Upload folder using huggingface_hub

Dockerfile

@@ -1,15 +1,21 @@
-# Use the official stable LiteLLM image as the base
-FROM ghcr.io/berriai/litellm:main-stable
+FROM python:3.11-slim
 
-# Set the working directory
-WORKDIR /app
+# Create a non-root user (UID 1000 is required by Hugging Face)
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+WORKDIR $HOME/app
 
-# Copy your local config into the image
-COPY litellm-config-auto.yaml /app/config.yaml
+# Install LiteLLM
+RUN pip install --no-cache-dir 'litellm[proxy]'
 
-# Expose the port (Render uses PORT env; default 4000 for local)
-EXPOSE 4000
+# Copy your config with correct ownership (source: litellm-config-auto.yaml → config.yaml)
+COPY --chown=user litellm-config-auto.yaml config.yaml
 
-# PORT from environment (Render sets it); config reads LITELLM_MASTER_KEY, OPENROUTER_API_KEY from env
+# MUST use port 7860 for Hugging Face; Render sets PORT at runtime
+EXPOSE 7860
+
+# PORT from env (Render); default 7860 for Hugging Face Spaces
 ENTRYPOINT ["/bin/sh", "-c"]
-CMD ["exec litellm --config /app/config.yaml --port ${PORT:-4000}"]
+CMD ["exec litellm --config config.yaml --port ${PORT:-7860} --host 0.0.0.0 --no-semantic-tool-filter"]

README.md

@@ -1,6 +1,16 @@
-# LiteLLM Proxy (Render)
+---
+title: LiteLLM Proxy
+emoji: 🔀
+colorFrom: indigo
+colorTo: blue
+sdk: docker
+app_port: 7860
+pinned: false
+---
 
-LiteLLM proxy for OpenRouter and other providers, deployable to Render and runnable locally with Docker.
+# LiteLLM Proxy (Render & Hugging Face Space)
+
+LiteLLM proxy for OpenRouter, Hugging Face, and other providers, deployable to Render, Hugging Face Spaces (Docker), and runnable locally with Docker.
 
 ## Fix: "Authentication Error, No api key passed in" (401)
 
@@ -21,6 +31,7 @@ The config reads **from environment variables** (`os.environ/LITELLM_MASTER_KEY`
    |-----|-------|--------|
    | `LITELLM_MASTER_KEY` | e.g. `sk-your-secret-key` | Mark as **Secret**. This is the key clients send. |
    | `OPENROUTER_API_KEY` | Your OpenRouter API key | Mark as **Secret**. |
+   | `HF_TOKEN` | Your Hugging Face token (`hf_...`) | Optional. Mark as **Secret**. Required only for Hugging Face models (`my-hf-models`). Create at [huggingface.co/settings/tokens](https://huggingface.co/settings/tokens). |
    | `PORT` | (optional) | Render sets this automatically; no need to add. |
 
 4. Save and redeploy.
@@ -60,3 +71,11 @@ Port is controlled by `PORT` in `.env` (default 4000).
 2. Render will use the **Dockerfile**; no build/start command needed.
 3. Add **Environment Variables** (see above): `LITELLM_MASTER_KEY` and `OPENROUTER_API_KEY` (mark as Secret).
 4. Deploy. Use the service URL and the same master key in `Authorization: Bearer ...` from your app or Cursor.
+
+## Deploy to Hugging Face Spaces (Docker)
+
+The README includes Spaces frontmatter (`sdk: docker`, `app_port: 7860`). To run this repo as a Space:
+
+1. Create a new Space at [huggingface.co/new-space](https://huggingface.co/new-space), choose **Docker**, and use this repo (or push this repo to the Space).
+2. In the Space **Settings** → **Variables and secrets**, add **Secrets**: `LITELLM_MASTER_KEY`, `OPENROUTER_API_KEY` (and optionally `HF_TOKEN` for Hugging Face models). Add a **Variable** `PORT` = `7860` so the proxy listens on the Space’s expected port.
+3. The Space will build from the **Dockerfile** and run the proxy. Use the Space URL (e.g. `https://your-username-litellm-proxy.hf.space`) with `Authorization: Bearer <LITELLM_MASTER_KEY>`.

docker-compose.yaml

@@ -9,5 +9,6 @@ services:
     environment:
       - OPENROUTER_API_KEY=${OPENROUTER_API_KEY}
       - LITELLM_MASTER_KEY=${LITELLM_MASTER_KEY:-sk-1234}
+      - HF_TOKEN=${HF_TOKEN}
       - PORT=${PORT:-4000}
     restart: always

litellm-config-auto.yaml

@@ -103,6 +103,15 @@ model_list:
     litellm_params:
       model: openrouter/meta-llama/llama-3-8b-instruct
       api_key: "os.environ/OPENROUTER_API_KEY"
+  # Hugging Face (set HF_TOKEN in env); format: huggingface/<provider>/<org>/<model>
+  - model_name: my-hf-models
+    litellm_params:
+      model: huggingface/meta-llama/Llama-3.3-70B-Instruct
+      api_key: "os.environ/HF_TOKEN"
+  - model_name: my-hf-models
+    litellm_params:
+      model: huggingface/together/deepseek-ai/DeepSeek-R1
+      api_key: "os.environ/HF_TOKEN"
 
 router_settings:
   routing_strategy: latency-based-routing