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

Fix test infra, sentence embeddings mixin

Browse source
This commit is contained in:
Ashwin Bharambe 2025-02-21 15:10:10 -08:00
parent 182608d4bf
commit e7d261ef4a
4 changed files with 12 additions and 34 deletions
Download patch file Download diff file Expand all files Collapse all files

11
llama_stack/distribution/library_client.py
View file

@ -230,12 +230,11 @@ class AsyncLlamaStackAsLibraryClient(AsyncLlamaStackClient):
if Api.telemetry in self.impls:
setup_logger(self.impls[Api.telemetry])
console = Console()
console.print(f"Using config [blue]{self.config_path_or_template_name}[/blue]:")
# Redact sensitive information before printing
safe_config = redact_sensitive_fields(self.config.model_dump())
console.print(yaml.dump(safe_config, indent=2))
if not os.environ.get("PYTEST_CURRENT_TEST"):
console = Console()
console.print(f"Using config [blue]{self.config_path_or_template_name}[/blue]:")
safe_config = redact_sensitive_fields(self.config.model_dump())
console.print(yaml.dump(safe_config, indent=2))
endpoints = get_all_api_endpoints()
endpoint_impls = {}

3
llama_stack/providers/utils/inference/embedding_mixin.py
View file

@ -14,6 +14,7 @@ from llama_stack.apis.inference import (
ModelStore,
TextTruncation,
)
from llama_stack.providers.utils.inference.prompt_adapter import interleaved_content_as_str
EMBEDDING_MODELS = {}
@ -34,7 +35,7 @@ class SentenceTransformerEmbeddingMixin:
) -> EmbeddingsResponse:
model = await self.model_store.get_model(model_id)
embedding_model = self._load_sentence_transformer_model(model.provider_resource_id)
embeddings = embedding_model.encode(contents)
embeddings = embedding_model.encode([interleaved_content_as_str(content) for content in contents])
return EmbeddingsResponse(embeddings=embeddings)
def _load_sentence_transformer_model(self, model: str) -> "SentenceTransformer":