Unlocking the Full Potential of LobeChat: A Complete Guide from Setup to Practical Application
本文最后更新于 317 天前,其中的信息可能已经有所发展或是发生改变,如有失效可到评论区留言。
Article Abstract
Lobechat as a local large language model UI tool, its complex settings and multiple API provider integration options often confuse users. By analyzing the operational differences between API providers (such as OpenAI, Google) and third-party proxy platforms (such as OhMyGPT), this article provides a convenient PWA-based installation solution and detailed configuration guide, covering core functions such as language model switching, system assistant customization, and voice service adaptation. Using a third-party API proxy can bypass geographical restrictions and reduce usage costs, while PWA support enhances the mobile experience, ultimately achieving practical application effects of flexibly calling multiple models and optimizing interaction efficiency.
Qwen3-14B · 2026-06-18

Preface

In previous articles, I introduced the installation of the local large language model UI: Lobechat (see article:Docker Series: Detailed Deployment Tutorial Based on the Open Source Large Language Model UI Framework: LobeChat), as well as the third-party API: OhMyGPT, and briefly mentioned that Lobechat + OhMyGPT can create a seamless switching experience across multiple API providers.

However, because Lobechat itself provides many features, and consequently has quite a few settings, it is not something that can be easily mastered right away. Coupled with the differences between services directly provided by API providers and services proxied by third-party API providers (such as OhMyGPT), this can cause quite a bit of confusion for those who are not very familiar with it. In addition, there are some tips and precautions when using Lobechat itself, so I think it is necessary to write a separate article to organize the settings and usage of Lobechat, which can also serve as a detailed tutorial for Lobechat.

Prerequisite Knowledge: API Providers and Third-Party API Providers

API Providers

Note: I have already introduced this part in detail in another article (see:Starting Your AI Journey: A Detailed Introduction to Local LLM UIs and LLM API Providers), so I won't say much here; this is just a brief statement for the completeness of the article structure.

Large language model API providers refer to companies that develop and provide powerful natural language processing models, offering services to developers and enterprises in the form of APIs. These models are typically based on advanced deep learning technologies and can understand, generate, and process human language. The APIs provided by these providers allow users to integrate these language models into various applications for tasks such as text generation, translation, dialogue, and data analysis. Common API providers include, but are not limited to:

  1. OpenAI (ChatGPT): OpenAI is one of the leading large language model providers, offering the ChatGPT API based on GPT models, which supports text generation and dialogue functions. ChatGPT can provide highly efficient natural language processing capabilities in various scenarios, widely applied from customer support to content creation.
  2. Google (Gemini): Google provides the Gemini series of models through Google Cloud's API services. These models are renowned for their deep language understanding and generation capabilities, performing exceptionally well in tasks such as multilingual processing, text analysis, and information extraction.
  3. Anthropic (Claude): Anthropic's Claude series is an emerging powerhouse in the field of large language models, and its API provides intelligent and safer dialogue generation capabilities. Claude excels at handling complex conversations and maintaining semantic consistency, widely used in scenarios like AI assistants and customer support.

Third-Party API Providers

What is a Third-Party API Provider?

Third-party API providers refer to companies or platforms that do not directly develop their own large language models or AI technologies, but instead integrate multiple mainstream API providers (such as OpenAI, Google, Anthropic, etc.) and provide unified interfaces and services to help users easily access these models. These third-party providers typically simplify the management and integration process of APIs, allowing developers and enterprises to choose and use different AI models from a single platform without having to register, configure, and manage APIs from multiple providers individually.

Their services can include cost reduction, unified billing systems, simplified API management, and seamless integration of multiple models, enabling enterprises and developers to quickly adopt AI technology in a more flexible and economical way.

How Third-Party API Providers Work

The operational principle of a third-party API provider can be simply understood as: a platform that integrates multiple large language model API providers, where users only need to use the unified API address and access key provided by the platform to call multiple different models.

The core functions of third-party API providers (taking OhMyGPT, which I use, as an example) are as follows:

Channel Management: On third-party API provider platforms, each channel corresponds to an API Key, which can be an API Key from large language models like OpenAI, Microsoft, Google, etc. One API Key can access multiple models from the same provider, and OhMyGPT will automatically select the appropriate channel to call a specific model based on the user's request.

Access Credentials: Users only need to use the unified access credentials of the third-party API provider to access all models integrated on the platform. There is no need to configure different API credentials for each large language model separately; by simply configuring the API address and access token of the third-party API provider, users can easily call models from multiple large language model API providers.

Operational Workflow:

• The user sends a request, specifying the required model name.
• OhMyGPT matches the corresponding API channel based on the model name in the request and selects the appropriate model to call.
• After a successful match, OhMyGPT sends the request to the actual large language model API provider to obtain the processing result.
• Finally, OhMyGPT returns the result to the user.

This architecture makes OhMyGPT a convenient third-party platform, allowing users to access multiple model providers through a unified interface without having to manage the details of each API individually, which significantly improves the efficiency of use and integration. This approach greatly simplifies the process of switching and calling between different models for users, avoiding the need to handle different interface formats and authentication methods for each provider.

Note: From a certain perspective, a third-party API provider can be viewed as an ‘API reverse proxy.’ By providing a unified interface and access key, it forwards user requests to different large language model API providers and returns the results, thereby simplifying the process of switching and calling multiple models.


There is an open-source project on GitHub with 18.4k stars called One API, which is actually a self-built API relay gateway (the project address is:https://github.com/songquanpeng/one-api), which can provide a unified interface for various large language model API providers through self-hosting. In essence, it works on the same principle as third-party API providers, so you can understand the operating principles of third-party API providers through One API, as shown in the figure below:

image.png

One API provides the following core functions (you can compare them with the core functions of the third-party API providers mentioned earlier):

Unified Interface : By defining a standardized interface, developers can call different AI model APIs through a single set of interfaces. This reduces the complexity of integrating multiple services.

Key Management : Provides flexible API key management functions for different services. Through One API, users can more easily manage and configure multiple API keys, ensuring the security and convenience of calls.

Logging and Monitoring : Provides logging and statistical analysis for each API request, helping developers monitor the usage and performance of each model.

Openness and Extensibility : As an open-source project, One API can be modified and extended according to specific needs to adapt to different scenarios and requirements.

However, the problem it solves is different from that of third-party API providers: its main purpose is to help users who have already purchased services from major API providers solve access issues caused by IP address restrictions (for example, providers not being open to mainland China). Users can deploy One API as a relay gateway on a foreign cloud host without IP restrictions, accessing major language model providers through this cloud host's API to bypass regional restrictions. In contrast, third-party API providers usually directly provide a unified API interface and access key, integrating services from multiple large model providers, solving the problem of allowing users to avoid purchasing or managing each provider's services themselves.

In other words, third-party API platforms mainly simplify switching and calling between multiple models, while One API focuses on solving regional restriction issues, allowing users to continue using the services they have already purchased.

Due to different focuses, One API, as an API relay gateway, needs to pay more attention to and resolve compatibility with various API providers, so it usually performs better in various scenarios. On the other hand, third-party providers (such as OhMyGPT) may have limited support for specific providers' APIs in certain scenarios, especially when going beyond simple dialogue requests. For example, in non-chat applications, AI plugins on WordPress (such as AI Engine) require complex content generation or analysis. Such calls have high requirements for API compatibility. In these use cases, if OhMyGPT does not accurately adapt to the provider's API format or return value processing logic, the success rate may decrease as a result.

Therefore, OhMyGPT is more suitable for chat-like application scenarios (such as LobeChat or ChatGPT Next Web). If you cannot successfully use third-party API providers like OhMyGPT in other scenarios, and happen to have a cloud host with a suitable IP, you can consider the One API solution.


Introduction to Third-Party API Providers

Common third-party API providers include but are not limited to:

OhMyGPT

Introduction: OhMyGPT is a third-party provider focusing on providing API integration services for multiple large language models. Through OhMyGPT, users can use multiple top-tier large language models such as OpenAI, Google Gemini, and Anthropic Claude without having to manage accounts for each provider separately. A major advantage of OhMyGPT is its ability to provide users with more convenient interfaces and lower usage costs, making it suitable for developers and enterprises wishing to use multiple models flexibly.

Features: Simplifies API management, supports multiple large model platforms, and has relatively low costs.

RapidAPI

Introduction: RapidAPI is the world's largest API marketplace, providing thousands of APIs for users to access, including large language model APIs. Developers can quickly find and connect to AI providers like OpenAI and IBM Watson through the RapidAPI platform, using a unified API key management and billing system. It provides developers with functions to test and monitor APIs, improving the efficiency of accessing different services.

Features: Rich variety of APIs, fast integration, unified management and billing.

NLP Cloud

Introduction: NLP Cloud provides APIs based on a variety of natural language processing models, supporting models like the GPT series, T5, BERT, etc. NLP Cloud focuses on providing optimized language model solutions for enterprises, performing particularly well in fields such as text generation, classification, and translation. It also provides users with options for privacy protection and custom models, making it highly suitable for enterprises requiring high security and customized features.

Features: Supports multiple NLP models, enterprise-grade solutions, and privacy protection.

AssemblyAI

Introduction: AssemblyAI is known for its speech recognition API, but it also provides services related to large language models through its platform. Users can integrate OpenAI's GPT models through AssemblyAI, combining language processing with speech recognition for multimodal scenarios such as speech-to-text and intelligent assistants. It provides developers with a fast and stable access experience.

Features: Multimodal support, combining speech and text processing, stable API services.

Spell

Introduction: Spell provides training and management services for machine learning and AI models, allowing developers to access language models like OpenAI and Google through its platform. Spell also offers options for custom training and deployment, suitable for enterprises or researchers who need to flexibly deploy and manage AI models.

Features: Custom model training, simplified deployment, and flexible integration of multiple AI models.

LangchainHub

Introduction: LangchainHub is a third-party platform focusing on natural language processing and large language model integration. Through LangchainHub, users can integrate multiple large language model APIs, such as OpenAI, Anthropic, Google, etc., simplifying calls to various language models and providing compatibility with different tools and frameworks to help developers and researchers quickly build NLP applications.

Features: Broad integration of multiple models, improved development efficiency, and multi-tool compatibility.

In this article, OhMyGPT is used as an example of a third-party API provider.

Optional: Using Lobechat via PWA (Progressive Web App)

Introduction to PWA

LobeChat supports PWA (Progressive Web Apps), enabling it to provide a native-like application experience on mobile and desktop devices. Through PWA support, users can add LobeChat shortcuts to their work device's desktop and open and run it just like a local application. The PWA features include the following:

  1. Offline Support: The PWA feature allows users to still access some functions when there is no network connection.
  2. Push Notifications: Users can receive real-time notifications (such as messages or task reminders) from LobeChat via PWA, improving interactivity.
  3. Quick Installation: Users can install with one click through the browser, experiencing a more convenient access method without downloading from an app store.
  4. Automatic Updates: PWA applications can automatically update to the latest version, ensuring that users always use the latest version of LobeChat.

With PWA, LobeChat can provide a consistent and convenient user experience across different devices, making it highly suitable for frequent use scenarios.

Installation via PWA

Generally, when logging into LobeChat for the first time, you will be prompted to install it, or you can install it by clicking the icon on the right side of the browser address bar, as shown in the figure below:

image.png

Once installed, it looks just like a regular application. For example, after I installed it on Mac, it displays as follows:
image.png

After that, you can directly click the icon to open LobeChat. It is actually similar to a shortcut containing a URL. When opened, it mostly calls the default browser to run, but it looks like an independent application on the interface. However, to enhance the user experience, PWAs will open in an independent window mode with ”no address bar and no tabs”, giving a feeling of being independent of the browser, looking like this:

image.png

On a technical level, it still relies on the browser engine to run, so the installed PWA shortcut will follow the updates and configurations of the default browser.

