Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -1,7 +1,7 @@
-__pycache__
-*.pyc
-.env
-
-.sixth
-.pytest_cache
+__pycache__
+*.pyc
+.env
+
+.sixth
+.pytest_cache
 .coverage   

README.md

@@ -1,920 +1,920 @@
----
-title: Content Moderation OpenEnv
-emoji: 🛡️
-colorFrom: blue
-colorTo: indigo
-sdk: docker
-app_file: server/main.py
-pinned: false
----
-
-# Content Moderation OpenEnv
-
-An AI content moderation environment built to the OpenEnv specification. Agents triage real-world content — spam emails, harmful social media posts, and AI-generated deepfakes — using a standard `step()` / `reset()` / `state()` API.
-
-[![OpenEnv Spec](https://img.shields.io/badge/OpenEnv-Spec-blue)](https://github.com/openenv-core/spec)
-[![Python 3.11+](https://img.shields.io/badge/Python-3.11+-blue.svg)](https://www.python.org/downloads/)
-[![FastAPI](https://img.shields.io/badge/FastAPI-0.111.0-green.svg)](https://fastapi.tiangolo.com/)
-[![Docker](https://img.shields.io/badge/Docker-Ready-blue.svg)](https://www.docker.com/)
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
-
----
-
-## 📋 Table of Contents
-
-- [Environment Description & Motivation](#environment-description--motivation)
-- [Task Descriptions](#task-descriptions)
-- [Observation Space](#observation-space)
-- [Action Space](#action-space)
-- [Reward Functions](#reward-functions)
-- [Baseline Scores](#baseline-scores)
-- [Setup & Usage](#setup--usage)
-  - [Requirements](#requirements)
-  - [Local Installation](#local-installation)
-  - [Docker Deployment](#docker-deployment)
-  - [HuggingFace Spaces Deployment](#huggingface-spaces-deployment)
-- [Running the Inference Script](#running-the-inference-script)
-- [API Reference](#api-reference)
-- [Project Structure](#project-structure)
-- [Environment Variables](#environment-variables)
-- [Running Tests](#running-tests)
-- [Troubleshooting](#troubleshooting)
-- [Citation](#citation)
-- [Acknowledgements](#acknowledgements)
-
----
-
-## Environment Description & Motivation
-
-Content moderation is a high-stakes, high-volume real-world task. Human moderators review millions of items daily across platforms and inboxes. This environment simulates a realistic moderation pipeline across three difficulty levels, enabling AI agents to learn decision-making strategies under resource constraints.
-
-**Key Challenges:**
-- Multi-label classification with imbalanced datasets
-- Confidence calibration under uncertainty
-- Real-world content variability (spam, deepfakes, policy violations)
-- Escalation vs. immediate action tradeoffs
-
-| Task | Difficulty | Content Type | Metrics | Description |
-|---|---|---|---|---|
-| `text_spam` | Easy | Email / SMS | Binary classification + confidence | Spam vs. legitimate email filtering with sender reputation signals |
-| `content_moderation` | Medium | Social media posts | Multi-label (up to 11 labels) | Detect policy violations (hate speech, harassment, violence, etc.) |
-| `deepfake_detection` | Hard | Multimodal (image + text) | Detection accuracy + labels | Identify AI-manipulated media using vision transformer + metadata |
-
-**Models Used:**
-- **Deepfake Detection**: `dima806/deepfake_vs_real_image_detection` (ViT, ~300MB)
-- **Language Model**: `meta-llama/Llama-3.1-8B-Instruct` (8B params, via transformers or HF API)
-- **Infrastructure**: FastAPI + Uvicorn, Docker containerization
-
----
-
-## Task Descriptions
-
-### Task 1: Text Spam Classification (Easy)
-**Objective:** Binary classification of emails/SMS as spam or legitimate.
-
-**Dataset:**
-- 50 items (30 spam, 20 legitimate)
-- Features: text content, sender reputation score, link count, source
-- Ground truth: decision + labels
-
-**Example:**
-```json
-{
-  "content_id": "ts_001",
-  "content_type": "text",
-  "text": "CONGRATULATIONS! You've won $1,000,000! Click here NOW to claim your prize!!!",
-  "metadata": {"source": "email", "sender_reputation": 0.05, "link_count": 3},
-  "ground_truth": {
-    "decision": "reject",
-    "labels": ["spam", "scam"],
-    "is_harmful": true
-  }
-}
-```
-
----
-
-### Task 2: Content Moderation (Medium)
-**Objective:** Multi-label classification of social media posts for policy violations.
-
-**Dataset:**
-- 40 items across diverse platforms
-- Labels: spam, scam, phishing, hate_speech, violence, harassment, misinformation, adult_content, deepfake, political_manipulation, fraud
-- Features: post text, engagement metrics, user reputation, report count
-
-**Violation Categories:**
-| Category | Definition | Examples |
-|---|---|---|
-| Hate Speech | Dehumanizing content targeting identity | Slurs, discrimination, incitement |
-| Violence | Threats or glorification of violence | Physical harm, weapon promotion |
-| Harassment | Coordinated or severe personal attacks | Doxxing, targeted campaigns |
-| Misinformation | False claims with societal impact | Election fraud claims, health hoaxes |
-
----
-
-### Task 3: Deepfake Detection (Hard)
-**Objective:** Detect AI-manipulated media and classify content appropriately.
-
-**Dataset:**
-- 30 items (multimodal: images + descriptions)
-- Deepfake detection model outputs raw confidence scores (0-1)
-- Features: image description, detector_score, metadata
-
-**Detector Score Interpretation:**
-- `0.0-0.3`: Likely real/authentic
-- `0.3-0.7`: Uncertain, may require additional analysis
-- `0.7-1.0`: Likely deepfake/manipulated
-
-**Example:**
-```json
-{
-  "content_id": "df_001",
-  "content_type": "multimodal",
-  "image_description": "Portrait of person in business attire, lighting appears natural",
-  "detector_score": 0.82,
-  "metadata": {"platform": "social_media", "report_count": 3}
-}
-```
-
----
-
-## Observation Space
-
-Every step returns a `ContentObservation` with the following structure:
-
-```json
-{
-  "content_id": "string",
-  "content_type": "text | multimodal",
-  "text": "string (optional, for text tasks)",
-  "image_description": "string (optional, deepfake task only)",
-  "detector_score": 0.0-1.0 (optional, deepfake task only),
-  "metadata": {
-    "source": "email | social_media | platform",
-    "sender_reputation": 0.0-1.0,
-    "link_count": 0,
-    "report_count": 0,
-    "timestamp": "ISO8601"
-  },
-  "step_num": 1,
-  "total_steps": 10
-}
-```
-
-| Field | Type | Required | Task | Description |
-|---|---|---|---|---|
-| `content_id` | string | All | Unique identifier for the content item |
-| `content_type` | string | All | Type of content: `text` or `multimodal` |
-| `text` | string | text_spam, content_moderation | The actual email/post body |
-| `image_description` | string | deepfake_detection | AI-generated description of the image |
-| `detector_score` | float | deepfake_detection | Raw output from deepfake model (0-1) |
-| `metadata` | object | All | Platform-specific signals (reputation, reports, etc.) |
-| `step_num` | int | All | Current step in episode |
-| `total_steps` | int | All | Total steps in this episode |
-
----
-
-## Action Space
-
-Agents must respond with a `ModerationAction` object:
-
-```json
-{
-  "decision": "approve | reject | escalate | flag",
-  "reason": "string (max 200 chars, explanation)",
-  "confidence": 0.0-1.0,
-  "labels": ["spam", "scam", "phishing", "hate_speech", "violence",
-             "harassment", "misinformation", "adult_content",
-             "deepfake", "political_manipulation", "fraud"]
-}
-```
-
-| Field | Type | Range | Description |
-|---|---|---|---|
-| `decision` | enum | {approve, reject, escalate, flag} | **approve**: Safe content; **reject**: Clear violation, remove immediately; **flag**: Borderline, needs review; **escalate**: Uncertain, route to specialist |
-| `reason` | string | 0-200 chars | Brief explanation of the decision |
-| `confidence` | float | [0.0, 1.0] | Agent's confidence in this decision. Calibration is rewarded. |
-| `labels` | array | 0-11 labels | Detected violation categories. Must be valid from the allowed set. |
-
-**Valid Labels:**
-- `spam` — Unsolicited bulk messaging
-- `scam` — Financial or identity theft attempts
-- `phishing` — Social engineering attacks
-- `hate_speech` — Dehumanizing content targeting identity groups
-- `violence` — Threats, glorification, or instruction of violence
-- `harassment` — Personal attacks, doxxing, coordinated abuse
-- `misinformation` — False claims with societal impact
-- `adult_content` — NSFW or sexually explicit material
-- `deepfake` — AI-manipulated media
-- `political_manipulation` — Coordinated inauthentic behavior
-- `fraud` — Financial scams, false claims
-
----
-
-## Reward Functions
-
-Rewards are computed per task based on decision accuracy, label coverage (F1), and confidence calibration.
