20263.13.0 Some requests regarding the functions of the AI assistant

Hi @Confused Hao,

I'm Maxime, AI Software Architect at Devolutions. I work on the MCP server and the AI Assistant integration for RDM.

I'll gladly help you with the issue you're facing. I created the custom provider for a specific use case for a client who was using a specific AI inference provider. Therefore, it's possible that there are issues with other products that I didn't test. Would you mind giving me more information about the product (website) you're using and how you've configured the custom providers (Anthropic, OpenAI with Response or Chat Completion API, Ollama), and which model you're trying to use?

Best regards,

Hi @Confused Hao,

I'm Maxime, AI Software Architect at Devolutions. I work on the MCP server and the AI Assistant integration for RDM.

I'll gladly help you with the issue you're facing. I created the custom provider for a specific use case for a client who was using a specific AI inference provider. Therefore, it's possible that there are issues with other products that I didn't test. Would you mind giving me more information about the product (website) you're using and how you've configured the custom providers (Anthropic, OpenAI with Response or Chat Completion API, Ollama), and which model you're trying to use?

Best regards,

@Maxime Forest

Thank you for your reply. The local model I am using is the distilled model from deepseek. The API format is compatible with OpenAI/Anthropic, but the model name needs to be customized.

Best regards

Hi @Confused Hao,

I'm Maxime, AI Software Architect at Devolutions. I work on the MCP server and the AI Assistant integration for RDM.

I'll gladly help you with the issue you're facing. I created the custom provider for a specific use case for a client who was using a specific AI inference provider. Therefore, it's possible that there are issues with other products that I didn't test. Would you mind giving me more information about the product (website) you're using and how you've configured the custom providers (Anthropic, OpenAI with Response or Chat Completion API, Ollama), and which model you're trying to use?

Best regards,

@Maxime Forest

Online document address: https://api-docs.deepseek.com/, for reference

Best regards

Thanks for the information!

Give me some time to investigate and see what I can do. It might take a bit of time since I don't have direct access to the DeepSeek Platform. I'll do tests on other similar platforms like OpenRouter, which I can configure in the AI Assistant using the same custom provider. OpenRouter has DeepSeek models, which I have access to.

I'll keep you informed as soon as I have more details.

Thanks for the information!

Give me some time to investigate and see what I can do. It might take a bit of time since I don't have direct access to the DeepSeek Platform. I'll do tests on other similar platforms like OpenRouter, which I can configure in the AI Assistant using the same custom provider. OpenRouter has DeepSeek models, which I have access to.

I'll keep you informed as soon as I have more details.

@Maxime Forest

Thank you for your reply. I will provide some simple information for your reference, hoping it will be helpful.

curl：

curl base_url  \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ${DEEPSEEK_API_KEY}" \
  -d '{
        "model": "model",
        "messages": [
          {"role": "system", "content": "You are a helpful assistant."},
          {"role": "user", "content": "Hello!"}
        ],
        "thinking": {"type": "enabled"},
        "reasoning_effort": "high",
        "stream": false
      }'

The example is of non-streaming output. You can set "stream" to true to use streaming output. look forward to your good news.

Best regards，

Hi @Confused Hao

I won't be able to test the full end-to-end integration with the DeepSeek API token since I don't have a subscription to the DeepSeek Platform, but rest assured I'll find a way to get this working for you.

I was able to test the DeepSeek model in another way using OpenRouter, and I applied fixes to get it working properly, but that alone doesn't guarantee it will work directly with a DeepSeek API token. Once I'm pretty confident in the fix, I'll let you know which version of RDM has it or provide you a custom RDM's installer for you to test.

I'll keep you informed when I have more details.

Best regards,

Hi @Confused Hao

I've created a test app that replicates the basic features of the AI Assistant of RDM so you can test the fix I have running in my local RDM and validate that it works with a DeepSeek API key.

I'll send you a private message on the Forum, in that private message you will have a link to https://send.devolutions.net which will have an attachment (.zip file).

We can continue exchanging in private messages after this until we figure out the solution to get it working.

Hi @Confused Hao

I've created a test app that replicates the basic features of the AI Assistant of RDM so you can test the fix I have running in my local RDM and validate that it works with a DeepSeek API key.

I'll send you a private message on the Forum, in that private message you will have a link to https://send.devolutions.net which will have an attachment (.zip file).

We can continue exchanging in private messages after this until we figure out the solution to get it working.

@Maxime Forest

Thank you very much. I have replied to your private message. Please check the content. I will do my best to provide assistance. Thank you.