llmflows VS llm-app

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.