-
-### text_spam (Easy)
-
-| Component | Reward | Condition |
-|---|---|---|
-| Correct decision | **+0.65** | `decision` matches ground truth |
-| Escalate on harmful | **+0.30** | Harmful content + escalate/flag (partial credit) |
-| Label F1 contribution | **+0.20** | F1 score of predicted vs. true labels |
-| Confidence calibration | **±0.10** | Bonus if confident on correct, penalty if confident on wrong |
-| **Max per step** | **1.00** | Sum of components (capped) |
-
-### content_moderation (Medium)
-
-| Component | Reward | Condition |
-|---|---|---|
-| Correct decision | **+0.50** | `decision` matches ground truth |
-| Partial credit | **+0.25** | Harmful content + flag/escalate (conservative approach) |
-| Label F1 contribution | **+0.35** | Multi-label F1 score (up to 11 labels) |
-| Confidence calibration | **±0.10** | Brier score penalty for miscalibration |
-| **Max per step** | **1.00** | Sum of components (capped) |
-
-### deepfake_detection (Hard)
-
-| Component | Reward | Condition |
-|---|---|---|
-| Correct decision | **+0.40** | `decision` matches ground truth |
-| Deepfake detection | **+0.30** | Accuracy vs. detector_score threshold |
-| Detector alignment | **+0.10** | Bonus for leveraging model signals |
-| Label F1 contribution | **+0.20** | Multi-label F1 (fewer labels than medium task) |
-| Confidence calibration | **±0.10** | Calibration error penalty |
-| **Max per step** | **1.00** | Sum of components (capped) |
-
-**Calibration Bonus Formula:**
-```
-bonus = 0.1 × (confidence if correct else -confidence)
-```
-
----
-
-## Baseline Scores
-
-Scores reported for **Llama-3.1-8B-Instruct** with `temperature=0.2` and `top-p=0.95`:
-
-| Task | Score | Steps | Notes |
-|---|---|---|---|
-| `text_spam` | **0.72** | 5 | Strong on obvious spam; struggles with phishing disguised as legitimate |
-| `content_moderation` | **0.58** | 8 | Good binary decisions; incomplete label coverage (F1 ≈0.52) |
-| `deepfake_detection` | **0.44** | 10 | Relies on image descriptions; independent detector signals underutilized |
-
----
-
-## Setup & Usage
-
-### Requirements
-
-- **Python**: 3.11 or higher
-- **Docker** (optional, for containerized deployment)
-- **GPU** (optional, recommended for deepfake models): CUDA 12.1+
-- **Memory**: 8GB+ RAM (16GB recommended for local LLM inference)
-- **Disk**: 10GB+ (models cached in `~/.cache/huggingface/`)
-
-### Local Installation
-
-1. **Clone and navigate:**
-   ```bash
-   git clone https://github.com/Anidipta/Content-Moderation-env.git
-   cd Content-Moderation-env
-   ```
-
-2. **Create virtual environment:**
-   ```bash
-   python -m venv venv
-   source venv/bin/activate  # On Windows: venv\Scripts\activate
-   ```
-
-3. **Install dependencies:**
-   ```bash
-   pip install -r server/requirements.txt
-   ```
-
-4. **Start the server:**
-   ```bash
-   uvicorn server.main:app --host 0.0.0.0 --port 7860
-   ```
-
-   Server runs at `http://localhost:7860`
-
-5. **Access API documentation:**
-   - Swagger UI: `http://localhost:7860/docs`
-   - ReDoc: `http://localhost:7860/redoc`
-
-### Docker Deployment
-
-#### Build the Image
-
-```bash
-# Basic build
-docker build -f server/Dockerfile -t content-moderation-env .
-
-# Build with memory allocation (recommended)
-docker build --memory=4g -f server/Dockerfile -t content-moderation-env .
-
-# Build with progress output
-docker build --progress=plain -f server/Dockerfile -t content-moderation-env .
-```
-
-#### Run the Container
-
-```bash
-# Basic run
-docker run -p 7860:7860 content-moderation-env
-
-# Run with environment variables
-docker run -p 7860:7860 \
-  -e API_BASE_URL="https://router.huggingface.co/v1" \
-  -e MODEL_NAME="meta-llama/Llama-3.1-8B-Instruct" \
-  -e HF_TOKEN="hf_your_token_here" \
-  content-moderation-env
-
-# Run with GPU support
-docker run --gpus all -p 7860:7860 content-moderation-env
-
-# Run with volume mounts (cache models locally)
-docker run -p 7860:7860 \
-  -v ~/.cache/huggingface:/app/.cache/huggingface \
-  content-moderation-env
-
-# Run in background
-docker run -d -p 7860:7860 --name moderation-env content-moderation-env
-
-# Check logs
-docker logs moderation-env
-
-# Stop container
-docker stop moderation-env
-```
-
-#### Dockerfile Details
-
-The [server/Dockerfile](server/Dockerfile) uses:
-- **Base Image**: `python:3.11-slim` (~300MB) — minimal footprint with Python runtime
-- **System Dependencies**: `libgl1 libglib2.0-0 curl` — required for vision models and health checks
-- **Dependencies Installation**: Multi-stage approach with pip cache optimization
-- **Model Preloading**: Deepfake detection model downloaded during build for faster startup
-- **Environment Setup**: HuggingFace cache directories and Python settings pre-configured
-- **Entry Point**: FastAPI app via Uvicorn on port 7860
-
-```dockerfile
-# Key optimizations:
-- --no-cache-dir: Reduces image size by 50%
-- --no-build-isolation: Prevents memory spikes during pip install
-- Pre-downloaded models: Eliminates first-run delays
-- Minimal dependencies: Only libraries needed for the environment
-```
-
-#### Deployment to Production
-
-**Docker Compose:**
-```yaml
-version: '3.8'
-services:
-  moderation-api:
-    build:
-      context: .
-      dockerfile: server/Dockerfile
-    ports:
-      - "7860:7860"
-    environment:
-      - API_BASE_URL=https://router.huggingface.co/v1
-      - MODEL_NAME=meta-llama/Llama-3.1-8B-Instruct
-      - HF_TOKEN=${HF_TOKEN}
-    volumes:
-      - ~/.cache/huggingface:/app/.cache/huggingface
-    restart: unless-stopped
-    healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:7860/health"]
-      interval: 30s
-      timeout: 10s
-      retries: 3
-```
-
-Run with: `docker-compose up -d`
-
-### HuggingFace Spaces Deployment
-
-1. Create a new Space with Docker SDK
-2. Add Secrets (Settings → Repository secrets):
-   - `HF_TOKEN`: Your HuggingFace API token
-3. Add Variables (Settings → Repository variables):
-   - `API_BASE_URL`: `https://router.huggingface.co/v1`
-   - `MODEL_NAME`: `meta-llama/Llama-3.1-8B-Instruct`
-4. Push this repository to the Space
-5. Space URL becomes your `PING_URL` for validation scripts
-
----
-
-## Running the Inference Script
-
-```bash
-# API mode (HF inference endpoint)
-export API_BASE_URL="https://router.huggingface.co/v1"
-export MODEL_NAME="meta-llama/Llama-3.1-8B-Instruct"
-export HF_TOKEN="hf_your_token_here"
-export SERVER_URL="http://localhost:7860"
-export TASK_NAME="text_spam"
-
-python inference.py
-
-# Local transformers pipeline mode
-export USE_LOCAL_MODEL="true"
-python inference.py
-```
-
-### Output Format
-
-```
-[START] task=text_spam env=content_moderation_env model=meta-llama/Llama-3.1-8B-Instruct
-[STEP] step=1 action={"decision":"reject","confidence":0.9,"labels":["spam"]} reward=0.85 done=false error=null
-[STEP] step=2 action={"decision":"approve","confidence":0.8,"labels":[]} reward=0.75 done=false error=null
-[STEP] step=3 action={"decision":"escalate","confidence":0.5,"labels":["scam"]} reward=0.30 done=false error=null
-[STEP] step=4 action={"decision":"reject","confidence":0.85,"labels":["phishing"]} reward=0.70 done=false error=null
-[STEP] step=5 action={"decision":"approve","confidence":0.88,"labels":[]} reward=0.75 done=true error=null
-[END] success=true steps=5 score=0.720 rewards=0.85,0.75,0.30,0.70,0.75
-```
-
-| Field | Type | Description |
-|---|---|---|
-| `task` | string | The task being evaluated |
-| `step` | int | Current step number in episode |
-| `decision` | string | Agent's moderation decision |
-| `confidence` | float | Agent's confidence (0-1) |
-| `labels` | array | Detected violation labels |
-| `reward` | float | Reward received for this step |
-| `done` | boolean | Episode completion flag |
-| `error` | string/null | Error message if applicable |
-| `score` | float | Final episode score |
-
----
-
-## API Reference
-
-### Server Endpoints
-
-All endpoints are JSON-based with FastAPI's automatic validation.
