DeepSeek Embedding model API

  • Resolved kovacev

    (@kovacev)


    4 months ago

    Hello,
    I’m testing various AI chatbots for my web shop. I liked MxChat at first, it looks professional, it has a lot to offer in the PRO version, but I’m trying to connect the API with DeepSeek and I can’t, because it asks for an additional API for the “Embedding Model”. The “embedding model” only supports Chat-GPT as far as I can see, but not DeepSeek.
    The question is, will the plugin support the deepseek Embedding Model in the future or not, so I can forget about this plugin right away.
    I don’t feel like paying for 2 API accounts, and personally, DeepSeek is cheaper and somewhat better for chat than Chat-GPT.

Viewing 2 replies - 1 through 2 (of 2 total)
  • Plugin Support m4xw3ll

    (@m4xw3ll)

    4 months ago

    Hi @kovacev,

    thanks for reaching out. Currently DeepSeek does not offer an embedding model. An embedding model is required for MxChat as that is how it is able to find and match relevant content from the database (the only way any AI system can do this is via embeddings).

    There are several embedding service providers available in MxChat: OpenAI, Google, and Voyage.

    Others who typically use DeepSeek tend to go with Voyage as its regionally available worldwide. If DeepSeek releases an embedding model it will be added!

    Thanks,

    Maxwell

    Thread Starter kovacev

    (@kovacev)

    4 months ago

    aha, ok. Thank you very much for your quick response…
    I’m going to continue testing MxChat, I hope I buy the “Agency +” license.

Viewing 2 replies - 1 through 2 (of 2 total)

You must be logged in to reply to this topic.

  • 2 replies
  • 2 participants
  • Last reply from: kovacev
  • Last activity: 4 months ago
  • Status: resolved