minuva/llm-flow-classification

LLM conversation flow classification 💬

20
/ 100
Experimental

This system helps AI product managers and developers understand how users interact with their LLMs by classifying conversation segments. It takes an LLM's input and output, such as a user's question and the LLM's response, and identifies specific conversational patterns like user complaints or agent apologies. This provides valuable insights for analytics and improving LLM performance.

No commits in the last 6 months.

Use this if you need to automatically categorize specific user and agent behaviors within LLM conversations to gain insights into interaction patterns.

Not ideal if you are looking for a standalone chat application or a general-purpose sentiment analysis tool, as this is focused on specific conversation flow events.

LLM analytics AI product management conversation design user experience monitoring chatbot performance
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Python

License

Apache-2.0

Last pushed

May 31, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/minuva/llm-flow-classification"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.