{"id":50749,"date":"2024-12-03T11:39:07","date_gmt":"2024-12-03T03:39:07","guid":{"rendered":"https:\/\/fwq.ai\/blog\/50749\/"},"modified":"2024-12-03T11:39:07","modified_gmt":"2024-12-03T03:39:07","slug":"%e5%b0%86%e6%95%b0%e6%8d%ae%e5%8a%a0%e8%bd%bd%e5%88%b0-neo4j-%e4%b8%ad","status":"publish","type":"post","link":"https:\/\/fwq.ai\/blog\/50749\/","title":{"rendered":"\u5c06\u6570\u636e\u52a0\u8f7d\u5230 Neo4j \u4e2d"},"content":{"rendered":"<p><b><\/b>     <\/p>\n<h1>\u5c06\u6570\u636e\u52a0\u8f7d\u5230 Neo4j \u4e2d<\/h1>\n<p>\u5927\u5bb6\u597d\uff0c\u6211\u4eec\u53c8\u89c1\u9762\u4e86\u554a~\u672c\u6587<span style=\"color: #FF6600;, Helvetica, Arial, sans-serif;font-size: 14px;background-color: #FFFFFF\">\u300a\u5c06\u6570\u636e\u52a0\u8f7d\u5230 Neo4j \u4e2d\u300b<\/span>\u7684\u5185\u5bb9\u4e2d\u5c06\u4f1a\u6d89\u53ca\u5230<span style=\"color: #FF6600;, Helvetica, Arial, sans-serif;font-size: 14px;background-color: #FFFFFF\"><\/span>\u7b49\u7b49\u3002\u5982\u679c\u4f60\u6b63\u5728\u5b66\u4e60<span style=\"color: #FF6600;, Helvetica, Arial, sans-serif;font-size: 14px;background-color: #FFFFFF\">\u6587\u7ae0<\/span>\u76f8\u5173\u77e5\u8bc6\uff0c\u6b22\u8fce\u5173\u6ce8\u6211\uff0c\u4ee5\u540e\u4f1a\u7ed9\u5927\u5bb6\u5e26\u6765\u66f4\u591a<span style=\"color: #FF6600;, Helvetica, Arial, sans-serif;font-size: 14px;background-color: #FFFFFF\">\u6587\u7ae0<\/span>\u76f8\u5173\u6587\u7ae0\uff0c\u5e0c\u671b\u6211\u4eec\u80fd\u4e00\u8d77\u8fdb\u6b65\uff01\u4e0b\u9762\u5c31\u5f00\u59cb\u672c\u6587\u7684\u6b63\u5f0f\u5185\u5bb9~<\/p>\n<p>\u5728\u4e0a\u4e00\u7bc7\u535a\u5ba2\u4e2d\uff0c\u6211\u4eec\u4e86\u89e3\u4e86\u5982\u4f55\u4f7f\u7528 2 \u4e2a\u63d2\u4ef6 apoc \u548c\u56fe\u5f62\u6570\u636e\u79d1\u5b66\u5e93 &#8211; gds \u5728\u672c\u5730\u5b89\u88c5\u548c\u8bbe\u7f6e neo4j\u3002\u5728\u8fd9\u7bc7\u535a\u5ba2\u4e2d\uff0c\u6211\u5c06\u83b7\u53d6\u4e00\u4e2a\u73a9\u5177\u6570\u636e\u96c6\uff08\u7535\u5b50\u5546\u52a1\u7f51\u7ad9\u4e2d\u7684\u4ea7\u54c1\uff09\u5e76\u5c06\u5176\u5b58\u50a8\u5728 neo4j \u4e2d\u3002<\/p>\n<p>&nbsp;<\/p>\n<p>\u5728\u5f00\u59cb\u52a0\u8f7d\u6570\u636e\u4e4b\u524d\uff0c\u5982\u679c\u60a8\u7684\u7528\u4f8b\u4e2d\u6709\u5927\u91cf\u6570\u636e\uff0c\u8bf7\u786e\u4fdd\u4e3a neo4j \u5206\u914d\u4e86\u8db3\u591f\u7684\u5185\u5b58\u3002\u4e3a\u6b64\uff1a<\/p>\n<ul>\n<li>\u70b9\u51fb\u6253\u5f00\u53f3\u4fa7\u7684<strong>\u4e09\u4e2a\u70b9<\/strong> <\/li>\n<\/ul>\n<p><img decoding=\"async\" src=\"https:\/\/www.17golang.com\/uploads\/20241127\/173267341367467f859ba9b.png\" class=\"aligncenter\" title=\"\u5c06\u6570\u636e\u52a0\u8f7d\u5230 Neo4j \u4e2d\u63d2\u56fe\" alt=\"\u5c06\u6570\u636e\u52a0\u8f7d\u5230 Neo4j \u4e2d\u63d2\u56fe\" \/><\/p>\n<ul>\n  \u70b9\u51fb <\/p>\n<li>\u6253\u5f00\u6587\u4ef6\u5939<strong>-&gt; <\/strong>\u914d\u7f6e<strong> <\/strong> <\/li>\n<\/ul>\n<p><img decoding=\"async\" src=\"https:\/\/www.17golang.com\/uploads\/20241127\/173267341467467f86b608a.png\" class=\"aligncenter\" title=\"\u5c06\u6570\u636e\u52a0\u8f7d\u5230 Neo4j \u4e2d\u63d2\u56fe1\" alt=\"\u5c06\u6570\u636e\u52a0\u8f7d\u5230 Neo4j \u4e2d\u63d2\u56fe1\" \/><\/p>\n<ul>\n  \u70b9\u51fb <\/p>\n<li>neo4j.conf<strong> <\/strong> <\/li>\n<\/ul>\n<p><img decoding=\"async\" src=\"https:\/\/www.17golang.com\/uploads\/20241127\/173267341667467f882754b.png\" class=\"aligncenter\" title=\"\u5c06\u6570\u636e\u52a0\u8f7d\u5230 Neo4j \u4e2d\u63d2\u56fe2\" alt=\"\u5c06\u6570\u636e\u52a0\u8f7d\u5230 Neo4j \u4e2d\u63d2\u56fe2\" \/><\/p>\n<ul>\n  \u5728neo4j.conf\u4e2d\u641c\u7d22 <\/p>\n<li>heap<strong>\uff0c\u53d6\u6d88\u7b2c77\u300178\u884c\u7684\u6ce8\u91ca\uff0c\u5e76\u5c06<\/strong>256m<strong>\u66f4\u6539\u4e3a<\/strong>2048m<strong>\uff0c\u8fd9\u6837\u53ef\u4ee5\u786e\u4fdd\u4e3aneo4j\u4e2d\u7684\u6570\u636e\u5b58\u50a8\u5206\u914d2048mb\u3002<\/strong> <\/li>\n<\/ul>\n<p><img decoding=\"async\" src=\"https:\/\/www.17golang.com\/uploads\/20241127\/173267341767467f897cebd.png\" class=\"aligncenter\" title=\"\u5c06\u6570\u636e\u52a0\u8f7d\u5230 Neo4j \u4e2d\u63d2\u56fe3\" alt=\"\u5c06\u6570\u636e\u52a0\u8f7d\u5230 Neo4j \u4e2d\u63d2\u56fe3\" \/><\/p>\n<p>&nbsp; <\/p>\n<p> &nbsp;<\/p>\n<p> \u521b\u5efa\u8282\u70b9 <\/p>\n<ul>\n<li>\u56fe\u6709\u4e24\u4e2a\u4e3b\u8981\u7ec4\u6210\u90e8\u5206\uff1a\u8282\u70b9\u548c\u5173\u7cfb\uff0c\u8ba9\u6211\u4eec\u5148\u521b\u5efa\u8282\u70b9\uff0c\u7136\u540e\u518d\u5efa\u7acb\u5173\u7cfb\u3002\n<\/p>\n<\/li>\n<li>\u6211\u6b63\u5728\u4f7f\u7528\u7684\u6570\u636e\u5728\u8fd9\u91cc &#8211; data\n<\/p>\n<\/li>\n<li>\u4f7f\u7528\u8fd9\u91cc\u63d0\u4f9b\u7684requirements.txt\u6765\u521b\u5efa\u4e00\u4e2apython\u865a\u62df\u73af\u5883-requirements.txt\n<\/p>\n<\/li>\n<li>\u8ba9\u6211\u4eec\u5b9a\u4e49\u5404\u79cd\u51fd\u6570\u6765\u63a8\u9001\u6570\u636e\u3002\n<\/p>\n<\/li>\n<li>\u5bfc\u5165\u5fc5\u8981\u7684\u5e93\n<p><\/p>\n<\/li>\n<\/ul>\n<pre>import pandas as pd\nfrom neo4j import graphdatabase\nfrom openai import openai\n<\/pre>\n<ul>\n  \u6211\u4eec\u5c06\u4f7f\u7528 openai \u6765\u751f\u6210\u5d4c\u5165 <\/p>\n<li> <\/li>\n<\/ul>\n<pre>client = openai(api_key=\"\")\nproduct_data_df = pd.read_csv('..