Feature integrate alibabacloud mysql vector

docs/components/vectordbs/dbs/alibabacloud_mysql.mdx

@@ -0,0 +1,157 @@
+[AlibabaCloud MySQL](https://www.alibabacloud.com/product/apsaradb-for-rds-mysql) is a fully managed MySQL database service that supports vector operations through MySQL's native VECTOR data type and vector functions. It provides high-performance vector similarity search capabilities with HNSW indexing.
+
+### Usage
+
+<CodeGroup>
+```python Python
+import os
+from mem0 import Memory
+
+os.environ["OPENAI_API_KEY"] = "sk-xx"
+
+config = {
+    "vector_store": {
+        "provider": "alibabacloud_mysql",
+        "config": {
+            "dbname": "vector_db",
+            "collection_name": "memories",
+            "user": "your_username",
+            "password": "your_password",
+            "host": "your-mysql-host.mysql.rds.aliyuncs.com",
+            "port": 3306,
+            "embedding_model_dims": 1536,
+            "distance_function": "euclidean",
+            "m_value": 16
+        }
+    }
+}
+
+m = Memory.from_config(config)
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movie? 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="alice", metadata={"category": "movies"})
+```
+
+```python Python (with connection string)
+import os
+from mem0 import Memory
+
+os.environ["OPENAI_API_KEY"] = "sk-xx"
+
+config = {
+    "vector_store": {
+        "provider": "alibabacloud_mysql",
+        "config": {
+            "connection_string": "mysql://username:password@host:3306/database",
+            "collection_name": "memories",
+            "distance_function": "cosine"
+        }
+    }
+}
+
+m = Memory.from_config(config)
+```
+
+```python Python (with SSL)
+import os
+from mem0 import Memory
+
+os.environ["OPENAI_API_KEY"] = "sk-xx"
+
+config = {
+    "vector_store": {
+        "provider": "alibabacloud_mysql",
+        "config": {
+            "dbname": "vector_db",
+            "collection_name": "memories",
+            "user": "your_username",
+            "password": "your_password",
+            "host": "your-mysql-host.mysql.rds.aliyuncs.com",
+            "port": 3306,
+            "embedding_model_dims": 1536,
+            "ssl_ca": "/path/to/ca-cert.pem",
+            "ssl_cert": "/path/to/client-cert.pem",
+            "ssl_key": "/path/to/client-key.pem"
+        }
+    }
+}
+
+m = Memory.from_config(config)
+```
+</CodeGroup>
+
+### Config
+
+Here are the parameters available for configuring AlibabaCloud MySQL:
+
+| Parameter | Description | Default Value |
+| --- | --- | --- |
+| `dbname` | The name of the database | `None` |
+| `collection_name` | The name of the collection (table) | `None` |
+| `embedding_model_dims` | Dimensions of the embedding model | `None` |
+| `user` | Database username | `None` |
+| `password` | Database password | `None` |
+| `host` | Database host address | `None` |
+| `port` | Database port | `3306` |
+| `distance_function` | Distance function for vector index ('euclidean' or 'cosine') | `euclidean` |
+| `m_value` | M parameter for HNSW index (3-200). Higher values = more accurate but slower | `16` |
+| `ssl_disabled` | Disable SSL connection | `False` |
+| `ssl_ca` | SSL CA certificate file path | `None` |
+| `ssl_cert` | SSL certificate file path | `None` |
+| `ssl_key` | SSL key file path | `None` |
+| `connection_string` | MySQL connection string (overrides individual connection parameters) | `None` |
+| `charset` | Character set for the connection | `utf8mb4` |
+| `autocommit` | Enable autocommit mode | `True` |
+
+### Features
+
+- **Native Vector Support**: Uses MySQL's native VECTOR data type for optimal performance
+- **HNSW Indexing**: Supports Hierarchical Navigable Small World (HNSW) indexing for fast similarity search
+- **Multiple Distance Functions**: Supports both Euclidean and Cosine distance functions
+- **SSL Support**: Full SSL/TLS encryption support for secure connections
+- **JSON Payload**: Store additional metadata as JSON alongside vectors
+- **Connection Pooling**: Efficient connection management with context managers
+- **Flexible Configuration**: Support for connection strings or individual parameters
+
+### Prerequisites
+
+1. **AlibabaCloud MySQL Instance**: You need an AlibabaCloud RDS MySQL instance with vector support enabled
+2. **Database Setup**: Ensure your MySQL instance supports the VECTOR data type and vector functions
+3. **Network Access**: Configure security groups and whitelist to allow connections from your application
+
+### Connection String Format
+
+The connection string should follow this format:
+```
+mysql://username:password@host:port/database
+```
+
+Example:
+```
+mysql://myuser:[email protected]:3306/vector_db
+```
+
+### Distance Functions
+
+- **euclidean**: Uses Euclidean distance for vector similarity
+- **cosine**: Uses Cosine distance for vector similarity
+
+The distance function is set during collection creation and affects the HNSW index configuration.
+
+### Performance Tuning
+
+- **m_value**: Controls the HNSW index quality vs speed tradeoff
+  - Lower values (3-16): Faster indexing, less memory, lower accuracy
+  - Higher values (32-200): Slower indexing, more memory, higher accuracy
+- **embedding_model_dims**: Should match your embedding model's output dimensions exactly
+
+### Error Handling
+
+The connector includes comprehensive error handling and logging:
+- Connection errors are automatically caught and logged
+- Failed transactions are rolled back automatically
+- Detailed error messages help with debugging

