phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

[API Updates] Model / shield / memory-bank routing + agent persistence + support for private headers (#92)

Browse source 
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.
This commit is contained in:
Ashwin Bharambe 2024-09-23 14:22:22 -07:00 • committed by GitHub
parent 8bf8c07eb3
commit ec4fc800cc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
130 changed files with 9701 additions and 11227 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/providers/impls/meta_reference/inference/config.py
View file

@ -6,17 +6,14 @@
from typing import Optional
from llama_models.datatypes import ModelFamily
from llama_models.schema_utils import json_schema_type
from llama_models.datatypes import * # noqa: F403
from llama_models.sku_list import all_registered_models, resolve_model
from llama_stack.apis.inference import * # noqa: F401, F403
from pydantic import BaseModel, Field, field_validator
from llama_stack.apis.inference import QuantizationConfig
@json_schema_type
class MetaReferenceImplConfig(BaseModel):
model: str = Field(
default="Meta-Llama3.1-8B-Instruct",
@ -34,6 +31,7 @@ class MetaReferenceImplConfig(BaseModel):
m.descriptor()
for m in all_registered_models()
if m.model_family == ModelFamily.llama3_1
or m.core_model_id == CoreModelId.llama_guard_3_8b
]
if model not in permitted_models:
model_list = "\n\t".join(permitted_models)