\/data\/product_data.csv')\n<\/pre>\n<ul>\n  \u751f\u6210\u5d4c\u5165 <\/p>\n<li> <\/li>\n<\/ul>\n<pre>def get_embedding(text):\n    \"\"\"\n    used to generate embeddings using openai embeddings model\n    :param text: str - text that needs to be converted to embeddings\n    :return: embedding\n    \"\"\"\n    model = \"text-embedding-3-small\"\n    text = text.replace(\"\\n\", \" \")\n    return client.embeddings.create(input=[text], model=model).data[0].embedding\n<\/pre>\n<ul>\n  \u6839\u636e\u6211\u4eec\u7684\u6570\u636e\u96c6\uff0c\u6211\u4eec\u53ef\u4ee5\u6709\u4e24\u4e2a\u552f\u4e00\u7684\u8282\u70b9\u6807\u7b7e\uff0c <\/p>\n<li>category<strong>\uff1a\u4ea7\u54c1\u7c7b\u522b\uff0c<\/strong>product<strong>\uff1a\u4ea7\u54c1\u540d\u79f0\u3002\u8ba9\u6211\u4eec\u521b\u5efa\u7c7b\u522b\u6807\u7b7e\uff0cneo4j \u63d0\u4f9b\u4e86\u4e00\u79cd\u79f0\u4e3a\u5c5e\u6027\u7684\u4e1c\u897f\uff0c\u60a8\u53ef\u4ee5\u5c06\u5b83\u4eec\u60f3\u8c61\u4e3a\u7279\u5b9a\u8282\u70b9\u7684\u5143\u6570\u636e\u3002\u8fd9\u91cc <\/strong>name<strong> \u548c <\/strong>embedding<strong> \u662f\u5c5e\u6027\u3002\u56e0\u6b64\uff0c\u6211\u4eec\u5c06\u7c7b\u522b\u540d\u79f0\u53ca\u5176\u76f8\u5e94\u7684\u5d4c\u5165\u5b58\u50a8\u5728\u6570\u636e\u5e93\u4e2d\u3002 <\/strong> <\/li>\n<\/ul>\n<pre>def create_category(product_data_df):\n    \"\"\"\n    used to generate queries for creating category nodes in neo4j\n    :param product_data_df: pandas dataframe - data\n    :return: query_list: list - list containing all create node queries for category\n    \"\"\"\n    cat_query = \"\"\"create (a:category {name: '%s', embedding: %s})\"\"\"\n    distinct_category = product_data_df['category'].unique()\n    query_list = []\n    for category in distinct_category:\n        embedding = get_embedding(category)\n        query_list.append(cat_query % (category, embedding))\n    return query_list\n<\/pre>\n<ul>\n  \u7c7b\u4f3c\u5730\uff0c\u6211\u4eec\u53ef\u4ee5\u521b\u5efa\u4ea7\u54c1\u8282\u70b9\uff0c\u8fd9\u91cc\u7684\u5c5e\u6027\u662f <\/p>\n<li>name<strong>\uff0c<\/strong>description<strong>\uff0c<\/strong>price<strong>\uff0c<\/strong>warranty_period<strong>\uff0c<\/strong>available_stock<strong>\uff0c<\/strong>review_ rating<strong>\uff0c<\/strong>product_release_date<strong>\uff0c<\/strong>embedding <strong> <\/strong> <\/li>\n<\/ul>\n<pre>def create_product(product_data_df):\n    \"\"\"\n    used to generate queries for creating product nodes in neo4j\n    :param product_data_df: pandas dataframe - data \n    :return: query_list: list - list containing all create node queries for product \n    \"\"\"\n    product_query = \"\"\"create (a:product {name: '%s', description: '%s', price: %d, warranty_period: %d, \n    available_stock: %d, review_rating: %f, product_release_date: date('%s'), embedding: %s})\"\"\"\n    query_list = []\n    for idx, row in product_data_df.iterrows():\n        embedding = get_embedding(row['product name'] + \" - \" + row['description'])\n        query_list.append(product_query % (row['product name'], row['description'], int(row['price (inr)']),\n                                           int(row['warranty period (years)']), int(row['stock']),\n                                           float(row['review rating']), str(row['product release date']), embedding))\n    return query_list\n<\/pre>\n<ul>\n  \u73b0\u5728\u8ba9\u6211\u4eec\u521b\u5efa\u53e6\u4e00\u4e2a\u51fd\u6570\u6765\u6267\u884c\u4e0a\u8ff0\u4e24\u4e2a\u51fd\u6570\u751f\u6210\u7684\u67e5\u8be2\u3002\u9002\u5f53\u66f4\u65b0\u60a8\u7684\u7528\u6237\u540d\u548c\u5bc6\u7801\u3002 <\/p>\n<li> <\/li>\n<\/ul>\n<pre>def execute_bulk_query(query_list):\n    \"\"\"\n    executes queries is a list one by one\n    :param query_list: list - list of cypher queries\n    :return: none\n    \"\"\"\n    url = \"bolt:\/\/localhost:7687\"\n    auth = (\"neo4j\", \"neo4j@123\")\n\n    with graphdatabase.driver(url, auth=auth) as driver:\n        with driver.session() as session:\n            for query in query_list:\n                try:\n                    session.run(query)\n                except exception as error:\n                    print(f\"error in executing query - {query}, error - {error}\")\n<\/pre>\n<ul>\n  \u5b8c\u6574\u4ee3\u7801 <\/p>\n<li> <\/li>\n<\/ul>\n<pre>import pandas as pd\nfrom neo4j import graphdatabase\nfrom openai import openai\n\nclient = openai(api_key=\"\")\nproduct_data_df = pd.read_csv('..\/data\/product_data.csv')\n\n\ndef preprocessing(df, columns_to_replace):\n    \"\"\"\n    used to preprocess certain column in dataframe\n    :param df: pandas dataframe - data\n    :param columns_to_replace: list - column name list\n    :return: df: pandas dataframe - processed data\n    \"\"\"\n    df[columns_to_replace] = df[columns_to_replace].apply(lambda col: col.str.replace(\"'s\", \"s\"))\n    df[columns_to_replace] = df[columns_to_replace].apply(lambda col: col.str.replace(\"'\", \"\"))\n    return df\n\n\ndef get_embedding(text):\n    \"\"\"\n    used to generate embeddings using openai embeddings model\n    :param text: str - text that needs to be converted to embeddings\n    :return: embedding\n    \"\"\"\n    model = \"text-embedding-3-small\"\n    text = text.replace(\"\\n\", \" \")\n    return client.embeddings.create(input=[text], model=model).data[0].embedding\n\n\ndef create_category(product_data_df):\n    \"\"\"\n    used to generate queries for creating category nodes in neo4j\n    :param product_data_df: pandas dataframe - data\n    :return: query_list: list - list containing all create node queries for category\n    \"\"\"\n    cat_query = \"\"\"create (a:category {name: '%s', embedding: %s})\"\"\"\n    distinct_category = product_data_df['category'].unique()\n    query_list = []\n    for category in distinct_category:\n        embedding = get_embedding(category)\n        query_list.append(cat_query % (category, embedding))\n    return query_list\n\n\ndef create_product(product_data_df):\n    \"\"\"\n    used to generate queries for creating product nodes in neo4j\n    :param product_data_df: pandas dataframe - data\n    :return: query_list: list - list containing all create node queries for product\n    \"\"\"\n    product_query = \"\"\"create (a:product {name: '%s', description: '%s', price: %d, warranty_period: %d, \n    available_stock: %d, review_rating: %f, product_release_date: date('%s'), embedding: %s})\"\"\"\n    query_list = []\n    for idx, row in product_data_df.iterrows():\n        embedding = get_embedding(row['product name'] + \" - \" + row['description'])\n        query_list.append(product_query % (row['product name'], row['description'], int(row['price (inr)']),\n                                           int(row['warranty period (years)']), int(row['stock']),\n                                           float(row['review rating']), str(row['product release date']), embedding))\n    return query_list\n\n\ndef execute_bulk_query(query_list):\n    \"\"\"\n    executes queries is a list one by one\n    :param query_list: list - list of cypher queries\n    :return: none\n    \"\"\"\n    url = \"bolt:\/\/localhost:7687\"\n    auth = (\"neo4j\", \"neo4j@123\")\n\n    with graphdatabase.driver(url, auth=auth) as driver:\n        with driver.session() as session:\n            for query in query_list:\n                try:\n                    session.run(query)\n                except exception as error:\n                    print(f\"error in executing query - {query}, error - {error}\")\n\n# preprocessing\nproduct_data_df = preprocessing(product_data_df, ['product name', 'description'])\n\n# create category\nquery_list = create_category(product_data_df)\nexecute_bulk_query(query_list)\n\n# create product\nquery_list = create_product(product_data_df)\nexecute_bulk_query(query_list)\n\n<\/pre>\n<p> &nbsp; <\/p>\n<p> &nbsp;<\/p>\n<p> \u5efa\u7acb\u5173\u7cfb <\/p>\n<ul>\n  \u6211\u4eec\u5c06\u5728 <\/p>\n<li>category<strong> \u548c <\/strong>product<strong> \u4e4b\u95f4\u521b\u5efa\u5173\u7cfb\uff0c\u8be5\u5173\u7cfb\u7684\u540d\u79f0\u4e3a <\/strong>category_contains_product<strong> <\/strong> <\/li>\n<\/ul>\n<pre>from neo4j import GraphDatabase\nimport pandas as pd\n\nproduct_data_df = pd.read_csv('..