klas/t6_mem0
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Added support for google vector search - (matching engine) (#2177)

Browse Source
This commit is contained in:
anchit-nishant
2025-03-05 11:45:47 +05:30
committed by GitHub
parent 7c8628eadc
commit 23dbce4f59
10 changed files with 1382 additions and 269 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
docs/components/vectordbs/config.mdx
View File

@@ -8,8 +8,9 @@ iconType: "solid"
The `config` is defined as an object with two main keys:
- `vector_store`: Specifies the vector database provider and its configuration
- `provider`: The name of the vector database (e.g., "chroma", "pgvector", "qdrant", "milvus", "azure_ai_search")
- `config`: A nested object containing provider-specific settings
- `provider`: The name of the vector database (e.g., "chroma", "pgvector", "qdrant", "milvus","azure_ai_search", "vertex_ai_vector_search")
- `config`: A nested dictionary containing provider-specific settings
## How to Use Config
@@ -86,6 +87,12 @@ Here's a comprehensive list of all parameters that can be used across different
| `url` | Full URL for the server |
| `api_key` | API key for the server |
| `on_disk` | Enable persistent storage |
| `endpoint_id` | Endpoint ID (vertex_ai_vector_search) |
| `index_id` | Index ID (vertex_ai_vector_search) |
| `deployment_index_id` | Deployment index ID (vertex_ai_vector_search) |
| `project_id` | Project ID (vertex_ai_vector_search) |
| `project_number` | Project number (vertex_ai_vector_search) |
| `vector_search_api_endpoint` | Vector search API endpoint (vertex_ai_vector_search) |
| `connection_string` | PostgreSQL connection string (for Supabase/PGVector) |
| `index_method` | Vector index method (for Supabase) |
| `index_measure` | Distance measure for similarity search (for Supabase) |

46
docs/components/vectordbs/dbs/vertex_ai_vector_search.mdx Normal file
View File

@@ -0,0 +1,46 @@
## Google Cloud Vertex AI Vector Search
### Usage
To use Google Cloud Vertex AI Vector Search with `mem0`, you need to configure the `vector_store` in your `mem0` config:
```python
import os
from mem0 import Memory
os.environ["GEMINI_API_KEY"] = = "sk-xx"
config = {
"vector_store": {
"provider": "vertex_ai_vector_search",
"config": {
"endpoint_id": "YOUR_ENDPOINT_ID", # Required: Vector Search endpoint ID
"index_id": "YOUR_INDEX_ID", # Required: Vector Search index ID
"deployment_index_id": "YOUR_DEPLOYMENT_INDEX_ID", # Required: Deployment-specific ID
"project_id": "YOUR_PROJECT_ID", # Required: Google Cloud project ID
"project_number": "YOUR_PROJECT_NUMBER", # Required: Google Cloud project number
"region": "YOUR_REGION", # Optional: Defaults to GOOGLE_CLOUD_REGION
"credentials_path": "path/to/credentials.json", # Optional: Defaults to GOOGLE_APPLICATION_CREDENTIALS
"vector_search_api_endpoint": "YOUR_API_ENDPOINT" # Required for get operations
}
}
}
m = Memory.from_config(config)
m.add("Your text here", user_id="user", metadata={"category": "example"})
```
### Required Parameters
| Parameter | Description | Required |
|-----------|-------------|----------|
| `endpoint_id` | Vector Search endpoint ID | Yes |
| `index_id` | Vector Search index ID | Yes |
| `deployment_index_id` | Deployment-specific index ID | Yes |
| `project_id` | Google Cloud project ID | Yes |
| `project_number` | Google Cloud project number | Yes |
| `vector_search_api_endpoint` | Vector search API endpoint | Yes (for get operations) |
| `region` | Google Cloud region | No (defaults to GOOGLE_CLOUD_REGION) |
| `credentials_path` | Path to service account credentials | No (defaults to GOOGLE_APPLICATION_CREDENTIALS) |