update doc with llama_index (#1180)

examples/pytorch/application/qwen_doc_search_QA_based_on_llamaindex.ipynb

@@ -2,6 +2,10 @@
  "cells": [
   {
    "cell_type": "markdown",
+   "id": "f4abc589d9bfffca",
+   "metadata": {
+    "collapsed": false
+   },
    "source": [
     "# Usage\n",
     "\n",
@@ -34,27 +38,29 @@
     "```\n",
     "\n",
     "## 3. Go!"
-   ],
+   ]
-   "metadata": {
-    "collapsed": false
-   },
-   "id": "f4abc589d9bfffca"
   },
   {
    "cell_type": "code",
+   "execution_count": null,
+   "id": "c32122833dd7b8c8",
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [],
    "source": [
     "!pip install modelscope\n",
     "!pip install transformers -U\n",
     "!pip install llama-index llama-index-llms-huggingface ipywidgets "
-   ],
+   ]
-   "metadata": {
-    "collapsed": false
-   },
-   "id": "c32122833dd7b8c8"
   },
   {
    "cell_type": "code",
+   "execution_count": null,
+   "id": "63704e2b21a9ba52",
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [],
    "source": [
     "!wget https://modelscope.oss-cn-beijing.aliyuncs.com/resource/rag/punkt.zip\n",
@@ -74,15 +80,90 @@
     "!mv /mnt/workspace/xianjiaoda.md /mnt/workspace/custom_data\n",
     "\n",
     "!cd /mnt/workspace"
-   ],
+   ]
-   "metadata": {
-    "collapsed": false
-   },
-   "id": "63704e2b21a9ba52"
   },
   {
    "cell_type": "code",
-   "outputs": [],
+   "execution_count": 2,
+   "id": "eef67659e94045c5",
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Downloading Model to directory: /mnt/workspace/.cache/modelscope/qwen/Qwen1.5-4B-Chat\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2025-01-13 15:52:53,260 - modelscope - INFO - Model revision not specified, using default: [master] version.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2025-01-13 15:52:53,637 - modelscope - INFO - Creating symbolic link [/mnt/workspace/.cache/modelscope/qwen/Qwen1.5-4B-Chat].\n",
+      "2025-01-13 15:52:53,638 - modelscope - WARNING - Failed to create symbolic link /mnt/workspace/.cache/modelscope/qwen/Qwen1.5-4B-Chat for /mnt/workspace/.cache/modelscope/qwen/Qwen1___5-4B-Chat.\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "4523c5dd31ba411d95cc0ce9e5da8ded",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "llm created\n",
+      "Downloading Model to directory: /mnt/workspace/.cache/modelscope/damo/nlp_gte_sentence-embedding_chinese-base\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2025-01-13 15:53:01,651 - modelscope - INFO - Model revision not specified, using default: [master] version.\n",
+      "2025-01-13 15:53:01,894 - modelscope - INFO - initiate model from /mnt/workspace/.cache/modelscope/hub/damo/nlp_gte_sentence-embedding_chinese-base\n",
+      "2025-01-13 15:53:01,895 - modelscope - INFO - initiate model from location /mnt/workspace/.cache/modelscope/hub/damo/nlp_gte_sentence-embedding_chinese-base.\n",
+      "2025-01-13 15:53:01,898 - modelscope - INFO - initialize model from /mnt/workspace/.cache/modelscope/hub/damo/nlp_gte_sentence-embedding_chinese-base\n",
+      "2025-01-13 15:53:02,532 - modelscope - WARNING - No preprocessor field found in cfg.\n",
+      "2025-01-13 15:53:02,533 - modelscope - WARNING - No val key and type key found in preprocessor domain of configuration.json file.\n",
+      "2025-01-13 15:53:02,533 - modelscope - WARNING - Cannot find available config to build preprocessor at mode inference, current config: {'model_dir': '/mnt/workspace/.cache/modelscope/hub/damo/nlp_gte_sentence-embedding_chinese-base'}. trying to build by task and model information.\n",
+      "2025-01-13 15:53:02,588 - modelscope - WARNING - No preprocessor field found in cfg.\n",
+      "2025-01-13 15:53:02,588 - modelscope - WARNING - No val key and type key found in preprocessor domain of configuration.json file.\n",
+      "2025-01-13 15:53:02,589 - modelscope - WARNING - Cannot find available config to build preprocessor at mode inference, current config: {'model_dir': '/mnt/workspace/.cache/modelscope/hub/damo/nlp_gte_sentence-embedding_chinese-base', 'sequence_length': 128}. trying to build by task and model information.\n",
+      "/root/miniconda3/envs/modelscope_1.21/lib/python3.9/site-packages/transformers/modeling_utils.py:1044: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers.\n",
+      "  warnings.warn(\n",
+      "/root/miniconda3/envs/modelscope_1.21/lib/python3.9/site-packages/transformers/generation/configuration_utils.py:628: UserWarning: `do_sample` is set to `False`. However, `temperature` is set to `0.0` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `temperature`.\n",
+      "  warnings.warn(\n",
+      "/root/miniconda3/envs/modelscope_1.21/lib/python3.9/site-packages/transformers/generation/configuration_utils.py:633: UserWarning: `do_sample` is set to `False`. However, `top_p` is set to `0.8` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `top_p`.\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "作为一所历史悠久的综合性研究型大学，西安交通大学有着丰富的校训文化。其中，\"厚德博学，求是创新\"是其最为人所知的校训之一。这句校训不仅体现了学校的教育理念，也反映了学校对学生的期望和要求。此外，西安交通大学还有一句著名的校训：\"明德尚志，自强不息\"，这也是学校对学生的一种激励和引导。这两句校训都强调了教育的重要性，以及学生应该具备的道德品质和自我提升的精神。\n"
+     ]
+    }
+   ],
    "source": [
     "import logging\n",
     "import sys\n",
@@ -93,9 +174,7 @@
     "from llama_index.core import (\n",
     "    SimpleDirectoryReader,\n",
     "    VectorStoreIndex,\n",
-    "    Settings,\n",
+    "    Settings\n",
-    "    ServiceContext,\n",
-    "    set_global_service_context,\n",
     ")\n",
     "from llama_index.core.base.embeddings.base import BaseEmbedding, Embedding\n",
     "from llama_index.core.prompts import PromptTemplate\n",
@@ -176,9 +255,8 @@
     "\n",
     "embedding_model = \"damo/nlp_gte_sentence-embedding_chinese-base\"\n",
     "embeddings = ModelScopeEmbeddings4LlamaIndex(model_id=embedding_model)\n",
-    "service_context = ServiceContext.from_defaults(embed_model=embeddings, llm=llm)\n",
-    "set_global_service_context(service_context)\n",
     "Settings.embed_model = embeddings\n",
+    "Settings.llm = llm\n",
     "\n",
     "# load example documents\n",
     "documents = SimpleDirectoryReader(\"/mnt/workspace/custom_data/\").load_data()\n",
@@ -192,11 +270,7 @@
     "# do query\n",
     "response = query_engine.query(\"西安较大的校训是什么\")\n",
     "print(response)\n"
-   ],
+   ]
-   "metadata": {
-    "collapsed": false
-   },
-   "id": "eef67659e94045c5"
   }
  ],
  "metadata": {