\/data\/product_data.csv')\n\n\ndef preprocessing(df, columns_to_replace):\n    \"\"\"\n    Used to preprocess certain column in dataframe\n    :param df: pandas dataframe - data\n    :param columns_to_replace: list - column name list\n    :return: df: pandas dataframe - processed data\n    \"\"\"\n    df[columns_to_replace] = df[columns_to_replace].apply(lambda col: col.str.replace(\"'s\", \"s\"))\n    df[columns_to_replace] = df[columns_to_replace].apply(lambda col: col.str.replace(\"'\", \"\"))\n    return df\n\n\ndef create_category_food_relationship_query(product_data_df):\n    \"\"\"\n    Used to create relationship between category and products\n    :param product_data_df: dataframe - data\n    :return: query_list: list - cypher queries\n    \"\"\"\n    query = \"\"\"MATCH (c:Category {name: '%s'}), (p:Product {name: '%s'}) CREATE (c)-[:CATEGORY_CONTAINS_PRODUCT]-&gt;(p)\"\"\"\n    query_list = []\n    for idx, row in product_data_df.iterrows():\n        query_list.append(query % (row['Category'], row['Product Name']))\n    return query_list\n\n\ndef execute_bulk_query(query_list):\n    \"\"\"\n    Executes queries is a list one by one\n    :param query_list: list - list of cypher queries\n    :return: None\n    \"\"\"\n    url = \"bolt:\/\/localhost:7687\"\n    auth = (\"neo4j\", \"neo4j@123\")\n\n    with GraphDatabase.driver(url, auth=auth) as driver:\n        with driver.session() as session:\n            for query in query_list:\n                try:\n                    session.run(query)\n                except Exception as error:\n                    print(f\"Error in executing query - {query}, Error - {error}\")\n\n\n# PREPROCESSING\nproduct_data_df = preprocessing(product_data_df, ['Product Name', 'Description'])\n\n# CATEGORY - FOOD RELATIONSHIP\nquery_list = create_category_food_relationship_query(product_data_df)\nexecute_bulk_query(query_list)\n\n<\/pre>\n<ul>\n  \u901a\u8fc7\u4f7f\u7528 match \u67e5\u8be2\u6765\u5339\u914d\u5df2\u7ecf\u521b\u5efa\u7684\u8282\u70b9\uff0c\u6211\u4eec\u5728\u5b83\u4eec\u4e4b\u95f4\u5efa\u7acb\u5173\u7cfb\u3002 <\/p>\n<li> <\/li>\n<\/ul>\n<p>&nbsp; <\/p>\n<p> &nbsp;<\/p>\n<p> \u53ef\u89c6\u5316\u521b\u5efa\u7684\u8282\u70b9 \u5c06\u9f20\u6807\u60ac\u505c\u5728 <\/p>\n<p>open<strong>\u56fe\u6807\u4e0a\uff0c\u7136\u540e\u5355\u51fb<\/strong>neo4j\u6d4f\u89c8\u5668<strong>\u4ee5\u53ef\u89c6\u5316\u6211\u4eec\u521b\u5efa\u7684\u8282\u70b9\u3002<\/strong> <br \/><img