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

Fix precommit check after moving to ruff (#927)

Browse source 
Lint check in main branch is failing. This fixes the lint check after we
moved to ruff in https://github.com/meta-llama/llama-stack/pull/921. We
need to move to a `ruff.toml` file as well as fixing and ignoring some
additional checks.

Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
This commit is contained in:
Yuan Tang 2025-02-02 09:46:45 -05:00 • committed by GitHub
parent 4773092dd1
commit 34ab7a3b6c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
217 changed files with 981 additions and 2681 deletions
Download patch file Download diff file Expand all files Collapse all files

12
llama_stack/providers/utils/memory/vector_store.py
View file

@ -141,9 +141,7 @@ async def content_from_doc(doc: RAGDocument) -> str:
return interleaved_content_as_str(doc.content)
def make_overlapped_chunks(
document_id: str, text: str, window_len: int, overlap_len: int
) -> List[Chunk]:
def make_overlapped_chunks(document_id: str, text: str, window_len: int, overlap_len: int) -> List[Chunk]:
tokenizer = Tokenizer.get_instance()
tokens = tokenizer.encode(text, bos=False, eos=False)
@ -171,9 +169,7 @@ class EmbeddingIndex(ABC):
raise NotImplementedError()
@abstractmethod
async def query(
self, embedding: NDArray, k: int, score_threshold: float
) -> QueryChunksResponse:
async def query(self, embedding: NDArray, k: int, score_threshold: float) -> QueryChunksResponse:
raise NotImplementedError()
@abstractmethod
@ -209,8 +205,6 @@ class VectorDBWithIndex:
score_threshold = params.get("score_threshold", 0.0)
query_str = interleaved_content_as_str(query)
embeddings_response = await self.inference_api.embeddings(
self.vector_db.embedding_model, [query_str]
)
embeddings_response = await self.inference_api.embeddings(self.vector_db.embedding_model, [query_str])
query_vector = np.array(embeddings_response.embeddings[0], dtype=np.float32)
return await self.index.query(query_vector, k, score_threshold)