forked from phoenix-oss/llama-stack-mirror
[memory refactor][2/n] Update faiss and make it pass tests (#830)
See https://github.com/meta-llama/llama-stack/issues/827 for the broader design. Second part: - updates routing table / router code - updates the faiss implementation ## Test Plan ``` pytest -s -v -k sentence test_vector_io.py --env EMBEDDING_DIMENSION=384 ```
This commit is contained in:
parent
3ae8585b65
commit
78a481bb22
19 changed files with 343 additions and 353 deletions
|
@ -23,7 +23,7 @@ def available_providers() -> List[ProviderSpec]:
|
|||
pip_packages=[],
|
||||
module="llama_stack.providers.inline.tool_runtime.memory",
|
||||
config_class="llama_stack.providers.inline.tool_runtime.memory.config.MemoryToolRuntimeConfig",
|
||||
api_dependencies=[Api.memory, Api.memory_banks, Api.inference],
|
||||
api_dependencies=[Api.vector_io, Api.vector_dbs, Api.inference],
|
||||
),
|
||||
InlineProviderSpec(
|
||||
api=Api.tool_runtime,
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue