yujunjun/LightRAG
1
0
Fork 0
mirror of https://github.com/HKUDS/LightRAG.git synced 2025-10-31 09:49:54 +00:00
Code Issues Packages Projects Releases Wiki Activity
LightRAG/examples/test_split_by_character.ipynb

1297 lines
57 KiB
Plaintext
Raw Normal View History

增加仅字符分割参数，如果开启，仅采用字符分割，不开启，在分割完以后如果chunk过大，会继续根据token size分割，更新测试文件
2025-01-09 11:55:49 +08:00
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "4b5690db12e34685",
"metadata": {
"ExecuteTime": {
"end_time": "2025-01-09T03:40:58.307102Z",
"start_time": "2025-01-09T03:40:51.935233Z"
}
},
"outputs": [],
"source": [
"import os\n",
"import logging\n",
"import numpy as np\n",
"from lightrag import LightRAG, QueryParam\n",
Separated llms from the main llm.py file and fixed some deprication bugs
2025-01-25 00:11:00 +01:00
"from lightrag.llm.openai import openai_complete_if_cache, openai_embed\n",
增加仅字符分割参数，如果开启，仅采用字符分割，不开启，在分割完以后如果chunk过大，会继续根据token size分割，更新测试文件
2025-01-09 11:55:49 +08:00
"from lightrag.utils import EmbeddingFunc\n",
"import nest_asyncio"
]
},
{
"cell_type": "markdown",
"id": "dd17956ec322b361",
"metadata": {},
"source": "#### split by character"
},
{
"cell_type": "code",
"execution_count": 3,
"id": "8c8ee7c061bf9159",
"metadata": {
"ExecuteTime": {
"end_time": "2025-01-09T03:41:13.961167Z",
"start_time": "2025-01-09T03:41:13.958357Z"
}
},
"outputs": [],
"source": [
"nest_asyncio.apply()\n",
"WORKING_DIR = \"../../llm_rag/paper_db/R000088_test1\"\n",
"logging.basicConfig(format=\"%(levelname)s:%(message)s\", level=logging.INFO)\n",
"if not os.path.exists(WORKING_DIR):\n",
" os.mkdir(WORKING_DIR)\n",
"API = os.environ.get(\"DOUBAO_API_KEY\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "a5009d16e0851dca",
"metadata": {
"ExecuteTime": {
"end_time": "2025-01-09T03:41:16.862036Z",
"start_time": "2025-01-09T03:41:16.859306Z"
}
},
"outputs": [],
"source": [
"async def llm_model_func(\n",
" prompt, system_prompt=None, history_messages=[], keyword_extraction=False, **kwargs\n",
") -> str:\n",
" return await openai_complete_if_cache(\n",
" \"ep-20241218114828-2tlww\",\n",
" prompt,\n",
" system_prompt=system_prompt,\n",
" history_messages=history_messages,\n",
" api_key=API,\n",
" base_url=\"https://ark.cn-beijing.volces.com/api/v3\",\n",
" **kwargs,\n",
" )\n",
"\n",
"\n",
"async def embedding_func(texts: list[str]) -> np.ndarray:\n",
Separated llms from the main llm.py file and fixed some deprication bugs
2025-01-25 00:11:00 +01:00
" return await openai_embed(\n",
增加仅字符分割参数，如果开启，仅采用字符分割，不开启，在分割完以后如果chunk过大，会继续根据token size分割，更新测试文件
2025-01-09 11:55:49 +08:00
" texts,\n",
" model=\"ep-20241231173413-pgjmk\",\n",
" api_key=API,\n",
" base_url=\"https://ark.cn-beijing.volces.com/api/v3\",\n",
" )"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "397fcad24ce4d0ed",
"metadata": {
"ExecuteTime": {
"end_time": "2025-01-09T03:41:24.950307Z",
"start_time": "2025-01-09T03:41:24.940353Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:lightrag:Logger initialized for working directory: ../../llm_rag/paper_db/R000088_test1\n",
"INFO:lightrag:Load KV llm_response_cache with 0 data\n",
"INFO:lightrag:Load KV full_docs with 0 data\n",
"INFO:lightrag:Load KV text_chunks with 0 data\n",
"INFO:nano-vectordb:Init {'embedding_dim': 4096, 'metric': 'cosine', 'storage_file': '../../llm_rag/paper_db/R000088_test1/vdb_entities.json'} 0 data\n",
"INFO:nano-vectordb:Init {'embedding_dim': 4096, 'metric': 'cosine', 'storage_file': '../../llm_rag/paper_db/R000088_test1/vdb_relationships.json'} 0 data\n",
"INFO:nano-vectordb:Init {'embedding_dim': 4096, 'metric': 'cosine', 'storage_file': '../../llm_rag/paper_db/R000088_test1/vdb_chunks.json'} 0 data\n",
