{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "9dKM5k8qsMIj"
      },
      "source": [
        "## LiteLLM Hugging Face\n",
        "\n",
        "Docs for huggingface: https://docs.litellm.ai/docs/providers/huggingface\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "BVDdmCp-o97j"
      },
      "outputs": [],
      "source": [
        "!pip install litellm"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "yp5UXRqtpu9f"
      },
      "source": [
        "## Serverless Inference Providers\n",
        "\n",
        "Read more about Inference Providers here: https://huggingface.co/blog/inference-providers.\n",
        "\n",
        "In order to use litellm with Hugging Face Inference Providers, you need to set `model=huggingface/<provider>/<model-id>`.\n",
        "\n",
        "Example: `huggingface/together/deepseek-ai/DeepSeek-R1` to run DeepSeek-R1 (https://huggingface.co/deepseek-ai/DeepSeek-R1) through Together AI.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Pi5Oww8gpCUm",
        "outputId": "659a67c7-f90d-4c06-b94e-2c4aa92d897a"
      },
      "outputs": [],
      "source": [
        "import os\n",
        "from litellm import completion\n",
        "\n",
        "# You can create a HF token here: https://huggingface.co/settings/tokens\n",
        "os.environ[\"HF_TOKEN\"] = \"hf_xxxxxx\"\n",
        "\n",
        "# Call DeepSeek-R1 model through Together AI\n",
        "response = completion(\n",
        "    model=\"huggingface/together/deepseek-ai/DeepSeek-R1\",\n",
        "    messages=[{\"content\": \"How many r's are in the word `strawberry`?\", \"role\": \"user\"}],\n",
        ")\n",
        "print(response)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "EU0UubrKzTFe"
      },
      "source": [
        "## Streaming\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "y-QfIvA-uJKX",
        "outputId": "b007bb98-00d0-44a4-8264-c8a2caed6768"
      },
      "outputs": [],
      "source": [
        "import os\n",
        "from litellm import completion\n",
        "\n",
        "os.environ[\"HF_TOKEN\"] = \"hf_xxxxxx\"\n",
        "\n",
        "response = completion(\n",
        "    model=\"huggingface/together/deepseek-ai/DeepSeek-R1\",\n",
        "    messages=[\n",
        "        {\n",
        "            \"role\": \"user\",\n",
        "            \"content\": \"How many r's are in the word `strawberry`?\",\n",
        "            \n",
        "        }\n",
        "    ],\n",
        "    stream=True,\n",
        ")\n",
        "\n",
        "for chunk in response:\n",
        "    print(chunk)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## With images as input\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "from litellm import completion\n",
        "\n",
        "# Set your Hugging Face Token\n",
        "os.environ[\"HF_TOKEN\"] = \"hf_xxxxxx\"\n",
        "\n",
        "messages = [\n",
        "    {\n",
        "        \"role\": \"user\",\n",
        "        \"content\": [\n",
        "            {\"type\": \"text\", \"text\": \"What's in this image?\"},\n",
        "            {\n",
        "                \"type\": \"image_url\",\n",
        "                \"image_url\": {\n",
        "                    \"url\": \"https://awsmp-logos.s3.amazonaws.com/seller-xw5kijmvmzasy/c233c9ade2ccb5491072ae232c814942.png\",\n",
        "                },\n",
        "            },\n",
        "        ],\n",
        "    }\n",
        "]\n",
        "\n",
        "response = completion(\n",
        "    model=\"huggingface/sambanova/meta-llama/Llama-3.3-70B-Instruct\",\n",
        "    messages=messages,\n",
        ")\n",
        "print(response.choices[0])"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Tools - Function Calling\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "import os\n",
        "from litellm import completion\n",
        "\n",
        "\n",
        "# Set your Hugging Face Token\n",
        "os.environ[\"HF_TOKEN\"] = \"hf_xxxxxx\"\n",
        "\n",
        "tools = [\n",
        "    {\n",
        "        \"type\": \"function\",\n",
        "        \"function\": {\n",
        "            \"name\": \"get_current_weather\",\n",
        "            \"description\": \"Get the current weather in a given location\",\n",
        "            \"parameters\": {\n",
        "                \"type\": \"object\",\n",
        "                \"properties\": {\n",
        "                    \"location\": {\n",
        "                        \"type\": \"string\",\n",
        "                        \"description\": \"The city and state, e.g. San Francisco, CA\",\n",
        "                    },\n",
        "                    \"unit\": {\"type\": \"string\", \"enum\": [\"celsius\", \"fahrenheit\"]},\n",
        "                },\n",
        "                \"required\": [\"location\"],\n",
        "            },\n",
        "        },\n",
        "    }\n",
        "]\n",
        "messages = [{\"role\": \"user\", \"content\": \"What's the weather like in Boston today?\"}]\n",
        "\n",
        "response = completion(\n",
        "    model=\"huggingface/sambanova/meta-llama/Llama-3.1-8B-Instruct\", messages=messages, tools=tools, tool_choice=\"auto\"\n",
        ")\n",
        "print(response)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Hugging Face Dedicated Inference Endpoints\n",
        "\n",
        "Steps to use\n",
        "\n",
        "- Create your own Hugging Face dedicated endpoint here: https://ui.endpoints.huggingface.co/\n",
        "- Set `api_base` to your deployed api base\n",
        "- set the model to `huggingface/tgi` so that litellm knows it's a huggingface Deployed Inference Endpoint.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "import os\n",
        "import litellm\n",
        "\n",
        "\n",
        "response = litellm.completion(\n",
        "    model=\"huggingface/tgi\",\n",
        "    messages=[{\"content\": \"Hello, how are you?\", \"role\": \"user\"}],\n",
        "    api_base=\"https://my-endpoint.endpoints.huggingface.cloud/v1/\",\n",
        ")\n",
        "print(response)"
      ]
    }
  ],
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "display_name": ".venv",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.12.0"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}