[PR #326] [MERGED] feat(common): add KAG to the awesome-deepseek list #442

New issue

Closed

opened 2026-10-26 09:57:52 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-26 09:57:52 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/awesome-deepseek-integration/pull/326
Author: @andylau-55
Created: 2/25/2025
Status: ✅ Merged
Merged: 2/25/2025
Merged by: @mowentian

Base: main ← Head: kag

📝 Commits (4)

49fa9b9 Update README_cn.md
3704666 Update README.md
4efb451 Update README.md
19fcb73 Update README_ja.md

📊 Changes

3 files changed (+15 additions, -1 deletions)

View changed files

📝 README.md (+5 -1)
📝 README_cn.md (+5 -0)
📝 README_ja.md (+5 -0)

📄 Description

Hi! I'd like to propose adding our project KAG to the awesome-deepseek list.

KAG is a logical reasoning and Q&A framework based on the OpenSPG engine and large language models, which is used to build logical reasoning and Q&A solutions for vertical domain knowledge bases. KAG can effectively overcome the ambiguity of traditional RAG vector similarity calculation and the noise problem of GraphRAG introduced by OpenIE. KAG supports logical reasoning and multi-hop fact Q&A, etc., and is significantly better than the current SOTA method.

The goal of KAG is to build a knowledge-enhanced LLM service framework in professional domains, supporting logical reasoning, factual Q&A, etc. KAG fully integrates the logical and factual characteristics of the KGs. Its core features include:

Knowledge and Chunk Mutual Indexing structure to integrate more complete contextual text information
Knowledge alignment using conceptual semantic reasoning to alleviate the noise problem caused by OpenIE
Schema-constrained knowledge construction to support the representation and construction of domain expert knowledge
Logical form-guided hybrid reasoning and retrieval to support logical reasoning and multi-hop reasoning Q&A

Thank you!

_{🔄 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/deepseek-ai/awesome-deepseek-integration/pull/326 **Author:** [@andylau-55](https://github.com/andylau-55) **Created:** 2/25/2025 **Status:** ✅ Merged **Merged:** 2/25/2025 **Merged by:** [@mowentian](https://github.com/mowentian) **Base:** `main` ← **Head:** `kag` --- ### 📝 Commits (4) - [`49fa9b9`](https://github.com/deepseek-ai/awesome-deepseek-integration/commit/49fa9b91ea61da554ca0cd909fb5b135d2a1ebfc) Update README_cn.md - [`3704666`](https://github.com/deepseek-ai/awesome-deepseek-integration/commit/370466691356ba060bd5ff16b339118e105586b5) Update README.md - [`4efb451`](https://github.com/deepseek-ai/awesome-deepseek-integration/commit/4efb4516cc0772cbbfe34d44a46bc0e687245242) Update README.md - [`19fcb73`](https://github.com/deepseek-ai/awesome-deepseek-integration/commit/19fcb73e2621c32d7ad8ad84a6b8be8ff61a6eed) Update README_ja.md ### 📊 Changes **3 files changed** (+15 additions, -1 deletions) <details> <summary>View changed files</summary> 📝 `README.md` (+5 -1) 📝 `README_cn.md` (+5 -0) 📝 `README_ja.md` (+5 -0) </details> ### 📄 Description Hi! I'd like to propose adding our project KAG to the awesome-deepseek list. KAG is a logical reasoning and Q&A framework based on the [OpenSPG](https://github.com/OpenSPG/openspg) engine and large language models, which is used to build logical reasoning and Q&A solutions for vertical domain knowledge bases. KAG can effectively overcome the ambiguity of traditional RAG vector similarity calculation and the noise problem of GraphRAG introduced by OpenIE. KAG supports logical reasoning and multi-hop fact Q&A, etc., and is significantly better than the current SOTA method. The goal of KAG is to build a knowledge-enhanced LLM service framework in professional domains, supporting logical reasoning, factual Q&A, etc. KAG fully integrates the logical and factual characteristics of the KGs. Its core features include: - Knowledge and Chunk Mutual Indexing structure to integrate more complete contextual text information - Knowledge alignment using conceptual semantic reasoning to alleviate the noise problem caused by OpenIE - Schema-constrained knowledge construction to support the representation and construction of domain expert knowledge - Logical form-guided hybrid reasoning and retrieval to support logical reasoning and multi-hop reasoning Q&A Thank you! --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-26 09:57:52 +00:00