mem0/configs/vector_stores/alibabacloud_mysql.py

@@ -0,0 +1,64 @@
+from typing import Any, Dict, Optional
+
+from pydantic import BaseModel, Field, model_validator
+
+
+class MySQLVectorConfig(BaseModel):
+    dbname: str = Field("mem0", description="Default name for the database")
+    collection_name: str = Field("mem0", description="Default name for the collection")
+    embedding_model_dims: Optional[int] = Field(1536, description="Dimensions of the embedding model")
+    user: Optional[str] = Field(None, description="Database user")
+    password: Optional[str] = Field(None, description="Database password")
+    host: Optional[str] = Field(None, description="Database host. Default is localhost")
+    port: Optional[int] = Field(None, description="Database port. Default is 3306")
+    distance_function: Optional[str] = Field("euclidean", description="Distance function for vector index ('euclidean' or 'cosine')")
+    m_value: Optional[int] = Field(16, description="M parameter for HNSW index (3-200). Higher values = more accurate but slower")
+    # SSL and connection options
+    ssl_disabled: Optional[bool] = Field(False, description="Disable SSL connection")
+    ssl_ca: Optional[str] = Field(None, description="SSL CA certificate file path")
+    ssl_cert: Optional[str] = Field(None, description="SSL certificate file path")
+    ssl_key: Optional[str] = Field(None, description="SSL key file path")
+    connection_string: Optional[str] = Field(None, description="AlibabaCloud MySQL connection string (overrides individual connection parameters)")
+    charset: Optional[str] = Field("utf8mb4", description="Character set for the connection")
+    autocommit: Optional[bool] = Field(True, description="Enable autocommit mode")
+
+    @model_validator(mode="before")
+    def check_auth_and_connection(cls, values):
+        # If connection_string is provided, skip validation of individual connection parameters
+        if values.get("connection_string") is not None:
+            return values
+
+        # Otherwise, validate individual connection parameters
+        user, password = values.get("user"), values.get("password")
+        host, port = values.get("host"), values.get("port")
+        if not user and not password:
+            raise ValueError("Both 'user' and 'password' must be provided when not using connection_string.")
+        if not host and not port:
+            raise ValueError("Both 'host' and 'port' must be provided when not using connection_string.")
+        return values
+
+    @model_validator(mode="before")
+    def validate_distance_function(cls, values):
+        distance_function = values.get("distance_function", "euclidean")
+        if distance_function not in ["euclidean", "cosine"]:
+            raise ValueError("distance_function must be either 'euclidean' or 'cosine'")
+        return values
+
+    @model_validator(mode="before")
+    def validate_m_value(cls, values):
+        m_value = values.get("m_value", 16)
+        if not (3 <= m_value <= 200):
+            raise ValueError("m_value must be between 3 and 200")
+        return values
+
+    @model_validator(mode="before")
+    @classmethod
+    def validate_extra_fields(cls, values: Dict[str, Any]) -> Dict[str, Any]:
+        allowed_fields = set(cls.model_fields.keys())
+        input_fields = set(values.keys())
+        extra_fields = input_fields - allowed_fields
+        if extra_fields:
+            raise ValueError(
+                f"Extra fields not allowed: {', '.join(extra_fields)}. Please input only the following fields: {', '.join(allowed_fields)}"
+            )
+        return values

mem0/utils/factory.py

@@ -186,6 +186,7 @@ class VectorStoreFactory:
         "baidu": "mem0.vector_stores.baidu.BaiduDB",
         "cassandra": "mem0.vector_stores.cassandra.CassandraDB",
         "neptune": "mem0.vector_stores.neptune_analytics.NeptuneAnalyticsVector",
+        "alibabacloud_mysql": "mem0.vector_stores.alibabacloud_mysql.MySQLVector",
     }
 
     @classmethod