x.comthreadDan Kornas (@DanKornas) on X
Agentset is an open-source (MIT-licensed) platform for building RAG and agentic applications, bundling ingestion, chunking, embeddings, retrieval, vector indexing, a citation-aware chat playground, evaluation/benchmark tooling, and a deployment layer (hosting, preview links, custom domains, typed SDKs, OpenAPI spec) into one codebase. It lets builders choose their own LLM, embedding model, and vector database rather than locking into a single stack.
TL;DR Open-source MIT platform bundling the full RAG pipeline - ingestion to hosted API - into one codebase.
Technologies named here
- Agentset
Techniques named here
- Turnkey RAG pipeline
- Citation-aware chat
Related in llm-apps
github.comrepocalmrocks/ai-engineer-notebooks
huggingface.coarticleTraining and Finetuning Multi-Vector Embedding Models with Sentence Transformers
huggingface.coarticleWire It, Run It, Deploy It: AI Workflows in Gradio
github.comrepo