CelVoxes/thinkR
gpt-o1 like chain of thoughts with local LLMs in R
This R package helps data scientists and analysts get more transparent and step-by-step reasoning from local Large Language Models (LLMs). You input a query or problem, and it outputs not just the answer, but also the intermediate thought process the LLM used to arrive at that answer, complete with confidence scores for each step. This allows R users to better understand how an LLM reaches its conclusions.
No commits in the last 6 months.
Use this if you are an R user who needs to understand the reasoning behind an LLM's answer for debugging, validation, or compliance purposes.
Not ideal if you primarily need quick, direct answers from an LLM without concern for its underlying thought process.
Stars
31
Forks
3
Language
R
License
—
Category
Last pushed
Oct 15, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/CelVoxes/thinkR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
SimonAytes/SoT
Official code repository for Sketch-of-Thought (SoT)
xuyige/SoftCoT
ACL'2025: SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs. and preprint:...
Fr0zenCrane/UniCoT
[ICLR 2026] Uni-CoT: Towards Unified Chain-of-Thought Reasoning Across Text and Vision
logikon-ai/cot-eval
A framework for evaluating the effectiveness of chain-of-thought reasoning in language models.
nicolay-r/THOR-ECAC
The official fork of THoR Chain-of-Thought framework, enhanced and adapted for Emotion Cause...