Search

More Filters

Show More
Add Listing
Go Back

platform war public

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

This repository is a multi-agent dialogue framework that combines knowledge graphs and retrieval-augmented generation (RAG) to extract opinionated knowledge from social platform comments and stage debates between agents that represent different platforms. It is intended for developers and researchers who want to build or reproduce a system that ingests clustered comment data, automatically extracts a knowledge graph, creates vectorized knowledge bases, and runs multi-party debates where agents speak in platform-representative voices. The project depends on a large model (moonshot-v1 by default) accessed via a Kimi API key configured in config.py, and uses FAISS for vector search. The codebase includes tools for extraction, embedding, storage, retrieval, visualization and a simple UI and chat runner to orchestrate platform-to-platform debates.

Links

Stars
778
App URL
https://github.com/LYiHub/platform-war-public
Github Repository
https://github.com/LYiHub/platform-war-public/blob/main/README.md

App Details

Features
The codebase is organized around a knowledge-graph-first RAG pipeline. Core files include knowledgeGraph.py with modular components implemented in graph_entity.py, graph_search.py, graph_storage.py and graph_visualization.py. Embedding_model.py controls the embedding model and device settings. Two utilities, knowledge_retriever.py and knowledgeGraphExtractor.py, perform information retrieval and automatic graph extraction from a specified result.json format. The main orchestration and user-facing scripts are platform_war.py, platform_war_UI.py and chat.py. The project supports FAISS GPU for vector data, provides conda environment and dependency instructions, and documents how to replace the model service by changing API_BASE_URL and model parameters. Pre-extracted vector databases for three platforms are provided separately to reproduce the demo.
Use Cases
This project helps teams automate the pipeline from raw social comments to structured debate-ready knowledge. It can ingest clustered comment JSON files, extract entities and relations into a knowledge graph, embed text for vector search, and load per-platform knowledge bases so agents can argue from platform-specific perspectives. The included retriever, visualization and UI components make it practical to explore extracted graphs and run multi-agent dialogues without building each piece from scratch. It is useful for prototyping opinion-mining, comparative analysis across platforms, or research on multi-agent discourse. Practical constraints and reproducibility aids are documented, including GPU/FAISS requirements, conda setup, API key configuration and known UI limitations.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1009)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (764)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

virtual lab

0 (0 review)
listing image

mnemo

0 (0 review)
listing image

EdgeChains

0 (0 review)
listing image

RAG Agents Accelerator

0 (0 review)
listing image

LLM Zero to Hundred

0 (0 review)

Featured Listings

Tags

Please fill the required fields*