本地搭建【文档助手】大模型版(LangChain+llama+Streamlit)

概述

本文的文档助手就是:我们上传一个文档,然后在对话框中输入问题,大模型会把问题的答案返回。

安装步骤

  1. 先下载代码到本地

LangChain调用llama模型的示例代码:https://github.com/afaqueumer/DocQA(代码不是本人写的,尊重原创)

java 复制代码
git clone https://github.com/afaqueumer/DocQA.git
  1. 环境安装
java 复制代码
双击 setup_env.bat
  • 如果没反应可能是缺少环境,打开控制台手动执行一下,缺python或者pip的自己根据报错下载一下

如果llama-cpp-python安装报错

(1)需要下载Visual Studio

(2)打开Visual Studio,工具,获取工具和功能

(3)等待下载完,重新运行setup_env.bat

如果还有报错【error C2061: 语法错误: 】,那么可能是Visual Studio的版本太低了,我一开始用的是2019版本,后来换成了2022

更新为2022之后重复上面操作

  1. 下载一个靠谱的模型
    https://huggingface.co/TheBloke/Llama-2-7B-GGUF
    本文用的是:TheBloke/Llama-2-7B-GGUF中的最精简版
  2. 进入DocQA,修改app.py

原始

java 复制代码
llm = LlamaCpp(model_path="./models/llama-7b.ggmlv3.q4_0.bin")
embeddings = LlamaCppEmbeddings(model_path="models/llama-7b.ggmlv3.q4_0.bin")

这里改成自己下载的模型地址,比如:llama-2-7b.Q2_K.gguf

java 复制代码
llm = LlamaCpp(model_path="../llama.cpp/models/7B/llama-2-7b.Q2_K.gguf")
embeddings = LlamaCppEmbeddings(model_path="../llama.cpp/models/7B/llama-2-7b.Q2_K.gguf")
  1. 运行
java 复制代码
双击run_app.bat
  1. 测试

准备好一个txt文档

java 复制代码
As of October this year, there were nearly 2,500 geographical indication products in China
The reporter learned from the State Intellectual Property Office that in recent years, the quantity and quality of China's geographical indication products have risen rapidly. As of October this year, China has approved a total of 2,495 geographical indication products, and approved 7,013 geographical indications to be registered as collective trademarks and certification trademarks. In 2021, the direct output value of GI products exceeded 700 billion yuan.
In recent years, the State Intellectual Property Office has conscientiously implemented the decisions and arrangements of the CPC Central Committee and the State Council, actively and steadily promoted the unified acceptance channels, unified special signs, unified announcements, unified protection and supervision, unified foreign cooperation and other work, and further improved the system of protection, management and application of geographical indications.
In terms of institutional construction, the State Intellectual Property Office issued the "14th Five-Year Plan for the Protection and Use of Geographical Indications", formulated and issued a unified special indication for geographical indications, revised and issued the "Measures for the Protection of Foreign Geographical Indication Products", and launched the legislative work on geographical indications; In the year, a total of 1,416 cases of infringement of geographical indications were investigated and dealt with across the country, involving an amount of 9.28 million yuan and a fine of 13.023 million yuan

上传到页面中

没有GPU的痛苦,运行太慢了

注意:别用中文问,这个模型好像不支持中文,换一个支持中文的模型就行了

相关推荐
第九序言T1 小时前
Python 数据处理进阶(十八)批量处理同结构文件:一个文件夹一次跑完
开发语言·python·自动化·pandas·数据处理
Java后端的Ai之路1 小时前
CAS并发控制-从CPU指令到企业级乐观锁
vue.js·人工智能·python·cas·乐观锁
qq_426003961 小时前
UI自动化高频次登录login限流解决方案
python·ui·自动化
Sakura_j_h_1 小时前
EasyEDA PCB 快速设计Skills
c++·python·github
quantdash_cc2 小时前
如何验证历史行情的交易日期是否完整覆盖研究区间?
python·数据分析·pandas·量化交易·股票数据·quantdash
I Am a robert girl3 小时前
当智能体学会“串通”:从长程交互中读懂涌现式合谋
python·多智能体系统·多智能体协作·llm agent·涌现式合谋·对齐问题·激励机制设计
Zzj_tju3 小时前
准确率不变,概率质量也不变吗?
人工智能·深度学习·机器学习·语言模型
云和数据.ChenGuang3 小时前
光哥说Python RAG 系统需要哪些评估指标:从检索到生成的全链路评测指南
网络·人工智能·python·算法·langchain
专注仿真4 小时前
线性回归和逻辑回归算法详解
开发语言·人工智能·python·大模型训练·控制算法
Zzj_tju4 小时前
长期记忆让智能体更可靠,还是让错误持续累积?
人工智能·机器学习·语言模型·自然语言处理