-
-#### 1. Reset Episode
-**POST** `/reset`
-
-Start a new moderation episode.
-
-**Request Body:**
-```json
-{
-  "task": "text_spam"
-}
-```
-
-**Response (200 OK):**
-```json
-{
-  "observation": {
-    "content_id": "ts_001",
-    "content_type": "text",
-    "text": "CONGRATULATIONS! You've won $1,000,000!...",
-    "metadata": {"source": "email", "sender_reputation": 0.05, "link_count": 3},
-    "step_num": 1,
-    "total_steps": 10
-  },
-  "info": {}
-}
-```
-
-**Error (400):**
-```json
-{
-  "detail": "Unknown task 'invalid_task'. Valid: ['text_spam', 'content_moderation', 'deepfake_detection']"
-}
-```
-
----
-
-#### 2. Submit Action
-**POST** `/step`
-
-Submit a moderation action for the current content.
-
-**Request Body:**
-```json
-{
-  "decision": "reject",
-  "reason": "Email contains typical spam patterns and suspicious links",
-  "confidence": 0.92,
-  "labels": ["spam", "scam"]
-}
-```
-
-**Response (200 OK):**
-```json
-{
-  "observation": {
-    "content_id": "ts_002",
-    "content_type": "text",
-    "text": "Hi Sarah, confirming our meeting tomorrow...",
-    "metadata": {"source": "email", "sender_reputation": 0.92, "link_count": 0},
-    "step_num": 2,
-    "total_steps": 10
-  },
-  "reward": 0.85,
-  "done": false,
-  "info": {}
-}
-```
-
----
-
-#### 3. Get Current State
-**GET** `/state`
-
-Retrieve the current episode state without taking an action.
-
-**Response (200 OK):**
-```json
-{
-  "observation": {...},
-  "reward": 0.85,
-  "done": false,
-  "info": {
-    "task": "text_spam",
-    "items_completed": 2,
-    "total_items": 10,
-    "cumulative_reward": 1.60
-  }
-}
-```
-
----
-
-#### 4. Close Episode
-**POST** `/close`
-
-Explicitly close the episode and clean up resources.
-
-**Response (200 OK):**
-```json
-{
-  "status": "closed",
-  "final_reward": 7.20,
-  "steps_completed": 10
-}
-```
-
----
-
-#### 5. List Available Tasks
-**GET** `/tasks`
-
-Get metadata about all available tasks.
-
-**Response (200 OK):**
-```json
-{
-  "text_spam": {
-    "description": "Classify email/message content as spam or legitimate",
-    "difficulty": "easy",
-    "num_items": 50,
-    "content_type": "text"
-  },
-  "content_moderation": {
-    "description": "Detect policy violations in social media posts",
-    "difficulty": "medium",
-    "num_items": 40,
-    "content_type": "text"
-  },
-  "deepfake_detection": {
-    "description": "Identify AI-manipulated media",
-    "difficulty": "hard",
-    "num_items": 30,
-    "content_type": "multimodal"
-  }
-}
-```
-
----
-
-#### 6. Health Check
-**GET** `/health`
-
-Check server health and status.
-
-**Response (200 OK):**
-```json
-{
-  "status": "ok"
-}
-```
-
----
-
-#### 7. Root Endpoint
-**GET** `/`
-
-Redirects to interactive Swagger UI documentation.
-
----
-
-## Project Structure
-
-```
-content-moderation-env/
-│
-├── README.md                          # This file
-├── uv.lock                            # Dependency lock file (UV package manager)
-├── inference.py                       # Baseline agent script (235 lines)
-│                                      # Demonstrates LLM agent interaction
-│                                      # Supports HF API and local inference modes
-│
-├── server/                            # FastAPI application (core)
-│   ├── __init__.py                    # Package marker (empty)
-│   │
-│   ├── main.py                        # FastAPI app & HTTP endpoints (57 lines)
-│   │                                  # Defines: /reset, /step, /state, /close
-│   │                                  # /tasks, /health, / endpoints
-│   │
-│   ├── env.py                         # OpenEnv environment implementation (122 lines)
-│   │                                  # Core logic: reset(), step(), state(), close()
-│   │                                  # Thread-safe with locks for concurrency
-│   │
-│   ├── models.py                      # Pydantic data models
-│   │                                  # Defines: ContentObservation, ModerationAction
-│   │                                  # StepResult, ResetResult, EnvState
-│   │
-│   ├── tasks.py                       # Task datasets & ground truth (193 lines)
-│   │                                  # Contains: text_spam, content_moderation,
-│   │                                  # deepfake_detection task definitions & items
-│   │
-│   ├── graders.py                     # Reward functions per task (95 lines)
-│   │                                  # Implements: label F1, calibration bonus,
-│   │                                  # decision accuracy scoring logic
-│   │
-│   ├── deepfake_model.py              # HF deepfake detection pipeline (90 lines)
-│   │                                  # Lazy-loads: dima806/deepfake_vs_real...
-│   │                                  # Caches model in HF_HOME for reuse
-│   │
-│   ├── openenv.yaml                   # OpenEnv specification metadata
-│   │                                  # Declares task specs, observation/action space
-│   │
-│   ├── Dockerfile                     # Docker container definition
-│   │                                  # Base: python:3.11-slim (~300MB)
-│   │                                  # Installs system deps, pip packages,
-│   │                                  # pre-downloads deepfake model
-│   │
-│   └── requirements.txt                # Python dependencies (12 packages)
-│                                      # Key: fastapi, uvicorn, transformers,
-│                                      # torch, openai, python-dotenv
-│
-├── test/                              # Test suite
-│   └── test.py                        # pytest tests (20+ test cases)
-│                                      # Coverage: tasks, endpoints, rewards
-│
-└── .env                               # Environment variables (git-ignored)
-                                       # Stores: HF_TOKEN, API_BASE_URL, etc.
-```
-
----
-
-## Environment Variables
-
-Configuration is controlled via environment variables. Create a `.env` file in the project root:
-
-```env
-# ============ API Configuration ============
-API_BASE_URL=https://router.huggingface.co/v1
-# URL of the LLM inference endpoint
-# Default: HuggingFace router (requires HF_TOKEN)
-
-MODEL_NAME=meta-llama/Llama-3.1-8B-Instruct
-# Which LLM to use for agent inference
-# Other options: gpt-3.5-turbo, claude-3-opus, mistral-large, etc.
-
-HF_TOKEN=hf_your_token_here
-# HuggingFace API token for authenticated requests
-# Get from: https://huggingface.co/settings/tokens
-
-# ============ Server Configuration ============
-SERVER_URL=http://localhost:7860
-# Where the OpenEnv API server runs
-# Used by inference.py to connect to environment
-
-# ============ Task & Inference Configuration ============
-TASK_NAME=text_spam
-# Which task to run: text_spam, content_moderation, deepfake_detection
-
-USE_LOCAL_MODEL=false
-# If true: Load Llama-3.1-8B locally via transformers
-# If false: Use remote API (requires HF_TOKEN)
-# Local mode requires 16GB+ RAM
-
-# ============ HuggingFace Model Caching ============
-HF_HOME=/app/.cache/huggingface
-# Directory for cached HF models and datasets
-# Mounted as volume in Docker for persistence
-
-TRANSFORMERS_CACHE=/app/.cache/huggingface
-# Alternative env var for transformers library caching
-
-# ============ Python Configuration ============
-PYTHONDONTWRITEBYTECODE=1
-# Don't create __pycache__ directories
-
-PYTHONUNBUFFERED=1
-# Stream logs immediately (useful in Docker)
-
-# ============ Logging ============
-LOG_LEVEL=INFO
-# Log level: DEBUG, INFO, WARNING, ERROR, CRITICAL
-```
-
-### Variable Precedence
-
-1. Environment variables (highest priority)
-2. `.env` file
-3. Hardcoded defaults in code (lowest priority)
-
-Example override:
-```bash
-export HF_TOKEN="hf_custom_token" && python inference.py
-# Uses custom token instead of .env value
-```
-
----
-
-## Running Tests
-
-The project includes a comprehensive test suite using pytest.
-
-### Setup
-
-```bash
-pip install pytest pytest-cov
-```
-
-### Run All Tests
-
-```bash
-pytest test/test.py -v
-```
-
-### Run Specific Test Class
-
-```bash
-pytest test/test.py::TestTasks -v
-```
-
-### Run with Coverage Report
-
-```bash
-pytest test/test.py --cov=server --cov-report=html
-# Opens htmlcov/index.html in browser for coverage visualization
-```
-
-### Test Categories
-
-| Test | Coverage | Status |
-|---|---|---|
-| Task loading | All 3 tasks initialize correctly | ✓ |
-| API endpoints | /reset, /step, /state, /close, /tasks, /health | ✓ |
-| Reward grading | text_spam, content_moderation, deepfake_detection | ✓ |
-| Input validation | Action schema validation, label validation | ✓ |
-| Edge cases | Empty labels, out-of-range confidence, etc. | ✓ |
-
----
-
-## Troubleshooting
-
-### Installation Issues
-
-**Problem:** `ImportError: No module named 'openai'`
-```bash
-Solution: pip install "openai>=1.40.0"
-```
-
-**Problem:** `ImportError: No module named 'torch'`
-```bash
-Solution: pip install torch torchvision
-# For GPU: pip install torch torchvision -f https://download.pytorch.org/whl/cu121/torch_stable.html
-```
-
-**Problem:** `FileNotFoundError: requirements.txt`
-```bash
-Solution: Ensure you're in the project root: cd content-moderation-env/
-# Then: pip install -r server/requirements.txt
-```
-
-### Docker Issues
-
-**Problem:** `Segmentation fault (core dumped)` during build
-```
-Solution: Allocate more memory to Docker build:
-docker build --memory=8g -f server/Dockerfile -t content-moderation-env .
