Replies: 1 comment
|
Additional Use, can be used to store additional relationship data: secondary associations, use-cases, code samples, extended OKF generation context |
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
The current architectures and service limitations of Gemini Enterprise are designed for efficiency for embedding generation and searchable indexes. This results in limited context awareness for tabular and hybrid tabular data.
Example Need
Spreadsheets commonly contain a hybrid of media, functions, and tabular data. The current OKF file spec enables the generation of data descriptions and embedded images, but the spatial and/or logical context is either lost or inefficiently consumed when only the summary data description/insights are needed for corpus awareness.
Solution
YAML back matter containing named sections are easily identified within markdown files. If deeper context into the positioning or data supporting embedded images is needed, then optional sections provides a means to reference additional data which increases efficiency by reducing the need for higher embedding limits or file/corpus ingest and subsequent analysis.
All reactions