{
  "repository_url": "https://github.com/ronelsolomon/cebras.git",
  "owner": "ronelsolomon",
  "name": "cebras.git",
  "extracted_at": "2026-03-02T22:49:08.429260",
  "files": {
    "requirements.txt": {
      "content": "cerebras-cloud-sdk>=0.1.0\npython-dotenv>=1.0.0\n",
      "size": 47,
      "language": "text"
    },
    "README.md": {
      "content": "# Cerebras Chat Completion Example\n\nThis project demonstrates how to use the Cerebras SDK to generate chat completions using the Llama 4 model.\n\n## Prerequisites\n\n- Python 3.8+\n- Cerebras API key (get it from [Cerebras Console](https://console.cerebras.net/))\n\n## Setup\n\n1. Clone this repository\n2. Install the required dependencies:\n   ```bash\n   pip install -r requirements.txt\n   ```\n3. Set your Cerebras API key as an environment variable:\n   ```bash\n   # On macOS/Linux\n   export CEREBRAS_API_KEY='your-api-key-here'\n   \n   # On Windows (Command Prompt)\n   set CEREBRAS_API_KEY=your-api-key-here\n   \n   # On Windows (PowerShell)\n   $env:CEREBRAS_API_KEY='your-api-key-here'\n   ```\n\n## Usage\n\nRun the chat completion example:\n\n```bash\npython cebras.py\n```\n\n## Environment Variables\n\n- `CEREBRAS_API_KEY`: Your Cerebras API key (required)\n\n## Example\n\nThe script will send a chat completion request to the Cerebras API and stream the response to the console.\n",
      "size": 962,
      "language": "markdown"
    },
    ".env": {
      "content": "CEREBRAS_API_KEY=\"csk-y933tjkj4d4fct3jr2xny2yp9k8xkx4kh3rk2d6e59kywpk3\"",
      "size": 71,
      "language": "unknown"
    },
    ".gitattributes": {
      "content": "# Auto detect text files and perform LF normalization\n* text=auto\n",
      "size": 66,
      "language": "unknown"
    },
    "cebras.py": {
      "content": "import os\nfrom cerebras.cloud.sdk import Cerebras\n\nclient = Cerebras(\n    # This is the default and can be omitted\n    api_key=\"csk-y933tjkj4d4fct3jr2xny2yp9k8xkx4kh3rk2d6e59kywpk3\"\n    #os.environ.get(\"csk-y933tjkj4d4fct3jr2xny2yp9k8xkx4kh3rk2d6e59kywpk3\")\n)\n\nstream = client.chat.completions.create(\n    messages=[\n        {\n            \"role\": \"system\",\n            \"content\": \"What is a Rock\"\n        }\n    ],\n    model=\"llama-4-scout-17b-16e-instruct\",\n    stream=True,\n    max_completion_tokens=2048,\n    temperature=0.2,\n    top_p=1\n)\n\nfor chunk in stream:\n  print(chunk.choices[0].delta.content or \"\", end=\"\")",
      "size": 617,
      "language": "python"
    }
  },
  "_cache_metadata": {
    "url": "https://github.com/ronelsolomon/cebras.git",
    "content_type": "github",
    "cached_at": "2026-03-02T22:49:08.429936",
    "cache_key": "2aa832db180a76e905044673bb878cbd"
  }
}