...

Links

Jumbo Bot Chat (requires TTS VPNa Tufts network connection (aside from Tufts_Guest))

• Test

• Stage

• Prod

Repositories

...

• Data: “Garbage in, garbage out” The training of any model hinges on accurate, high quality data in an optimal format. If a department lacks this, it can hinder development and even worse, lead to unreliable model output. Data can broken down into the following aspects:

  • Accuracy: The data for a process is accurate and up-to-date

  • Volume: There’s an adequate amount of data to train, per model requirements

  • Format: Data is in an adequate format for training

• Hallucinations: If a model lacks adequate data on a particular topic it can potentially provide false information. Tuning of model parameters (e.g temperature) can help minimize hallucinations.

• Infrastucture Costs

Data

Jumbo Bot’s responses are based on data scraped from the following websites on a weekly basis:

• https://access.tufts.edu/

• https://it.tufts.edu/guides

• https://tuftsedtech.screenstepslive.com

• https://tufts.edu

Technical Details

Technical details such as design, code, testing, deployment and data ingestion can be found here: https://github.com/Tufts-Technology-Services/jumbo-bot/blob/stage/README.md

...