328 lines
11 KiB
Plaintext
328 lines
11 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 5,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# 创建批处理xlsx文件\n",
|
||
"\n",
|
||
"import pandas as pd\n",
|
||
"\n",
|
||
"customid = 1\n",
|
||
"method = \"POST\"\n",
|
||
"url = \"/v4/chat/completions\"\n",
|
||
"model = \"glm-4\"\n",
|
||
"role = \"system\"\n",
|
||
"instruction = \"你是生命周期领域富有经验和知识的专家。根据你所掌握的知识回答问题；不要列出几点来回答，不需要换行，只需要用1句话回答问题。\"\n",
|
||
"\n",
|
||
"temperature = 0.95\n",
|
||
"top_p = 0.7\n",
|
||
"max_tokens = 4096\n",
|
||
"\n",
|
||
"df = pd.DataFrame(columns=[\"custom_id\",\"method\",\"url\",\"model\",\"role\",\"content\",\"role1\",\"content1\",\"temperature\",\"top_p\",\"max_tokens\"])\n",
|
||
" "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 4,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"question = []\n",
|
||
"with open(\"/home/zhangxj/WorkFile/LCA-GPT/QA/filters/question.txt\",\"r\",encoding=\"utf-8\") as file:\n",
|
||
" for line in file.readlines():\n",
|
||
" question.append(line.strip())"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 12,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"data = []\n",
|
||
"for ques in question:\n",
|
||
" row = {\n",
|
||
" \"custom_id\": f\"request-{customid}\",\n",
|
||
" \"method\":method,\n",
|
||
" \"url\":url,\n",
|
||
" \"model\":model,\n",
|
||
" \"role\":role,\n",
|
||
" \"content\":instruction,\n",
|
||
" \"role1\":\"user\",\n",
|
||
" \"content1\":ques,\n",
|
||
" \"temperature\":temperature,\n",
|
||
" \"top_p\":top_p,\n",
|
||
" \"max_tokens\":max_tokens\n",
|
||
" }\n",
|
||
" data.append(row)\n",
|
||
" customid+=1"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 13,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"3933"
|
||
]
|
||
},
|
||
"execution_count": 13,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"len(data)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 14,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"df = pd.DataFrame(data)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 15,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<div>\n",
|
||
"<style scoped>\n",
|
||
" .dataframe tbody tr th:only-of-type {\n",
|
||
" vertical-align: middle;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe tbody tr th {\n",
|
||
" vertical-align: top;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe thead th {\n",
|
||
" text-align: right;\n",
|
||
" }\n",
|
||
"</style>\n",
|
||
"<table border=\"1\" class=\"dataframe\">\n",
|
||
" <thead>\n",
|
||
" <tr style=\"text-align: right;\">\n",
|
||
" <th></th>\n",
|
||
" <th>custom_id</th>\n",
|
||
" <th>method</th>\n",
|
||
" <th>url</th>\n",
|
||
" <th>model</th>\n",
|
||
" <th>role</th>\n",
|
||
" <th>content</th>\n",
|
||
" <th>role1</th>\n",
|
||
" <th>content1</th>\n",
|
||
" <th>temperature</th>\n",
|
||
" <th>top_p</th>\n",
|
||
" <th>max_tokens</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>request-1</td>\n",
|
||
" <td>POST</td>\n",
|
||
" <td>/v4/chat/completions</td>\n",
|
||
" <td>glm-4</td>\n",
|
||
" <td>system</td>\n",
|
||
" <td>你是生命周期领域富有经验和知识的专家。根据你所掌握的知识回答问题；不要列出几点来回答，不需要...</td>\n",
|
||
" <td>user</td>\n",
|
||
" <td>什么是生命周期分析（LCA）的主要目标？</td>\n",
|
||
" <td>0.95</td>\n",
|
||
" <td>0.7</td>\n",
|
||
" <td>4096</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>request-2</td>\n",
|
||
" <td>POST</td>\n",
|
||
" <td>/v4/chat/completions</td>\n",
|
||
" <td>glm-4</td>\n",
|
||
" <td>system</td>\n",
|
||
" <td>你是生命周期领域富有经验和知识的专家。根据你所掌握的知识回答问题；不要列出几点来回答，不需要...</td>\n",
|
||
" <td>user</td>\n",
|
||
" <td>在LCA中，如何确定研究的范围？</td>\n",
|
||
" <td>0.95</td>\n",
|
||
" <td>0.7</td>\n",
|
||
" <td>4096</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>request-3</td>\n",
|
||
" <td>POST</td>\n",
|
||
" <td>/v4/chat/completions</td>\n",
|
||
" <td>glm-4</td>\n",
|
||
" <td>system</td>\n",
|
||
" <td>你是生命周期领域富有经验和知识的专家。根据你所掌握的知识回答问题；不要列出几点来回答，不需要...</td>\n",
|
||
" <td>user</td>\n",
|
||
" <td>医疗废物如何处理？</td>\n",
|
||
" <td>0.95</td>\n",
|
||
" <td>0.7</td>\n",
|
||
" <td>4096</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>request-4</td>\n",
|
||
" <td>POST</td>\n",
|
||
" <td>/v4/chat/completions</td>\n",
|
||
