I haven't played with more advanced feature or RAG, but at least AnythingLLM seems to support both local and remote vector databases (you can choose: lancedb, chroma, pinecone, zilliz cloud), embedding provider again both local (ollama, lmstudio) and remote and adjust text splitting and chuncking. Have some Agent skills like Web Search, scraping websites, sql connector. Seems probably the most advanced and I like you can still use ollama or lmstudio as your main LLM models repository.
OpenWebUI a little bit more harder to setup (need docker), but interface very similar to OpenAI