"INFO:lightrag:Loaded document status storage with 0 records\n"
]
}
],
"source": [
"rag = LightRAG(\n",
" working_dir=WORKING_DIR,\n",
" llm_model_func=llm_model_func,\n",
" embedding_func=EmbeddingFunc(\n",
" embedding_dim=4096, max_token_size=8192, func=embedding_func\n",
" ),\n",
" chunk_token_size=512,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "1dc3603677f7484d",
"metadata": {
"ExecuteTime": {
"end_time": "2025-01-09T03:41:37.947456Z",
"start_time": "2025-01-09T03:41:37.941901Z"
}
},
"outputs": [],
"source": [
"with open(\n",
" \"../../llm_rag/example/R000088/auto/R000088_full_txt.md\", \"r\", encoding=\"utf-8\"\n",
") as f:\n",
" content = f.read()\n",
"\n",
"\n",
"async def embedding_func(texts: list[str]) -> np.ndarray:\n",
Separated llms from the main llm.py file and fixed some deprication bugs
2025-01-25 00:11:00 +01:00
" return await openai_embed(\n",
增加仅字符分割参数，如果开启，仅采用字符分割，不开启，在分割完以后如果chunk过大，会继续根据token size分割，更新测试文件
2025-01-09 11:55:49 +08:00
" texts,\n",
" model=\"ep-20241231173413-pgjmk\",\n",
" api_key=API,\n",
" base_url=\"https://ark.cn-beijing.volces.com/api/v3\",\n",
" )\n",
"\n",
"\n",
"async def get_embedding_dim():\n",
" test_text = [\"This is a test sentence.\"]\n",
" embedding = await embedding_func(test_text)\n",
" embedding_dim = embedding.shape[1]\n",
" return embedding_dim"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "6844202606acfbe5",
"metadata": {
"ExecuteTime": {
"end_time": "2025-01-09T03:41:39.608541Z",
"start_time": "2025-01-09T03:41:39.165057Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n"
]
}
],
"source": [
"embedding_dimension = await get_embedding_dim()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "d6273839d9681403",
"metadata": {
"ExecuteTime": {
"end_time": "2025-01-09T03:44:34.295345Z",
"start_time": "2025-01-09T03:41:48.324171Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:lightrag:Processing 1 new unique documents\n",
"Processing batch 1: 0%| | 0/1 [00:00<?, ?it/s]INFO:lightrag:Inserting 35 vectors to chunks\n",
"\n",
"Generating embeddings: 0%| | 0/2 [00:00<?, ?batch/s]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"\n",
"Generating embeddings: 50%|█████ | 1/2 [00:00<00:00, 1.36batch/s]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"\n",
"Generating embeddings: 100%|██████████| 2/2 [00:04<00:00, 2.25s/batch]\u001b[A\n",
"\n",
"Extracting entities from chunks: 0%| | 0/35 [00:00<?, ?chunk/s]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠙ Processed 1 chunks, 1 entities(duplicated), 0 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 3%|▎ | 1/35 [00:04<02:47, 4.93s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠹ Processed 2 chunks, 2 entities(duplicated), 0 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 6%|▌ | 2/35 [00:05<01:18, 2.37s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠸ Processed 3 chunks, 9 entities(duplicated), 5 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 9%|▊ | 3/35 [00:26<05:43, 10.73s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠼ Processed 4 chunks, 16 entities(duplicated), 11 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 11%|█▏ | 4/35 [00:26<03:24, 6.60s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠴ Processed 5 chunks, 24 entities(duplicated), 18 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 14%|█▍ | 5/35 [00:33<03:24, 6.82s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠦ Processed 6 chunks, 35 entities(duplicated), 28 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 17%|█▋ | 6/35 [00:42<03:38, 7.53s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠧ Processed 7 chunks, 47 entities(duplicated), 36 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 20%|██ | 7/35 [00:43<02:28, 5.31s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠇ Processed 8 chunks, 61 entities(duplicated), 49 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 23%|██▎ | 8/35 [00:45<01:52, 4.16s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠏ Processed 9 chunks, 81 entities(duplicated), 49 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠋ Processed 10 chunks, 90 entities(duplicated), 62 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 29%|██▊ | 10/35 [00:46<01:06, 2.64s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠙ Processed 11 chunks, 101 entities(duplicated), 80 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 31%|███▏ | 11/35 [00:52<01:19, 3.31s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠹ Processed 12 chunks, 108 entities(duplicated), 85 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 34%|███▍ | 12/35 [00:54<01:11, 3.12s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠸ Processed 13 chunks, 120 entities(duplicated), 100 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 37%|███▋ | 13/35 [00:59<01:18, 3.55s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠼ Processed 14 chunks, 131 entities(duplicated), 110 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 40%|████ | 14/35 [01:00<00:59, 2.82s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠴ Processed 15 chunks, 143 entities(duplicated), 110 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 43%|████▎ | 15/35 [01:02<00:52, 2.64s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠦ Processed 16 chunks, 162 entities(duplicated), 124 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 46%|████▌ | 16/35 [01:05<00:53, 2.80s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠧ Processed 17 chunks, 174 entities(duplicated), 132 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 49%|████▊ | 17/35 [01:06<00:39, 2.19s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠇ Processed 18 chunks, 185 entities(duplicated), 137 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 51%|█████▏ | 18/35 [01:12<00:53, 3.15s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠏ Processed 19 chunks, 193 entities(duplicated), 149 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 54%|█████▍ | 19/35 [01:18<01:06, 4.14s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠋ Processed 20 chunks, 205 entities(duplicated), 158 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 57%|█████▋ | 20/35 [01:19<00:50, 3.35s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠙ Processed 21 chunks, 220 entities(duplicated), 187 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 60%|██████ | 21/35 [01:27<01:02, 4.47s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠹ Processed 22 chunks, 247 entities(duplicated), 216 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 63%|██████▎ | 22/35 [01:30<00:54, 4.16s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠸ Processed 23 chunks, 260 entities(duplicated), 230 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 66%|██████▌ | 23/35 [01:34<00:48, 4.05s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠼ Processed 24 chunks, 291 entities(duplicated), 253 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 69%|██████▊ | 24/35 [01:38<00:44, 4.03s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠴ Processed 25 chunks, 304 entities(duplicated), 262 