siq-proxy / README.md
AlexWortega's picture
siq-proxy: streaming OpenAI bridge to RunPod serverless SIQ-1
999c1b5 unverified
|
Raw
History Blame Contribute Delete
1.03 kB
---
title: SIQ Proxy
emoji: πŸ›°οΈ
colorFrom: indigo
colorTo: purple
sdk: docker
app_port: 7860
pinned: false
---
# siq-proxy
Streaming OpenAI-compatible proxy for the **SIQ-1-35B** RunPod serverless endpoint,
fronting the [Pi Agent](https://alexwortega.github.io/pi-agent) web app's
"SIQ-1-35B (cloud)" model. Holds the RunPod API key server-side, adds CORS, applies
SIQ-1 request shaping (thinking toggle, reasoning effort, `max_tokens` floor), and
streams the vLLM worker's SSE through to the browser.
## Endpoints
- `GET /api/health` β†’ `{ ok, siq, model }`
- `GET /api/siq/v1/models`
- `POST /api/siq/v1/chat/completions` (OpenAI, `stream: true`)
The web app points `VITE_SIQ_API` at `https://<this-space>.hf.space/api/siq`.
## Secrets (Space settings β†’ Variables and secrets)
- `RUNPOD_API_KEY` (required) β€” RunPod API key
- `SIQ_EID` (required) β€” RunPod serverless endpoint id
- `SIQ_MODEL` (default `siq`) β€” served-model-name on the worker
- `SIQ_MINTOK` (default 2048), `SIQ_LIMIT_HOUR_IP` (default 240)