diff --git a/notebooks/llm-rag-langchain/llm-rag-langchain.ipynb b/notebooks/llm-rag-langchain/llm-rag-langchain.ipynb index 757fe586912..bb197010a2a 100644 --- a/notebooks/llm-rag-langchain/llm-rag-langchain.ipynb +++ b/notebooks/llm-rag-langchain/llm-rag-langchain.ipynb @@ -59,10 +59,21 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 50, "id": "1f077b32-5d36-44b0-9041-407e996283a3", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[33mWARNING: Skipping openvino-dev as it is not installed.\u001b[0m\u001b[33m\n", + "\u001b[0m\u001b[33mWARNING: Skipping openvino as it is not installed.\u001b[0m\u001b[33m\n", + "\u001b[0mNote: you may need to restart the kernel to use updated packages.\n", + "Note: you may need to restart the kernel to use updated packages.\n" + ] + } + ], "source": [ "%pip uninstall -q -y openvino-dev openvino openvino-nightly optimum optimum-intel\n", "%pip install -q --extra-index-url https://download.pytorch.org/whl/cpu\\\n", @@ -72,7 +83,7 @@ "\"accelerate\"\\\n", "\"openvino-nightly\"\\\n", "\"gradio\"\\\n", - "\"onnx\" \"einops\" \"transformers_stream_generator\" \"tiktoken\" \"transformers>=4.38.1\" \"bitsandbytes\" \"chromadb\" \"sentence_transformers\" \"langchain>=0.1.15\" \"langchainhub\" \"unstructured\" \"scikit-learn\" \"python-docx\" \"pdfminer.six\" " + "\"onnx\" \"einops\" \"transformers_stream_generator\" \"tiktoken\" \"transformers>=4.38.1\" \"bitsandbytes\" \"chromadb\" \"sentence_transformers\" \"langchain>=0.1.15\" \"langchainhub\" \"unstructured\" \"scikit-learn\" \"python-docx\" \"pypdf\" " ] }, { @@ -85,11 +96,16 @@ "import shutil\n", "from pathlib import Path\n", "import requests\n", + "import io\n", "\n", "# fetch model configuration\n", "\n", "config_shared_path = Path(\"../../utils/llm_config.py\")\n", "config_dst_path = Path(\"llm_config.py\")\n", + "text_example_en_path = Path(\"text_example_en.pdf\")\n", + "text_example_cn_path = Path(\"text_example_cn.pdf\")\n", + "text_example_en = \"https://github.com/openvinotoolkit/openvino_notebooks/files/15039728/Platform.Brief_Intel.vPro.with.Intel.Core.Ultra_Final.pdf\"\n", + "text_example_cn = \"https://github.com/openvinotoolkit/openvino_notebooks/files/15039713/Platform.Brief_Intel.vPro.with.Intel.Core.Ultra_Final_CH.pdf\"\n", "\n", "if not config_dst_path.exists():\n", " if config_shared_path.exists():\n", @@ -97,7 +113,19 @@ " else:\n", " r = requests.get(url=\"https://raw.githubusercontent.com/openvinotoolkit/openvino_notebooks/latest/utils/llm_config.py\")\n", " with open(\"llm_config.py\", \"w\") as f:\n", - " f.write(r.text)" + " f.write(r.text)\n", + "\n", + "if not text_example_en_path.exists():\n", + " r = requests.get(url=text_example_en)\n", + " content = io.BytesIO(r.content)\n", + " with open(\"text_example_en.pdf\", \"wb\") as f:\n", + " f.write(content.read())\n", + "\n", + "if not text_example_cn_path.exists():\n", + " r = requests.get(url=text_example_cn)\n", + " content = io.BytesIO(r.content)\n", + " with open(\"text_example_cn.pdf\", \"wb\") as f:\n", + " f.write(content.read())" ] }, { @@ -173,7 +201,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "8aff9565ac6f4c0993359ef2df59734c", + "model_id": "ed92457ad3cf42b2a22ca224141fe738", "version_major": 2, "version_minor": 0 }, @@ -214,12 +242,12 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "84cb9d80223e4cab856c3e5ea9d88ea0", + "model_id": "aad6acd73a9a40fbae5ec40195512a80", "version_major": 2, "version_minor": 0 }, "text/plain": [ - "Dropdown(description='Model:', index=10, options=('tiny-llama-1b-chat', 'gemma-2b-it', 'red-pajama-3b-chat', '…" + "Dropdown(description='Model:', index=9, options=('tiny-llama-1b-chat', 'gemma-2b-it', 'red-pajama-3b-chat', 'g…" ] }, "execution_count": 4, @@ -250,7 +278,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Selected LLM model llama-3-8b-instruct\n" + "Selected LLM model neural-chat-7b-v3-1\n" ] } ], @@ -308,7 +336,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "82f25885896749728c96d9f909f65a5a", + "model_id": "009a1f80d9e24964a084d5d31cfecccd", "version_major": 2, "version_minor": 0 }, @@ -322,7 +350,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "1731c06ddd1b4ad792516efb23b51f80", + "model_id": "f79b9054accd4501acad346d05ef3c6d", "version_major": 2, "version_minor": 0 }, @@ -336,7 +364,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "6a8bd8732be14625ba4474989c4d6545", + "model_id": "a1af239531b44c04a2cac15dacb629bd", "version_major": 2, "version_minor": 0 }, @@ -522,7 +550,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Size of model with INT4 compressed weights is 5106.56 MB\n" + "Size of model with INT4 compressed weights is 5069.90 MB\n" ] } ], @@ -562,7 +590,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "7cdeb3e1ce7c464f84c81d118c3856b8", + "model_id": "7ff9bbb6909d40968b638df90683f360", "version_major": 2, "version_minor": 0 }, @@ -648,7 +676,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "060d8facb29e4ab99ba5c5a51a36a0cd", + "model_id": "ff064eaa037440a7b22af61047422e9c", "version_major": 2, "version_minor": 0 }, @@ -741,12 +769,12 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "31871e2ec744496ca8ccfad377310c5c", + "model_id": "1448cdadd58b41fa8116605d114285ef", "version_major": 2, "version_minor": 0 }, "text/plain": [ - "Dropdown(description='Device:', options=('CPU', 'GPU.0', 'GPU.1', 'AUTO'), value='CPU')" + "Dropdown(description='Device:', options=('CPU', 'GPU', 'AUTO'), value='CPU')" ] }, "execution_count": 15, @@ -803,12 +831,12 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "1c269bd0ac424e8eb1a9c5738d1709d6", + "model_id": "321d8385fc0345498f07154637c09eb4", "version_major": 2, "version_minor": 0 }, "text/plain": [ - "Dropdown(description='Device:', options=('CPU', 'GPU.0', 'GPU.1', 'AUTO'), value='CPU')" + "Dropdown(description='Device:', options=('CPU', 'GPU', 'AUTO'), value='CPU')" ] }, "execution_count": 17, @@ -865,12 +893,12 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "889f3eb31f0d4cfaacefb453d58065df", + "model_id": "1f833b438e18488c9b9c85cb87786b26", "version_major": 2, "version_minor": 0 }, "text/plain": [ - "Dropdown(description='Device:', options=('CPU', 'GPU.0', 'GPU.1', 'AUTO'), value='CPU')" + "Dropdown(description='Device:', options=('CPU', 'GPU', 'AUTO'), value='CPU')" ] }, "execution_count": 19, @@ -941,16 +969,14 @@ "name": "stderr", "output_type": "stream", "text": [ - "2024-04-19 00:18:35.178975: I tensorflow/core/util/port.cc:111] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n", - "2024-04-19 00:18:35.181441: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used.\n", - "2024-04-19 00:18:35.212245: E tensorflow/compiler/xla/stream_executor/cuda/cuda_dnn.cc:9342] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n", - "2024-04-19 00:18:35.212267: E tensorflow/compiler/xla/stream_executor/cuda/cuda_fft.cc:609] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n", - "2024-04-19 00:18:35.212295: E tensorflow/compiler/xla/stream_executor/cuda/cuda_blas.cc:1518] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n", - "2024-04-19 00:18:35.219017: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used.\n", - "2024-04-19 00:18:35.219908: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n", + "2024-04-25 23:24:53.325545: I tensorflow/core/util/port.cc:111] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n", + "2024-04-25 23:24:53.329247: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used.\n", + "2024-04-25 23:24:53.374367: E tensorflow/compiler/xla/stream_executor/cuda/cuda_dnn.cc:9342] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n", + "2024-04-25 23:24:53.374399: E tensorflow/compiler/xla/stream_executor/cuda/cuda_fft.cc:609] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n", + "2024-04-25 23:24:53.374437: E tensorflow/compiler/xla/stream_executor/cuda/cuda_blas.cc:1518] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n", + "2024-04-25 23:24:53.385838: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n", "To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n", - "2024-04-19 00:18:36.155999: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n", - "The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable.\n", + "2024-04-25 23:24:54.133894: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n", "Compiling the model to CPU ...\n" ] }, @@ -1050,7 +1076,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "b815fe3af56542cbb08c2d06e9e9dd26", + "model_id": "42271e02cc19435f89659d127241fb1a", "version_major": 2, "version_minor": 0 }, @@ -1096,20 +1122,26 @@ "id": "f7f708db-8de1-4efd-94b2-fcabc48d52f4", "metadata": {}, "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "The argument `trust_remote_code` is to be used along with export=True. It will be ignored.\n" + ] + }, { "name": "stdout", "output_type": "stream", "text": [ - "Loading model from llama-3-8b-instruct/INT4_compressed_weights\n" + "Loading model from neural-chat-7b-v3-1/INT4_compressed_weights\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ - "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", - "The argument `trust_remote_code` is to be used along with export=True. It will be ignored.\n", - "Compiling the model to CPU ...\n" + "Compiling the model to CPU ...\n", + "Setting `pad_token_id` to `eos_token_id`:2 for open-end generation.\n" ] }, { @@ -1208,7 +1240,7 @@ "from langchain.document_loaders import (\n", " CSVLoader,\n", " EverNoteLoader,\n", - " PDFMinerLoader,\n", + " PyPDFLoader,\n", " TextLoader,\n", " UnstructuredEPubLoader,\n", " UnstructuredHTMLLoader,\n", @@ -1255,11 +1287,30 @@ " \".html\": (UnstructuredHTMLLoader, {}),\n", " \".md\": (UnstructuredMarkdownLoader, {}),\n", " \".odt\": (UnstructuredODTLoader, {}),\n", - " \".pdf\": (PDFMinerLoader, {}),\n", + " \".pdf\": (PyPDFLoader, {}),\n", " \".ppt\": (UnstructuredPowerPointLoader, {}),\n", " \".pptx\": (UnstructuredPowerPointLoader, {}),\n", " \".txt\": (TextLoader, {\"encoding\": \"utf8\"}),\n", - "}" + "}\n", + "\n", + "chinese_examples = [\n", + " [\"英特尔®酷睿™ Ultra处理器可以降低多少功耗？\"],\n", + " [\"相比英特尔之前的移动处理器产品，英特尔®酷睿™ Ultra处理器的AI推理性能提升了多少？\"],\n", + " [\"英特尔博锐® Enterprise系统提供哪些功能？\"],\n", + "]\n", + "\n", + "english_examples = [\n", + " [\"How much power consumption can Intel® Core™ Ultra Processors help save?\"],\n", + " [\"Compared to Intel’s previous mobile processor, what is the advantage of Intel® Core™ Ultra Processors for Artificial Intelligence?\"],\n", + " [\"What can Intel vPro® Enterprise systems offer?\"],\n", + "]\n", + "\n", + "if model_language.value == \"English\":\n", + " text_example_path = \"text_example_en.pdf\"\n", + "else:\n", + " text_example_path = \"text_example_cn.pdf\"\n", + "\n", + "examples = chinese_examples if (model_language.value == \"Chinese\") else english_examples" ] }, { @@ -1388,6 +1439,7 @@ "\n", " global combine_docs_chain\n", " combine_docs_chain = create_stuff_documents_chain(llm, prompt)\n", + "\n", " global rag_chain\n", " rag_chain = create_retrieval_chain(retriever, combine_docs_chain)\n", "\n", @@ -1488,6 +1540,7 @@ " with gr.Column(scale=1):\n", " docs = gr.File(\n", " label=\"Step 1: Load text files\",\n", + " value=[text_example_path],\n", " file_count=\"multiple\",\n", " file_types=[\n", " \".csv\",\n", @@ -1608,6 +1661,7 @@ " submit = gr.Button(\"Submit\")\n", " stop = gr.Button(\"Stop\")\n", " clear = gr.Button(\"Clear\")\n", + " gr.Examples(examples, inputs=msg, label=\"Click on any example and press the 'Submit' button\")\n", " retriever_argument = gr.Accordion(\"Retriever Configuration\", open=True)\n", " with retriever_argument:\n", " with gr.Row():\n", @@ -1685,11 +1739,11 @@ " queue=False,\n", " )\n", " clear.click(lambda: None, None, chatbot, queue=False)\n", - " vector_search_top_k.change(\n", + " vector_search_top_k.release(\n", " update_retriever,\n", " [vector_search_top_k, vector_rerank_top_n, do_rerank, search_method],\n", " )\n", - " vector_rerank_top_n.change(\n", + " vector_rerank_top_n.release(\n", " update_retriever,\n", " [vector_search_top_k, vector_rerank_top_n, do_rerank, search_method],\n", " )\n", @@ -1726,7 +1780,7 @@ ], "metadata": { "kernelspec": { - "display_name": "Python 3", + "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, @@ -1740,7 +1794,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.4" + "version": "3.10.12" }, "openvino_notebooks": { "imageUrl": "https://github.com/openvinotoolkit/openvino_notebooks/assets/29454499/304aa048-f10c-41c6-bb31-6d2bfdf49cf5",