[PR #246] [MERGED] TNT-LLM #1325

Closed
opened 2026-02-20 17:44:27 -05:00 by yindo · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/langchain-ai/langgraph/pull/246
Author: @hinthornw
Created: 3/31/2024
Status: Merged
Merged: 6/9/2024
Merged by: @nfcampos

Base: mainHead: wfh/tnt-llm


📝 Commits (5)

📊 Changes

2 files changed (+1084 additions, -0 deletions)

View changed files

examples/tnt-llm/img/tnt_llm.png (+0 -0)
examples/tnt-llm/tnt-llm.ipynb (+1084 -0)

📄 Description

https://arxiv.org/pdf/2403.12173.pdf

Haven't implemented the last steps (applying the taxonomy for labeling + training a log reg classifier ), but this is the more lang-graphy part.

If we want to include that, I think we could add as a second notebook perhaps since this is already sufficiently involved.

The other thing I may consider incorporating later is the steps to subdivide the data to add sub-categories. This would basically add two nodes:

  1. Label documents according to the given clusters.
  2. split state and recurse on this graph.

And then would make that conditional edge dependent on the depth the user configures (probably default to 0 or 1 levels of recursion)


🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/langchain-ai/langgraph/pull/246 **Author:** [@hinthornw](https://github.com/hinthornw) **Created:** 3/31/2024 **Status:** ✅ Merged **Merged:** 6/9/2024 **Merged by:** [@nfcampos](https://github.com/nfcampos) **Base:** `main` ← **Head:** `wfh/tnt-llm` --- ### 📝 Commits (5) - [`f4ef67c`](https://github.com/langchain-ai/langgraph/commit/f4ef67c5d3723e84c970fe221b6a49f9ada8962a) Draft tnt llm - [`62ac195`](https://github.com/langchain-ai/langgraph/commit/62ac195d391809dc6560b46a734fb27a6c5e18b5) Run TNT-LLM - [`ab0b6d3`](https://github.com/langchain-ai/langgraph/commit/ab0b6d3c0dfb984fc75df1864f646fb94c0e65df) Add img - [`6bfb9ec`](https://github.com/langchain-ai/langgraph/commit/6bfb9ec666aad2489a158db01006eed749f87c71) Include classification steps - [`2f22bb9`](https://github.com/langchain-ai/langgraph/commit/2f22bb9f10f19dd5f2ebe0ff1012982731c43206) commentary ### 📊 Changes **2 files changed** (+1084 additions, -0 deletions) <details> <summary>View changed files</summary> ➕ `examples/tnt-llm/img/tnt_llm.png` (+0 -0) ➕ `examples/tnt-llm/tnt-llm.ipynb` (+1084 -0) </details> ### 📄 Description https://arxiv.org/pdf/2403.12173.pdf Haven't implemented the last steps (applying the taxonomy for labeling + training a log reg classifier ), but this is the more lang-graphy part. If we want to include that, I think we could add as a second notebook perhaps since this is already sufficiently involved. The other thing I may consider incorporating later is the steps to subdivide the data to add sub-categories. This would basically add two nodes: 1. Label documents according to the given clusters. 2. split state and recurse on this graph. And then would make that conditional edge dependent on the depth the user configures (probably default to 0 or 1 levels of recursion) --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-02-20 17:44:27 -05:00
yindo closed this issue 2026-02-20 17:44:27 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/langgraph#1325