[Frontend] Rerank API (Jina- and Cohere-compatible API) (#12376)

Signed-off-by: Kyle Mistele <kyle@mistele.com>
This commit is contained in:
Kyle Mistele
2025-01-26 20:58:45 -06:00
committed by GitHub
parent 72bac73067
commit 0034b09ceb
9 changed files with 552 additions and 11 deletions

View File

@@ -10,12 +10,7 @@ MODEL_NAME = "BAAI/bge-reranker-v2-m3"
@pytest.fixture(scope="module")
def server():
args = [
"--enforce-eager",
# Will be used on tests to compare prompt input length
"--max-model-len",
"100"
]
args = ["--enforce-eager", "--max-model-len", "100"]
with RemoteOpenAIServer(MODEL_NAME, args) as remote_server:
yield remote_server