LLM App
build a realtime LLM app in 30 lines, with no vector database. A no-code RAG server that keeps answers in sync with your documents. Works with 8 vector databases. Built on Pathway. We’ve built a LLM microservice that answers questions about a corpus of documents, while automatically reacting to additions of new docs.
Self-hostedOpen source
Reactions (1)
Similar products
by description similarity
Text-To-Speech, RAG, and LLMs. All local!
LLMWare
github.comSmall Specialized Function Calling 1B LLMs for Multi-Step RAG
Sandboxes for AI agents. Securely run untrusted, LLM-generated code in isolated Firecracker microVM sandboxes that scale from one to thousands — with snapshot, suspend/resume, and durable orchestration.
After struggling with complex prompt engineering and unreliable parsing, we built L1M, a simple API that lets you extract structured data from unstructured text and images.
SwiftAI
github.comopen-source library to easily build LLM features on iOS/macOS