Documentation

Docs homeGetting startedWorkspaceLibrary filesAbstractsPresentationsDashboardsOrganizationsSecurity & privacyDeveloper APIMCP serverIntegrationsTool catalog
Documentation

Library files

Upload source material once and reuse it across every research session — no re-uploading.

Open your library
Research library
2 folders · 4 files · reused across sessions
Drop to upload
Trial operations
Folder · select several files with @
trial-cohort-baseline-2026.csv
412 rows · 18 columns
alzheimers-tau-pet-meta-analysis.pdf
27 pages · cited 11 times
consort-2025-revisions.docx
38 pages · attached to 2 sessions
uploading: enrollment-q1.csv
Uploading…
Drag & drop PDFs, CSVs, or docs here. Files become reusable context for every future session.

What to upload

Anything that should ground a session or become reusable context.
Papers & reports
PDFs, policy docs, whitepapers, and research notes.
Datasets
CSV, Excel & tabular files to clean, summarize, or analyze.
Scientific data
EEG (EDF/BrainVision), ECG/WFDB, NWB & HDF5, NIfTI & DICOM imaging, genomics, mass-spec, and molecular structures become ready from trusted upload metadata; the compute sandbox validates and reads the stored original only when you analyze it. Large recordings are read in bounded windows rather than loaded wholly into memory. An uploaded structure (PDB, mmCIF, SDF, MOL2) can also be rendered in the inline 3D viewer — your own coordinates, not a public entry for the same molecule.
Reference material
Protocols, schemas, dictionaries, and background docs.

Each file can be up to 5 GB, and a Library holds up to 5,000 files or 50 GB in total — the same on every plan, personal or organization. Saving a generated artifact back to the Library is capped at 25 MB.

Executables, installers, and opaque archives (like .exe, .dmg, or .zip) are not accepted — upload the underlying research files directly. PowerPoint files (.pptx) are also not accepted; to build slides, ask for a presentation instead. Multi-file scientific formats (BrainVision .vhdr/.vmrk/.eeg, WFDB .hea/.dat) work best uploaded together into one folder so Cortexa can stage the whole bundle.

Large text and delimited datasets remain stored in full, but the searchable preview is built from the first 4 MB of a text, CSV, TSV, or JSON file, and keeps at most 200,000 characters — otherwise upload processing would stall on a large file. This matters when you ask a question the whole file has to answer, such as counting rows or finding the maximum of a column: ask for the analysis rather than the preview, because analysis tools receive the original file and read it in chunks.

Visual analysis accepts valid PNG, JPEG, WebP, and GIF images up to 5 MB. Cortexa reads an image by looking at it, and does not yet recognize text inside one — a scanned page or a screenshot of a table is described rather than transcribed, so upload the underlying PDF or CSV when the words or figures matter. Cortexa validates the stored image before model analysis and asks for a replacement instead of failing the session when bytes are corrupt, mislabeled, or in an unsupported SVG or unconverted HEIC format.

Folders & workspaces

Organize reusable files without weakening workspace isolation.
One-level folders
Create folders, upload directly into them, and move or delete several selected files at once. Deleting a folder returns its files to Library root.
Workspace separated
Personal and organization Libraries are separate. Folders and files are private by default; sharing is always explicit.
Website snapshots
Public website crawls save a private Markdown snapshot with one inspectable URL and content fingerprint per page. They count toward the same Library storage limits as uploaded files.

How to use files

Mention a file by name and the agent uses it — attach in chat for one question, or save it to the Library to reuse everywhere.
Enrollment QA
Library file · enrollment-q1.csv
Live
Use the uploaded enrollment-q1.csv — flag any missing fields before we build the training split.
Tools usedenrollment-q1.csv
3 columns have missing values: age (4%), site_id (1%), baseline_score (7%). I'd impute age and baseline, then drop rows missing site_id. Want a cleaned table?
3 columns have missing values: age (4%), site_id (1%), baseline_score (7%). I'd impute age and baseline, then drop rows missing site_id. Want a cleaned table?
enrollment-q1.csv
Ask Cortexa — drugs, genes, trials, structures…

Select @ in the composer to open the Library browser. Use Select all on a folder or check individual ready files, then choose Attach files. The message stores a snapshot of the selected file references, so later folder changes do not alter historical chats.

You can also drag files onto the composer, or paste a screenshot straight into it — a pasted image is saved with the date and time you pasted it, so several are still tellable apart. A copy that carries both an image and text (a spreadsheet range, say) pastes as text.

Files you attach with the paperclip in chat are session uploads — they stay with that conversation until you delete the session. To reuse one in future chats, abstracts, or decks, click Save to Library on the attachment chip (before or after sending). Scope only changes when you click that button; nothing is silently promoted.

Saving generated artifacts

Outputs Cortexa creates stay in the transcript. Save one to the Library to reuse it later.
Transcript artifact
Great for review and citation in this session. Not mounted into the next Python run.
Library file
Saved for durable reuse across future sessions, analysis, abstracts, and presentations.

Good hygiene

A little naming discipline helps teammates and the agent alike.
Descriptive filenames
trial-cohort-baseline-2026.csv beats data_final.csv.
Separate raw & derived
Keep originals immutable; put cleaned outputs in experiments.

On this page

What to uploadFolders & workspacesHow to use filesArtifactsGood hygiene
Cortexa.

The agent for research teams. 1.4K+ research tools across scientific and professional fields, with sources attached to the claims they support.

Product

  • Documentation
  • Integrations
  • Tool catalog
  • Security & privacy
  • Pricing

Get started

  • Start research
  • Sign in
  • Developer API
  • MCP server

Support

  • Help center
  • Contact us
  • Terms of Service
  • Privacy Policy

© 2026 Cortexa. All rights reserved.

TermsPrivacy·For research context only · Not medical, legal, or financial advice.