-```
-
-**Problem:** `failed to solve: failed to compute cache key`
-```
-Solution: Ensure requirements.txt is in server/ directory:
-# Current: server/requirements.txt (correct)
-# Wrong: ./requirements.txt
-```
-
-**Problem:** Port 7860 already in use
-```bash
-Solution: Use different port:
-docker run -p 8000:7860 content-moderation-env
-# Now access at http://localhost:8000
-```
-
-### Runtime Issues
-
-**Problem:** `Connection refused: localhost:7860`
-```bash
-Solution: Ensure server is running:
-uvicorn server.main:app --host 0.0.0.0 --port 7860
-
-In Docker, use: docker logs <container_id>
-```
-
-**Problem:** `Client.__init__() got an unexpected keyword argument 'proxies'`
-```bash
-Solution: Update OpenAI client:
-pip install --upgrade openai
-```
-
-**Problem:** HuggingFace models downloading very slowly
-```bash
-Solution: Check internet connection and verify HF_TOKEN:
-export HF_TOKEN="hf_your_token_here"
-# Or download models ahead of time
-python -c "from transformers import pipeline; pipeline('image-classification', model='dima806/deepfake_vs_real_image_detection')"
-```
-
-### API Issues
-
-**Problem:** Invalid request to `/step` without `/reset`
-```json
-Error: "Environment not initialized. Call /reset first."
-Solution: Always call POST /reset before any /step requests
-```
-
-**Problem:** Invalid label in action
-```json
-Error: {"detail": "Invalid label: 'unknown_label'"}
-Solution: Use only valid labels from the specification
-```
-
-**Problem:** Confidence out of range
-```
-Solution: Ensure confidence is between 0.0 and 1.0
-```
-
----
-
-## Citation
-
-If you use this environment in your research, please cite:
-
-```bibtex
-@software{content_moderation_openenv_2025,
-  title={Content Moderation OpenEnv: A Real-World AI Triage Environment},
-  author={Anidipta},
-  year={2025},
-  url={https://github.com/Anidipta/Content-Moderation-env},
-  note={OpenEnv Specification Compliant}
-}
-```
-
----
-
-## Acknowledgements
-
-🙏 Built for the **OpenEnv Hackathon 2025**.
-
-**Special Thanks To:**
-- OpenEnv community for the specification and framework
-- HuggingFace for model hosting and inference APIs
-- Meta for the Llama-3.1-8B-Instruct model
-- Contributors and testers who improved the environment
-
-**Dataset & Content Note:**
-The email and content corpus is entirely **synthetic** and does not represent any real individuals, companies, organizations, or actual events. All examples are generated for demonstration and testing purposes only.
-
-**License:** MIT License — See [LICENSE](LICENSE) file for details
-
-**Questions?** Open an issue on GitHub or contact the maintainers.
-
----
-
-**Last Updated:** April 8, 2026 | **OpenEnv Spec Version:** 1.0
-colorTo: green
-sdk: docker
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
->>>>>>> f6dee02010a32ba1936311cbb3790fa087282e74
+---
+title: Content Moderation OpenEnv
+emoji: 🛡️
+colorFrom: blue
+colorTo: indigo
+sdk: docker
+app_file: server/main.py
+pinned: false
+---
+
+# Content Moderation OpenEnv
+
+An AI content moderation environment built to the OpenEnv specification. Agents triage real-world content — spam emails, harmful social media posts, and AI-generated deepfakes — using a standard `step()` / `reset()` / `state()` API.
+
+[![OpenEnv Spec](https://img.shields.io/badge/OpenEnv-Spec-blue)](https://github.com/openenv-core/spec)
+[![Python 3.11+](https://img.shields.io/badge/Python-3.11+-blue.svg)](https://www.python.org/downloads/)
+[![FastAPI](https://img.shields.io/badge/FastAPI-0.111.0-green.svg)](https://fastapi.tiangolo.com/)
+[![Docker](https://img.shields.io/badge/Docker-Ready-blue.svg)](https://www.docker.com/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
+
+---
+
+## 📋 Table of Contents
+
+- [Environment Description & Motivation](#environment-description--motivation)
+- [Task Descriptions](#task-descriptions)
+- [Observation Space](#observation-space)
+- [Action Space](#action-space)
+- [Reward Functions](#reward-functions)
+- [Baseline Scores](#baseline-scores)
+- [Setup & Usage](#setup--usage)
+  - [Requirements](#requirements)
+  - [Local Installation](#local-installation)
+  - [Docker Deployment](#docker-deployment)
+  - [HuggingFace Spaces Deployment](#huggingface-spaces-deployment)
+- [Running the Inference Script](#running-the-inference-script)
+- [API Reference](#api-reference)
+- [Project Structure](#project-structure)
+- [Environment Variables](#environment-variables)
+- [Running Tests](#running-tests)
+- [Troubleshooting](#troubleshooting)
+- [Citation](#citation)
+- [Acknowledgements](#acknowledgements)
+
+---
+
+## Environment Description & Motivation
+
+Content moderation is a high-stakes, high-volume real-world task. Human moderators review millions of items daily across platforms and inboxes. This environment simulates a realistic moderation pipeline across three difficulty levels, enabling AI agents to learn decision-making strategies under resource constraints.
+
+**Key Challenges:**
+- Multi-label classification with imbalanced datasets
+- Confidence calibration under uncertainty
+- Real-world content variability (spam, deepfakes, policy violations)
+- Escalation vs. immediate action tradeoffs
+
+| Task | Difficulty | Content Type | Metrics | Description |
+|---|---|---|---|---|
+| `text_spam` | Easy | Email / SMS | Binary classification + confidence | Spam vs. legitimate email filtering with sender reputation signals |
+| `content_moderation` | Medium | Social media posts | Multi-label (up to 11 labels) | Detect policy violations (hate speech, harassment, violence, etc.) |
+| `deepfake_detection` | Hard | Multimodal (image + text) | Detection accuracy + labels | Identify AI-manipulated media using vision transformer + metadata |
+
+**Models Used:**
+- **Deepfake Detection**: `dima806/deepfake_vs_real_image_detection` (ViT, ~300MB)
+- **Language Model**: `meta-llama/Llama-3.1-8B-Instruct` (8B params, via transformers or HF API)
+- **Infrastructure**: FastAPI + Uvicorn, Docker containerization
+
+---
+
+## Task Descriptions
+
+### Task 1: Text Spam Classification (Easy)
+**Objective:** Binary classification of emails/SMS as spam or legitimate.
+
+**Dataset:**
+- 50 items (30 spam, 20 legitimate)
+- Features: text content, sender reputation score, link count, source
+- Ground truth: decision + labels
+
+**Example:**
+```json
+{
+  "content_id": "ts_001",
+  "content_type": "text",
+  "text": "CONGRATULATIONS! You've won $1,000,000! Click here NOW to claim your prize!!!",
+  "metadata": {"source": "email", "sender_reputation": 0.05, "link_count": 3},
+  "ground_truth": {
+    "decision": "reject",
+    "labels": ["spam", "scam"],
+    "is_harmful": true
+  }
+}
+```
+
+---
+
+### Task 2: Content Moderation (Medium)
+**Objective:** Multi-label classification of social media posts for policy violations.
+
+**Dataset:**
+- 40 items across diverse platforms
+- Labels: spam, scam, phishing, hate_speech, violence, harassment, misinformation, adult_content, deepfake, political_manipulation, fraud
+- Features: post text, engagement metrics, user reputation, report count
+
+**Violation Categories:**
+| Category | Definition | Examples |
+|---|---|---|
+| Hate Speech | Dehumanizing content targeting identity | Slurs, discrimination, incitement |
+| Violence | Threats or glorification of violence | Physical harm, weapon promotion |
+| Harassment | Coordinated or severe personal attacks | Doxxing, targeted campaigns |
+| Misinformation | False claims with societal impact | Election fraud claims, health hoaxes |
+
+---
+
+### Task 3: Deepfake Detection (Hard)
+**Objective:** Detect AI-manipulated media and classify content appropriately.
