The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
Python agentic-memoryagentic-memory-systemagentsaiai-agentschatgptgenaillmlong-term-memorymemorymemory-managementpythonragstate-management
Add Support for Vertex AI Embeddings (#1840)
Divyanshu Prasad959f4bb05920
diff --git a/docs/components/embedders/config.mdx b/docs/components/embedders/config.mdxindex 91731be88..95860b807 100644--- a/docs/components/embedders/config.mdx+++ b/docs/components/embedders/config.mdx@@ -53,6 +53,7 @@ Here's a comprehensive list of all parameters that can be used across different| `model_kwargs` | Key-Value arguments for the Huggingface embedding model || `azure_kwargs` | Key-Value arguments for the AzureOpenAI embedding model || `openai_base_url` | Base URL for OpenAI API | OpenAI |+| `vertex_credentials_json` | Path to the Google Cloud credentials JSON file for VertexAI |## Supported Embedding Modelsdiff --git a/docs/components/embedders/models/vertexai.mdx b/docs/components/embedders/models/vertexai.mdxnew file mode 100644index 000000000..1fe8b95ee--- /dev/null+++ b/docs/components/embedders/models/vertexai.mdx@@ -0,0 +1,35 @@+### Vertex AI++To use Google Cloud's Vertex AI for text embedding models, set the `GOOGLE_APPLICATION_CREDENTIALS` environment variable to point to the path of your service account's credentials JSON file. These credentials can be created in the [Google Cloud Console](https://console.cloud.google.com/).++### Usage++```python+import os+from mem0 import Memory++# Set the path to your Google Cloud credentials JSON file+os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "/path/to/your/credentials.json"++config = {+ "embedder": {+ "provider": "vertexai",+ "config": {+ "model": "text-embedding-004"+ }+ }+}++m = Memory.from_config(config)+m.add("I'm visiting Paris", user_id="john")+```++### Config++Here are the parameters available for configuring the Vertex AI embedder:++| Parameter | Description | Default Value |+| ------------------------- | ------------------------------------------------ | -------------------- |+| `model` | The name of the Vertex AI embedding model to use | `text-embedding-004` |+| `vertex_credentials_json` | Path to the Google Cloud credentials JSON file | `None` |+| `embedding_dims` | Dimensions of the embedding model | `256` |diff --git a/docs/components/embedders/overview.mdx b/docs/components/embedders/overview.mdxindex 2cd78c128..f1d7d7e58 100644--- a/docs/components/embedders/overview.mdx+++ b/docs/components/embedders/overview.mdx@@ -13,6 +13,7 @@ See the list of supported embedders below.<Card title="Azure OpenAI" href="/components/embedders/models/azure_openai"></Card><Card title="Ollama" href="/components/embedders/models/ollama"></Card><Card title="Hugging Face" href="/components/embedders/models/huggingface"></Card>+ <Card title="Vertex AI" href="/components/embedders/models/vertexai"></Card></CardGroup>## Usagediff --git a/mem0/embeddings/configs.py b/mem0/embeddings/configs.pyindex 73aa9b30a..9e3848cf2 100644--- a/mem0/embeddings/configs.py+++ b/mem0/embeddings/configs.py@@ -15,7 +15,7 @@ class EmbedderConfig(BaseModel):@field_validator("config")def validate_config(cls, v, values):provider = values.data.get("provider")- if provider in ["openai", "ollama", "huggingface", "azure_openai"]:+ if provider in ["openai", "ollama", "huggingface", "azure_openai", "vertexai"]:return velse:raise ValueError(f"Unsupported embedding provider: {provider}")diff --git a/mem0/embeddings/vertexai.py b/mem0/embeddings/vertexai.pynew file mode 100644index 000000000..4839a2f32--- /dev/null+++ b/mem0/embeddings/vertexai.py@@ -0,0 +1,39 @@+import os+from typing import Optional++from vertexai.language_models import TextEmbeddingModel++from mem0.configs.embeddings.base import BaseEmbedderConfig+from mem0.embeddings.base import EmbeddingBase++class VertexAI(EmbeddingBase):+ def __init__(self, config: Optional[BaseEmbedderConfig] = None):+ super().__init__(config)++ self.config.model = self.config.model or "text-embedding-004"+ self.config.embedding_dims = self.config.embedding_dims or 256++ credentials_path = self.config.vertex_credentials_json++ if credentials_path:+ os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = credentials_path+ elif not os.getenv("GOOGLE_APPLICATION_CREDENTIALS"):+ raise ValueError(+ "Google application credentials JSON is not provided. Please provide a valid JSON path or set the 'GOOGLE_APPLICATION_CREDENTIALS' environment variable."+ )++ self.model = TextEmbeddingModel.from_pretrained(self.config.model)++ def embed(self, text):+ """+ Get the embedding for the given text using Vertex AI.++ Args:+ text (str): The text to embed.++ Returns:+ list: The embedding vector.+ """+ embeddings = self.model.get_embeddings(texts=[text], output_dimensionality= self.config.embedding_dims)++ return embeddings[0].values