jakobgm
Joined 9 years ago
Joined 9 years ago
Any new to share on file upload support? We have shipped a MCP server and it has been really frustrating to observe MCP clients fumbling around with base64-encodings, polluting their context window with binary data. SEP-1306 (Binary Mode Elicitation) was superseded by SEP-2356 (File input support for tools and elicitation), and that was in turn superseded by SEP-2631 (File Objects and Transfer) which is currently left in a draft state with little activity.
Allowing LLM-based agents to shuffle binary data around efficiently and reliably seems like a pretty big gap in the current specification, if you ask me!
In case anybody else also isn't familiar with "PI" as an abbreviation in this context:
> In many countries, the term principal investigator (PI) refers to the holder of an independent grant and the lead researcher for the grant project, usually in the sciences, such as a laboratory study or a clinical trial.
Source: https://en.wikipedia.org/wiki/Principal_investigator
The data set is apparently ~20GB [0], so a cheap VPS instance might do the job of hosting the data in a searchable format.
[0] https://github.com/github/CodeSearchNet#downloading-data-fro...
Especially happy to see Tesseract OCR v4.0 [0] now being in the mainline repository. Tesseract was the main motivation for changing my web stack to docker a couple of weeks ago, and I had to use a separate builder image [1] in Alpine 3.8. Now it is just:
> apk add tesseract-ocr
[0] https://pkgs.alpinelinux.org/package/v3.9/community/armhf/te...
Co-founder and CTO at https://cardboard.inc
[ my public key: https://keybase.io/jakobgm; my proof: https://keybase.io/jakobgm/sigs/OiTDj-6QsuKd3J5lyucT_PKet8_XLeG3J4yc0D514oU ]