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 71%|███████▏ | 25/35 [01:41<00:36, 3.67s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠦ Processed 26 chunks, 313 entities(duplicated), 271 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 74%|███████▍ | 26/35 [01:41<00:24, 2.76s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠧ Processed 27 chunks, 321 entities(duplicated), 283 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 77%|███████▋ | 27/35 [01:47<00:28, 3.52s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠇ Processed 28 chunks, 333 entities(duplicated), 290 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 80%|████████ | 28/35 [01:52<00:28, 4.08s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠏ Processed 29 chunks, 348 entities(duplicated), 307 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 83%|████████▎ | 29/35 [01:59<00:29, 4.88s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠋ Processed 30 chunks, 362 entities(duplicated), 329 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 86%|████████▌ | 30/35 [02:02<00:21, 4.29s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠙ Processed 31 chunks, 373 entities(duplicated), 337 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 89%|████████▊ | 31/35 [02:03<00:13, 3.28s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠹ Processed 32 chunks, 390 entities(duplicated), 369 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 91%|█████████▏| 32/35 [02:03<00:07, 2.55s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠸ Processed 33 chunks, 405 entities(duplicated), 378 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 94%|█████████▍| 33/35 [02:07<00:05, 2.84s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠼ Processed 34 chunks, 435 entities(duplicated), 395 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 97%|█████████▋| 34/35 [02:10<00:02, 2.94s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠴ Processed 35 chunks, 456 entities(duplicated), 440 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 100%|██████████| 35/35 [02:23<00:00, 4.10s/chunk]\u001b[A\n",
"INFO:lightrag:Inserting entities into storage...\n",
"\n",
"Inserting entities: 100%|██████████| 324/324 [00:00<00:00, 17456.96entity/s]\n",
"INFO:lightrag:Inserting relationships into storage...\n",
"\n",
"Inserting relationships: 100%|██████████| 427/427 [00:00<00:00, 29956.31relationship/s]\n",
"INFO:lightrag:Inserting 324 vectors to entities\n",
"\n",
"Generating embeddings: 0%| | 0/11 [00:00<?, ?batch/s]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"\n",
"Generating embeddings: 9%|▉ | 1/11 [00:00<00:06, 1.48batch/s]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"\n",
"Generating embeddings: 18%|█▊ | 2/11 [00:02<00:11, 1.25s/batch]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"\n",
"Generating embeddings: 27%|██▋ | 3/11 [00:02<00:06, 1.17batch/s]\u001b[A\n",
"Generating embeddings: 36%|███▋ | 4/11 [00:03<00:04, 1.50batch/s]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"\n",
"Generating embeddings: 45%|████▌ | 5/11 [00:03<00:03, 1.78batch/s]\u001b[A\n",
"Generating embeddings: 55%|█████▍ | 6/11 [00:03<00:02, 2.01batch/s]\u001b[A\n",
"Generating embeddings: 64%|██████▎ | 7/11 [00:04<00:01, 2.19batch/s]\u001b[A\n",
"Generating embeddings: 73%|███████▎ | 8/11 [00:04<00:01, 2.31batch/s]\u001b[A\n",
"Generating embeddings: 82%|████████▏ | 9/11 [00:04<00:00, 2.41batch/s]\u001b[A\n",
"Generating embeddings: 91%|█████████ | 10/11 [00:05<00:00, 2.48batch/s]\u001b[A\n",
"Generating embeddings: 100%|██████████| 11/11 [00:05<00:00, 1.91batch/s]\u001b[A\n",
