Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
Python agent-contextagent-memoryagent-pluginsagentic-ragcontext-databasedsh-pluginknowledge-basememorymemory-managementself-evolvingvector-database
feat(config): expose embedding.max_concurrent and vlm.max_concurrent in ov.conf (#282)
yangxinxin-77c6bebefb9f0
diff --git a/README.md b/README.mdindex fa5b5b65f..862d23bfa 100644--- a/README.md+++ b/README.md@@ -238,13 +238,15 @@ Create a configuration file `~/.openviking/ov.conf`, remove the comments before"provider" : "<provider-type>", // Provider type: "volcengine" or "openai" (currently supported)"dimension": 1024, // Vector dimension"model" : "<model-name>" // Embedding model name (e.g., doubao-embedding-vision-250615 or text-embedding-3-large)- }+ },+ "max_concurrent": 10 // Max concurrent embedding requests (default: 10)},"vlm": {"api_base" : "<api-endpoint>", // API endpoint address"api_key" : "<your-api-key>", // Model service API Key"provider" : "<provider-type>", // Provider type (volcengine, openai, deepseek, anthropic, etc.)- "model" : "<model-name>" // VLM model name (e.g., doubao-seed-1-8-251228 or gpt-4-vision-preview)+ "model" : "<model-name>", // VLM model name (e.g., doubao-seed-1-8-251228 or gpt-4-vision-preview)+ "max_concurrent": 100 // Max concurrent LLM calls for semantic processing (default: 100)}}```@@ -274,13 +276,15 @@ Create a configuration file `~/.openviking/ov.conf`, remove the comments before"provider" : "volcengine","dimension": 1024,"model" : "doubao-embedding-vision-250615"- }+ },+ "max_concurrent": 10},"vlm": {"api_base" : "https://ark.cn-beijing.volces.com/api/v3","api_key" : "your-volcengine-api-key","provider" : "volcengine",- "model" : "doubao-seed-1-8-251228"+ "model" : "doubao-seed-1-8-251228",+ "max_concurrent": 100}}```@@ -306,13 +310,15 @@ Create a configuration file `~/.openviking/ov.conf`, remove the comments before"provider" : "openai","dimension": 3072,"model" : "text-embedding-3-large"- }+ },+ "max_concurrent": 10},"vlm": {"api_base" : "https://api.openai.com/v1","api_key" : "your-openai-api-key","provider" : "openai",- "model" : "gpt-4-vision-preview"+ "model" : "gpt-4-vision-preview",+ "max_concurrent": 100}}```diff --git a/README_CN.md b/README_CN.mdindex 3c55e6bb4..5310b456a 100644--- a/README_CN.md+++ b/README_CN.md@@ -101,13 +101,15 @@ OpenViking 支持多种模型服务:"provider" : "<provider-type>", // 提供商类型(volcengine、openai 或 jina)"dimension": 1024, // 向量维度"model" : "<model-name>" // Embedding 模型名称(如 doubao-embedding-vision-250615 或 text-embedding-3-large)- }+ },+ "max_concurrent": 10 // Embedding 最大并发请求数(默认:10)},"vlm": {"api_base" : "<api-endpoint>", // API 服务端点地址"api_key" : "<your-api-key>", // 模型服务的 API 密钥"provider" : "<provider-type>", // 提供商类型(volcengine、openai 或 jina)- "model" : "<model-name>" // VLM 模型名称(如 doubao-seed-1-8-251228 或 gpt-4-vision-preview)+ "model" : "<model-name>", // VLM 模型名称(如 doubao-seed-1-8-251228 或 gpt-4-vision-preview)+ "max_concurrent": 100 // 语义处理最大并发 LLM 调用数(默认:100)}}```@@ -135,13 +137,15 @@ OpenViking 支持多种模型服务:"provider" : "volcengine","dimension": 1024,"model" : "doubao-embedding-vision-250615"- }+ },+ "max_concurrent": 10},"vlm": {"api_base" : "https://ark.cn-beijing.volces.com/api/v3","api_key" : "your-volcengine-api-key","provider" : "volcengine",- "model" : "doubao-seed-1-8-251228"+ "model" : "doubao-seed-1-8-251228",+ "max_concurrent": 100}}```@@ -167,13 +171,15 @@ OpenViking 支持多种模型服务:"provider" : "openai","dimension": 3072,"model" : "text-embedding-3-large"- }+ },+ "max_concurrent": 10},"vlm": {"api_base" : "https://api.openai.com/v1","api_key" : "your-openai-api-key","provider" : "openai",- "model" : "gpt-4-vision-preview"+ "model" : "gpt-4-vision-preview",+ "max_concurrent": 100}}```diff --git a/openviking/service/core.py b/openviking/service/core.pyindex 59d81163a..cab39dfe9 100644--- a/openviking/service/core.py+++ b/openviking/service/core.py@@ -89,7 +89,9 @@ class OpenVikingService:self._initialized = False# Initialize storage- self._init_storage(config.storage, config.embedding.max_concurrent)+ self._init_storage(+ config.storage, config.embedding.max_concurrent, config.vlm.max_concurrent+ )# Initialize embedderself._embedder = config.embedding.get_embedder()@@ -97,7 +99,12 @@ class OpenVikingService:f"Initialized embedder (dim {config.embedding.dimension}, sparse {self._embedder.is_sparse})")- def _init_storage(self, config: StorageConfig, max_concurrent_embedding: int = 1) -> None:+ def _init_storage(+ self,+ config: StorageConfig,+ max_concurrent_embedding: int = 10,+ max_concurrent_semantic: int = 100,+ ) -> None:"""Initialize storage resources."""if config.agfs.backend == "local":self._agfs_manager = AGFSManager(config=config.agfs)@@ -113,6 +120,7 @@ class OpenVikingService:agfs_url=self._agfs_url,timeout=config.agfs.timeout,max_concurrent_embedding=max_concurrent_embedding,+ max_concurrent_semantic=max_concurrent_semantic,)else:logger.warning("AGFS URL not configured, skipping queue manager initialization")@@ -196,7 +204,11 @@ class OpenVikingService:returnif self._vikingdb_manager is None:- self._init_storage(self._config.storage, self._config.embedding.max_concurrent)+ self._init_storage(+ self._config.storage,+ self._config.embedding.max_concurrent,+ self._config.vlm.max_concurrent,+ )if self._embedder is None:self._embedder = self._config.embedding.get_embedder()diff --git a/openviking/storage/queuefs/queue_manager.py b/openviking/storage/queuefs/queue_manager.pyindex 7ceab4dfe..3c5de9c01 100644--- a/openviking/storage/queuefs/queue_manager.py+++ b/openviking/storage/queuefs/queue_manager.py@@ -30,7 +30,8 @@ def init_queue_manager(agfs_url: str = "http://localhost:8080",timeout: int = 10,mount_point: str = "/queue",- max_concurrent_embedding: int = 1,+ max_concurrent_embedding: int = 10,+ max_concurrent_semantic: int = 100,) -> "QueueManager":"""Initialize QueueManager singleton."""global _instance@@ -39,6 +40,7 @@ def init_queue_manager(timeout=timeout,mount_point=mount_point,max_concurrent_embedding=max_concurrent_embedding,+ max_concurrent_semantic=max_concurrent_semantic,)return _instance@@ -66,13 +68,15 @@ class QueueManager:agfs_url: str = "http://localhost:8080",timeout: int = 10,mount_point: str = "/queue",- max_concurrent_embedding: int = 1,+ max_concurrent_embedding: int = 10,+ max_concurrent_semantic: int = 100,):"""Initialize QueueManager."""self._agfs_url = agfs_urlself.timeout = timeoutself.mount_point = mount_pointself._max_concurrent_embedding = max_concurrent_embedding+ self._max_concurrent_semantic = max_concurrent_semanticself._agfs: Optional[Any] = Noneself._queues: Dict[str, NamedQueue] = {}self._started = False@@ -124,7 +128,7 @@ class QueueManager:logger.info("Embedding queue initialized with TextEmbeddingHandler")# Semantic Queue- semantic_processor = SemanticProcessor()+ semantic_processor = SemanticProcessor(max_concurrent_llm=self._max_concurrent_semantic)self.get_queue(self.SEMANTIC,dequeue_handler=semantic_processor,diff --git a/openviking_cli/utils/config/embedding_config.py b/openviking_cli/utils/config/embedding_config.pyindex 5184ddab6..2d4f1164b 100644--- a/openviking_cli/utils/config/embedding_config.py+++ b/openviking_cli/utils/config/embedding_config.py@@ -105,7 +105,7 @@ class EmbeddingConfig(BaseModel):hybrid: Optional[EmbeddingModelConfig] = Field(default=None)max_concurrent: int = Field(- default=1, description="Maximum number of concurrent embedding requests"+ default=10, description="Maximum number of concurrent embedding requests")model_config = {"extra": "forbid"}diff --git a/openviking_cli/utils/config/vlm_config.py b/openviking_cli/utils/config/vlm_config.pyindex e3ce672ed..4e5942075 100644--- a/openviking_cli/utils/config/vlm_config.py+++ b/openviking_cli/utils/config/vlm_config.py@@ -28,6 +28,10 @@ class VLMConfig(BaseModel):thinking: bool = Field(default=False, description="Enable thinking mode for VolcEngine models")+ max_concurrent: int = Field(+ default=100, description="Maximum number of concurrent LLM calls for semantic processing"+ )+_vlm_instance: Optional[Any] = Nonemodel_config = {"arbitrary_types_allowed": True, "extra": "forbid"}