shiyue/upage-git
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add support for DouBao, Ernie, Kimi, Qwen, ZhiPu LLM providers

Browse Source 
Introduces new provider modules for DouBao, Ernie, Kimi, Qwen, and ZhiPu, and registers them in the LLM registry. Updates documentation and .env.example to include configuration instructions for these providers. Refactors OpenAI provider to support OpenAI-compatible endpoints. Adds @ai-sdk/openai-compatible and node-fetch dependencies.
This commit is contained in:
LIlGG
2025-09-29 16:28:56 +08:00
parent ed0f9a81e1
commit c31e366af9
13 changed files with 407 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
.env.example
View File

@@ -19,8 +19,9 @@ MAX_UPLOAD_SIZE_MB=5
# DEFAULT_NUM_CTX=6144 # Consumes 24GB of VRAM
DEFAULT_NUM_CTX=
# LLM Configuration Options
# Enabled model providers, currently supporting Anthropic, Cohere, DeepSeek, Google, Groq, HuggingFace, Hyperbolic, Mistral, Ollama, OpenAI, OpenRouter, Perplexity, xAI, Together, LMStudio, AmazonBedrock, Github
# Enabled model providers, currently supporting Anthropic, Cohere, Deepseek, DouBao, Ernie, Google, Groq,
# HuggingFace, Hyperbolic, Kimi, Mistral, Ollama, OpenAI, OpenRouter, OpenAILike, Perplexity, Qwen, xAI,
# ZhiPu, Together, LMStudio, AmazonBedrock, Github
LLM_PROVIDER=
# BASE URL of the current model provider, some providers require this to be set, such as OpenAI, Ollama, LMStudio