Feature: tencent vector db integration

docs/components/vectordbs/dbs/tencent.mdx

@@ -0,0 +1,47 @@
+[TencentVectorDB](https://cloud.tencent.com/product/vdb) is an open-source vector database that suits AI applications of every size, from running a demo chatbot in a Jupyter notebook to building web-scale search that serves billions of users.
+
+### Usage
+
+```python
+import os
+from mem0 import Memory
+
+config = {
+    "vector_store": {
+        "provider": "tencent",
+        "config": {
+            "url": "http://your-tencent-vdb-instance-url",
+            "key": "your-tencent-vdb-api-key",
+        }
+    }
+}
+
+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="alice", metadata={"category": "movies"})
+```
+
+### Config
+
+Here are the parameters available for configuring TencentVectorDB:
+
+| Parameter | Description | Default Value |
+| --- | --- | --- |
+| `url` | URL for TencentVectorDB instance | Required |
+| `key` | API key for TencentVectorDB instance | Required |
+| `username` | Username for TencentVectorDB instance | `root` |
+| `database_name` | Name of the database | `mem0` |
+| `collection_name` | Name of the collection | `mem0` |
+| `embedding_model_dims` | Dimensions of the embedding model | `1536` |
+| `metric_type` | Metric type for similarity search | `COSINE` |
+| `index_type` | Index type for vectors | `HNSW` |
+| `shard_num` | Number of shards in the collection | `2` |
+| `replica_num` | Number of replicas for the collection | `2` |
+| `field_type` | Field type for the embedding vectors | `vector` |
+| `params` | Parameters for the index | `None` |
+| `no_index_fields` | Fields that will not be indexed | `None` |

docs/docs.json

@@ -224,7 +224,8 @@
                               "components/vectordbs/dbs/cassandra",
                               "components/vectordbs/dbs/s3_vectors",
                               "components/vectordbs/dbs/databricks",
-                              "components/vectordbs/dbs/neptune_analytics"
+                              "components/vectordbs/dbs/neptune_analytics",
+                              "components/vectordbs/dbs/tencent"
                             ]
                           }
                         ]

mem0/configs/vector_stores/tencent.py

@@ -0,0 +1,31 @@
+from typing import Any, Dict, List
+
+from pydantic import BaseModel, ConfigDict, Field, model_validator
+
+
+class TencentVectorDBConfig(BaseModel):
+    url: str = Field(None, description="URL for TencentVectorDB instance")
+    key: str = Field(None, description="API key for TencentVectorDB instance")
+    username: str = Field("root", description="Username for TencentVectorDB instance")
+    database_name: str = Field("mem0", description="Name of the database")
+    collection_name: str = Field("mem0", description="Name of the collection")
+    embedding_model_dims: int = Field(1536, description="Dimensions of the embedding model")
+    metric_type: str = Field("COSINE", description="Metric type for similarity search")
+    index_type: str = Field("HNSW", description="Index type for vectors")
+    shard_num: int = Field(2, description="Number of shards in the collection")
+    replica_num: int = Field(2, description="Number of replicas for the collection")
+    field_type: str = Field("vector", description="Field type for the embedding vectors")
+    params: Dict[str, Any] = Field({}, description="Parameters for the index")
+    no_index_fields: List[str] = Field([], description="Fields that will not be indexed")
+
+    @model_validator(mode="before")
+    @classmethod
+    def validate_extra_fields(cls, values: Dict[str, Any]) -> Dict[str, Any]:
+        url, key = values.get("url"), values.get("key")
+        if not url or not key:
+            raise ValueError(
+                "Both 'url' and 'key' must be provided."
+            )
+        return values
+
+    model_config = ConfigDict(arbitrary_types_allowed=True)

mem0/utils/factory.py

@@ -12,10 +12,12 @@
 from mem0.configs.llms.vllm import VllmConfig
 from mem0.configs.rerankers.base import BaseRerankerConfig
 from mem0.configs.rerankers.cohere import CohereRerankerConfig
-from mem0.configs.rerankers.sentence_transformer import SentenceTransformerRerankerConfig
-from mem0.configs.rerankers.zero_entropy import ZeroEntropyRerankerConfig
-from mem0.configs.rerankers.llm import LLMRerankerConfig
 from mem0.configs.rerankers.huggingface import HuggingFaceRerankerConfig
+from mem0.configs.rerankers.llm import LLMRerankerConfig
+from mem0.configs.rerankers.sentence_transformer import (
+    SentenceTransformerRerankerConfig,
+)
+from mem0.configs.rerankers.zero_entropy import ZeroEntropyRerankerConfig
 from mem0.embeddings.mock import MockEmbeddings
 
 
@@ -186,6 +188,7 @@ class VectorStoreFactory:
         "baidu": "mem0.vector_stores.baidu.BaiduDB",
         "cassandra": "mem0.vector_stores.cassandra.CassandraDB",
         "neptune": "mem0.vector_stores.neptune_analytics.NeptuneAnalyticsVector",
+        "tencent": "mem0.vector_stores.tencent.TencentVectorDB",
     }
 
     @classmethod

mem0/vector_stores/configs.py

@@ -34,6 +34,7 @@ class VectorStoreConfig(BaseModel):
         "faiss": "FAISSConfig",
         "langchain": "LangchainConfig",
         "s3_vectors": "S3VectorsConfig",
+        "tencent": "TencentVectorDBConfig",
     }
 
     @model_validator(mode="after")