实时网页信息爬取+RAG的问答系统搭建 【复现贴】 #57

Open
opened 2025-01-02 15:54:10 +08:00 by GANGUAGUA · 0 comments

安装环境

wget https://repo.anaconda.com/miniconda/Miniconda3-py38_23.5.2-0-Linux-x86_64.sh

创建并激活conda环境

conda create -n db python=3.10 #db是自己给环境取得名字
conda activate db #激活conda

安装依赖库

在conda环境内安装依赖库:

pip install pyway -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install pandas -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install requests -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install tqdm -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install loguru -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install lxml -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install pymysql -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install dbutils -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install openpyxl -i https://pypi.tuna.tsinghua.edu.cn/simple

可以通过conda list来查安装了哪些包

使用Xinference部署模型

语言模型

嵌入模型

用OneAPI接入模型

启动FastGPT

转到fastgpt目录下,启动fastgpt

cd fastgpt
docker-compose up -d

修改文件

.pyway.conf

dockers-compose.yml

  • 修改镜像源

  • 修改docker compose版本号

可通过docker-compose --version来查看docker compose的版本号

rag_api_utils.py

修改API Key与API根目录

  • 获取API key

  • 获取API根目录

粘贴到rag_api_utils.py文件里

main.py

  • 修改服务器ip
  • 修改端口号
  • 修改数据库名字

  • 修改cookie

登录天眼查

按F2获取Cookie

启动数据库容器

cd db_docker
sudo su
docker compose up -d

查看容器日志确认数据库已启动

docker logs -f tianyancha_db_prod_test

创建数据表

要在刚刚创建的conda环境下执行

conda activate db
cd db_create
pyway migrate

# 安装环境 ```plain wget https://repo.anaconda.com/miniconda/Miniconda3-py38_23.5.2-0-Linux-x86_64.sh ``` ![](https://cdn.nlark.com/yuque/0/2024/png/48118617/1735024960138-3c9e4aa6-fe33-463f-b4ec-9c4f3cd16781.png) # 创建并激活conda环境 ```plain conda create -n db python=3.10 #db是自己给环境取得名字 conda activate db #激活conda ``` ![](https://cdn.nlark.com/yuque/0/2024/png/48118617/1735025374271-542e8fcc-e8a8-46b3-9582-739963cbb3d2.png) ![](https://cdn.nlark.com/yuque/0/2024/png/48118617/1735025394462-aa9183af-605d-4a8e-9a92-4410655bdb41.png) ![](https://cdn.nlark.com/yuque/0/2024/png/48118617/1735025441908-7397e4e1-39b5-423a-921d-912d53c19b50.png) # 安装依赖库 <u>在conda环境内</u>安装依赖库: ```plain pip install pyway -i https://pypi.tuna.tsinghua.edu.cn/simple pip install pandas -i https://pypi.tuna.tsinghua.edu.cn/simple pip install requests -i https://pypi.tuna.tsinghua.edu.cn/simple pip install tqdm -i https://pypi.tuna.tsinghua.edu.cn/simple pip install loguru -i https://pypi.tuna.tsinghua.edu.cn/simple pip install lxml -i https://pypi.tuna.tsinghua.edu.cn/simple pip install pymysql -i https://pypi.tuna.tsinghua.edu.cn/simple pip install dbutils -i https://pypi.tuna.tsinghua.edu.cn/simple pip install openpyxl -i https://pypi.tuna.tsinghua.edu.cn/simple ``` 可以通过`conda list`来查安装了哪些包 # 使用Xinference部署模型 语言模型 ![](https://cdn.nlark.com/yuque/0/2025/png/48118617/1735803407601-724777b7-201a-4e3f-a5f0-adf45b0b96dc.png) ![](https://cdn.nlark.com/yuque/0/2025/png/48118617/1735803390041-a43aefe1-0550-4f80-9d35-26111665af5a.png) 嵌入模型 ![](https://cdn.nlark.com/yuque/0/2024/png/48118617/1735095226823-a2e3717a-640d-404e-ac9d-f0bf41e632b9.png) ![](https://cdn.nlark.com/yuque/0/2024/png/48118617/1735097080852-40eb42b9-20bd-43cc-8fc0-b540659c39ab.png) # 用OneAPI接入模型 ![](https://cdn.nlark.com/yuque/0/2024/png/48118617/1735179091937-1275c20b-9839-4f98-a0b9-47f4b945e5b4.png) ![](https://cdn.nlark.com/yuque/0/2024/png/48118617/1735178805466-5ebf70c1-b8d7-4bc9-b58f-74b6912bf3e3.png) # 启动FastGPT 转到fastgpt目录下,启动fastgpt ```plain cd fastgpt docker-compose up -d ``` # 修改文件 ## .pyway.conf ![](https://cdn.nlark.com/yuque/0/2024/png/48118617/1735025699811-1e58a798-31ad-432a-aad6-d8a37b82ded1.png) ![](https://cdn.nlark.com/yuque/0/2024/png/48118617/1735025811216-6f5d06d1-022f-49a0-9d7c-b9989e93789f.png) ## dockers-compose.yml + 修改镜像源 ![](https://cdn.nlark.com/yuque/0/2024/png/48118617/1735026551382-aacdb484-6335-4d7b-8991-07ff094a619f.png) ![](https://cdn.nlark.com/yuque/0/2024/png/48118617/1735026344280-8cdf177f-e7d4-451f-8721-c3baf210c05d.png) ![](https://cdn.nlark.com/yuque/0/2024/png/48118617/1735026441249-7b65cb4a-176b-4a26-8e01-31234771f487.png) + 修改docker compose版本号 可通过`docker-compose --version`来查看docker compose的版本号 ![](https://cdn.nlark.com/yuque/0/2024/png/48118617/1735026594267-687894e9-7396-4c27-a429-b28d1ac4873c.png) ## rag_api_utils.py 修改API Key与API根目录 ![](https://cdn.nlark.com/yuque/0/2025/png/48118617/1735796445173-4d41310c-d29a-4030-b753-7f40d240fcfd.png) + 获取API key ![](https://cdn.nlark.com/yuque/0/2025/png/48118617/1735796248285-a5b91c0e-2911-45fb-abcd-4df4d7faf697.png) ![](https://cdn.nlark.com/yuque/0/2025/png/48118617/1735796261416-d5546062-da4b-45bc-a40e-9a4545522259.png) + 获取API根目录 ![](https://cdn.nlark.com/yuque/0/2025/png/48118617/1735796415002-930f7d3c-1cc6-40e6-87ec-2fe26cd14c73.png) 粘贴到rag_api_utils.py文件里 ![](https://cdn.nlark.com/yuque/0/2025/png/48118617/1735796445173-4d41310c-d29a-4030-b753-7f40d240fcfd.png) ## main.py + 修改服务器ip + 修改端口号 + 修改数据库名字 ![](https://cdn.nlark.com/yuque/0/2024/png/48118617/1735025811216-6f5d06d1-022f-49a0-9d7c-b9989e93789f.png) + 修改cookie 登录天眼查 ![](https://cdn.nlark.com/yuque/0/2025/png/48118617/1735788721891-3b0f680e-a367-4988-97a4-ca1a401ed3f7.png) 按F2获取Cookie ![](https://cdn.nlark.com/yuque/0/2025/png/48118617/1735789993933-2fe701ae-f744-439a-a454-8117b7a096cc.png) ![](https://cdn.nlark.com/yuque/0/2025/png/48118617/1735789963780-9216cccf-5c06-43dd-aba8-9be2629ac2de.png) # 启动数据库容器 ```plain cd db_docker sudo su docker compose up -d ``` ![](https://cdn.nlark.com/yuque/0/2024/png/48118617/1735025901055-3ff2734b-ed6d-4f4d-ad44-6d7a78528239.png) ![](https://cdn.nlark.com/yuque/0/2024/png/48118617/1735026645802-fbf7395a-e080-4def-a5af-05a6392ad884.png) 查看容器日志确认数据库已启动 ```plain docker logs -f tianyancha_db_prod_test ``` ![](https://cdn.nlark.com/yuque/0/2024/png/48118617/1735026808613-37128ad6-0837-4e64-94b2-99482c2052d3.png) # 创建数据表 要在刚刚创建的conda环境下执行 ```plain conda activate db cd db_create pyway migrate ``` ![](https://cdn.nlark.com/yuque/0/2024/png/48118617/1735026978185-37ae20b0-7d29-44e9-9e7a-d62376c12996.png) ![](https://cdn.nlark.com/yuque/0/2024/png/48118617/1735027067053-44fc2bc6-0c72-49e5-b79d-b1c94a0ed416.png) ![](https://cdn.nlark.com/yuque/0/2025/png/48118617/1735789963780-9216cccf-5c06-43dd-aba8-9be2629ac2de.png) ![](https://cdn.nlark.com/yuque/0/2025/png/48118617/1735796223110-6f175004-6d94-4738-b9ac-05d5dc689058.png) ![](https://cdn.nlark.com/yuque/0/2025/png/48118617/1735796199081-10ce49de-b1f4-4ceb-adc8-54cdaddd7484.png) ![](https://cdn.nlark.com/yuque/0/2025/png/48118617/1735796248285-a5b91c0e-2911-45fb-abcd-4df4d7faf697.png) ![](https://cdn.nlark.com/yuque/0/2025/png/48118617/1735796261416-d5546062-da4b-45bc-a40e-9a4545522259.png) ![](https://cdn.nlark.com/yuque/0/2025/png/48118617/1735796415002-930f7d3c-1cc6-40e6-87ec-2fe26cd14c73.png) ![](https://cdn.nlark.com/yuque/0/2025/png/48118617/1735796445173-4d41310c-d29a-4030-b753-7f40d240fcfd.png) ![](https://cdn.nlark.com/yuque/0/2025/png/48118617/1735795948427-c2cf0ab7-371d-447c-88cc-d6489a11749a.png) ![](https://cdn.nlark.com/yuque/0/2025/png/48118617/1735800843420-ef95190c-147a-4758-8d39-e7df009c6e3d.png) ![](https://cdn.nlark.com/yuque/0/2025/png/48118617/1735800889661-9445fc85-2773-4f20-90f9-52370d3be7ba.png) ![](https://cdn.nlark.com/yuque/0/2025/png/48118617/1735801127139-e2d98cd5-af76-4e35-bc6b-ab5ce8a32f33.png) ![](https://cdn.nlark.com/yuque/0/2025/png/48118617/1735800977067-204ca23d-c5f9-4ef1-9ccd-fd0865c63f9d.png)
Sign in to join this conversation.
No Label
No Milestone
No project
No Assignees
1 Participants
Notifications
Due Date
The due date is invalid or out of range. Please use the format 'yyyy-mm-dd'.

No due date set.

Dependencies

No dependencies set.

Reference: HswOAuth/llm_share#57
No description provided.