Full support for PWAs depends on the features of the default browser. If the default browser supports rich PWA features, the performance and experience of the PWA will also be better. Especially the support for ”Service Workers”, ”Web App Manifest”, and ”HTTPS”. Therefore, the support for PWAs varies when different browsers are used as the default browser:

  1. Browsers with better support: Modern browsers such as Chrome, Edge, Firefox, and Safari all support the basic functions of PWAs, such as offline access, home screen shortcuts, push notifications, etc. On these browsers, the PWA experience is close to that of native applications.
  2. Mobile: On Android devices, Chrome and Edge support PWA installation, allowing users to add them directly to the home screen from the browser. Safari on iOS also supports PWAs, but its features are slightly limited (such as not supporting push notifications and background updates).
  3. Desktop: Chrome, Edge, and Firefox support PWA installation on the desktop, allowing users to manage them just like native applications.

Therefore, to get the best PWA experience, it is recommended to use the latest version of browsers like Chrome or Edge as your default browser.

Lobechat App Settings

Introduction to App Settings

LobeChat's “Settings“ interface is the hub for comprehensively configuring application functions, including multiple tabs such as ”General Settings”, ”System Agent”, ”Language Model”, ”TTS Service”, and ”Default Agent", helping users optimize the behavior and interface effects of the AI assistant.

• General Settings: Users can configure basic settings here, such as the application theme, display language, and chat style, to customize the overall interface style and user experience.

• System Assistant: This tab is used to manage and configure system-level assistant functions. Users can set the role and specific tasks of the system assistant to ensure it operates efficiently in different application scenarios.

• Language Models: Here, users can select and configure the language models to be used, including model types, model parameters, etc., to better adapt to different conversation needs and task complexities.

• Voice Services: Provides configuration options for speech recognition and speech synthesis functions. Users can enable voice input or voice output to enhance the way they interact with the AI assistant.

• Default Assistant: Users can set the default chat assistant here, including adjusting its personality, conversation style, and parameters (such as randomness), to adapt it to the needs of daily communication or specific tasks.

“The ”Settings" interface helps users flexibly customize various functions of LobeChat to adapt to different work scenarios and usage preferences.

To enter ”Settings”, you need to log in first, and then you can click on the avatar in the red box in the upper left corner:

image.png

Select ”Settings” to enter:
image.png

Language Models

In LobeChat's settings, ”Language Model” is the most important setting item. This option allows users to select and configure specific Large Language Model API providers for chat and other AI-driven tasks. This option defines the type of model used (such as GPT-4, Claude 3.5 Sonnet, Gemini, etc.) and sets parameters such as API provider, API KEY, API proxy address, and models to customize responses based on the capabilities of the selected model:

image.png

Generally speaking, we divide it into two ways of use.

Directly Using API Provider Official Services

This method is suitable for friends who live abroad, or who live in China but know how to use VPNs/proxies to freely change their IP (and have plenty of money, as the official OpenAI Plus plan costs $20).

Directly use official OpenAI services:

image.png

Directly use official Azure OpenAI services:
image.png

Directly use official Anthropic services:
image.png

Note 1: There is not much to say about directly using official services. As long as you have a legitimate API key purchased directly from the official source, and the public IP of the device running LobeChat is not a Chinese IP, it will work.

Note 2: The reason for mentioning the IP issue is that normal foreign large language model API providers basically block direct access from domestic IPs, and Azure OpenAI, the only one that does not block them, is only available to enterprise users. Below is the email notification received on October 17:

image.png

In my previous article, I even recommended this method of directly using the official OpenAI without scientific internet access in China. I didn't expect that man proposes, God disposes (it seems it has always been only for the enterprise version, it's just that they opened it up during the application process now). Now this thought of mine is completely dead~. In the future, if you only have a domestic IP, just honestly use the products of domestic large language model manufacturers.

Note 3: The experience of the ”Use client request mode” request varies depending on the person and environment, so please try it yourself.

Using API Provider Services via Third-Party API Provider Proxies

This method is more suitable for friends who are in China and do not have scientific or magical means, or who have scientific or magical means but find using the official service directly too expensive (like me?). However, the premise of this method is that you already have a third-party API provider that suits your needs. Taking myself as an example, the third-party API provider I am currently using is OhMyGPT, which has been mentioned many times above, so it will also be used as an example below.

