llm-app VS streamlit

Answering queries and defining alerts: Our application running on Pathway LLM-App exposes the HTTP REST API endpoint to send queries and receive real-time responses. It is used by the Streamlit UI app. Queries are answered by looking up relevant documents in the index, as in the Retrieval-augmented generation (RAG) implementation. Next, queries are categorized for intent: an LLM probes them for natural language commands synonymous with notify or send an alert.

(used in https://github.com/pathwaycom/llm-app/blob/69709a2cf58cdf6ea...)

In this case, you need to build a custom LLM (Language Learning Model) app efficiently to give context to the answer process. A promising approach you find on the internet is utilizing LLMs with vector databases that come with costs like increased prep work, infrastructure, and complexity. Keeping source and vectors in sync is painful. Instead, you can use an open-source LLM App library in Python to implement real-time in-memory data indexing directly reading data from any compatible storage and showing this data on Streamlit UI.

🔗 - Here's the repo link: https://github.com/pathwaycom/llm-app.

To quickly get to the application sources please go to:

- https://github.com/pathwaycom/llm-app/blob/main/llm_app/path... for the simplest contextless app

- https://github.com/pathwaycom/llm-app/blob/main/llm_app/path... for the default app that builds a reactive index of context documents

- https://github.com/pathwaycom/llm-app/blob/main/llm_app/path... for the contextful app reading data from s3

- https://github.com/pathwaycom/llm-app/blob/main/llm_app/path... for the app using locally available models

This article explores how LLMs(Large Language Models) and LLM apps such as Pathway can be leveraged for effective and efficient developer education, which can boost the utilization of your product.

UI: Streamlit for creating an interactive and user-friendly interface.

Streamlit - quickly creates web UI from Python without much frontend skills, great for POCs (Streamlit API Reference)

Streamlit is a platform that enables you to build web applications that can be hosted in the cloud in just minutes. It helps you build interactive dashboards, generate reports, or create chat applications. Once you’ve created an app, you can use the Community Cloud platform to deploy, manage, and share your application.

Go to the Streamlit website, and you'll see written in front of you: "A faster way to build and share data apps". That seems to be what we're looking for 😄. A few minutes browsing the documentation confirms it. It's simple to install, use, and deploy, and it's all in Python. Let's see if it fits the bill!

I decided to use Streamlit to build the UI as it is a popular and fitting choice. Streamlit is an open-source Python library used for building interactive web applications specially for AI and data applications. Since the application code is written only in Python, it is easy to learn and build with.

Streamlit (https://streamlit.io/)

Does it need to be live (i.e when database or underlying spreadsheet updates does it need to be reflected in real time on the dashboard) or are you ok with static display.

Live updating data is a pain I've messed around using javascript to force refresh html iframes on a timer. But I was never really satisfied with this. I've heard you can do things with websockets but that is starting to get too complicated for me (I'm not a programmer).

For static stuff one of the data scientists in my org pointed me to Streamlit (https://streamlit.io/) it's a python package I found very easy to use. Can easily combine SQL with CSV imports and display them all on one dashboard. Can use forms toggle butotns etc to control the display.

Note that there are many tools that make this easier/simpler to prototype, including chainlit, streamlit, etc… The backend API we built is amenable to interacting with them as well.