liunian-Jay/CoCoA
[Under Review] CoCoA: Collaborative Chain-of-Agents for Parametric-Retrieved Knowledge Synergy
This is a framework for researchers and developers working with large language models (LLMs) to enhance their ability to answer complex questions by integrating internal and external knowledge sources. It takes existing LLMs and external knowledge (like Wikipedia articles and their embeddings) as input, and outputs an LLM that can make more informed decisions by collaboratively processing information. Its primary users are AI/ML researchers and practitioners focused on improving LLM reasoning and knowledge integration.
No commits in the last 6 months.
Use this if you are an AI/ML researcher or developer looking to improve the knowledge integration and reasoning capabilities of large language models for complex question-answering tasks.
Not ideal if you are an end-user simply looking to apply an existing LLM for basic tasks, or if you don't have experience with LLM training and infrastructure.
Stars
21
Forks
—
Language
Python
License
—
Category
Last pushed
Oct 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/liunian-Jay/CoCoA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
deepsense-ai/ragbits
Building blocks for rapid development of GenAI applications
infiniflow/ragflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses...
GiovanniPasq/agentic-rag-for-dummies
A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.
truefoundry/cognita
RAG (Retrieval Augmented Generation) Framework for building modular, open source applications...
vectara/py-vectara-agentic
A python library for creating AI assistants with Vectara, using Agentic RAG