Note: For a detailed introduction to OhMyGPT, please refer to my other article: , so I won't repeat it here.

So, how should OhMyGPT be used in LobeChat? The following uses the OpenAI settings interface to demonstrate:

image.png

There are 3 key settings here: API KEY, API Proxy Address, and Model List.

For the API KEY in the image above, fill in the API KEY from your OhMyGPT account:

image.png

For the API Proxy Address, fill in the OhMyGPT line address that suits you:
image.png

Model List: You can directly set the required model version in the ”Model List” of the LobeChat OpenAI settings interface:
image.png


If the model version provided by LobeChat by default is not what you need, but there is a model version in the ”Settings” of your OhMyGPT account (a bit embarrassing, I searched for a long time and couldn't find one, so I made one up, let's assume it is gpt-4-32k-1230), you can directly create it in OpenAI's ”Model List”. In the image below, you can see that LobeChat does not have built-in support for this version (of course not, I made it up~), so it will provide the option to ”Create and add gpt-4-32k-1230 model”:

image.png

After that, this model version will appear in the model list:
image.png

Note: In LobeChat's language model options, although it seemingly uses the model list under the OpenAI settings, if the API proxy address already points to OhMyGPT, then all requests will be processed directly through OhMyGPT. At this point, as long as the model version selected in the model list is correct and OhMyGPT supports that model (not necessarily an OpenAI model version, such as gemini-1.5-pro-002 in the image above), it can identify which API provider the request is to be sent to (for example, here it knows that the gemini-1.5-pro-002 model version is sent to Anthropic); based on the model version, OhMyGPT can also automatically generate the API request format that the provider can understand. Therefore, even if it looks like you are selecting OpenAI on the LobeChat language model interface, as long as the API proxy address points to OhMyGPT, you can call models from other API providers in this way.


Additional Knowledge: Why Choose to Use OpenAI's Settings Interface to Call Models from Other API Providers?

Choosing the OpenAI settings interface to do this is closely related to compatibility and popularity. The specific reasons can be summarized as follows:

OpenAI's Widespread Use and Standardization:

OpenAI's API interface and models are widely used in the field of AI applications, so many developers and users are very familiar with its interface and configuration options. Using the OpenAI settings interface can maximize compatibility with existing user habits while simplifying the development and integration process.

Higher Compatibility:

OpenAI's API design structure and calling methods have become a relatively universal standard, allowing many AI proxy services (such as OhMyGPT) or intermediary platforms to easily parse and forward OpenAI-style API requests to other providers, such as Ollama, Google, and Anthropic. This structure is simple yet powerful, so when proxying or forwarding, OpenAI's interface and settings can better adapt to the needs of different AI providers.

Reduce development complexity:

Since OpenAI's API structure is widely accepted, application developers can adapt to multiple AI providers through a unified API interface design (OpenAI style), without needing to design different interfaces and UIs for each provider individually. This not only reduces development complexity but also enhances the platform's flexibility, making it easier to add more models and providers in the future.

Universality and extensibility:

OpenAI's settings interface usually has high universality, capable of converting requests into other providers' API formats through a proxy mechanism. This allows the application, even if it seemingly uses OpenAI's settings box on the surface, to actually access more different models and providers through a backend proxy, enhancing extensibility.

Therefore, choosing OpenAI's interface to call models from other API providers is not only because of its popularity, but also because of its universality and flexibility, making it easier to be compatible with multiple AI models and providers.

System Assistant

Under the System Assistant option in the Lobechat app settings, the three key items are “Topic Naming Model”, “Translation Model”, and “Assistant Metadata Generation Model”:

image.png

Topic Naming Model:

This model is used to automatically generate the topic name of the session. Especially when the conversation is long or involves multiple topics, it can intelligently name the session based on the conversation content, helping users better organize and review different topics.

