Rename embedchain to mem0 and open sourcing code for long term memory (#1474)

Co-authored-by: Deshraj Yadav <deshrajdry@gmail.com>

mem0/embeddings/base.py

@@ -0,0 +1,16 @@
+from abc import ABC, abstractmethod
+
+
+class EmbeddingBase(ABC):
+    @abstractmethod
+    def embed(self, text):
+        """
+        Get the embedding for the given text.
+
+        Args:
+            text (str): The text to embed.
+
+        Returns:
+            list: The embedding vector.
+        """
+        pass

mem0/embeddings/huggingface.py

@@ -0,0 +1,19 @@
+from embedding.base import EmbeddingBase
+from sentence_transformers import SentenceTransformer
+
+
+class HuggingFaceEmbedding(EmbeddingBase):
+    def __init__(self, model_name="multi-qa-MiniLM-L6-cos-v1"):
+        self.model = SentenceTransformer(model_name)
+
+    def get_embedding(self, text):
+        """
+        Get the embedding for the given text using Hugging Face.
+
+        Args:
+            text (str): The text to embed.
+
+        Returns:
+            list: The embedding vector.
+        """
+        return self.model.encode(text)

mem0/embeddings/ollama.py

@@ -0,0 +1,30 @@
+import ollama
+from embedding.base import EmbeddingBase
+
+
+class OllamaEmbedding(EmbeddingBase):
+    def __init__(self, model="nomic-embed-text"):
+        self.model = model
+        self._ensure_model_exists()
+        self.dims = 512
+
+    def _ensure_model_exists(self):
+        """
+        Ensure the specified model exists locally. If not, pull it from Ollama.
+        """
+        model_list = [m["name"] for m in ollama.list()["models"]]
+        if not any(m.startswith(self.model) for m in model_list):
+            ollama.pull(self.model)
+
+    def embed(self, text):
+        """
+        Get the embedding for the given text using Ollama.
+
+        Args:
+            text (str): The text to embed.
+
+        Returns:
+            list: The embedding vector.
+        """
+        response = ollama.embeddings(model=self.model, prompt=text)
+        return response["embedding"]

mem0/embeddings/openai.py

@@ -0,0 +1,27 @@
+from openai import OpenAI
+
+from mem0.embeddings.base import EmbeddingBase
+
+
+class OpenAIEmbedding(EmbeddingBase):
+    def __init__(self, model="text-embedding-3-small"):
+        self.client = OpenAI()
+        self.model = model
+        self.dims = 1536
+
+    def embed(self, text):
+        """
+        Get the embedding for the given text using OpenAI.
+
+        Args:
+            text (str): The text to embed.
+
+        Returns:
+            list: The embedding vector.
+        """
+        text = text.replace("\n", " ")
+        return (
+            self.client.embeddings.create(input=[text], model=self.model)
+            .data[0]
+            .embedding
+        )