soumil-rathi
a488e19044
Co-authored-by: Soumil Rathi <soumilrathi@gmail.com> Co-authored-by: Saket Aryan <saketaryan2002@gmail.com> Co-authored-by: chaithanyak42 <chaithanya.kumar42a@gmail.com> Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
73 lines
2.9 KiB
Python
73 lines
2.9 KiB
Python
import os
|
|
from typing import Literal, Optional
|
|
|
|
from azure.identity import DefaultAzureCredential, get_bearer_token_provider
|
|
from openai import AzureOpenAI
|
|
|
|
from mem0.configs.embeddings.base import BaseEmbedderConfig
|
|
from mem0.embeddings.base import EmbeddingBase
|
|
|
|
SCOPE = "https://cognitiveservices.azure.com/.default"
|
|
|
|
|
|
class AzureOpenAIEmbedding(EmbeddingBase):
|
|
def __init__(self, config: Optional[BaseEmbedderConfig] = None):
|
|
super().__init__(config)
|
|
|
|
api_key = self.config.azure_kwargs.api_key or os.getenv("EMBEDDING_AZURE_OPENAI_API_KEY")
|
|
azure_deployment = self.config.azure_kwargs.azure_deployment or os.getenv("EMBEDDING_AZURE_DEPLOYMENT")
|
|
azure_endpoint = self.config.azure_kwargs.azure_endpoint or os.getenv("EMBEDDING_AZURE_ENDPOINT")
|
|
api_version = self.config.azure_kwargs.api_version or os.getenv("EMBEDDING_AZURE_API_VERSION")
|
|
default_headers = self.config.azure_kwargs.default_headers
|
|
|
|
# If the API key is not provided or is a placeholder, use DefaultAzureCredential.
|
|
if api_key is None or api_key == "" or api_key == "your-api-key":
|
|
self.credential = DefaultAzureCredential()
|
|
azure_ad_token_provider = get_bearer_token_provider(
|
|
self.credential,
|
|
SCOPE,
|
|
)
|
|
api_key = None
|
|
else:
|
|
azure_ad_token_provider = None
|
|
|
|
self.client = AzureOpenAI(
|
|
azure_deployment=azure_deployment,
|
|
azure_endpoint=azure_endpoint,
|
|
azure_ad_token_provider=azure_ad_token_provider,
|
|
api_version=api_version,
|
|
api_key=api_key,
|
|
http_client=self.config.http_client,
|
|
default_headers=default_headers,
|
|
)
|
|
|
|
def embed(self, text, memory_action: Optional[Literal["add", "search", "update"]] = None):
|
|
"""
|
|
Get the embedding for the given text using OpenAI.
|
|
|
|
Args:
|
|
text (str): The text to embed.
|
|
memory_action (optional): The type of embedding to use. Must be one of "add", "search", or "update". Defaults to None.
|
|
Returns:
|
|
list: The embedding vector.
|
|
"""
|
|
text = text.replace("\n", " ")
|
|
return self.client.embeddings.create(input=[text], model=self.config.model).data[0].embedding
|
|
|
|
def embed_batch(self, texts, memory_action="add"):
|
|
"""Embed multiple texts in a single Azure OpenAI API call.
|
|
|
|
Automatically chunks into batches of 100 to stay within API limits.
|
|
"""
|
|
MAX_BATCH = 100
|
|
texts = [text.replace("\n", " ") for text in texts]
|
|
all_embeddings = []
|
|
for i in range(0, len(texts), MAX_BATCH):
|
|
chunk = texts[i : i + MAX_BATCH]
|
|
response = self.client.embeddings.create(
|
|
input=chunk,
|
|
model=self.config.model,
|
|
)
|
|
all_embeddings.extend(item.embedding for item in sorted(response.data, key=lambda x: x.index))
|
|
return all_embeddings
|