kartik-mem0
2ef6291307
The Python Together LLM and embedder ignored TOGETHER_API_BASE, unlike their TypeScript siblings, so users behind a gateway or proxy could not redirect Together traffic. Add together_base_url to a new TogetherConfig (LLM side) and to BaseEmbedderConfig (embedder side, matching the existing openai_base_url/huggingface_base_url pattern), and resolve base_url with explicit config value > TOGETHER_API_BASE env var > hardcoded default in both mem0/llms/together.py and mem0/embeddings/together.py. Also register TogetherConfig in LlmFactory.provider_to_class so config dicts routed through Memory pick it up. Closes #6587
45 lines
1.8 KiB
Python
45 lines
1.8 KiB
Python
import os
|
|
from typing import Literal, Optional
|
|
|
|
from together import Together
|
|
|
|
from mem0.configs.embeddings.base import BaseEmbedderConfig
|
|
from mem0.embeddings.base import EmbeddingBase
|
|
|
|
|
|
class TogetherEmbedding(EmbeddingBase):
|
|
def __init__(self, config: Optional[BaseEmbedderConfig] = None):
|
|
super().__init__(config)
|
|
|
|
self.config.model = self.config.model or "intfloat/multilingual-e5-large-instruct"
|
|
api_key = self.config.api_key or os.getenv("TOGETHER_API_KEY")
|
|
base_url = self.config.together_base_url or os.getenv("TOGETHER_API_BASE") or "https://api.together.ai/v1"
|
|
self.config.embedding_dims = self.config.embedding_dims or 1024
|
|
self.client = Together(api_key=api_key, base_url=base_url)
|
|
|
|
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.
|
|
"""
|
|
|
|
return self.client.embeddings.create(model=self.config.model, input=text).data[0].embedding
|
|
|
|
def embed_batch(self, texts, memory_action="add"):
|
|
if not texts:
|
|
return []
|
|
response = self.client.embeddings.create(model=self.config.model, input=texts)
|
|
sorted_data = sorted(response.data, key=lambda x: x.index)
|
|
embeddings = [item.embedding for item in sorted_data]
|
|
if len(embeddings) != len(texts):
|
|
raise ValueError(
|
|
f"Together embed_batch() returned {len(embeddings)} embeddings for {len(texts)} texts"
|
|
f" using model '{self.config.model}'"
|
|
)
|
|
return embeddings
|