decoding=\"async\" src=\"https:\/\/www.17golang.com\/uploads\/20241127\/173267341867467f8ad46e5.png\" class=\"aligncenter\" title=\"\u5c06\u6570\u636e\u52a0\u8f7d\u5230 Neo4j \u4e2d\u63d2\u56fe4\" alt=\"\u5c06\u6570\u636e\u52a0\u8f7d\u5230 Neo4j \u4e2d\u63d2\u56fe4\" \/><\/p>\n<p><img decoding=\"async\" src=\"https:\/\/www.17golang.com\/uploads\/20241127\/173267341967467f8bf2b96.png\" class=\"aligncenter\" title=\"\u5c06\u6570\u636e\u52a0\u8f7d\u5230 Neo4j \u4e2d\u63d2\u56fe5\" alt=\"\u5c06\u6570\u636e\u52a0\u8f7d\u5230 Neo4j \u4e2d\u63d2\u56fe5\" \/><\/p>\n<p><img decoding=\"async\" src=\"https:\/\/www.17golang.com\/uploads\/20241127\/173267342167467f8d4eeb0.png\" class=\"aligncenter\" title=\"\u5c06\u6570\u636e\u52a0\u8f7d\u5230 Neo4j \u4e2d\u63d2\u56fe6\" alt=\"\u5c06\u6570\u636e\u52a0\u8f7d\u5230 Neo4j \u4e2d\u63d2\u56fe6\" \/><\/p>\n<p>\u6211\u4eec\u7684\u6570\u636e\u8fde\u540c\u5b83\u4eec\u7684\u5d4c\u5165\u4e00\u8d77\u52a0\u8f7d\u5230 neo4j \u4e2d\u3002 <\/p>\n<p>&nbsp; <\/p>\n<p> \u5728\u63a5\u4e0b\u6765\u7684\u535a\u5ba2\u4e2d\uff0c\u6211\u4eec\u5c06\u770b\u5230\u5982\u4f55\u4f7f\u7528 python \u6784\u5efa\u56fe\u5f62\u67e5\u8be2\u5f15\u64ce\u5e76\u4f7f\u7528\u83b7\u53d6\u7684\u6570\u636e\u8fdb\u884c\u589e\u5f3a\u751f\u6210\u3002<\/p>\n<p>\u5e0c\u671b\u8fd9\u6709\u5e2e\u52a9&#8230;\u518d\u89c1\uff01 <\/p>\n<p>linkedin &#8211; https:\/\/www.linkedin.com\/in\/praveenr2998\/ <\/p>\n<p> github &#8211; https:\/\/github.com\/praveenr2998\/creating-lightweight-rag-systems-with-graphs\/tree\/main\/push_data_to_db<\/p>\n<p>\u4eca\u5929\u5e26\u5927\u5bb6\u4e86\u89e3\u4e86\u7684\u76f8\u5173\u77e5\u8bc6\uff0c\u5e0c\u671b\u5bf9\u4f60\u6709\u6240\u5e2e\u52a9\uff1b\u5173\u4e8e\u6587\u7ae0\u7684\u6280\u672f\u77e5\u8bc6\u6211\u4eec\u4f1a\u4e00\u70b9\u70b9\u6df1\u5165\u4ecb\u7ecd\uff0c\u6b22\u8fce\u5927\u5bb6\u5173\u6ce8\u7c73\u4e91\u516c\u4f17\u53f7\uff0c\u4e00\u8d77\u5b66\u4e60\u7f16\u7a0b~<\/p>\n<p>      \u7248\u672c\u58f0\u660e \u672c\u6587\u8f6c\u8f7d\u4e8e\uff1adev.to \u5982\u6709\u4fb5\u72af\uff0c\u8bf7\u8054\u7cfb\u5220\u9664<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u5c06\u6570\u636e\u52a0\u8f7d\u5230 Neo4j \u4e2d \u5927\u5bb6\u597d\uff0c\u6211\u4eec\u53c8\u89c1\u9762\u4e86\u554a~\u672c\u6587\u300a\u5c06\u6570\u636e\u52a0\u8f7d\u5230 Neo4j \u4e2d\u300b\u7684\u5185\u5bb9\u4e2d\u5c06\u4f1a\u6d89\u53ca\u5230\u7b49\u7b49\u3002\u5982\u679c\u4f60\u6b63\u5728\u5b66\u4e60\u6587\u7ae0\u76f8\u5173\u77e5\u8bc6\uff0c\u6b22\u8fce\u5173\u6ce8\u6211\uff0c\u4ee5\u540e\u4f1a\u7ed9\u5927\u5bb6\u5e26\u6765\u66f4\u591a\u6587\u7ae0\u76f8\u5173\u6587\u7ae0\uff0c\u5e0c\u671b\u6211\u4eec\u80fd\u4e00\u8d77\u8fdb\u6b65\uff01\u4e0b\u9762\u5c31\u5f00\u59cb\u672c\u6587\u7684\u6b63\u5f0f\u5185\u5bb9~ \u5728\u4e0a\u4e00\u7bc7\u535a\u5ba2\u4e2d\uff0c\u6211\u4eec\u4e86\u89e3\u4e86\u5982\u4f55\u4f7f\u7528 2 \u4e2a\u63d2\u4ef6 apoc \u548c\u56fe\u5f62\u6570\u636e\u79d1\u5b66\u5e93 &#8211; gds \u5728\u672c\u5730\u5b89\u88c5\u548c\u8bbe\u7f6e neo4j\u3002\u5728\u8fd9\u7bc7\u535a\u5ba2\u4e2d\uff0c\u6211\u5c06\u83b7\u53d6\u4e00\u4e2a\u73a9\u5177\u6570\u636e\u96c6\uff08\u7535\u5b50\u5546\u52a1\u7f51\u7ad9\u4e2d\u7684\u4ea7\u54c1\uff09\u5e76\u5c06\u5176\u5b58\u50a8\u5728 neo4j \u4e2d\u3002 &nbsp; \u5728\u5f00\u59cb\u52a0\u8f7d\u6570\u636e\u4e4b\u524d\uff0c\u5982\u679c\u60a8\u7684\u7528\u4f8b\u4e2d\u6709\u5927\u91cf\u6570\u636e\uff0c\u8bf7\u786e\u4fdd\u4e3a neo4j \u5206\u914d\u4e86\u8db3\u591f\u7684\u5185\u5b58\u3002\u4e3a\u6b64\uff1a \u70b9\u51fb\u6253\u5f00\u53f3\u4fa7\u7684\u4e09\u4e2a\u70b9 \u70b9\u51fb \u6253\u5f00\u6587\u4ef6\u5939-&gt; \u914d\u7f6e \u70b9\u51fb neo4j.conf \u5728neo4j.conf\u4e2d\u641c\u7d22 heap\uff0c\u53d6\u6d88\u7b2c77\u300178\u884c\u7684\u6ce8\u91ca\uff0c\u5e76\u5c06256m\u66f4\u6539\u4e3a2048m\uff0c\u8fd9\u6837\u53ef\u4ee5\u786e\u4fdd\u4e3aneo4j\u4e2d\u7684\u6570\u636e\u5b58\u50a8\u5206\u914d2048mb\u3002 &nbsp; &nbsp; \u521b\u5efa\u8282\u70b9 \u56fe\u6709\u4e24\u4e2a\u4e3b\u8981\u7ec4\u6210\u90e8\u5206\uff1a\u8282\u70b9\u548c\u5173\u7cfb\uff0c\u8ba9\u6211\u4eec\u5148\u521b\u5efa\u8282\u70b9\uff0c\u7136\u540e\u518d\u5efa\u7acb\u5173\u7cfb\u3002 \u6211\u6b63\u5728\u4f7f\u7528\u7684\u6570\u636e\u5728\u8fd9\u91cc &#8211; data \u4f7f\u7528\u8fd9\u91cc\u63d0\u4f9b\u7684requirements.txt\u6765\u521b\u5efa\u4e00\u4e2apython\u865a\u62df\u73af\u5883-requirements.txt \u8ba9\u6211\u4eec\u5b9a\u4e49\u5404\u79cd\u51fd\u6570\u6765\u63a8\u9001\u6570\u636e\u3002 \u5bfc\u5165\u5fc5\u8981\u7684\u5e93 import pandas as pd from neo4j import graphdatabase from openai import openai \u6211\u4eec\u5c06\u4f7f\u7528 openai \u6765\u751f\u6210\u5d4c\u5165 client [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[16],"tags":[],"class_list":["post-50749","post","type-post","status-publish","format-standard","hentry","category-16"],"_links":{"self":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/posts\/50749","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/comments?post=50749"}],"version-history":[{"count":0,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/posts\/50749\/revisions"}],"wp:attachment":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/media?parent=50749"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/categories?post=50749"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/tags?post=50749"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}