Translation Model:

The translation model is used to convert conversation content between different languages. Users can choose different language models according to their needs to translate conversations in real time, making cross-language communication smoother.

Assistant Metadata Generation Model:

This model is responsible for generating metadata related to the conversation, which is typically used for conversation management or further analysis. Metadata may include conversation context, sentiment analysis, keyword extraction, etc., helping to optimize the conversation experience and data processing.

The models previously created in the language models can all be selected here as dropdown menu options:

image.png

General Settings

image.png

Under the “General Settings” option of the Lobechat app, in addition to setting the interface ”Language”, users can also adjust the overall Lobechat interface, including theme, font size, primary color, neutral color. Additionally, they can reset all settings and clear all conversation messages. This part is very simple; you can tell just by looking at the interface, so I won't say much more.

Voice Services

In the settings of the Lobechat app,Voice Servicesoptions provide voice-related function configurations, mainly including the following setting functions:

image.png

  1. Speech Recognition Service: Configure the speech recognition service used by the app to convert the user's voice input into text. The dropdown menu has two options: OpenAI and browser.
  2. Auto-stop Speech Recognition Switch: Controls whether speech recognition automatically stops when finished, making it easier to optimize the recognition process during non-continuous input.
  3. OpenAI Speech Synthesis Model: Set the OpenAI speech synthesis model to convert text into speech output.
  4. OpenAI Speech Recognition Model: Set the OpenAI speech recognition model to achieve speech-to-text conversion.

Default Assistant

The Role of the Default Assistant Option

In Lobechat's app settings, the purpose of the “Default Assistant” option is to automatically assign a preset intelligent assistant to the user's conversation. When a user starts a new conversation, the system will enable this assistant by default to provide corresponding answers and interactions.


Lobechat's default assistant is usually the “Just Chat” assistant that exists by default in the chat interface. When you start a new conversation, this assistant will automatically load, ready to conduct ordinary conversations or provide daily help. You can change the type of this default assistant in the app settings as needed to adapt to different chat needs or tasks:

image.png


The roles of the default assistant include:

  1. Personalized Interaction: Based on the set default assistant, users can get a personalized conversation experience. For example, you can choose an assistant focused on a specific field (such as programming or content creation), and the system will answer related questions based on the assistant's preset configuration.
  2. Simplify the Workflow: Eliminates the step of manually selecting an assistant every time a new conversation is started, improving the convenience of the user experience.
  3. Specific Use Cases: Suitable for users who focus on a certain task for a long time, such as using a specific assistant for translation, writing, or professional Q&A. By setting a default assistant, users can directly enter this mode.

You can specify the most commonly used or most suitable assistant for the current task through Lobechat's “Default Assistant” setting, ensuring that the intelligent experience of each conversation meets your expectations and needs.

Illustrated Guide to Default Assistant Settings

image.png

image.png

image.png


In the use of AI assistants, ”Prompt” plays a vital role, directly affecting the quality of the assistant's understanding and response: A Prompt is a piece of text or a question entered by the user to tell the AI what task to complete or what information to provide. Its role and importance are as follows:

Clarify Task Intent

The Prompt defines the user's needs, enabling the AI to understand and respond to specific requests. For example, a detailed Prompt can help the AI assistant more accurately understand the background of the question, the tone, or the expected output format, thereby generating more relevant responses. Without a clear prompt, the AI assistant may give off-topic answers.

Control Generated Content

By optimizing and designing the Prompt, users can control the content generated by the AI assistant in the conversation. A good Prompt can specify the AI's response style (such as humorous, professional), content details (such as clear points, detailed explanations), and even tone. Especially in long conversations, the Prompt helps maintain content consistency.

Improve Interaction Efficiency

The design of the Prompt directly affects the efficiency of interaction. A clear Prompt can reduce unnecessary clarifications, allowing the AI assistant to provide more accurate and comprehensive answers, thereby reducing the number of back-and-forth communications. Therefore, properly designing the Prompt can help users complete tasks efficiently.

