mirror of
https://github.com/lobehub/lobehub.git
synced 2026-09-20 04:56:13 +08:00
YuTengjing
191f3fe776
* 📝 docs: fix outdated content across the docs site Audited docs/ against the current codebase and fixed stale content that drifted after major refactors (Clerk/NextAuth → Better Auth, src/server → apps/server, src/{config,envs,locales} → packages/*, model-bank updates). - self-hosting/auth: mark removed NextAuth/Clerk pages with deprecation warnings; fix microsoft/zitadel alias claims and the Logto callback path - environment-variables & advanced: correct wrong defaults (S3_SET_ACL, AI_IMAGE_DEFAULT_IMAGE_NUM, index/proxy URLs), drop non-existent env vars and fictional feature flags, fix OIDC config guidance - development: update refactored paths, Better Auth, .mjs configs, remove the MSW section (msw is not a dependency) - providers & model examples: replace retired model ids with in-bank ones; fix comfyui frontmatter corruption - usage: rename Moderator→Orchestrator, GTD→Task, correct shortcut keys, channel capability tables, Feishu/Lark WebSocket mode - platform/migration: fix dead links, docker service name, npx/npm → bun EN and zh-CN pairs updated together. * 📝 docs: fix Logto callback path and AUTH_SECRET deprecation guidance - Revert Logto/Sealos callback URLs to /api/auth/callback/logto to match the runtime SSO redirectURI override - Narrow legacy auth Callout: AUTH_SECRET remains required for Better Auth; mark NEXT_AUTH_SECRET as deprecated in zh-CN * 📝 docs: refresh agent skills for locales, env, auth, and agentRun paths Align OSS agent guidance with post-refactor layout: - packages/locales/src/default + bun run i18n - packages/env/src for env schemas (@/envs alias) - spa-auth shell + src/routes/auth segments - chat agentRun/transports/hetero instead of aiChat * 📝 docs: document APP_URL as required for Better Auth base URL Self-hosted auth uses appEnv.APP_URL as baseURL, not request-header auto-detection. NEXT_PUBLIC_AUTH_URL remains deprecated. * 📝 docs: note self-host search provider setup for web search Built-in lobe-web-browsing needs no client plugin, but self-hosted servers still require SEARCH_PROVIDERS / SEARXNG_URL (default SearXNG). * 📝 docs: point feature guide welcome UI at AgentHome Opening message/questions on the agent chat page live in src/features/AgentHome, not Onboarding WelcomeMessage.
63 lines
2.6 KiB
Plaintext
63 lines
2.6 KiB
Plaintext
---
|
||
title: Using DeepSeek API Key in LobeHub
|
||
description: >-
|
||
Learn how to configure and use the DeepSeek language model in LobeHub, obtain
|
||
your API key, and start chatting.
|
||
tags:
|
||
- LobeHub
|
||
- DeepSeek
|
||
- DeepSeek R1
|
||
- API Key
|
||
- Web UI
|
||
---
|
||
|
||
# Using DeepSeek in LobeHub
|
||
|
||
<Image alt={'Using DeepSeek in LobeHub'} cover src={'/blog/assets34400653/b4d12904-9d5d-46de-bd66-901eeb9c8e52.webp'} />
|
||
|
||
[DeepSeek](https://www.deepseek.com/) is a cutting-edge open-source large language model (LLM). The latest versions, DeepSeek V4 Pro and DeepSeek V4 Flash, feature significant architectural and performance improvements, particularly in reasoning capabilities. Through innovative training methods and reinforcement learning techniques, DeepSeek has achieved near state-of-the-art performance, rivaling top-tier models from OpenAI.
|
||
|
||
This guide will walk you through how to use DeepSeek in LobeHub:
|
||
|
||
<Steps>
|
||
### Step 1: Get Your DeepSeek API Key
|
||
|
||
- First, sign up and log in to the [DeepSeek Open Platform](https://platform.deepseek.com/)
|
||
|
||
<Callout type={'info'}>New users currently receive 500M tokens for free.</Callout>
|
||
|
||
- Navigate to the `API keys` section and click `Create API Key`
|
||
|
||
<Image alt={'Create DeepSeek API Key'} inStep src={'/blog/assets34400653/5707b392-1ee6-4db6-95cb-9d6c902747d2.webp'} />
|
||
|
||
- Enter a name for your API key in the pop-up dialog
|
||
|
||
<Image alt={'Enter DeepSeek API Key Name'} inStep src={'/blog/assets34400653/c1d1d816-6339-41a6-9bc9-e2c3b2762291.webp'} />
|
||
|
||
- Copy the generated API key and store it securely
|
||
|
||
<Image alt={'Save DeepSeek API Key'} inStep src={'/blog/assets34400653/198217a6-84fa-441c-bcbe-8cded1106d6c.webp'} />
|
||
|
||
<Callout type={'warning'}>
|
||
Make sure to store your key securely, as it will only be shown once. If you lose it, you’ll need to generate a new one.
|
||
</Callout>
|
||
|
||
### Step 2: Configure DeepSeek in LobeHub
|
||
|
||
- Go to the `App Settings` page in LobeHub
|
||
- Under `AI Providers`, find the `DeepSeek` configuration section
|
||
|
||
<Image alt={'Enter DeepSeek API Key in LobeHub'} inStep src={'/blog/assets93da89c4892a80e2e5a6caa49d80af5f.webp'} />
|
||
|
||
- Enable DeepSeek and paste in your API key
|
||
- Choose a DeepSeek model for your assistant to start chatting
|
||
|
||
<Image alt={'Select DeepSeek Model'} inStep src={'/blog/assetsb09a1f1dc99b86343ae196fcfdcc3fe1.webp'} />
|
||
|
||
<Callout type={'warning'}>
|
||
You may incur charges from the API provider during usage. Please refer to DeepSeek’s pricing policy for details.
|
||
</Callout>
|
||
</Steps>
|
||
|
||
And that’s it! You’re now ready to start chatting with DeepSeek-powered models in LobeHub.
|