Add Couchbase Vector Store Support

docs/components/vectordbs/config.mdx

@@ -6,7 +6,7 @@ Config in mem0 is a dictionary that specifies the settings for your vector datab
 
 The config is defined as a Python dictionary 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")
+  - `provider`: The name of the vector database (e.g., "chroma", "pgvector", "qdrant", "milvus", "azure_ai_search", "couchbase")
   - `config`: A nested dictionary containing provider-specific settings
 
 ## How to Use Config

docs/components/vectordbs/dbs/couchbase.mdx

@@ -0,0 +1,50 @@
+[Couchbase](https://www.couchbase.com/) is an award-winning distributed NoSQL developer database platform that delivers unmatched versatility,
+performance, scalability, and financial value for your critical applications. 
+Couchbase embraces AI with coding assistance for developers,
+plus AI services for building applications that include RAG-powered agents, real-time analytics, and cloud-to-edge vector search.
+
+### Usage
+
+```python
+import os
+from mem0 import Memory
+
+os.environ["OPENAI_API_KEY"] = "sk-xx"
+
+config = {
+    "vector_store": {
+        "provider": "couchbase",
+        "config": {
+            "connection_str": "couchbase://localhost",
+            "username": "Administrator",
+            "password": "password",
+            "bucket_name": "mem0",
+            "scope_name": "_default",
+            "collection_name": "_default",
+            "embedding_model_dims": 1536,
+            "index_name": "_default_index",
+        }
+    }
+}
+
+m = Memory.from_config(config)
+m.add("Likes to play cricket on weekends", user_id="alice", metadata={"category": "hobbies"})
+```
+
+### Config
+
+Let's see the available parameters for the `couchbase` config:
+
+| Parameter | Description | Default Value |
+| --- | --- | --- |
+| `connection_str` | The connection string for the Couchbase server | `None` |
+| `username` | The username for the Couchbase server | `None` |
+| `password` | The password for the Couchbase server | `None` |
+| `bucket_name` | The name of the bucket to store the vectors | `mem0` |
+| `scope_name` | The name of the scope to store the vectors | `_default` |
+| `collection_name` | The name of the collection to store the vectors | `_default` |
+| `embedding_model_dims` | Dimensions of the embedding model | `1536` |
+| `index_name` | The name of the index to create for the vectors | `_default_index` |
+```
+
+

docs/components/vectordbs/overview.mdx

@@ -15,6 +15,7 @@ See the list of supported vector databases below.
   <Card title="Milvus" href="/components/vectordbs/dbs/milvus"></Card>
   <Card title="Azure AI Search" href="/components/vectordbs/dbs/azure_ai_search"></Card>
   <Card title="Redis" href="/components/vectordbs/dbs/redis"></Card>
+  <Card title="Couchbase" href="/components/vectordbs/dbs/couchbase"></Card>
 </CardGroup>
 
 ## Usage
@@ -33,4 +34,3 @@ for example 768, you may encounter below error:
 `ValueError: shapes (0,1536) and (768,) not aligned: 1536 (dim 1) != 768 (dim 0)`
 
 you could add `"embedding_model_dims": 768,` to the config of the vector_store to overcome this issue.
-

docs/mint.json

@@ -113,7 +113,8 @@
                 "components/vectordbs/dbs/pgvector",
                 "components/vectordbs/dbs/milvus",
                 "components/vectordbs/dbs/azure_ai_search",
-                "components/vectordbs/dbs/redis"
+                "components/vectordbs/dbs/redis",
+                "components/vectordbs/dbs/couchbase"
               ]
             }
           ]

mem0/configs/vector_stores/couchbase.py

@@ -0,0 +1,28 @@
+from typing import Any, Dict, Optional
+
+from pydantic import BaseModel, Field, model_validator
+
+
+class CouchbaseConfig(BaseModel):
+
+    connection_str: str = Field(..., description="Connection string for Couchbase server")
+    username: str = Field(..., description="Username for Couchbase authentication")
+    password: str = Field(..., description="Password for Couchbase authentication")
+    bucket_name: str = Field(..., description="Name of the Couchbase bucket")
+    scope_name: Optional[str] = Field("_default", description="Name of the scope")
+    collection_name: Optional[str] = Field("_default", description="Name of the collection")
+    index_name: Optional[str] = Field(None, description="Name of the search index")
+    embedding_model_dims: Optional[int] = Field(1536, description="Dimensions of the embedding model")
+
+    @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

@@ -66,6 +66,7 @@ class VectorStoreFactory:
         "milvus": "mem0.vector_stores.milvus.MilvusDB",
         "azure_ai_search": "mem0.vector_stores.azure_ai_search.AzureAISearch",
         "redis": "mem0.vector_stores.redis.RedisDB",
+        "couchbase": "mem0.vector_stores.couchbase.Couchbase",
     }
 
     @classmethod

mem0/vector_stores/configs.py

@@ -17,6 +17,7 @@ class VectorStoreConfig(BaseModel):
         "milvus": "MilvusDBConfig",
         "azure_ai_search": "AzureAISearchConfig",
         "redis": "RedisDBConfig",
+        "couchbase": "CouchbaseConfig",
     }
 
     @model_validator(mode="after")