I feel like you can do the same using a single markdown file and an LLM (e.g. Claude Code).
I do it that way and then I hooked it up with the Telegram API. I’m able to ask things like “What’s my passport number?” and it just works.
Combine it with git and you have a Datomic-esque way of seeing facts getting added and retracted simply by traversing the commits.
I arrived to the solution after trying more complex triplets-based approach and seeing that plain text-files + HTTP calls work as good and are human (and AI) friendly.
The main disadvantage is having unstructured data, but for content that fits inside the LLM context window, it doesn’t matter practically speaking. And even then, when context starts being the limiting factor, you can start segmenting by categories or start using embeddings.
I'm curious, how do you find your passport number in Telegram? Do you embed every message and then do cosine similarity to find the message that is relevant to the question? Please write about your system more :)
Specifically, it’s a file that contains a list of Entity-Attribute-Value assertions in triplets.
It’s called “FACTS.md” and each line represents a fact. Such as “<OP>, PASSPORT_NUMBER, <VALUE>”
Then put it in context, ask question, and then use Telegram API and suddenly I have a “Private ChatGPT” that’s aware of my filesystem, can run my own binaries/tools, and has access to a private document store.
It gets cool once you add function calling to open images on demand (or any type of file) with vision capabilities/OCR and you start running shell commands and combining that with many media types from Telegram.
Funny enough, I called the project “COO” initially. Been thinking of writing up something about it.
I think it’s a no brainer and I’m confident OpenAI, Claude, and Notion will go there.
In the meantime, I have good-ol’ vi, .md/.txt, and HTTP/SMTP!
I do it that way and then I hooked it up with the Telegram API. I’m able to ask things like “What’s my passport number?” and it just works.
Combine it with git and you have a Datomic-esque way of seeing facts getting added and retracted simply by traversing the commits.
I arrived to the solution after trying more complex triplets-based approach and seeing that plain text-files + HTTP calls work as good and are human (and AI) friendly.
The main disadvantage is having unstructured data, but for content that fits inside the LLM context window, it doesn’t matter practically speaking. And even then, when context starts being the limiting factor, you can start segmenting by categories or start using embeddings.