+
+**Dataset:**
+- 30 items (multimodal: images + descriptions)
+- Deepfake detection model outputs raw confidence scores (0-1)
+- Features: image description, detector_score, metadata
+
+**Detector Score Interpretation:**
+- `0.0-0.3`: Likely real/authentic
+- `0.3-0.7`: Uncertain, may require additional analysis
+- `0.7-1.0`: Likely deepfake/manipulated
+
+**Example:**
+```json
+{
+  "content_id": "df_001",
+  "content_type": "multimodal",
+  "image_description": "Portrait of person in business attire, lighting appears natural",
+  "detector_score": 0.82,
+  "metadata": {"platform": "social_media", "report_count": 3}
+}
+```
+
+---
+
+## Observation Space
+
+Every step returns a `ContentObservation` with the following structure:
+
+```json
+{
+  "content_id": "string",
+  "content_type": "text | multimodal",
+  "text": "string (optional, for text tasks)",
+  "image_description": "string (optional, deepfake task only)",
+  "detector_score": 0.0-1.0 (optional, deepfake task only),
+  "metadata": {
+    "source": "email | social_media | platform",
+    "sender_reputation": 0.0-1.0,
+    "link_count": 0,
+    "report_count": 0,
+    "timestamp": "ISO8601"
+  },
+  "step_num": 1,
+  "total_steps": 10
+}
+```
+
+| Field | Type | Required | Task | Description |
+|---|---|---|---|---|
+| `content_id` | string | All | Unique identifier for the content item |
+| `content_type` | string | All | Type of content: `text` or `multimodal` |
+| `text` | string | text_spam, content_moderation | The actual email/post body |
+| `image_description` | string | deepfake_detection | AI-generated description of the image |
+| `detector_score` | float | deepfake_detection | Raw output from deepfake model (0-1) |
+| `metadata` | object | All | Platform-specific signals (reputation, reports, etc.) |
+| `step_num` | int | All | Current step in episode |
+| `total_steps` | int | All | Total steps in this episode |
+
+---
+
+## Action Space
+
+Agents must respond with a `ModerationAction` object:
+
+```json
+{
+  "decision": "approve | reject | escalate | flag",
+  "reason": "string (max 200 chars, explanation)",
+  "confidence": 0.0-1.0,
+  "labels": ["spam", "scam", "phishing", "hate_speech", "violence",
+             "harassment", "misinformation", "adult_content",
+             "deepfake", "political_manipulation", "fraud"]
+}
+```
+
+| Field | Type | Range | Description |
+|---|---|---|---|
+| `decision` | enum | {approve, reject, escalate, flag} | **approve**: Safe content; **reject**: Clear violation, remove immediately; **flag**: Borderline, needs review; **escalate**: Uncertain, route to specialist |
+| `reason` | string | 0-200 chars | Brief explanation of the decision |
+| `confidence` | float | [0.0, 1.0] | Agent's confidence in this decision. Calibration is rewarded. |
+| `labels` | array | 0-11 labels | Detected violation categories. Must be valid from the allowed set. |
+
+**Valid Labels:**
+- `spam` — Unsolicited bulk messaging
+- `scam` — Financial or identity theft attempts
+- `phishing` — Social engineering attacks
+- `hate_speech` — Dehumanizing content targeting identity groups
+- `violence` — Threats, glorification, or instruction of violence
+- `harassment` — Personal attacks, doxxing, coordinated abuse
+- `misinformation` — False claims with societal impact
+- `adult_content` — NSFW or sexually explicit material
+- `deepfake` — AI-manipulated media
+- `political_manipulation` — Coordinated inauthentic behavior
+- `fraud` — Financial scams, false claims
+
+---
+
+## Reward Functions
+
+Rewards are computed per task based on decision accuracy, label coverage (F1), and confidence calibration.
+
+### text_spam (Easy)
+
+| Component | Reward | Condition |
+|---|---|---|
+| Correct decision | **+0.65** | `decision` matches ground truth |
+| Escalate on harmful | **+0.30** | Harmful content + escalate/flag (partial credit) |
+| Label F1 contribution | **+0.20** | F1 score of predicted vs. true labels |
+| Confidence calibration | **±0.10** | Bonus if confident on correct, penalty if confident on wrong |
+| **Max per step** | **1.00** | Sum of components (capped) |
+
+### content_moderation (Medium)
+
+| Component | Reward | Condition |
+|---|---|---|
+| Correct decision | **+0.50** | `decision` matches ground truth |
+| Partial credit | **+0.25** | Harmful content + flag/escalate (conservative approach) |
+| Label F1 contribution | **+0.35** | Multi-label F1 score (up to 11 labels) |
+| Confidence calibration | **±0.10** | Brier score penalty for miscalibration |
+| **Max per step** | **1.00** | Sum of components (capped) |
+
+### deepfake_detection (Hard)
+
+| Component | Reward | Condition |
+|---|---|---|
+| Correct decision | **+0.40** | `decision` matches ground truth |
+| Deepfake detection | **+0.30** | Accuracy vs. detector_score threshold |
+| Detector alignment | **+0.10** | Bonus for leveraging model signals |
+| Label F1 contribution | **+0.20** | Multi-label F1 (fewer labels than medium task) |
+| Confidence calibration | **±0.10** | Calibration error penalty |
+| **Max per step** | **1.00** | Sum of components (capped) |
+
+**Calibration Bonus Formula:**
+```
+bonus = 0.1 × (confidence if correct else -confidence)
+```
+
+---
+
+## Baseline Scores
+
+Scores reported for **Llama-3.1-8B-Instruct** with `temperature=0.2` and `top-p=0.95`:
+
+| Task | Score | Steps | Notes |
+|---|---|---|---|
+| `text_spam` | **0.72** | 5 | Strong on obvious spam; struggles with phishing disguised as legitimate |
+| `content_moderation` | **0.58** | 8 | Good binary decisions; incomplete label coverage (F1 ≈0.52) |
+| `deepfake_detection` | **0.44** | 10 | Relies on image descriptions; independent detector signals underutilized |
+
+---
+
+## Setup & Usage
+
+### Requirements
+
+- **Python**: 3.11 or higher
+- **Docker** (optional, for containerized deployment)
+- **GPU** (optional, recommended for deepfake models): CUDA 12.1+
+- **Memory**: 8GB+ RAM (16GB recommended for local LLM inference)
+- **Disk**: 10GB+ (models cached in `~/.cache/huggingface/`)
+
+### Local Installation
+
+1. **Clone and navigate:**
+   ```bash
+   git clone https://github.com/Anidipta/Content-Moderation-env.git
+   cd Content-Moderation-env
+   ```
+
+2. **Create virtual environment:**
+   ```bash
+   python -m venv venv
+   source venv/bin/activate  # On Windows: venv\Scripts\activate
+   ```
+
+3. **Install dependencies:**
+   ```bash
+   pip install -r server/requirements.txt
+   ```
+
+4. **Start the server:**
+   ```bash
+   uvicorn server.main:app --host 0.0.0.0 --port 7860
+   ```
+
+   Server runs at `http://localhost:7860`
+
+5. **Access API documentation:**
+   - Swagger UI: `http://localhost:7860/docs`
+   - ReDoc: `http://localhost:7860/redoc`
+
+### Docker Deployment
+
+#### Build the Image
+
+```bash
+# Basic build
+docker build -f server/Dockerfile -t content-moderation-env .
+
+# Build with memory allocation (recommended)
+docker build --memory=4g -f server/Dockerfile -t content-moderation-env .
+
+# Build with progress output
+docker build --progress=plain -f server/Dockerfile -t content-moderation-env .
+```
+
+#### Run the Container
+
+```bash
+# Basic run
+docker run -p 7860:7860 content-moderation-env
+
+# Run with environment variables
+docker run -p 7860:7860 \
+  -e API_BASE_URL="https://router.huggingface.co/v1" \
+  -e MODEL_NAME="meta-llama/Llama-3.1-8B-Instruct" \
+  -e HF_TOKEN="hf_your_token_here" \
+  content-moderation-env
+
+# Run with GPU support
+docker run --gpus all -p 7860:7860 content-moderation-env
+
+# Run with volume mounts (cache models locally)
+docker run -p 7860:7860 \
+  -v ~/.cache/huggingface:/app/.cache/huggingface \
+  content-moderation-env
+
+# Run in background
+docker run -d -p 7860:7860 --name moderation-env content-moderation-env
+
+# Check logs
+docker logs moderation-env
+
+# Stop container
+docker stop moderation-env
+```
+
+#### Dockerfile Details
+
+The [server/Dockerfile](server/Dockerfile) uses:
+- **Base Image**: `python:3.11-slim` (~300MB) — minimal footprint with Python runtime
+- **System Dependencies**: `libgl1 libglib2.0-0 curl` — required for vision models and health checks
+- **Dependencies Installation**: Multi-stage approach with pip cache optimization
+- **Model Preloading**: Deepfake detection model downloaded during build for faster startup
+- **Environment Setup**: HuggingFace cache directories and Python settings pre-configured
+- **Entry Point**: FastAPI app via Uvicorn on port 7860
+
+```dockerfile
+# Key optimizations:
+- --no-cache-dir: Reduces image size by 50%
+- --no-build-isolation: Prevents memory spikes during pip install
+- Pre-downloaded models: Eliminates first-run delays
+- Minimal dependencies: Only libraries needed for the environment
+```
+
+#### Deployment to Production
+
+**Docker Compose:**
+```yaml
+version: '3.8'
+services:
+  moderation-api:
+    build:
+      context: .
