mem0ai-azure-mysql 0.1.116.12__py3-none-any.whl → 0.2.1__py3-none-any.whl

mem0/__init__.py

@@ -2,5 +2,4 @@ import importlib.metadata
 
 __version__ = importlib.metadata.version("mem0ai-azure-mysql")
 
-from mem0.client.main import AsyncMemoryClient, MemoryClient  # noqa
-from mem0.memory.main import AsyncMemory, Memory  # noqa
+from mem0.memory.main import AsyncMemory  # noqa

mem0/configs/llms/base.py

@@ -29,7 +29,7 @@ class BaseLlmConfig(ABC):
         Initialize a base configuration class instance for the LLM.
 
         Args:
-            model: The model identifier to use (e.g., "gpt-4o-mini", "claude-3-5-sonnet-20240620")
+            model: The model identifier to use (e.g., "gpt-5.1", "claude-3-5-sonnet-20240620")
                 Defaults to None (will be set by provider-specific configs)
             temperature: Controls the randomness of the model's output.
                 Higher values (closer to 1) make output more random, lower values make it more deterministic.

mem0/embeddings/configs.py

@@ -5,26 +5,15 @@ from pydantic import BaseModel, Field, field_validator
 
 class EmbedderConfig(BaseModel):
     provider: str = Field(
-        description="Provider of the embedding model (e.g., 'ollama', 'openai')",
-        default="openai",
+        description="Provider of the embedding model (e.g., 'azure_openai')",
+        default="azure_openai",
     )
     config: Optional[dict] = Field(description="Configuration for the specific embedding model", default={})
 
     @field_validator("config")
     def validate_config(cls, v, values):
         provider = values.data.get("provider")
-        if provider in [
-            "openai",
-            "ollama",
-            "huggingface",
-            "azure_openai",
-            "gemini",
-            "vertexai",
-            "together",
-            "lmstudio",
-            "langchain",
-            "aws_bedrock",
-        ]:
+        if provider in ["azure_openai"]:
             return v
         else:
             raise ValueError(f"Unsupported embedding provider: {provider}")

mem0/graphs/configs.py

@@ -1,4 +1,4 @@
-from typing import Optional, Union
+from typing import Optional
 
 from pydantic import BaseModel, Field, field_validator, model_validator
 
@@ -8,7 +8,7 @@ from mem0.llms.configs import LlmConfig
 class RerankConfig(BaseModel):
     provider: str = Field(
         description="Provider of the rerank model (e.g., 'openai', 'azure', 'cohere')",
-        default="cohere", 
+        default="cohere",
     )
     config: Optional[dict] = Field(
         description="Configuration for the specific rerank model", default={}
@@ -33,7 +33,7 @@ class Neo4jConfig(BaseModel):
         )
         if not url or not username or not password:
             raise ValueError("Please provide 'url', 'username' and 'password'.")
-        
+
         if values.get("rerank") is not None:
             values["rerank"] = RerankConfig(**values.get("rerank"))
             if values["rerank"].provider not in ("cohere"):
@@ -42,62 +42,12 @@ class Neo4jConfig(BaseModel):
         return values
 
