Skip to content

Feature request: RAG for search and chat #5

@taichimaeda

Description

@taichimaeda
  • Ollama for local embedding
  • RAG algorithm similar to LlamaIndex.TS
  • IndexedDB for vector store (currently not supported by LlamaIndex.TS)

Links:

https://ollama.com/blog/embedding-models
https://ts.llamaindex.ai/

Metadata

Metadata

Assignees

Labels

No labels
No labels

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions