← Back to context Comment by antipaul 3 months ago Nice list.What about for on-device RAG use cases? 1 comment antipaul Reply sanchitmonga22 3 months ago RCLI includes local RAG out of the box. You can ingest PDFs, DOCX, and plain text, then query by voice or text:rcli rag ingest ~/Documents/notes rcli ask --rag ~/Library/RCLI/index "summarize the project plan"It uses hybrid retrieval (vector + BM25 with Reciprocal Rank Fusion) and runs at ~4ms over 5K+ chunks. Embeddings are computed locally with Snowflake Arctic, so nothing leaves you're machine.
sanchitmonga22 3 months ago RCLI includes local RAG out of the box. You can ingest PDFs, DOCX, and plain text, then query by voice or text:rcli rag ingest ~/Documents/notes rcli ask --rag ~/Library/RCLI/index "summarize the project plan"It uses hybrid retrieval (vector + BM25 with Reciprocal Rank Fusion) and runs at ~4ms over 5K+ chunks. Embeddings are computed locally with Snowflake Arctic, so nothing leaves you're machine.
RCLI includes local RAG out of the box. You can ingest PDFs, DOCX, and plain text, then query by voice or text:
rcli rag ingest ~/Documents/notes rcli ask --rag ~/Library/RCLI/index "summarize the project plan"
It uses hybrid retrieval (vector + BM25 with Reciprocal Rank Fusion) and runs at ~4ms over 5K+ chunks. Embeddings are computed locally with Snowflake Arctic, so nothing leaves you're machine.