Tolstoy Library

Overview

Tolstoy Library brings your video and image content into ChatGPT. If you're a Tolstoy merchant, your uploads, social imports, and product-tagged media are now a chat away. What you can do: • "Show me my 20 most recent library uploads" — instant list with thumbnails • "Find my beach reel" — search by name or UGC creator handle • "Get details for that asset, including its tagged products and playlists" • "Rename it to 'Summer launch hero'" or mark it as a favorite

Tools

get_asset

ChatGPT

Fetch full details for one or more library assets by id, including connections (tagged products, playlists, Shopify tags) for library (vod) assets. Input. assets is a batch of { id, type } pairs (1..50 entries). Read these from a prior list_assets result. The type discriminator is required because library (vod) and AI Studio (studio) assets live in separate stores. Output. For each asset: name, media type (video/image), favorite status, thumbnail URL, creation date. For vod assets only, also includes the products, playlists, and Shopify tags currently connected. Structured content carries all fields for programmatic use.

list_assets

ChatGPT

Returns the merchant's 20 most recent media library assets — a mixed feed of imported library content (videos, images, uploads, social imports) and AI Studio drafts (unpublished AI-generated content), each tagged with a type discriminator (vod or studio) so callers can distinguish them. Use this for: "what's in my library", "what's new", "show my recent uploads", "what AI drafts do I have", "show my favorites". This tool always returns the most recent 20 (no pagination, no search) — a recency feed, not a search interface. Filters. type narrows to one source. favoritedOnly returns only starred assets within the recent 20. Omit filters for the latest 20 across all sources. Output. Markdown list with each asset's name, type, creation date, and thumbnail URL. structuredContent.items carries { id, type } for each asset.

search_assets

ChatGPT

Find specific assets in the merchant's imported library (videos and images they uploaded or imported from social platforms) by display name or UGC creator handle. Returns up to 20 matches. Matching is OpenSearch match_phrase against the asset name AND the ugcUsername field. Phrase order matters; tokens are analyzed but must appear in sequence. No fuzzy matching, no typo correction. Use this when the user asks to find a specific asset by name: "find my beach reel", "show me videos from @cooluser", "do I have anything called summer dress?". Targeted lookup only — not for enumeration. Scope. Searches imported VOD library only (uploads, social imports, UGC). Does NOT search AI Studio drafts — Studio assets have no text-search backend. Output. Markdown list of matches with name, type, date, thumbnail. structuredContent.items carries { id, type: "vod" } for each match.

update_asset

ChatGPT

Rename an asset or toggle its favorite status. Works for both library (vod) assets and AI Studio (studio) drafts. Input. assetId and type identify the asset (read them from a prior list_assets or get_asset result). At least one of name or favorite must be supplied. Idempotent. Calling with the same name/favorite repeatedly is safe — the underlying service deduplicates. Output. Confirmation of what changed. The merchant sees the new state immediately in their platform UI.

Capabilities

InteractiveWrites

Links

Documentation ↗Privacy Policy ↗

App Stats

Tools

ChatGPT

Platforms

Works with

ChatGPT

Data refreshed daily