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.

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"
os.environ["OPENAI_API_KEY"] = "your_api_key" # For LLM

config = {
    "embedder": {
        "provider": "vertexai",
        "config": {
            "model": "gemini-embedding-001",
            "memory_add_embedding_type": "RETRIEVAL_DOCUMENT",
            "memory_update_embedding_type": "RETRIEVAL_DOCUMENT",
            "memory_search_embedding_type": "RETRIEVAL_QUERY"
        }
    }
}

m = Memory.from_config(config)
messages = [
    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
    {"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
    {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
]
m.add(messages, user_id="john")

The embedding types can be one of the following:

SEMANTIC_SIMILARITY
CLASSIFICATION
CLUSTERING
RETRIEVAL_DOCUMENT, RETRIEVAL_QUERY, QUESTION_ANSWERING, FACT_VERIFICATION
CODE_RETRIEVAL_QUERY
Check out the Vertex AI documentation for more information.

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	`gemini-embedding-001`
`vertex_credentials_json`	Path to the Google Cloud credentials JSON file	`None`
`embedding_dims`	Dimensions of the embedding model	`256`
`memory_add_embedding_type`	The type of embedding to use for the add memory action	`RETRIEVAL_DOCUMENT`
`memory_update_embedding_type`	The type of embedding to use for the update memory action	`RETRIEVAL_DOCUMENT`
`memory_search_embedding_type`	The type of embedding to use for the search memory action	`RETRIEVAL_QUERY`