Enhance the Applicability of AI Applications

The flexibility of the Prompt allows the AI assistant to adapt to a variety of application scenarios, such as writing assistance, code generation, data analysis, etc. Users can specify specific tasks or domains through the Prompt, leveraging the AI assistant's generation capabilities to complete different types of work.

In general, a Prompt acts as an ”instruction” in AI assistants, providing direction and details for the conversation. Excellent Prompt design not only improves the response quality of the AI assistant but also enables a more efficient and accurate interaction experience. Therefore, properly designing and using Prompts is the key to making AI assistants work efficiently.


Lobechat - “Chat” Interface

Lobechat's conversation interface is the core platform for users to interact with AI assistants (usually the main workspace), supporting instant conversation, topic management, and conversation history functions, helping users get real-time replies and maintain conversation consistency. Users can handle multiple tasks simultaneously and optimize the conversation experience through custom settings (such as randomness, nucleus sampling, etc.). It is an efficient and convenient task management tool, and the interface is as follows:

image.png

The assistant bar on the left allows you to select different assistants by clicking. Once selected, you can click the assistant's avatar on the right to enter the specific settings of that assistant:
image.png

The following options are similar to the default assistant configuration options mentioned earlier, such as assistant information:
image.png

Role settings:
image.png

Chat preferences”
image.png

Model settings:
image.png

Voice services:
image.png

Each assistant can configure these options independently, which is very flexible.

Lobechat - “Files”

Lobechat's “Files” interface is not only a tool for users to upload, store, and view files, but also supports integration with self-built knowledge bases. Users can add content to the knowledge base by uploading files, and the AI assistant can perform data analysis, document reading, and information retrieval based on the file content, improving the intelligence and efficiency of the conversation. The interface also provides categorization and search functions, making it easy for users to quickly find files or information in the knowledge base, further enhancing the experience of task processing and personalized conversations. The interface is as follows:

image.png

Note: This part of the content is only available in the server-side database version. Whether it can be used normally depends on whether the object storage parameters provided during deployment are correct. However, I haven't used this part of the features much, especially the knowledge base part. I will supplement it with actual experience after using it in the future.

Lobechat - ”Discover” Interface

“Introduction to the ”Discover" Interface

Lobechat's “Discover” interface is the center for users to explore and access more features, covering modules such as ”Assistants”, ”Plugins”, ”Models”, and ”Model Providers". Users can find and enable different assistants and plugins through this interface to expand the capabilities of the AI assistant and meet diverse application scenarios. At the same time, users can also select and switch between differentModel, and connects to multiple model service providers to optimize model performance and service experience based on needs. The interface also provides the latest feature updates and popular resource recommendations to help users continuously improve the application effectiveness of AI:

image.png

Note: The functions of ”Model” and ”Model Service Provider” overlap with what I previously explained in the ”Application Settings - Language Model - Model List” section, which is basically about how to create a new ”Model Version” and so on. I won't repeat that here, so I will only introduce ”Assistant” and ”Plugin” in this section.

Assistants

The ”Assistant” tab in LobeChat's ”Discover” interface is used to help users browse and select different AI assistants: users can view the functions and applicable scenarios of each assistant here, and add or switch them according to their needs to meet specific tasks or conversation requirements:

image.png

For example, if you want to add a ”full-stack” development assistant, you can search for ”full-stack” directly in the search box:
image.png

Then the assistant details interface will appear, where you can confirm and complete the addition of the assistant:
image.png

The added AI assistant will appear in LobeChat's ”Chat” interface:
image.png

You can add more types of assistants in the same way.

plugins

The ”Plugin” tab in LobeChat's ”Discover” interface is used to browse and manage various functional extensions: users can select and enable different plugins here to enhance the capabilities of the AI assistant, such as integrating third-party tools and processing specific tasks. Through plugins, users can expand LobeChat's capabilities as needed, improving its flexibility and practicality in adapting to different application scenarios. The interface is shown in the figure below:

image.png

Below, I will use the ”Current Time Assistant” plugin as an example to demonstrate how to add and use this plugin so that the AI assistant can obtain the current time.


