mem0ai--mem0/mem0/embeddings/lmstudio.py

from typing import Literal, Optional

from openai import OpenAI

from mem0.configs.embeddings.base import BaseEmbedderConfig
from mem0.embeddings.base import EmbeddingBase


class LMStudioEmbedding(EmbeddingBase):
    def __init__(self, config: Optional[BaseEmbedderConfig] = None):
        super().__init__(config)

        self.config.model = self.config.model or "nomic-ai/nomic-embed-text-v1.5-GGUF/nomic-embed-text-v1.5.f16.gguf"
        self.config.embedding_dims = self.config.embedding_dims or 1536
        self.config.api_key = self.config.api_key or "lm-studio"

        self.client = OpenAI(base_url=self.config.lmstudio_base_url, api_key=self.config.api_key)

    def embed(self, text, memory_action: Optional[Literal["add", "search", "update"]] = None):
        """
        Get the embedding for the given text using LM Studio.
        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"):
        if not texts:
            return []
        cleaned = [t.replace("\n", " ") for t in texts]
        response = self.client.embeddings.create(input=cleaned, model=self.config.model)
        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"LM Studio embed_batch() returned {len(embeddings)} embeddings for {len(texts)} texts"
                f" using model '{self.config.model}'"
            )
        return embeddings