Ingest AI - Build an AI knowledge base of what you know. Source: about 1 year ago

Congrats on this launch! We at IngestAI[1] are in similar space albeit with different focus - we answer from all internal documentation in Slack/Discord/Whatsapp. We did a show hn just a few weeks ago[2] & has been wild since then - we have close to 10k+ users and counting. If you would like build slack/discord/whatsapp/telegram bots answer your customer questions from internal docs - please try us [1] :... - Source: Hacker News / over 1 year ago

The title makes it sound like those are mutually exclusive but I thought there was a bunch of services doing exactly what they are describing, all built on ChatGPT. E.g. https://ingestai.io/. - Source: Hacker News / over 1 year ago

How does this compare in terms of latency, cost, and effectiveness to jsonformer? https://github.com/1rgs/jsonformer. - Source: Hacker News / 11 months ago

I'm not sure how this is different than: https://github.com/1rgs/jsonformer or https://github.com/mkuchnik/relm or https://github.com/Shopify/torch-grammar Overall there are a ton of these logit based guidance systems, the reason they don't get tons of traction is the SOTA models are behind REST APIs that don't enable this fine-grained approach. Those... - Source: Hacker News / 11 months ago

You're correct with interpreting how the model works wrt it returning tokens one at a time. The model returns one token, and the entire context window gets shifted right by one to for account it when generating the next one. As for model performance at different context sizes, it's seems a bit complicated. From what I understand, even if models are tweaked (for example using the superHOT RoPE hack or sparse... - Source: Hacker News / 11 months ago

From here, we just need to continue generating tokens until we get to a closing quote. This approach was borrowed from Jsonformer which uses a similar approach to induce LLMs to generate structured output. Continuing to do so for each property using Replit's code LLM gives the following output:. - Source: dev.to / 12 months ago

Https://github.com/1rgs/jsonformer or https://github.com/microsoft/guidance may help get better results, but I ended up with a bit more of a custom solution. Source: 12 months ago