llama-stack-mirror

phoenix-oss/llama-stack-mirror

Fork 1

mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-07 22:34:37 +00:00

Commit graph

Author	SHA1	Message	Date
Sébastien Han	c245cb580c	chore: remove nested imports * Since our API packages use import * in __init__.py, we can import directly from llama_stack.apis.models instead of llama_stack.apis.models.models. However, the choice to use import * is debatable and may need to be reconsidered in the future. * Remove the unnecessary Ruff F401 suppression. * Consolidate the Ruff F403 rule configuration in pyproject.toml. Signed-off-by: Sébastien Han <seb@redhat.com>	2025-06-25 13:07:15 +02:00
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

Author

SHA1

Message

Date

Sébastien Han

c245cb580c

chore: remove nested imports

* Since our API packages use import * in __init__.py, we can import
  directly from llama_stack.apis.models instead of
  llama_stack.apis.models.models.  However, the choice to use import *
  is debatable and may need to be reconsidered in the future.

* Remove the unnecessary Ruff F401 suppression.

* Consolidate the Ruff F403 rule configuration in
pyproject.toml.

Signed-off-by: Sébastien Han <seb@redhat.com>

2025-06-25 13:07:15 +02:00

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

2 commits