"INFO:lightrag:Inserting 427 vectors to relationships\n",
"\n",
"Generating embeddings: 0%| | 0/14 [00:00<?, ?batch/s]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"\n",
"Generating embeddings: 7%|▋ | 1/14 [00:01<00:14, 1.11s/batch]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"\n",
"Generating embeddings: 14%|█▍ | 2/14 [00:02<00:14, 1.18s/batch]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"\n",
"Generating embeddings: 21%|██▏ | 3/14 [00:02<00:08, 1.23batch/s]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"\n",
"Generating embeddings: 29%|██▊ | 4/14 [00:03<00:06, 1.56batch/s]\u001b[A\n",
"Generating embeddings: 36%|███▌ | 5/14 [00:03<00:04, 1.85batch/s]\u001b[A\n",
"Generating embeddings: 43%|████▎ | 6/14 [00:03<00:03, 2.05batch/s]\u001b[A\n",
"Generating embeddings: 50%|█████ | 7/14 [00:04<00:03, 2.23batch/s]\u001b[A\n",
"Generating embeddings: 57%|█████▋ | 8/14 [00:04<00:02, 2.37batch/s]\u001b[A\n",
"Generating embeddings: 64%|██████▍ | 9/14 [00:04<00:02, 2.46batch/s]\u001b[A\n",
"Generating embeddings: 71%|███████▏ | 10/14 [00:05<00:01, 2.54batch/s]\u001b[A\n",
"Generating embeddings: 79%|███████▊ | 11/14 [00:05<00:01, 2.59batch/s]\u001b[A\n",
"Generating embeddings: 86%|████████▌ | 12/14 [00:06<00:00, 2.64batch/s]\u001b[A\n",
"Generating embeddings: 93%|█████████▎| 13/14 [00:06<00:00, 2.65batch/s]\u001b[A\n",
"Generating embeddings: 100%|██████████| 14/14 [00:06<00:00, 2.05batch/s]\u001b[A\n",
"INFO:lightrag:Writing graph with 333 nodes, 427 edges\n",
"Processing batch 1: 100%|██████████| 1/1 [02:45<00:00, 165.90s/it]\n"
]
}
],
"source": [
"# rag.insert(content)\n",
"rag.insert(content, split_by_character=\"\\n#\")"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "c4f9ae517151a01d",
"metadata": {
"ExecuteTime": {
"end_time": "2025-01-09T03:45:11.668987Z",
"start_time": "2025-01-09T03:45:11.664744Z"
}
},
"outputs": [],
"source": [
"prompt1 = \"\"\"你是一名经验丰富的论文分析科学家，你的任务是对一篇英文学术研究论文进行关键信息提取并深入分析。\n",
"请按照以下步骤进行分析：\n",
"1. 该文献主要研究的问题是什么？\n",
"2. 该文献采用什么方法进行分析？\n",
"3. 该文献的主要结论是什么？\n",
"首先在<分析>标签中，针对每个问题详细分析你的思考过程。然后在<回答>标签中给出所有问题的最终答案。\"\"\""
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "7a6491385b050095",
"metadata": {
"ExecuteTime": {
"end_time": "2025-01-09T03:45:40.829111Z",
"start_time": "2025-01-09T03:45:13.530298Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:lightrag:Local query uses 5 entites, 12 relations, 3 text units\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:lightrag:Global query uses 8 entites, 5 relations, 4 text units\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"<分析>\n",
"1. **该文献主要研究的问题是什么？**\n",
" - 思考过程：通过浏览论文内容，查找作者明确阐述研究目的的部分。文中多处提及“Our study was performed to explore whether folic acid treatment was associated with cancer outcomes and all-cause mortality after extended follow-up”，表明作者旨在探究叶酸治疗与癌症结局及全因死亡率之间的关系，尤其是在经过长期随访后。\n",
"2. **该文献采用什么方法进行分析？**\n",
" - 思考过程：寻找描述研究方法和数据分析过程的段落。文中提到“Survival curves were constructed using the Kaplan-Meier method and differences in survival between groups were analyzed using the log-rank test. Estimates of hazard ratios (HRs) with 95% CIs were obtained by using Cox proportional hazards regression models stratified by trial”，可以看出作者使用了Kaplan-Meier法构建生存曲线、log-rank检验分析组间生存差异以及Cox比例风险回归模型估计风险比等方法。\n",
"3. **该文献的主要结论是什么？**\n",
" - 思考过程：定位到论文中总结结论的部分，如“Conclusion Treatment with folic acid plus vitamin $\\mathsf{B}_{12}$ was associated with increased cancer outcomes and all-cause mortality in patients with ischemic heart disease in Norway, where there is no folic acid fortification of foods”，可知作者得出叶酸加维生素$\\mathsf{B}_{12}$治疗与癌症结局和全因死亡率增加有关的结论。\n",
