{"cells": [{"attachments": {}, "cell_type": "markdown", "id": "2e33dced-e587-4397-81b3-d6606aa1738a", "metadata": {}, "source": ["# DataBricks\n", "\n", "集成DataBricks LLMs API。\n"]}, {"cell_type": "markdown", "id": "0c4105d3", "metadata": {}, "source": ["## 先决条件\n", "\n", "- [Databricks个人访问令牌](https://docs.databricks.com/en/dev-tools/auth/pat.html)用于查询和访问Databricks模型服务端点。\n", "\n", "- 在[支持的区域](https://docs.databricks.com/en/machine-learning/model-serving/model-serving-limits.html#regions)中拥有[Databricks工作区](https://docs.databricks.com/en/workspace/index.html)，以便使用Foundation Model APIs按令牌付费。\n"]}, {"attachments": {}, "cell_type": "markdown", "id": "5863dde9-84a0-4c33-ad52-cc767442f63f", "metadata": {}, "source": ["## 设置\n"]}, {"cell_type": "markdown", "id": "833bdb2b", "metadata": {}, "source": ["如果您在colab上打开这个笔记本，您可能需要安装LlamaIndex 🦙。\n"]}, {"cell_type": "code", "execution_count": null, "id": "4aff387e", "metadata": {}, "outputs": [], "source": ["% pip install llama-index-llms-databricks"]}, {"cell_type": "code", "execution_count": null, "id": "9bbbc106", "metadata": {}, "outputs": [], "source": ["!pip install llama-index"]}, {"cell_type": "code", "execution_count": null, "id": "ad297f19-998f-4485-aa2f-d67020058b7d", "metadata": {}, "outputs": [{"name": "stderr", "output_type": "stream", "text": ["None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.\n"]}], "source": ["from llama_index.llms.databricks import DataBricks"]}, {"cell_type": "markdown", "id": "4eefec25", "metadata": {}, "source": ["```bash\n", "export DATABRICKS_API_KEY=<你的API密钥>\n", "export DATABRICKS_API_BASE=<你的API服务端点>\n", "```\n", "\n", "或者，你可以在初始化时将你的API密钥和服务端点传递给LLM：\n"]}, {"cell_type": "code", "execution_count": null, "id": "152ced37-9a42-47be-9a39-4218521f5e72", "metadata": {}, "outputs": [], "source": ["llm = DataBricks(\n", "    model=\"databricks-dbrx-instruct\",\n", "    api_key=\"your_api_key\",\n", "    api_base=\"https://[your-work-space].cloud.databricks.com/serving-endpoints/[your-serving-endpoint]\",\n", ")"]}, {"cell_type": "markdown", "id": "562455fe", "metadata": {}, "source": ["可以在[这里](https://console.groq.com/docs/models)找到可用的LLM模型列表。\n"]}, {"cell_type": "code", "execution_count": null, "id": "d61b10bb-e911-47fb-8e84-19828cf224be", "metadata": {}, "outputs": [], "source": ["response = llm.complete(\"Explain the importance of open source LLMs\")"]}, {"cell_type": "code", "execution_count": null, "id": "3bd14f4e-c245-4384-a471-97e4ddfcb40e", "metadata": {}, "outputs": [], "source": ["print(response)"]}, {"attachments": {}, "cell_type": "markdown", "id": "3ba9503c-b440-43c6-a50c-676c79993813", "metadata": {}, "source": ["#### 使用消息列表调用 `chat`\n"]}, {"cell_type": "code", "execution_count": null, "id": "ee8a4a55-5680-4dc6-a44c-fc8ad7892f80", "metadata": {}, "outputs": [], "source": ["from llama_index.core.llms import ChatMessage\n", "\n", "messages = [\n", "    ChatMessage(\n", "        role=\"system\", content=\"You are a pirate with a colorful personality\"\n", "    ),\n", "    ChatMessage(role=\"user\", content=\"What is your name\"),\n", "]\n", "resp = llm.chat(messages)"]}, {"cell_type": "code", "execution_count": null, "id": "2a9bfe53-d15b-4e75-9d91-8c5d024f4eda", "metadata": {}, "outputs": [], "source": ["print(resp)"]}, {"attachments": {}, "cell_type": "markdown", "id": "25ad1b00-28fc-4bcd-96c4-d5b35605721a", "metadata": {}, "source": ["### Streaming\n"]}, {"attachments": {}, "cell_type": "markdown", "id": "13c641fa-345a-4dce-87c5-ab1f6dcf4757", "metadata": {}, "source": ["使用 `stream_complete` 终端点\n"]}, {"cell_type": "code", "execution_count": null, "id": "06da1ef1-2f6b-497c-847b-62dd2df11491", "metadata": {}, "outputs": [], "source": ["response = llm.stream_complete(\"Explain the importance of open source LLMs\")"]}, {"cell_type": "code", "execution_count": null, "id": "1b851def-5160-46e5-a30c-5a3ef2356b79", "metadata": {}, "outputs": [], "source": ["for r in response:\n", "    print(r.delta, end=\"\")"]}, {"attachments": {}, "cell_type": "markdown", "id": "ca52051d-6b28-49d7-98f5-82e266a1c7a6", "metadata": {}, "source": ["使用 `stream_chat` 端点\n"]}, {"cell_type": "code", "execution_count": null, "id": "fe553190-52a9-436d-84ae-4dd99a1808f4", "metadata": {}, "outputs": [], "source": ["from llama_index.core.llms import ChatMessage\n", "\n", "messages = [\n", "    ChatMessage(\n", "        role=\"system\", content=\"You are a pirate with a colorful personality\"\n", "    ),\n", "    ChatMessage(role=\"user\", content=\"What is your name\"),\n", "]\n", "resp = llm.stream_chat(messages)"]}, {"cell_type": "code", "execution_count": null, "id": "154c503c-f893-4b6b-8a65-a9a27b636046", "metadata": {}, "outputs": [], "source": ["for r in resp:\n", "    print(r.delta, end=\"\")"]}], "metadata": {"kernelspec": {"display_name": "Python 3 (ipykernel)", "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"}}, "nbformat": 4, "nbformat_minor": 5}