AB
AB
AiBoss

All Categories

Tutorials

DeepSeek API Calls and Local Deployment Tutorial: Understand It All in One Article

DeepSeek has recently become a hot topic not only within the AI community but also beyond, becoming a subject of widespread discussion. This is excellent; AI technology is entering everyday life, and the widespread adoption of AI in 2025 is something to look forward to. AI tools...

DeepSeek API调用和本地部署教程，一文搞懂

recent DeepSeek Not only in AI It became a huge hit within the community and even successfully "went beyond" to become a hot topic of discussion nationwide, which is excellent.AI Technology is entering people's lives; by 2025... AI The widespread adoption of [the technology/equipment] will be even more anticipated.AI We will continue to share more toolsets with you.practicalof AI tool!

Station MasterrecommendHow to resolve the DeepSeek server being busy? (16 questions)freeR1 Full-Power Alternative

However, with the explosive popularity of DeepSeek, server lag issues have become frequent, preventing many users from using it normally.AIIn the "toolset" community, many members are complaining about this issue. Therefore,AIThis toolkit provides a complete solution, including:

  • Get official API Key
  • Local deployment of DeepSeek
  • Excellent third party AI Clientrecommend

I. Obtain the official API Key

API Key: An API Key can be understood as a password that allows you to directly access DeepSeek services.

Although using the official API Key is the bestSimpleHowever, due to excessive server load, the lag issue still exists.

You can visit https://platform.deepseek.com/api_keys to create an API Key, which will be discussed later in this article.AIThe toolset will explain how to use it.

It should be noted that using an API Key incurs a fee, but currently, due to special circumstances,The official recharge service has been suspended.It is recommended to use a third-party API as an alternative: SiliconFlow.

II. Local Deployment of DeepSeek

To resolve the server lag issueAItoolset recommendEveryone uses Ollama ToolsLocal deploymentOllama not only supports DeepSeek,It can also run many other types of programs. AI Model.

The deployment method is as follows:

1. Download Ollama

First, visit the official Ollama website, download the version of Ollama corresponding to your computer's operating system, and then install it.

Ollama is a tool for running and managing locally. AI A tool for interacting with various models.

You can also see the Ollama icon on your computer; simply double-click to open it.

2. Download the DeepSeek model

Next, you need to open your computer's terminal command-line tool and enter the command. ollama run deepseek-r1The default installation includes DeepSeek 7b models.

  • Command line opening method:
    • On Windows: Press the Win+R key combination to open the "Run" dialog box, type "cmd" or "powershell", and click "OK" or press Enter to open the corresponding command-line tool.
    • On Mac: Press Command + Space to open Spotlight, search for "Terminal" and open it.

    Then you can download the DeepSeek model normally:

    3. Testing DeepSeek

    After the download is complete, interact with DeepSeek directly in the terminal, for example, by typing: "Please introduce..."AIToolset.”, then wait for DeepSeek to think and reply:

    AIToolset: This section compiles some commonly used Ollama commands. When using them... Simply replace it with the specific model name:

    • Install model: ollama pull
    • Running the model: ollama run
    • Delete model: ollama rm
    • All installed models: ollama list

    III. Third Party AI Clientrecommend

    For users unfamiliar with the command lineAItoolset recommendthe following 3 excellent third-party AI ClientThis makes DeepSeek easier to use:

    • ChatBox
    • CherryStudio
    • AnythingLLM

    1. ChatBox

    ChatBox is a multi-platform... AI The client supports document, image, and code processing, emphasizing local data storage and privacy protection. Official website: ChatBox

    It can be started after installation:

    1.1 Using the DeepSeek API

    • First, click the settings icon in the bottom left corner, and then follow these steps:
      1. Select "DEEPSEEK API" as the model provider.
      2. Enter the API Key you copied earlier.
      3. save

    1.2 Using Ollama

    • First, click the settings icon in the bottom left corner, and then follow these steps:
      1. Select "OLLAMA API" as the model provider.
      2. Enter the API domain name as: http://localhost:11434
      3. Select the previously installed model
      4. save

    1.3 Start a conversation. ChatBox also supports...Add images, files, links, and online queriesIt's very convenient.

    2. CherryStudio

    CherryStudio is a useful tool. AI The client application supports services for multiple large-scale language models, providing an intuitive visual interface and remote API, reducing reliance on local hardware and improving efficiency. Official website: CherryStudio

    It can be started after installation:

    2.1 Using the DeepSeek API

    • First, click the settings icon in the bottom left corner, and then follow these steps:
      1. Click "Model Service"
      2. Click "Explore Deeper"
      3. Enter the copied API Key in the "API Key" field, and add "DeepSeek Reasoner Model" below it.
      4. Enable service

    Then you need to set the default model to "DeepSeek Reasoner model":

    2.2 Using Ollama

    • First, click the settings icon in the bottom left corner, and then follow these steps:
      1. Click "Model Service"
      2. Click “Ollama”
      3. In the model, click "Manage" and add the previously installed DeepSeek model.
      4. Enable service

    2.3 Start the conversation

    3. AnythingLLM

    AnythingLLM It is a tool that supports local deployment. AI This tool allows users to run and manage large language models locally, providing a visual interface for easy interaction with the models. Official website: AnythingLLM

    It can be started after installation:

    3.1 Using the DeepSeek API

    • First, click the settings icon in the bottom left corner, and then follow these steps:
      1. Click "LLM Preferences
      2. exist"LLM Provider selection DeepSeek
      3. Enter the API Key you copied earlier in the "API Key" field.
      4. Select the "deepseek-reasoner model"
      5. save

    3.2 Using Ollama

    • First, click the settings icon in the bottom left corner, and then follow these steps:
      1. Click "LLM Preferences
      2. exist"LLM Select "Ollama" as the provider.
      3. Select the "deepseek-reasoner model"
      4. save

    3.3 Configure the workspace

    • Anything LLM Compared to other tools, it has an additional "Set up workspace" step. Each workspace can use different models. The configuration process is as follows:
      1. Click "New Workspace" to create
      2. Click Workspace Settings
      3. Choose the method you want to use, such as DeepSeek or Ollama. Chris is using Ollama here.
      4. save

    3.4 Starting a Conversation: You can create a new conversation to engage in normal dialogue with DeepSeek.

    This article mainly introduces how to use the DeepSeek API and local deployment, and primarily analyzes three excellent third-party libraries. AI The client allows everyone to...High efficiencyThis involves using DeepSeek. Of course, there are many other similar software programs, and we welcome suggestions from everyone.

    Hopefully by 2025,AI It can be made more widespread, allowing more people to access it. AI Bless yourself and unleash your creativity.

Back