datahub VS spaCy

Sounds like you are looking for a data catalog tool instead of db schema management tool. You can check out Amundsen (https://www.amundsen.io/), DataHub (https://datahubproject.io/)

If you are looking for schema change management tool, then you can check out Bytebase (bytebase.com). But it can't answer questions like "which collections contain links to bigmongo.user.id?"

IIUC DataHub (open source project out of LinkedIn) might be relevant here

I’m a huge fan of DataHub, the open source data catalogue spun out of LinkedIn, but it’s best thought of as an observability layer for data assets that can be shared by data engineers and analyst-types. For data users: it’s a stellar search/discovery interface (what datasets are there on this keyword, which are most broadly used across the organization, what downstream products are made with this data, what’s it usually joined to, are it’s upstream pipelines reliable). For data engineers, it’s a comprehensive asset cataloger, crawling your warehouse, orchestrator, modeling layers, features, and reports, matching the lineage into a graph where it can.

If you are looking for a data cataloguing solution, look at Datahub. Haven't used it, but heard good things about it.

What I am looking for is a solution (similar to Amundsen or [Datahub](https://datahubproject.io/)) that also allows to add tables and their metadata manually.

Hello everyone, I'm looking for an open-source data lineage app (e.g. tokern, datahubproject, openmetadata).

What about DataHub? Haven't really used it but I'm actively reading about it and about to use it for some light documentation for some small pipelines.

Hi Community, In this article, I will demonstrate below steps to create your own chatbot by using spaCy (spaCy is an open-source software library for advanced natural language processing, written in the programming languages Python and Cython):

SpaCy: An open-source library providing tools for advanced NLP tasks like tokenization, entity recognition, and part-of-speech tagging.

spaCy https://spacy.io/

In this article, I'm going to walk through a sentiment analysis project from start to finish, using open-source Amazon product reviews. However, using the same approach, you can easily implement mass sentiment analysis on your own products. We'll explore an approach to sentiment analysis with one of the most popular Python NLP packages: spaCy.

Spacy [0] is a state-of-art / easy-to-use NLP library from the pre-LLM era. This post is the Spacy founder's thoughts on how to integrate LLMs with the kind of problems that "traditional" NLP is used for right now. It's an advertisement for Prodigy [1], their paid tool for using LLMs to assist data labeling. That said, I think I largely agree with the premise, and it's worth reading the entire post.

The steps described in "LLM pragmatism" are basically what I see my data science friends doing — it's hard to justify the cost (money and latency) in using LLMs directly for all tasks, and even if you want to you'll need a baseline model to compare against, so why not use LLMs for dataset creation or augmentation in order to train a classic supervised model?

[0] https://spacy.io/

[1] https://prodi.gy/

spaCy

I chose spacy. Although it's not state of the art, it's very well established and stable.