Spaces:
Sleeping
Sleeping
File size: 1,445 Bytes
81598c5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 | """
Azure AI Foundry embedding provider.
Uses text-embedding-ada-002 (or whatever deployment is configured).
"""
from openai import AzureOpenAI
from openmark.embeddings.base import EmbeddingProvider
from openmark import config
class AzureEmbedder(EmbeddingProvider):
def __init__(self):
self._client = AzureOpenAI(
azure_endpoint=config.AZURE_ENDPOINT,
api_key=config.AZURE_API_KEY,
api_version=config.AZURE_API_VERSION,
)
self._deployment = config.AZURE_DEPLOYMENT_EMBED
print(f"Azure embedder ready — deployment: {self._deployment}")
def _embed(self, texts: list[str]) -> list[list[float]]:
response = self._client.embeddings.create(
input=texts,
model=self._deployment,
)
return [item.embedding for item in response.data]
def embed_documents(self, texts: list[str]) -> list[list[float]]:
results = []
batch_size = 100
for i in range(0, len(texts), batch_size):
batch = texts[i:i + batch_size]
results.extend(self._embed(batch))
print(f" Azure embedded {min(i + batch_size, len(texts))}/{len(texts)}")
return results
def embed_query(self, text: str) -> list[float]:
return self._embed([text])[0]
@property
def dimension(self) -> int:
return 1536 # ada-002 dimension
|