+      dockerfile: server/Dockerfile
+    ports:
+      - "7860:7860"
+    environment:
+      - API_BASE_URL=https://router.huggingface.co/v1
+      - MODEL_NAME=meta-llama/Llama-3.1-8B-Instruct
+      - HF_TOKEN=${HF_TOKEN}
+    volumes:
+      - ~/.cache/huggingface:/app/.cache/huggingface
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:7860/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+```
+
+Run with: `docker-compose up -d`
+
+### HuggingFace Spaces Deployment
+
+1. Create a new Space with Docker SDK
+2. Add Secrets (Settings → Repository secrets):
+   - `HF_TOKEN`: Your HuggingFace API token
+3. Add Variables (Settings → Repository variables):
+   - `API_BASE_URL`: `https://router.huggingface.co/v1`
+   - `MODEL_NAME`: `meta-llama/Llama-3.1-8B-Instruct`
+4. Push this repository to the Space
+5. Space URL becomes your `PING_URL` for validation scripts
+
+---
+
+## Running the Inference Script
+
+```bash
+# API mode (HF inference endpoint)
+export API_BASE_URL="https://router.huggingface.co/v1"
+export MODEL_NAME="meta-llama/Llama-3.1-8B-Instruct"
+export HF_TOKEN="hf_your_token_here"
+export SERVER_URL="http://localhost:7860"
+export TASK_NAME="text_spam"
+
+python inference.py
+
+# Local transformers pipeline mode
+export USE_LOCAL_MODEL="true"
+python inference.py
+```
+
+### Output Format
+
+```
+[START] task=text_spam env=content_moderation_env model=meta-llama/Llama-3.1-8B-Instruct
+[STEP] step=1 action={"decision":"reject","confidence":0.9,"labels":["spam"]} reward=0.85 done=false error=null
+[STEP] step=2 action={"decision":"approve","confidence":0.8,"labels":[]} reward=0.75 done=false error=null
+[STEP] step=3 action={"decision":"escalate","confidence":0.5,"labels":["scam"]} reward=0.30 done=false error=null
+[STEP] step=4 action={"decision":"reject","confidence":0.85,"labels":["phishing"]} reward=0.70 done=false error=null
+[STEP] step=5 action={"decision":"approve","confidence":0.88,"labels":[]} reward=0.75 done=true error=null
+[END] success=true steps=5 score=0.720 rewards=0.85,0.75,0.30,0.70,0.75
+```
+
+| Field | Type | Description |
+|---|---|---|
+| `task` | string | The task being evaluated |
+| `step` | int | Current step number in episode |
+| `decision` | string | Agent's moderation decision |
+| `confidence` | float | Agent's confidence (0-1) |
+| `labels` | array | Detected violation labels |
+| `reward` | float | Reward received for this step |
+| `done` | boolean | Episode completion flag |
+| `error` | string/null | Error message if applicable |
+| `score` | float | Final episode score |
+
+---
+
+## API Reference
+
+### Server Endpoints
+
+All endpoints are JSON-based with FastAPI's automatic validation.
+
+#### 1. Reset Episode
+**POST** `/reset`
+
+Start a new moderation episode.
+
+**Request Body:**
+```json
+{
+  "task": "text_spam"
+}
+```
+
+**Response (200 OK):**
+```json
+{
+  "observation": {
+    "content_id": "ts_001",
+    "content_type": "text",
+    "text": "CONGRATULATIONS! You've won $1,000,000!...",
+    "metadata": {"source": "email", "sender_reputation": 0.05, "link_count": 3},
+    "step_num": 1,
+    "total_steps": 10
+  },
+  "info": {}
+}
+```
+
+**Error (400):**
+```json
+{
+  "detail": "Unknown task 'invalid_task'. Valid: ['text_spam', 'content_moderation', 'deepfake_detection']"
+}
+```
+
+---
+
+#### 2. Submit Action
+**POST** `/step`
+
+Submit a moderation action for the current content.
+
+**Request Body:**
+```json
+{
+  "decision": "reject",
+  "reason": "Email contains typical spam patterns and suspicious links",
+  "confidence": 0.92,
+  "labels": ["spam", "scam"]
+}
+```
+
+**Response (200 OK):**
+```json
+{
+  "observation": {
+    "content_id": "ts_002",
+    "content_type": "text",
+    "text": "Hi Sarah, confirming our meeting tomorrow...",
+    "metadata": {"source": "email", "sender_reputation": 0.92, "link_count": 0},
+    "step_num": 2,
+    "total_steps": 10
+  },
+  "reward": 0.85,
+  "done": false,
+  "info": {}
+}
+```
+
+---
+
+#### 3. Get Current State
+**GET** `/state`
+
+Retrieve the current episode state without taking an action.
+
+**Response (200 OK):**
+```json
+{
+  "observation": {...},
+  "reward": 0.85,
+  "done": false,
+  "info": {
+    "task": "text_spam",
+    "items_completed": 2,
+    "total_items": 10,
+    "cumulative_reward": 1.60
+  }
+}
+```
+
+---
+
+#### 4. Close Episode
+**POST** `/close`
+
+Explicitly close the episode and clean up resources.
+
+**Response (200 OK):**
+```json
+{
+  "status": "closed",
+  "final_reward": 7.20,
+  "steps_completed": 10
+}
+```
+
+---
+
+#### 5. List Available Tasks
+**GET** `/tasks`
+
+Get metadata about all available tasks.
+
+**Response (200 OK):**
+```json
+{
+  "text_spam": {
+    "description": "Classify email/message content as spam or legitimate",
+    "difficulty": "easy",
+    "num_items": 50,
+    "content_type": "text"
+  },
+  "content_moderation": {
+    "description": "Detect policy violations in social media posts",
+    "difficulty": "medium",
+    "num_items": 40,
+    "content_type": "text"
+  },
+  "deepfake_detection": {
+    "description": "Identify AI-manipulated media",
+    "difficulty": "hard",
+    "num_items": 30,
+    "content_type": "multimodal"
+  }
+}
+```
+
+---
+
+#### 6. Health Check
+**GET** `/health`
+
+Check server health and status.
+
+**Response (200 OK):**
+```json
+{
+  "status": "ok"
+}
+```
+
+---
+
+#### 7. Root Endpoint
+**GET** `/`
+
+Redirects to interactive Swagger UI documentation.
+
+---
+
+## Project Structure
+
+```
+content-moderation-env/
+│
+├── README.md                          # This file
+├── uv.lock                            # Dependency lock file (UV package manager)
+├── inference.py                       # Baseline agent script (235 lines)
+│                                      # Demonstrates LLM agent interaction
+│                                      # Supports HF API and local inference modes
+│
+├── server/                            # FastAPI application (core)
+│   ├── __init__.py                    # Package marker (empty)
+│   │
+│   ├── main.py                        # FastAPI app & HTTP endpoints (57 lines)
+│   │                                  # Defines: /reset, /step, /state, /close
+│   │                                  # /tasks, /health, / endpoints
+│   │
+│   ├── env.py                         # OpenEnv environment implementation (122 lines)
+│   │                                  # Core logic: reset(), step(), state(), close()
+│   │                                  # Thread-safe with locks for concurrency
+│   │
+│   ├── models.py                      # Pydantic data models
+│   │                                  # Defines: ContentObservation, ModerationAction
+│   │                                  # StepResult, ResetResult, EnvState
+│   │
+│   ├── tasks.py                       # Task datasets & ground truth (193 lines)
+│   │                                  # Contains: text_spam, content_moderation,
+│   │                                  # deepfake_detection task definitions & items
+│   │
+│   ├── graders.py                     # Reward functions per task (95 lines)
+│   │                                  # Implements: label F1, calibration bonus,
+│   │                                  # decision accuracy scoring logic
+│   │
+│   ├── deepfake_model.py              # HF deepfake detection pipeline (90 lines)
+│   │                                  # Lazy-loads: dima806/deepfake_vs_real...
+│   │                                  # Caches model in HF_HOME for reuse
+│   │
+│   ├── openenv.yaml                   # OpenEnv specification metadata
+│   │                                  # Declares task specs, observation/action space
+│   │
+│   ├── Dockerfile                     # Docker container definition
+│   │                                  # Base: python:3.11-slim (~300MB)
+│   │                                  # Installs system deps, pip packages,
+│   │                                  # pre-downloads deepfake model
+│   │
+│   └── requirements.txt                # Python dependencies (12 packages)
+│                                      # Key: fastapi, uvicorn, transformers,
+│                                      # torch, openai, python-dotenv
+│
+├── test/                              # Test suite
+│   └── test.py                        # pytest tests (20+ test cases)
+│                                      # Coverage: tasks, endpoints, rewards
+│
+└── .env                               # Environment variables (git-ignored)
+                                       # Stores: HF_TOKEN, API_BASE_URL, etc.
