PytorchConnectomics / PytorchConnectomics/pytc-client

feature: natural language to initial workflow config

Open
#95 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

low priority
Dominant language
Python
Stars
2
Forks
6
PR merge metrics
No merged PRs in 30d

Description

a formalization of hanson's current item:

as it stands, the initial workflow setup requires the user to manually select every module that they wish to utilize.

Image

ideally, the user should be able to describe their workflow in natural language, and have their workflow configured for them.

mechanistically, this consists of implementing an llm which, when given a semantic of a workflow, outputs a config file corresponding to a set of modules to be used in the app which are then loaded from that. Ensuring the llm outputs a working config file will require a bit of prompt engineering/repeat querying to ensure that we conform to the rigid format.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue names no files, tests, model provider, or config schema. Start by locating the initial workflow setup and the module configuration format; define how natural-language input becomes a validated config and confirm that the selected modules load successfully.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.