2 commits

Author	SHA1	Message	Date
Ashwin Bharambe	3ae8585b65	[memory refactor][1/n] Rename Memory -> VectorIO, MemoryBanks -> VectorDBs (#828) ... See https://github.com/meta-llama/llama-stack/issues/827 for the broader design. This is the first part: - delete other kinds of memory banks (keyvalue, keyword, graph) for now; we will introduce a keyvalue store API as part of this design but not use it in the RAG tool yet. - renaming of the APIs	2025-01-22 09:59:30 -08:00
Ashwin Bharambe	ec4fc800cc	[API Updates] Model / shield / memory-bank routing + agent persistence + support for private headers (#92) ... This is yet another of those large PRs (hopefully we will have less and less of them as things mature fast). This one introduces substantial improvements and some simplifications to the stack. Most important bits: * Agents reference implementation now has support for session / turn persistence. The default implementation uses sqlite but there's also support for using Redis. * We have re-architected the structure of the Stack APIs to allow for more flexible routing. The motivating use cases are: - routing model A to ollama and model B to a remote provider like Together - routing shield A to local impl while shield B to a remote provider like Bedrock - routing a vector memory bank to Weaviate while routing a keyvalue memory bank to Redis * Support for provider specific parameters to be passed from the clients. A client can pass data using `x_llamastack_provider_data` parameter which can be type-checked and provided to the Adapter implementations.	2024-09-23 14:22:22 -07:00