DeepSeek 大模子 + LlamaIndex + MySQL 数据库 + 知识文档实现简朴 RAG 体系 - IT评测·应用市场-qidao123.com技术社区

pip install llama-index deepseek-cpm mysql-connector-python

复制代码

CREATE TABLE documents (
id INT AUTO_INCREMENT PRIMARY KEY,
content TEXT
);

复制代码

INSERT INTO documents (content) VALUES
('去年公司的营收为10亿元人民币。'),
('今年计划增加研发投入，预算为2亿元。');

复制代码

公司成立于2010年，专注于技术研发。
去年的研发投入为5亿元。

复制代码

import mysql.connector
def load_data_from_mysql():
# 连接 MySQL 数据库
conn = mysql.connector.connect(
host="localhost",
user="yourusername",
password="yourpassword",
database="yourdatabase"
)
cursor = conn.cursor()
# 查询 documents 表中的所有记录
cursor.execute("SELECT content FROM documents")
rows = cursor.fetchall()
# 将查询结果转换为文本列表
documents = [row[0] for row in rows]
cursor.close()
conn.close()
return documents
# 加载 MySQL 数据
mysql_documents = load_data_from_mysql()
print("Loaded from MySQL:", mysql_documents)

复制代码

def load_data_from_file(file_path):
with open(file_path, 'r', encoding='utf-8') as file:
content = file.read()
return [content]
# 加载知识文档
file_documents = load_data_from_file('knowledge.txt')
print("Loaded from file:", file_documents)

复制代码

from llama_index import SimpleDirectoryReader, GPTListIndex, Document
def build_index(documents):
# 将文档列表转换为 Document 对象
docs = [Document(text) for text in documents]
# 构建索引
index = GPTListIndex.from_documents(docs)
return index
# 合并来自 MySQL 和文件的数据
all_documents = mysql_documents + file_documents
print("All documents:", all_documents)
# 构建索引
index = build_index(all_documents)

复制代码

def query_index(index, query_text):
response = index.query(query_text)
return response.response
# 测试查询
query = "去年公司的研发投入是多少？"
response = query_index(index, query)
print("Query Response:", response)

复制代码

import deepseek_cpm
def generate_response_with_model(query, context):
prompt = f"问题: {query}\n上下文: {context}\n回答:"
response = deepseek_cpm.generate(prompt)
return response
# 获取检索结果作为上下文
context = query_index(index, query)
final_response = generate_response_with_model(query, context)
print("Final Response with Model:", final_response)

复制代码

import mysql.connector
from llama_index import SimpleDirectoryReader, GPTListIndex, Document
import deepseek_cpm
# 1. 从 MySQL 数据库加载数据
def load_data_from_mysql():
conn = mysql.connector.connect(
host="localhost",
user="yourusername",
password="yourpassword",
database="yourdatabase"
)
cursor = conn.cursor()
cursor.execute("SELECT content FROM documents")
rows = cursor.fetchall()
documents = [row[0] for row in rows]
cursor.close()
conn.close()
return documents
# 2. 从知识文档加载数据
def load_data_from_file(file_path):
with open(file_path, 'r', encoding='utf-8') as file:
content = file.read()
return [content]
# 3. 合并数据并构建索引
def build_index(documents):
docs = [Document(text) for text in documents]
index = GPTListIndex.from_documents(docs)
return index
# 4. 定义查询函数
def query_index(index, query_text):
response = index.query(query_text)
return response.response
# 5. 结合 DeepSeek 大模型生成最终回答
def generate_response_with_model(query, context):
prompt = f"问题: {query}\n上下文: {context}\n回答:"
response = deepseek_cpm.generate(prompt)
return response
# 主程序
if __name__ == "__main__":
# 加载数据
mysql_documents = load_data_from_mysql()
file_documents = load_data_from_file('knowledge.txt')
all_documents = mysql_documents + file_documents
# 构建索引
index = build_index(all_documents)
# 测试查询
query = "去年公司的研发投入是多少？"
context = query_index(index, query)
final_response = generate_response_with_model(query, context)
print("Final Response with Model:", final_response)

复制代码