baidu-ai-search

{ "cells": [ { "cell_type": "markdown", "id": "bd16bc4e-9e7a-4119-a9e8-55b1adb7b560", "metadata": {}, "source": [ "# console端知识库操作助手\n", "\n", "## 目标\n", "用户可通过SDK对console端知识库进行操作，实现创建知识库、添加知识文档、查询知识库文档、删除知识文档等操作，可在平台console中查看结果。\n", "\n", "## 准备工作\n", "### 平台注册\n", "1.先在appbuilder平台注册，获取token\n", "\n", "2.安装appbuilder-sdk" ] }, { "cell_type": "code", "execution_count": null, "id": "f66602fd-680d-4f28-8f2d-fb4b79845a70", "metadata": {}, "outputs": [], "source": [ "!pip install appbuilder-sdk" ] }, { "cell_type": "code", "execution_count": 1, "id": "7fef1d24-0aa5-4697-b49e-9b087408e319", "metadata": { "ExecuteTime": { "end_time": "2024-02-02T09:04:39.646010Z", "start_time": "2024-02-02T09:04:39.638630Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "init done\n" ] } ], "source": [ "import os\n", "\n", "# 设置环境变量\n", "# 请前往千帆AppBuilder官网创建密钥，流程详见：https://cloud.baidu.com/doc/AppBuilder/s/Olq6grrt6#1%E3%80%81%E5%88%9B%E5%BB%BA%E5%AF%86%E9%92%A5\n", "os.environ[\"APPBUILDER_TOKEN\"] = \"...\"\n", "\n", "print(\"init done\")" ] }, { "cell_type": "markdown", "id": "da65c0ca-c7b8-416d-be70-4b7f83f8376c", "metadata": {}, "source": [ "## 开发过程" ] }, { "cell_type": "markdown", "source": [ "### 初始化已有知识库\n", "获取线上已有知识库的ID，可在[console](https://console.bce.baidu.com/ai_apaas/dataset)端查看，示例\n", "\n", "<img width=\"1536\" alt=\"image\" src=\"./image/dataset示例.png\">" ], "metadata": { "collapsed": false }, "id": "4fcce3379af01f31" }, { "cell_type": "code", "execution_count": null, "outputs": [], "source": [ "import appbuilder\n", "# 初始化已有线上知识库, dataset_id 可在平台console中查看\n", "dataset_id = \"...\"\n", "dataset = appbuilder.console.Dataset(dataset_id)" ], "metadata": { "collapsed": false }, "id": "e6512896d659d339" }, { "cell_type": "markdown", "id": "0b9e894c-9b1c-4d14-8fba-85607c07d091", "metadata": {}, "source": [ "### 创建全新知识库" ] }, { "cell_type": "code", "execution_count": null, "id": "cb554cf7-3f07-4a16-a760-57064f35f6cc", "metadata": {}, "outputs": [], "source": [ "# 创建全新知识库\n", "dataset = appbuilder.console.Dataset.create_dataset(\"my_dataset\")" ] }, { "cell_type": "markdown", "id": "4305e336-67da-4aec-a807-d5ef1b66987c", "metadata": {}, "source": [ "### 上传文档到知识库" ] }, { "cell_type": "code", "execution_count": null, "id": "41fc3bd1-1a9d-4515-99d5-4704adaec508", "metadata": {}, "outputs": [], "source": [ "# 设置文档路径，例如“./test.pdf”\n", "file_path1 = \"...\"\n", "file_path2 = \"...\"\n", "file_paths = [file_path1, file_path2]\n", "# 将文档上传到知识库\n", "document_infos = dataset.add_documents(file_paths)\n", "print(document_infos)" ] }, { "cell_type": "markdown", "id": "7e4fc1bf-7af9-4a69-a409-e1f0c53b3651", "metadata": {}, "source": [ "### 获取知识库关联文档" ] }, { "cell_type": "code", "execution_count": null, "id": "fd628ef9-1f61-4350-81f6-9eaea5342400", "metadata": {}, "outputs": [], "source": [ "# 获取第一页的文档列表, 每页10条\n", "document_list = dataset.get_documents(1, 10)\n", "print(document_list)" ] }, { "cell_type": "markdown", "id": "6dc7f0ec-e556-4246-b7c6-92a7242c8194", "metadata": {}, "source": [ "### 删除知识库中的文档" ] }, { "cell_type": "code", "execution_count": null, "id": "17c50ea0-521d-42c2-82c8-34a70510be3d", "metadata": {}, "outputs": [], "source": [ "# 删除第一个文档\n", "document_ids = [document_list.data[0].id]\n", "dataset.delete_documents(document_ids)" ] } ], "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", "version": "3.11.5" } }, "nbformat": 4, "nbformat_minor": 5 }