"<回答>\n",
"1. 该文献主要研究的问题是：叶酸治疗与癌症结局及全因死亡率之间的关系，尤其是在经过长期随访后，叶酸治疗是否与癌症结局和全因死亡率相关。\n",
"2. 该文献采用的分析方法包括：使用Kaplan-Meier法构建生存曲线、log-rank检验分析组间生存差异、Cox比例风险回归模型估计风险比等。\n",
"3. 该文献的主要结论是：在挪威没有叶酸强化食品的情况下，叶酸加维生素$\\mathsf{B}_{12}$治疗与缺血性心脏病患者的癌症结局和全因死亡率增加有关。\n",
"\n",
"**参考文献**\n",
"- [VD] In2Norwegianhomocysteine-lowering trialsamongpatientswithischemicheart disease, there was a statistically nonsignificantincreaseincancerincidenceinthe groupsassignedtofolicacidtreatment.15,16 Our study was performed to explore whetherfolicacidtreatmentwasassociatedwithcanceroutcomesandall-cause mortality after extended follow-up.\n",
"- [VD] Survivalcurveswereconstructedusing theKaplan-Meiermethodanddifferences insurvivalbetweengroupswereanalyzed usingthelog-ranktest.Estimatesofhazard ratios (HRs) with $95\\%$ CIs were obtainedbyusingCoxproportionalhazards regressionmodelsstratifiedbytrial.\n",
"- [VD] Conclusion Treatment with folic acid plus vitamin $\\mathsf{B}_{12}$ was associated with increased cancer outcomes and all-cause mortality in patients with ischemic heart disease in Norway, where there is no folic acid fortification of foods.\n"
]
}
],
"source": [
"resp = rag.query(prompt1, param=QueryParam(mode=\"mix\", top_k=5))\n",
"print(resp)"
]
},
{
"cell_type": "markdown",
"id": "4e5bfad24cb721a8",
"metadata": {},
"source": "#### split by character only"
},
{
"cell_type": "code",
"execution_count": 11,
"id": "44e2992dc95f8ce0",
"metadata": {
"ExecuteTime": {
"end_time": "2025-01-09T03:47:40.988796Z",
"start_time": "2025-01-09T03:47:40.982648Z"
}
},
"outputs": [],
"source": [
"WORKING_DIR = \"../../llm_rag/paper_db/R000088_test2\"\n",
"if not os.path.exists(WORKING_DIR):\n",
" os.mkdir(WORKING_DIR)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "62c63385d2d973d5",
"metadata": {
"ExecuteTime": {
"end_time": "2025-01-09T03:51:39.951329Z",
"start_time": "2025-01-09T03:49:15.218976Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:lightrag:Logger initialized for working directory: ../../llm_rag/paper_db/R000088_test2\n",
"INFO:lightrag:Load KV llm_response_cache with 0 data\n",
"INFO:lightrag:Load KV full_docs with 0 data\n",
"INFO:lightrag:Load KV text_chunks with 0 data\n",
"INFO:nano-vectordb:Init {'embedding_dim': 4096, 'metric': 'cosine', 'storage_file': '../../llm_rag/paper_db/R000088_test2/vdb_entities.json'} 0 data\n",
"INFO:nano-vectordb:Init {'embedding_dim': 4096, 'metric': 'cosine', 'storage_file': '../../llm_rag/paper_db/R000088_test2/vdb_relationships.json'} 0 data\n",
"INFO:nano-vectordb:Init {'embedding_dim': 4096, 'metric': 'cosine', 'storage_file': '../../llm_rag/paper_db/R000088_test2/vdb_chunks.json'} 0 data\n",
"INFO:lightrag:Loaded document status storage with 0 records\n",
"INFO:lightrag:Processing 1 new unique documents\n",
"Processing batch 1: 0%| | 0/1 [00:00<?, ?it/s]INFO:lightrag:Inserting 12 vectors to chunks\n",
"\n",
"Generating embeddings: 0%| | 0/1 [00:00<?, ?batch/s]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"\n",
"Generating embeddings: 100%|██████████| 1/1 [00:02<00:00, 2.95s/batch]\u001b[A\n",
"\n",