+```
+
+---
+
+## Environment Variables
+
+Configuration is controlled via environment variables. Create a `.env` file in the project root:
+
+```env
+# ============ API Configuration ============
+API_BASE_URL=https://router.huggingface.co/v1
+# URL of the LLM inference endpoint
+# Default: HuggingFace router (requires HF_TOKEN)
+
+MODEL_NAME=meta-llama/Llama-3.1-8B-Instruct
+# Which LLM to use for agent inference
+# Other options: gpt-3.5-turbo, claude-3-opus, mistral-large, etc.
+
+HF_TOKEN=hf_your_token_here
+# HuggingFace API token for authenticated requests
+# Get from: https://huggingface.co/settings/tokens
+
+# ============ Server Configuration ============
+SERVER_URL=http://localhost:7860
+# Where the OpenEnv API server runs
+# Used by inference.py to connect to environment
+
+# ============ Task & Inference Configuration ============
+TASK_NAME=text_spam
+# Which task to run: text_spam, content_moderation, deepfake_detection
+
+USE_LOCAL_MODEL=false
+# If true: Load Llama-3.1-8B locally via transformers
+# If false: Use remote API (requires HF_TOKEN)
+# Local mode requires 16GB+ RAM
+
+# ============ HuggingFace Model Caching ============
+HF_HOME=/app/.cache/huggingface
+# Directory for cached HF models and datasets
+# Mounted as volume in Docker for persistence
+
+TRANSFORMERS_CACHE=/app/.cache/huggingface
+# Alternative env var for transformers library caching
+
+# ============ Python Configuration ============
+PYTHONDONTWRITEBYTECODE=1
+# Don't create __pycache__ directories
+
+PYTHONUNBUFFERED=1
+# Stream logs immediately (useful in Docker)
+
+# ============ Logging ============
+LOG_LEVEL=INFO
+# Log level: DEBUG, INFO, WARNING, ERROR, CRITICAL
+```
+
+### Variable Precedence
+
+1. Environment variables (highest priority)
+2. `.env` file
+3. Hardcoded defaults in code (lowest priority)
+
+Example override:
+```bash
+export HF_TOKEN="hf_custom_token" && python inference.py
+# Uses custom token instead of .env value
+```
+
+---
+
+## Running Tests
+
+The project includes a comprehensive test suite using pytest.
+
+### Setup
+
+```bash
+pip install pytest pytest-cov
+```
+
+### Run All Tests
+
+```bash
+pytest test/test.py -v
+```
+
+### Run Specific Test Class
+
+```bash
+pytest test/test.py::TestTasks -v
+```
+
+### Run with Coverage Report
+
+```bash
+pytest test/test.py --cov=server --cov-report=html
+# Opens htmlcov/index.html in browser for coverage visualization
+```
+
+### Test Categories
+
+| Test | Coverage | Status |
+|---|---|---|
+| Task loading | All 3 tasks initialize correctly | ✓ |
+| API endpoints | /reset, /step, /state, /close, /tasks, /health | ✓ |
+| Reward grading | text_spam, content_moderation, deepfake_detection | ✓ |
+| Input validation | Action schema validation, label validation | ✓ |
+| Edge cases | Empty labels, out-of-range confidence, etc. | ✓ |
+
+---
+
+## Troubleshooting
+
+### Installation Issues
+
+**Problem:** `ImportError: No module named 'openai'`
+```bash
+Solution: pip install "openai>=1.40.0"
+```
+
+**Problem:** `ImportError: No module named 'torch'`
+```bash
+Solution: pip install torch torchvision
+# For GPU: pip install torch torchvision -f https://download.pytorch.org/whl/cu121/torch_stable.html
+```
+
+**Problem:** `FileNotFoundError: requirements.txt`
+```bash
+Solution: Ensure you're in the project root: cd content-moderation-env/
+# Then: pip install -r server/requirements.txt
+```
+
+### Docker Issues
+
+**Problem:** `Segmentation fault (core dumped)` during build
+```
+Solution: Allocate more memory to Docker build:
+docker build --memory=8g -f server/Dockerfile -t content-moderation-env .
+```
+
+**Problem:** `failed to solve: failed to compute cache key`
+```
+Solution: Ensure requirements.txt is in server/ directory:
+# Current: server/requirements.txt (correct)
+# Wrong: ./requirements.txt
+```
+
+**Problem:** Port 7860 already in use
+```bash
+Solution: Use different port:
+docker run -p 8000:7860 content-moderation-env
+# Now access at http://localhost:8000
+```
+
+### Runtime Issues
+
+**Problem:** `Connection refused: localhost:7860`
+```bash
+Solution: Ensure server is running:
+uvicorn server.main:app --host 0.0.0.0 --port 7860
+
+In Docker, use: docker logs <container_id>
+```
+
+**Problem:** `Client.__init__() got an unexpected keyword argument 'proxies'`
+```bash
+Solution: Update OpenAI client:
+pip install --upgrade openai
+```
+
+**Problem:** HuggingFace models downloading very slowly
+```bash
+Solution: Check internet connection and verify HF_TOKEN:
+export HF_TOKEN="hf_your_token_here"
+# Or download models ahead of time
+python -c "from transformers import pipeline; pipeline('image-classification', model='dima806/deepfake_vs_real_image_detection')"
+```
+
+### API Issues
+
+**Problem:** Invalid request to `/step` without `/reset`
+```json
+Error: "Environment not initialized. Call /reset first."
+Solution: Always call POST /reset before any /step requests
+```
+
+**Problem:** Invalid label in action
+```json
+Error: {"detail": "Invalid label: 'unknown_label'"}
+Solution: Use only valid labels from the specification
+```
+
+**Problem:** Confidence out of range
+```
+Solution: Ensure confidence is between 0.0 and 1.0
+```
+
+---
+
+## Citation
+
+If you use this environment in your research, please cite:
+
+```bibtex
+@software{content_moderation_openenv_2025,
+  title={Content Moderation OpenEnv: A Real-World AI Triage Environment},
+  author={Anidipta},
+  year={2025},
+  url={https://github.com/Anidipta/Content-Moderation-env},
+  note={OpenEnv Specification Compliant}
+}
+```
+
+---
+
+## Acknowledgements
+
+🙏 Built for the **OpenEnv Hackathon 2025**.
+
+**Special Thanks To:**
+- OpenEnv community for the specification and framework
+- HuggingFace for model hosting and inference APIs
+- Meta for the Llama-3.1-8B-Instruct model
+- Contributors and testers who improved the environment
+
+**Dataset & Content Note:**
+The email and content corpus is entirely **synthetic** and does not represent any real individuals, companies, organizations, or actual events. All examples are generated for demonstration and testing purposes only.
+
+**License:** MIT License — See [LICENSE](LICENSE) file for details
+
+**Questions?** Open an issue on GitHub or contact the maintainers.
+
+---
+
+**Last Updated:** April 8, 2026 | **OpenEnv Spec Version:** 1.0
+colorTo: green
+sdk: docker
+pinned: false
+license: mit
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+>>>>>>> f6dee02010a32ba1936311cbb3790fa087282e74

uv.lock

@@ -1,236 +1,236 @@
-# This file is automatically @generated by uv and should not be manually edited.
-# Use `uv lock` to regenerate this file.
