Love this package. has a bunch of functions for most face recognition, detection and feature extraction purposes. love the readme.md docs for familiarizing with the basic features. PLUS it offers different models(backends) for the tasks which lets you try out a bunch of approach for the same task without writing a custom function

could you share a few resources on it. looking forward to your writeup

There are already solutions to this kind of problem. Using embeddings to store semantic meaning -> query the vector database with a question -> use extractive q/a models to get relevant context -> using a Reader model to generate answers based on the context from the document.

just checkout Haystack tutorials. I started looking into it after getting introduced to the concept by articles mentioning OpenAI embeddings and GPT 3 api, but it can be done using open source models.

Would like to bring up LangChain as well : https://langchain.readthedocs.io/en/latest/. We recently integrated Milvus (https://milvus.io) into LangChain, so you'll be able to store and process billions of documents.

I used Haystack due to the readily available colab notebook[1] for their tutorials. I wanted to feed my own text corpus to it, and that was the fastest way available.

Langchain docs are helpful, and it would be even better if you published an end-to-end notebook using a popular dataset. Definitely looking forward to try langchain as I dive deeper into this.

1. https://haystack.deepset.ai/blog/how-to-build-a-semantic-sea...

You can checkout our library too which does just that :)

https://github.com/jerpint/buster

Is there documentation for feeding your own documentation into it?

We will be adding that soon

I use this method to answer questions about historic and real-time social media comments.

https://foretale.io/toolbox/Social_Media_QA

Thanks for such a detailed response.

I guess Canada is a safer bet in terms of career. Australia's weather is a plus for me, and I know a few people who moved there.

Anyways, looks like I can't go wrong either way.

fastai uses its forums to manage discussions for specific chapters. It wouldn't be hard setting it up, but the instructor would have to declare it in the video or description to actually send students to the forum.

fastai forum : https://forums.fast.ai/

fastai is a no brainer. You can go into the nitty gritty later, but doing this course will let you see the power of AI and deep learning from the start.

Thank you! Checking it out during winter break!

I also lost my father in 2021, and my life hasn't been the same. I have to deal with a ton of more responsibilities while taking care of my mother and brother. I was also very close to him, and we went on trips whenever we were free and shared similar interests in photography and cycling. I've been doing my best to live upto his expectations, and hope you'll be able to do so too. Best of luck friend.

I agree with this. It's gotten way easier to use pre-trained models to deploy software with custom prompt engineering.

As an aspiring web developer, I agree with his rationale. I believe I would be better able to connect and learn from other programmers IRL than online.

These are my favorite Blender resources:

- Blender Guru : Start with the Donut Tutorial

- Arrimus3D : For hard-surface modeling and topology (software agnostic)

- CGBoost : high information density

- Ian Hubert and Blender Secrets - Short and direct tutorials

- Erindale : Procedural Shader and Geometry Nodes

- CGCookie : another general Blender channel

- Derek Elliot : Product animation and motion graphics