By default, LobeChat's AI assistant cannot answer inquiries about the current time:

image.png

This is because many AI assistants (including certain versions of ChatGPT or other language models) do not have real-time information access. Their design and deployment rely on pre-trained models, which cannot obtain real-time information such as the current time without accessing external data sources. At the same time, these assistants do not have external connections in most application scenarios, meaning they are not connected to real-time clocks or external APIs. All answers are based on training data or a set fixed time (this is also for privacy and security, preventing access to device time or other information on the user's system without explicit permission). Therefore, they usually prompt that they cannot provide real-time data.


image.png

image.png

Then, you only need to select the newly installed ”Current Time Assistant” plugin in the functional area of the ”Chat” interface:
image.png

Then ask about the current time again, and the AI assistant will be able to answer:
image.png

Other extension plugins can be added or enabled in the same way; you can just follow this approach. However, please note that some plugins may require a VPN or proxy (scientific internet access) to function properly, such as plugins related to YouTube or Google.

Afterword

Before writing this tutorial, I didn't expect to write so much, and I discovered many setting details that I hadn't noticed before. Sure enough, ”putting pen to paper” really helps with deep learning and understanding (I feel like I've said similar things many times~).

But thinking about it, it's normal. As a currently popular Chat-type local large language model UI, LobeChat is very strong in terms of comprehensive features, flexibility, high customizability, local deployment, and user experience, making it especially suitable for individuals and small teams. However, relatively speaking, for users who are unfamiliar with large language models or lack a basic technical background, LobeChat's advanced settings (such as model parameter configuration) may be difficult to get started with, and there may be a certain learning curve for these users (I only basically figured it out after finishing this tutorial).

Therefore, in this tutorial, I have tried to write some settings and usage details as thoroughly as possible, hoping to help more friends with less technical background. However, even so, a learning curve is still unavoidable. I just hope that through this tutorial and the previous articles, everyone can avoid some of the detours I took before.

View Related Categories · 3 Matches
📌 Content Structure Prompt:
This content is part of the following knowledge map, where you can view the complete content path: AI Learning Map。
📎 Related Articles
Share this article
The blog content is original, please indicate the source when reposting! The RSS address of the blog is:https://blog.tangwudi.com/feed, welcome to subscribe; if needed, you can join theTelegram Groupto discuss questions together.
No Comments

Send Comment Edit Comment


				
|´・ω・)ノ
ヾ(≧∇≦*)ゝ
(☆ω☆)
(╯‵□′)╯︵┴─┴
 ̄﹃ ̄
(/ω\)
∠( ᐛ 」∠)_
(๑•̀ㅁ•́ฅ)
→_→
୧(๑•̀⌄•́๑)૭
٩(ˊᗜˋ*)و
(ノ°ο°)ノ
(´இ皿இ`)
⌇●﹏●⌇
(ฅ´ω`ฅ)
(╯°A°)╯︵○○○
φ( ̄∇ ̄o)
ヾ(´・ ・`。)ノ"
( ง ᵒ̌皿ᵒ̌)ง⁼³₌₃
(ó﹏ò。)
Σ(っ °Д °;)っ
( ,,´・ω・)ノ"(´っω・`。)
╮(╯▽╰)╭
o(*////▽////*)q
>﹏<
( ๑´•ω•) "(ㆆᴗ
😂
😀
😅
😊
🙂
🙃
😌
😍
😘
😜
😝
😏
😒
🙄
😳
😡
😔
😫
😱
😭
💩
👻
🙌
🖕
👍
👫
👬
👭
🌚
🌝
🙈
💊
😶
🙏
🍦
🍉
😣
Source: github.com/k4yt3x/flowerhd
Kaomoji
Emoji
Little Dinosaur
Flower!
Previous
Next
       

👋 Welcome to “Wudi's Personal Blog”

Here, long-term exploration is mainly carried out around the following directions:

🧱 Personal Digital Infrastructure and Blog System Construction
☁️ Cloudflare and Network Architecture Practice
🧠 AI and Knowledge System Exploration
🛡️ Network Security and Access Optimization
🎵 Music and Sound Cognition
👁️ Cognitive Perspectives and Worldviews