panodata / panodata/omniload

Unstructured

Open
#181 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

connector pitch
Dominant language
Python
Stars
5
Forks
4
Avg merge
9h 49m
Merged PRs (30d)
55

Description

About

Well. We didn't know that the venerable unstructured library already provides a complete ingest framework including a CLI and a Python API.

The Ingest Library is a powerful tool designed to coordinate the process of pulling data from data providers, partitioning the content, and pushing that new content to a desired location.

Evaluation

However, its array of destination connectors seems to be biased towards ingesting into vector databases, less general purpose SQL databases. However, after apparently converging to a dedicated unstructured-ingest package, this might change as we go.

References

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

Start with the linked unstructured ingest documentation, its destination connector pages, and the unstructured-ingest package referenced in the issue; also review GH-45 and the linked Suraya issue for project context. The issue does not define a target connector, files, tests, or acceptance criteria, so the desired outcome needs clarification before implementation.

Written by the indexing model from the issue text.

Assessment

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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.