 
-class MemgraphConfig(BaseModel):
-    url: Optional[str] = Field(None, description="Host address for the graph database")
-    username: Optional[str] = Field(None, description="Username for the graph database")
-    password: Optional[str] = Field(None, description="Password for the graph database")
-
-    @model_validator(mode="before")
-    def check_host_port_or_path(cls, values):
-        url, username, password = (
-            values.get("url"),
-            values.get("username"),
-            values.get("password"),
-        )
-        if not url or not username or not password:
-            raise ValueError("Please provide 'url', 'username' and 'password'.")
-        return values
-
-
-class NeptuneConfig(BaseModel):
-    endpoint: Optional[str] = (
-        Field(
-            None,
-            description="Endpoint to connect to a Neptune Analytics Server as neptune-graph://<graphid>",
-        ),
-    )
-    base_label: Optional[bool] = Field(None, description="Whether to use base node label __Entity__ for all entities")
-
-    @model_validator(mode="before")
-    def check_host_port_or_path(cls, values):
-        endpoint = values.get("endpoint")
-        if not endpoint:
-            raise ValueError("Please provide 'endpoint' with the format as 'neptune-graph://<graphid>'.")
-        if endpoint.startswith("neptune-db://"):
-            raise ValueError("neptune-db server is not yet supported")
-        elif endpoint.startswith("neptune-graph://"):
-            # This is a Neptune Analytics Graph
-            graph_identifier = endpoint.replace("neptune-graph://", "")
-            if not graph_identifier.startswith("g-"):
-                raise ValueError("Provide a valid 'graph_identifier'.")
-            values["graph_identifier"] = graph_identifier
-            return values
-        else:
-            raise ValueError(
-                "You must provide an endpoint to create a NeptuneServer as either neptune-db://<endpoint> or neptune-graph://<graphid>"
-            )
-
-
-class KuzuConfig(BaseModel):
-    db: Optional[str] = Field(":memory:", description="Path to a Kuzu database file")
-
-
 class GraphStoreConfig(BaseModel):
     provider: str = Field(
-        description="Provider of the data store (e.g., 'neo4j', 'memgraph', 'neptune', 'kuzu')",
+        description="Provider of the data store (e.g., 'neo4j')",
         default="neo4j",
     )
-    config: Union[Neo4jConfig, MemgraphConfig, NeptuneConfig, KuzuConfig] = Field(
+    config: Optional[Neo4jConfig] = Field(
         description="Configuration for the specific data store", default=None
     )
     llm: Optional[LlmConfig] = Field(description="LLM configuration for querying the graph store", default=None)
@@ -108,13 +58,7 @@ class GraphStoreConfig(BaseModel):
     @field_validator("config")
     def validate_config(cls, v, values):
         provider = values.data.get("provider")
-        if provider == "neo4j":
+        if provider in ("neo4j", "default"):
             return Neo4jConfig(**v.model_dump())
-        elif provider == "memgraph":
-            return MemgraphConfig(**v.model_dump())
-        elif provider == "neptune":
-            return NeptuneConfig(**v.model_dump())
-        elif provider == "kuzu":
-            return KuzuConfig(**v.model_dump())
         else:
             raise ValueError(f"Unsupported graph store provider: {provider}")

mem0/llms/azure_openai.py

@@ -36,7 +36,7 @@ class AzureOpenAILLM(LLMBase):
 
         # Model name should match the custom deployment name chosen for it.
         if not self.config.model:
-            self.config.model = "gpt-4o"
+            self.config.model = "gpt-5.1"
 
         api_key = self.config.azure_kwargs.api_key or os.getenv("LLM_AZURE_API_KEY")
         azure_ad_token = self.config.azure_kwargs.azure_ad_token or os.getenv("LLM_AZURE_AD_TOKEN")

mem0/llms/configs.py

@@ -4,31 +4,13 @@ from pydantic import BaseModel, Field, field_validator
 
 
 class LlmConfig(BaseModel):
-    provider: str = Field(description="Provider of the LLM (e.g., 'ollama', 'openai')", default="openai")
+    provider: str = Field(description="Provider of the LLM (e.g., 'azure_openai')", default="azure_openai")
     config: Optional[dict] = Field(description="Configuration for the specific LLM", default={})
 
     @field_validator("config")
     def validate_config(cls, v, values):
         provider = values.data.get("provider")
-        if provider in (
-            "openai",
-            "ollama",
-            "anthropic",
-            "groq",
-            "together",
-            "aws_bedrock",
-            "litellm",
-            "azure_openai",
-            "openai_structured",
-            "azure_openai_structured",
-            "gemini",
-            "deepseek",
-            "xai",
-            "sarvam",
-            "lmstudio",
-            "vllm",
-            "langchain",
-        ):
+        if provider in ("azure_openai",):
             return v
         else:
             raise ValueError(f"Unsupported LLM provider: {provider}")