ondrong/coding-assistant
0
DeepSeek-V4-Pro API Server
OpenAI-compatible /v1/chat/completions endpoint for VS Code LM API integration.
Features
- ✅ Streaming SSE responses
- ✅ Tool calling support
- ✅ Persistent memory (SQLite + ChromaDB semantic search)
- ✅ Session continuity across requests
- ✅ Docker deployment on Hugging Face Spaces
VS Code Configuration (settings.json)
"lm.customProviders": [
{
"name": "DeepSeek-V4-Pro",
"vendor": "customendpoint",
"apiKey": "${input:chat.lm.secret.1c1c1b9c}",
"apiType": "chat-completions",
"models": [
{
"id": "deepseek-v4-pro",
"name": "DeepSeek-V4-Pro",
"url": "https://hf-ds.iclick.site/v1",
"toolCalling": true,
"vision": false,
"maxInputTokens": 1000000,
"maxOutputTokens": 32000
}
]
}
]Local Development
cp .env.example .env # edit with your HF_TOKEN
bash run.shDocs at http://localhost:7860/docs
