HelloJelly2021
HelloJelly2021
Thanks for your feedbacks. I updated the docker-compose.yml as you saied, but it didn't work. services: openmemory-mcp: image: mem0/openmemory-mcp:latest build: api/ environment: - OPENAI_BASE_URL=https://api.siliconflow.cn/v1 - OPENAI_API_KEY=sk-... - USER=worker - MILVUS_HOST=10.x.x.x...
After Openmemory mcp server and SpringAI application mcp client establish a connection, Openmemory mcp server sent an sse message "heartbeat" with null event name, and SpringAI application mcp client rejected....
Thanks for your feedback and fixes. My api/config.json as flows: { "mem0": { "llm": { "provider": "openai", "config": { "model": "deepseek-ai/DeepSeek-R1", "openai_base_url": "https://api.siliconflow.cn/v1", "api_key": "sk-...", "temperature": 0.1, "max_tokens": 2000 }...
> [@HelloJelly2021](https://github.com/HelloJelly2021) According to the [API documentation](https://docs.siliconflow.com/en/api-reference/chat-completions/chat-completions), the base URL is 'https://api.siliconflow.com/v1/' not 'https://api.siliconflow.cn/v1/' CN for big China.
The root cause is that the categorization Mode name is hard code to be "gpt-4o-mini", and SiliconFlow does not provide the model "gpt-4o-mini". @retry(stop=stop_after_attempt(3), wait=wait_exponential(multiplier=1, min=4, max=15)) def get_categories_for_memory(memory: str)...
> > The root cause is that the categorization Mode name is hard code to be "gpt-4o-mini", and SiliconFlow does not provide the model "gpt-4o-mini". > > [@Retry](https://github.com/Retry)(stop=stop_after_attempt(3), wait=wait_exponential(multiplier=1, min=4,...
Does anyone know the final solution to this problem? It's not a problem for the LLM provider, it's a problem where the classification model doesn't exist.
你好，我也遇到此问题。我用的版本是1.0.0.4，使用LlmRoutingAgent路由的时候，不会依赖历史对话，所以没办法实现多轮对话。在路由到具体智能体后，由于取的是messages的第一条，在多轮对话的时候，会反复回答第一个问题。 下面是1.0.0.4版本的RoutingEdgeAction： @Override public CompletableFuture apply(OverAllState state) { CompletableFuture result = new CompletableFuture(); try { String taskDetail = state.value(taskKey, ""); result.complete(this.chatClient.prompt(taskDetail).call().content()); } catch (Exception e) { result.completeExceptionally(e); } return result;...
@yuluo-yx 请问这个问题有修复吗？