"Extracting entities from chunks: 0%| | 0/12 [00:00<?, ?chunk/s]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠙ Processed 1 chunks, 0 entities(duplicated), 0 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 8%|▊ | 1/12 [00:03<00:43, 3.93s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠹ Processed 2 chunks, 8 entities(duplicated), 8 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 17%|█▋ | 2/12 [00:29<02:44, 16.46s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠸ Processed 3 chunks, 17 entities(duplicated), 15 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 25%|██▌ | 3/12 [00:30<01:25, 9.45s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠼ Processed 4 chunks, 27 entities(duplicated), 22 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 33%|███▎ | 4/12 [00:39<01:16, 9.52s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠴ Processed 5 chunks, 36 entities(duplicated), 33 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 42%|████▏ | 5/12 [00:40<00:43, 6.24s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠦ Processed 6 chunks, 49 entities(duplicated), 42 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 50%|█████ | 6/12 [00:49<00:43, 7.33s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠧ Processed 7 chunks, 62 entities(duplicated), 65 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 58%|█████▊ | 7/12 [01:05<00:50, 10.05s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠇ Processed 8 chunks, 81 entities(duplicated), 90 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 67%|██████▋ | 8/12 [01:23<00:50, 12.69s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠏ Processed 9 chunks, 99 entities(duplicated), 117 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 75%|███████▌ | 9/12 [01:32<00:34, 11.54s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠋ Processed 10 chunks, 123 entities(duplicated), 140 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 83%|████████▎ | 10/12 [01:48<00:25, 12.79s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠙ Processed 11 chunks, 158 entities(duplicated), 174 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 92%|█████████▏| 11/12 [02:03<00:13, 13.50s/chunk]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"⠹ Processed 12 chunks, 194 entities(duplicated), 221 relations(duplicated)\r"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Extracting entities from chunks: 100%|██████████| 12/12 [02:13<00:00, 11.15s/chunk]\u001b[A\n",
"INFO:lightrag:Inserting entities into storage...\n",
"\n",
"Inserting entities: 100%|██████████| 170/170 [00:00<00:00, 11610.25entity/s]\n",
"INFO:lightrag:Inserting relationships into storage...\n",
"\n",
"Inserting relationships: 100%|██████████| 218/218 [00:00<00:00, 15913.51relationship/s]\n",
"INFO:lightrag:Inserting 170 vectors to entities\n",
"\n",
"Generating embeddings: 0%| | 0/6 [00:00<?, ?batch/s]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"\n",
"Generating embeddings: 17%|█▋ | 1/6 [00:01<00:05, 1.10s/batch]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"\n",
"Generating embeddings: 33%|███▎ | 2/6 [00:02<00:04, 1.07s/batch]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"\n",
"Generating embeddings: 50%|█████ | 3/6 [00:02<00:02, 1.33batch/s]\u001b[A\n",
"Generating embeddings: 67%|██████▋ | 4/6 [00:02<00:01, 1.67batch/s]\u001b[A\n",
"Generating embeddings: 83%|████████▎ | 5/6 [00:03<00:00, 1.95batch/s]\u001b[A\n",
"Generating embeddings: 100%|██████████| 6/6 [00:03<00:00, 1.66batch/s]\u001b[A\n",
"INFO:lightrag:Inserting 218 vectors to relationships\n",
"\n",
"Generating embeddings: 0%| | 0/7 [00:00<?, ?batch/s]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"\n",
"Generating embeddings: 14%|█▍ | 1/7 [00:01<00:10, 1.74s/batch]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"\n",
"Generating embeddings: 29%|██▊ | 2/7 [00:02<00:05, 1.04s/batch]\u001b[A\n",
"Generating embeddings: 43%|████▎ | 3/7 [00:02<00:02, 1.35batch/s]\u001b[A\n",
"Generating embeddings: 57%|█████▋ | 4/7 [00:03<00:01, 1.69batch/s]\u001b[AINFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"\n",