-
-version = 1
-requires-python = ">=3.11"
-
-[[package]]
-name = "accelerate"
-version = "0.30.0"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.8"
-dependencies = [
-    { name = "numpy", version = ">=1.17" },
-    { name = "packaging", version = ">=20.0" },
-    { name = "psutil" },
-    { name = "pyyaml" },
-    { name = "torch", version = ">=1.4.0" },
-]
-
-[[package]]
-name = "anyio"
-version = "4.1.1"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.8"
-dependencies = [
-    { name = "sniffio", version = ">=1.1" },
-]
-
-[[package]]
-name = "certifi"
-version = "2024.2.2"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.6"
-
-[[package]]
-name = "charset-normalizer"
-version = "3.3.2"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.7"
-
-[[package]]
-name = "click"
-version = "8.1.7"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.7"
-
-[[package]]
-name = "fastapi"
-version = "0.111.0"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.8"
-dependencies = [
-    { name = "pydantic", version = "!=1.8.1,>=1.7.4" },
-    { name = "starlette", version = "==0.37.0" },
-    { name = "typing-extensions", version = ">=4.8.0" },
-]
-
-[[package]]
-name = "filelock"
-version = "3.13.1"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.8"
-
-[[package]]
-name = "huggingface-hub"
-version = "0.21.4"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.8"
-dependencies = [
-    { name = "filelock" },
-    { name = "fsspec" },
-    { name = "requests" },
-    { name = "tqdm" },
-    { name = "typing-extensions" },
-    { name = "urllib3" },
-    { name = "pyyaml", version = ">=5.1" },
-]
-
-[[package]]
-name = "idna"
-version = "3.6"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.5"
-
-[[package]]
-name = "numpy"
-version = "1.26.4"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.9"
-
-[[package]]
-name = "openai"
-version = "1.42.0"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.7"
-dependencies = [
-    { name = "anyio", version = "<5,>=3.5.0" },
-    { name = "distro", version = "<2,>=1.7.0" },
-    { name = "httpx", version = "<1,>=0.23.1" },
-    { name = "pydantic", version = "<3,>=1.9.0" },
-    { name = "sniffio" },
-    { name = "typing-extensions", version = "<5,>=4.11" },
-]
-
-[[package]]
-name = "packaging"
-version = "24.0"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.7"
-
-[[package]]
-name = "pillow"
-version = "10.3.0"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.8"
-
-[[package]]
-name = "pydantic"
-version = "2.7.1"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.8"
-dependencies = [
-    { name = "pydantic-core", version = "==2.18.1" },
-    { name = "typing-extensions", version = "!=4.7.0,>=4.6.1" },
-    { name = "annotated-types", version = ">=0.4.0" },
-]
-
-[[package]]
-name = "pydantic-core"
-version = "2.18.1"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.8"
-
-[[package]]
-name = "python-dotenv"
-version = "1.0.0"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.5"
-
-[[package]]
-name = "pyyaml"
-version = "6.0.1"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.6"
-
-[[package]]
-name = "requests"
-version = "2.31.0"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.7"
-dependencies = [
-    { name = "charset-normalizer", version = ">=2,<4" },
-    { name = "idna", version = ">=2.5,<4" },
-    { name = "urllib3", version = ">=1.21.1,<3" },
-    { name = "certifi", version = ">=2017.4.17" },
-]
-
-[[package]]
-name = "sniffio"
-version = "1.3.1"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.7"
-
-[[package]]
-name = "starlette"
-version = "0.37.0"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.8"
-dependencies = [
-    { name = "anyio", version = "<5,>=3.4.0" },
-]
-
-[[package]]
-name = "torch"
-version = "2.3.0"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.8"
-
-[[package]]
-name = "torchvision"
-version = "0.18.0"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.8"
-dependencies = [
-    { name = "numpy" },
-    { name = "pillow", version = "!=8.3.0,>=5.3.0" },
-    { name = "torch", version = "==2.3.0" },
-    { name = "requests" },
-]
-
-[[package]]
-name = "tqdm"
-version = "4.66.2"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.7"
-
-[[package]]
-name = "transformers"
-version = "4.41.2"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.8"
-dependencies = [
-    { name = "filelock" },
-    { name = "huggingface-hub", version = ">=0.21.1" },
-    { name = "numpy", version = ">=1.17" },
-    { name = "packaging", version = ">=20.0" },
-    { name = "pyyaml", version = ">=5.1" },
-    { name = "regex", version = "!=2019.12.17" },
-    { name = "requests" },
-    { name = "safetensors", version = ">=0.4.1" },
-    { name = "tokenizers", version = ">=0.14,<0.15" },
-    { name = "torch", version = ">=1.9" },
-    { name = "tqdm", version = ">=4.27" },
-]
-
-[[package]]
-name = "typing-extensions"
-version = "4.10.0"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.8"
-
-[[package]]
-name = "urllib3"
-version = "2.1.0"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.8"
-
-[[package]]
-name = "uvicorn"
-version = "0.29.0"
-source = { registry = "https://pypi.org/simple" }
-requires-python = ">=3.8"
-dependencies = [
-    { name = "click", version = ">=7.0" },
-    { name = "h11", version = ">=0.8" },
-]
+# This file is automatically @generated by uv and should not be manually edited.
+# Use `uv lock` to regenerate this file.
+
+version = 1
+requires-python = ">=3.11"
+
+[[package]]
+name = "accelerate"
+version = "0.30.0"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.8"
+dependencies = [
+    { name = "numpy", version = ">=1.17" },
+    { name = "packaging", version = ">=20.0" },
+    { name = "psutil" },
+    { name = "pyyaml" },
+    { name = "torch", version = ">=1.4.0" },
+]
+
+[[package]]
+name = "anyio"
+version = "4.1.1"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.8"
+dependencies = [
+    { name = "sniffio", version = ">=1.1" },
+]
+
+[[package]]
+name = "certifi"
+version = "2024.2.2"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.6"
+
+[[package]]
+name = "charset-normalizer"
+version = "3.3.2"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.7"
+
+[[package]]
+name = "click"
+version = "8.1.7"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.7"
+
+[[package]]
+name = "fastapi"
+version = "0.111.0"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.8"
+dependencies = [
+    { name = "pydantic", version = "!=1.8.1,>=1.7.4" },
+    { name = "starlette", version = "==0.37.0" },
+    { name = "typing-extensions", version = ">=4.8.0" },
+]
+
+[[package]]
+name = "filelock"
+version = "3.13.1"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.8"
+
+[[package]]
+name = "huggingface-hub"
+version = "0.21.4"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.8"
+dependencies = [
+    { name = "filelock" },
+    { name = "fsspec" },
+    { name = "requests" },
+    { name = "tqdm" },
+    { name = "typing-extensions" },
+    { name = "urllib3" },
+    { name = "pyyaml", version = ">=5.1" },
+]
+
+[[package]]
+name = "idna"
+version = "3.6"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.5"
+
+[[package]]
+name = "numpy"
+version = "1.26.4"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.9"
+
+[[package]]
+name = "openai"
+version = "1.42.0"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.7"
+dependencies = [
+    { name = "anyio", version = "<5,>=3.5.0" },
+    { name = "distro", version = "<2,>=1.7.0" },
+    { name = "httpx", version = "<1,>=0.23.1" },
+    { name = "pydantic", version = "<3,>=1.9.0" },
+    { name = "sniffio" },
+    { name = "typing-extensions", version = "<5,>=4.11" },
+]
+
+[[package]]
+name = "packaging"
+version = "24.0"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.7"
+
+[[package]]
+name = "pillow"
+version = "10.3.0"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.8"
+
+[[package]]
+name = "pydantic"
+version = "2.7.1"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.8"
+dependencies = [
+    { name = "pydantic-core", version = "==2.18.1" },
+    { name = "typing-extensions", version = "!=4.7.0,>=4.6.1" },
+    { name = "annotated-types", version = ">=0.4.0" },
+]
+
+[[package]]
+name = "pydantic-core"
+version = "2.18.1"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.8"
+
+[[package]]
+name = "python-dotenv"
+version = "1.0.0"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.5"
+
+[[package]]
+name = "pyyaml"
+version = "6.0.1"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.6"
+
+[[package]]
+name = "requests"
+version = "2.31.0"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.7"
+dependencies = [
+    { name = "charset-normalizer", version = ">=2,<4" },
+    { name = "idna", version = ">=2.5,<4" },
+    { name = "urllib3", version = ">=1.21.1,<3" },
+    { name = "certifi", version = ">=2017.4.17" },
+]
+
+[[package]]
+name = "sniffio"
+version = "1.3.1"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.7"
+
+[[package]]
+name = "starlette"
+version = "0.37.0"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.8"
+dependencies = [
+    { name = "anyio", version = "<5,>=3.4.0" },
+]
+
+[[package]]
+name = "torch"
+version = "2.3.0"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.8"
+
+[[package]]
+name = "torchvision"
+version = "0.18.0"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.8"
+dependencies = [
+    { name = "numpy" },
+    { name = "pillow", version = "!=8.3.0,>=5.3.0" },
+    { name = "torch", version = "==2.3.0" },
+    { name = "requests" },
+]
+
+[[package]]
+name = "tqdm"
+version = "4.66.2"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.7"
+
+[[package]]
+name = "transformers"
+version = "4.41.2"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.8"
+dependencies = [
+    { name = "filelock" },
+    { name = "huggingface-hub", version = ">=0.21.1" },
+    { name = "numpy", version = ">=1.17" },
+    { name = "packaging", version = ">=20.0" },
+    { name = "pyyaml", version = ">=5.1" },
+    { name = "regex", version = "!=2019.12.17" },
+    { name = "requests" },
+    { name = "safetensors", version = ">=0.4.1" },
+    { name = "tokenizers", version = ">=0.14,<0.15" },
+    { name = "torch", version = ">=1.9" },
+    { name = "tqdm", version = ">=4.27" },
+]
+
+[[package]]
+name = "typing-extensions"
+version = "4.10.0"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.8"
+
+[[package]]
+name = "urllib3"
+version = "2.1.0"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.8"
+
+[[package]]
+name = "uvicorn"
+version = "0.29.0"
+source = { registry = "https://pypi.org/simple" }
+requires-python = ">=3.8"
+dependencies = [
+    { name = "click", version = ">=7.0" },
+    { name = "h11", version = ">=0.8" },
+]