DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to pull structured contact fields out of messy text with Needle

Use Needle 3 structured extraction to turn a sentence into fields like name, phone, and email.

Who it is forA person who receives contact details in free text, such as a message or a note, and needs them in a structured form.

The problemContact details buried in a sentence have to be copied by hand into fields, which is slow and error prone.

The outcomeStructured contact information pulled from the input text by the on-device Needle 3 model.

What you need first

  • An Android phone with Termux and the Termux:API app installed
  • Python and git available in Termux, with the Ubuntu PRoot environment set up as the README describes
  • A Telegram bot token if you want remote control

Steps

  1. Complete the Termux and Ubuntu setup from the README, then clone the repo and install requirements.txt in an activated virtual environment.
  2. Start the command-line assistant with python termux_needle.py --model 3.
  3. Type "extract contact info from: Call Alex Vance at +15550199 [email protected]" at the prompt.
  4. Compare the extracted name, phone number, and email with the original sentence.
  5. Repeat with your own text, changing only the sentence after the colon.

Prompt for your agent

In the Needle repo, run python termux_needle.py --model 3 and submit "extract contact info from: <text>" with the target text. Expect structured contact fields with name, phone, and email. Verify that each field appears verbatim in the input text before using the result.

Caveat. The README gives one example of structured extraction and does not describe the output format, so check the returned fields against the source text each time.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page