"Generating embeddings: 71%|███████▏ | 5/7 [00:03<00:01, 1.96batch/s]\u001b[A\n",
"Generating embeddings: 86%|████████▌ | 6/7 [00:03<00:00, 2.17batch/s]\u001b[A\n",
"Generating embeddings: 100%|██████████| 7/7 [00:04<00:00, 1.68batch/s]\u001b[A\n",
"INFO:lightrag:Writing graph with 174 nodes, 218 edges\n",
"Processing batch 1: 100%|██████████| 1/1 [02:24<00:00, 144.69s/it]\n"
]
}
],
"source": [
"rag = LightRAG(\n",
" working_dir=WORKING_DIR,\n",
" llm_model_func=llm_model_func,\n",
" embedding_func=EmbeddingFunc(\n",
" embedding_dim=4096, max_token_size=8192, func=embedding_func\n",
" ),\n",
" chunk_token_size=512,\n",
")\n",
"\n",
"# rag.insert(content)\n",
"rag.insert(content, split_by_character=\"\\n#\", split_by_character_only=True)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "3c7aa9836d8d43c7",
"metadata": {
"ExecuteTime": {
"end_time": "2025-01-09T03:52:37.000418Z",
"start_time": "2025-01-09T03:52:09.933584Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:lightrag:Local query uses 5 entites, 3 relations, 2 text units\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/embeddings \"HTTP/1.1 200 OK\"\n",
"INFO:lightrag:Global query uses 9 entites, 5 relations, 4 text units\n",
"INFO:httpx:HTTP Request: POST https://ark.cn-beijing.volces.com/api/v3/chat/completions \"HTTP/1.1 200 OK\"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"<分析>\n",
"- **该文献主要研究的问题是什么？**\n",
" - **思考过程**：通过浏览论文的标题、摘要、引言等部分，寻找关于研究目的和问题的描述。论文标题为“Cancer Incidence and Mortality After Treatment With Folic Acid and Vitamin B12”，摘要中的“Objective”部分明确指出研究目的是“To evaluate effects of treatment with B vitamins on cancer outcomes and all-cause mortality in 2 randomized controlled trials”。因此，可以确定该文献主要研究的问题是评估B族维生素治疗对两项随机对照试验中癌症结局和全因死亡率的影响。\n",
"- **该文献采用什么方法进行分析？**\n",
" - **思考过程**：在论文的“METHODS”部分详细描述了研究方法。文中提到这是一个对两项随机、双盲、安慰剂对照临床试验（Norwegian Vitamin [NORVIT] trial和Western Norway B Vitamin Intervention Trial [WENBIT]）数据的联合分析，并进行了观察性的试验后随访。具体包括对参与者进行分组干预（不同剂量的叶酸、维生素B12、维生素B6或安慰剂），收集临床信息和血样，分析循环B族维生素、同型半胱氨酸和可替宁等指标，并进行基因分型等，还涉及到多种统计分析方法，如计算预期癌症发生率、构建生存曲线、进行Cox比例风险回归模型分析等。\n",
"- **该文献的主要结论是什么？**\n",
" - **思考过程**：在论文的“Results”和“Conclusion”部分寻找主要结论。研究结果表明，在治疗期间，接受叶酸加维生素B12治疗的参与者血清叶酸浓度显著增加，且在后续随访中，该组癌症发病率、癌症死亡率和全因死亡率均有所上升，主要是肺癌发病率增加，而维生素B6治疗未显示出显著影响。结论部分明确指出“Treatment with folic acid plus vitamin $\\mathsf{B}_{12}$ was associated with increased cancer outcomes and all-cause mortality in patients with ischemic heart disease in Norway, where there is no folic acid fortification of foods”。\n",
"</分析>\n",
"\n",
"<回答>\n",
"- **主要研究问题**：评估B族维生素治疗对两项随机对照试验中癌症结局和全因死亡率的影响。\n",
"- **研究方法**：采用对两项随机、双盲、安慰剂对照临床试验（Norwegian Vitamin [NORVIT] trial和Western Norway B Vitamin Intervention Trial [WENBIT]）数据的联合分析，并进行观察性的试验后随访，涉及分组干预、多种指标检测以及多种统计分析方法。\n",
"- **主要结论**：在挪威（食品中未添加叶酸），对于缺血性心脏病患者，叶酸加维生素B12治疗与癌症结局和全因死亡率的增加有关，而维生素B6治疗未显示出显著影响。\n",
"\n",
"**参考文献**\n",
"- [VD] Cancer Incidence and Mortality After Treatment With Folic Acid and Vitamin B12\n",
"- [VD] METHODS Study Design, Participants, and Study Intervention\n",
"- [VD] RESULTS\n",
"- [VD] Conclusion\n",
"- [VD] Objective To evaluate effects of treatment with B vitamins on cancer outcomes and all-cause mortality in 2 randomized controlled trials.\n"
]
}
],
"source": [
"resp = rag.query(prompt1, param=QueryParam(mode=\"mix\", top_k=5))\n",
"print(resp)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7ba6fa79a2550d10",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.6"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Reference in New Issue Copy Permalink