mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-06 20:44:58 +00:00
b6a3ef51da
Some providers need to be factorized and considered as thin routing layers on top of other providers. Consider two examples: - The inference API should be a routing layer over inference providers, routed using the "model" key - The memory banks API is another instance where various memory bank types will be provided by independent providers (e.g., a vector store is served by Chroma while a keyvalue memory can be served by Redis or PGVector) This commit introduces a generalized routing layer for this purpose. |
||
|---|---|---|
| .. | ||
| agentic_system | ||
| batch_inference | ||
| cli | ||
| common | ||
| configs/distributions | ||
| core | ||
| dataset/api | ||
| evaluations/api | ||
| inference | ||
| memory | ||
| models/api | ||
| post_training/api | ||
| reward_scoring/api | ||
| safety | ||
| synthetic_data_generation/api | ||
| telemetry | ||
| tools | ||
| __init__.py | ||
| stack.py | ||