galgia

Every time I start a new project I have to collect the data and guide clients through the first few weeks before I get some decent results to show them. This is why I created a libary to quickly build classic data science pipelines with LLMs, which you can use to demo any pipeline and even use it in production for non-critical use cases.

Good point! LLMs are best when you are starting from point 0.

LLMs are not the most efficient way to solve the problem, but they can solve it.

Exactly, scale after you need to.

Yes, LLMs are not always the best option, they are an option. Sometimes requirements of the project are such that they are also the best option.

There is one browser that uses price matching example that is impossible to do without a full-blown data science team right now: https://github.com/Pravko-Solutions/FlashLearn/tree/main/exa...

+ I assumed that most people will ctrl+a -> ctrl+c -> ChatGPT -> ctrl+v

I belive that LLMs will become better and better in the near future and pipelines will replace classic approaches with LLM-enriched pipelines will drastically simplify the ETL flows.

If your problem is compute, you are already optimizing. This is here for all the steps before you start thinking latency-compute. Not all use cases are made equal.

I see it as a gray area - long term there will be a need for both and you will have just one tool to choose from when presented with time-budget-quality constraints.

You are right! This is here to be used when your resources do not allow you to build full-blow solutions. Yes, I used LLMs to help create examples from my existing code, but they are based on things I have put in production when the client's resources were limited and wanted to move from point 0 to test out the potential of LLMs on their data.

Exactly!

Thank you! It took a while :)

Every time I wanted to use LLMs in my existing pipelines the integration was very bloated, complex, and too slow. This is why I created a lightweight library that works just like scikit-learn, the flow generally follows a pipeline-like structure where you “fit” (learn) a skill from sample data or an instruction set, then “predict” (apply the skill) to new data, returning structured results.

High-Level Concept Flow

Your Data --> Load Skill / Learn Skill --> Create Tasks --> Run Tasks --> Structured Results --> Downstream Steps

Each step results can be turned to JSON and reused later or elsewhere.

Installation:

pip install flashlearn

Minimal Perplexity clone.

What it does:

- Input user query - Generate 1 to n google queries to find the answer - Use this queries to query Google - Generate response with links to sources

You can retrieve from any source line this and improve the quality of answers for multi-hop questions from your users.

Have fun!

When you want AI to perform tasks independently, it's important to be able to control it and understand its actions. Additionally, you need a way to organize the results and manage the inputs efficiently. FlashLearn simplifies this process by using JSON definitions to structure everything clearly. This structured approach ensures that you can easily define tasks, process results, and handle inputs, making AI management more straightforward.

Yes, you can! The responses are always structured, you will have to read the files yourself (as img/text/audio or mixed) and then you can feed them to the FlashLearn agent to complete tasks with them.

Yes, you can find them on GitHub in the folder /examples. There you will find more samples and flows on how to use it. The examples are elementary, but they should give you an idea of how to build one.

This is very useful if you plan to do business in the EU!

OP here!

I made a free ChatGPT bot for students with a bit of smart prompt engineering and data structuring(embeddings). There is a PRO version for longer responses etc. but you will not need it in 99% of the cases :)

Hey!

If you have been playing around with OpenAIs APIs you know how annoying it is to actually integrate them to existing rpducts, since it's responses are not consistent and are really just generated text.

I have created an API that structures the responses for the most common NLP tasks to simply intgerate it into any existing app.

Have FUN!

Yes, we need to build a better index. Right now we are at around 1.5k reviews but we should get to around 100k in the next few weeks. Would you be intrested to submit the product you would like the review be generated for?

Hello everyone,

We are excited to announce the launch of our new review system that uses cutting-edge data mining and natural language processing technology. Our system gathers millions of reviews from various platforms and presents them to you in an unbiased and comprehensive format, all the reviews are summarized by AI with no human intervention.

Our goal is to help you make informed decisions by providing you with a deeper understanding of the thoughts and feelings of real users. We utilize the latest advancements from OpenAI's GPT-3 technology to provide the most insightful reviews, giving you a more complete view of a product before making a purchase.

Please visit https://peereviews.net/ and check it out, We would love to hear your thoughts.