" <td>glm-4</td>\n",
|
||
" <td>system</td>\n",
|
||
" <td>你是生命周期领域富有经验和知识的专家。根据你所掌握的知识回答问题；不要列出几点来回答，不需要...</td>\n",
|
||
" <td>user</td>\n",
|
||
" <td>LCA数据清单收集阶段需要哪些信息？</td>\n",
|
||
" <td>0.95</td>\n",
|
||
" <td>0.7</td>\n",
|
||
" <td>4096</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4</th>\n",
|
||
" <td>request-5</td>\n",
|
||
" <td>POST</td>\n",
|
||
" <td>/v4/chat/completions</td>\n",
|
||
" <td>glm-4</td>\n",
|
||
" <td>system</td>\n",
|
||
" <td>你是生命周期领域富有经验和知识的专家。根据你所掌握的知识回答问题；不要列出几点来回答，不需要...</td>\n",
|
||
" <td>user</td>\n",
|
||
" <td>生命周期影响评价阶段的目标是什么？</td>\n",
|
||
" <td>0.95</td>\n",
|
||
" <td>0.7</td>\n",
|
||
" <td>4096</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" custom_id method url model role \\\n",
|
||
"0 request-1 POST /v4/chat/completions glm-4 system \n",
|
||
"1 request-2 POST /v4/chat/completions glm-4 system \n",
|
||
"2 request-3 POST /v4/chat/completions glm-4 system \n",
|
||
"3 request-4 POST /v4/chat/completions glm-4 system \n",
|
||
"4 request-5 POST /v4/chat/completions glm-4 system \n",
|
||
"\n",
|
||
" content role1 \\\n",
|
||
"0 你是生命周期领域富有经验和知识的专家。根据你所掌握的知识回答问题；不要列出几点来回答，不需要... user \n",
|
||
"1 你是生命周期领域富有经验和知识的专家。根据你所掌握的知识回答问题；不要列出几点来回答，不需要... user \n",
|
||
"2 你是生命周期领域富有经验和知识的专家。根据你所掌握的知识回答问题；不要列出几点来回答，不需要... user \n",
|
||
"3 你是生命周期领域富有经验和知识的专家。根据你所掌握的知识回答问题；不要列出几点来回答，不需要... user \n",
|
||
"4 你是生命周期领域富有经验和知识的专家。根据你所掌握的知识回答问题；不要列出几点来回答，不需要... user \n",
|
||
"\n",
|
||
" content1 temperature top_p max_tokens \n",
|
||
"0 什么是生命周期分析（LCA）的主要目标？ 0.95 0.7 4096 \n",
|
||
"1 在LCA中，如何确定研究的范围？ 0.95 0.7 4096 \n",
|
||
"2 医疗废物如何处理？ 0.95 0.7 4096 \n",
|
||
"3 LCA数据清单收集阶段需要哪些信息？ 0.95 0.7 4096 \n",
|
||
"4 生命周期影响评价阶段的目标是什么？ 0.95 0.7 4096 "
|
||
]
|
||
},
|
||
"execution_count": 15,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"df.head()\n",
|
||
"\n",
|
||
"# \"custom_id\",\"method\",\"url\",\"model\",\"role\",\"content\",\"role1\",\"content1\",\"temperature\",\"top_p\",\"max_tokens\"])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 16,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"df.to_excel(\"/home/zhangxj/WorkFile/LCA-GPT/QA/questionForBatch.xlsx\",index=False)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 20,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Batch(id='batch_1823353255129645056', completion_window='24h', created_at=1723556266945, endpoint='/v4/chat/completions', input_file_id='1723556210_f79e4160ab3840b4b02f44c821d27752', object='batch', status='validating', cancelled_at=None, cancelling_at=None, completed_at=None, error_file_id=None, errors=None, expired_at=None, expires_at=None, failed_at=None, finalizing_at=None, in_progress_at=None, metadata={'description': '回答问题'}, output_file_id=None, request_counts=BatchRequestCounts(completed=None, failed=None, total=3933))\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from zhipuai import ZhipuAI\n",
|
||
" \n",
|
||
"client = ZhipuAI(api_key=\"434790cf952335f18b6347e7b6de9777.V50p55zfk8Ye4ojV\") # 填写您自己的APIKey\n",
|
||
"\n",
|
||
"create = client.batches.create(\n",
|
||
" input_file_id=\"1723556210_f79e4160ab3840b4b02f44c821d27752\",\n",
|
||
" endpoint=\"/v4/chat/completions\", \n",
|
||
" completion_window=\"24h\", #完成时间只支持 24 小时\n",
|
||
" metadata={\n",
|
||
" \"description\": \"回答问题\"\n",
|
||
" }\n",
|
||
")\n",
|
||
"print(create)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 21,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Batch(id=None, completion_window=None, created_at=None, endpoint=None, input_file_id=None, object=None, status=None, cancelled_at=None, cancelling_at=None, completed_at=None, error_file_id=None, errors=None, expired_at=None, expires_at=None, failed_at=None, finalizing_at=None, in_progress_at=None, metadata=None, output_file_id=None, request_counts=None)\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"batch_job = client.batches.retrieve(\"batch_id\")\n",
|
||
"print(batch_job)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": []
|
||
}
|
||
],
|
||
"metadata": {
|
||
"kernelspec": {
|
||
"display_name": "Qwen",
|
||
"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": "3.10.14"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 2
|
||
}
|