Comments (1)
本项目不是使用微调的方式,所以并不涉及到训练过程。
主要原理是输入文档路径后,读取文本➡️文本分割➡️文本向量化➡️问句向量化➡️在文本向量中匹配出与问句向量最相似的top k个➡️匹配出的文本作为上下文和问题一起添加到prompt中➡️提交给llm生成回答
from langchain-chatchat.
Related Issues (20)
- [BUG] reranker后报错了:0SError:[WinError 10038]在一个非套接字上尝试了一个操作;麻烦大佬看一看 HOT 5
- embedding的时候只能用到单卡 HOT 1
- 未找到相关文档,该回答为大模型自身能力解答! HOT 1
- 以docker方式运行时,如何修改启动参数 HOT 1
- 本地加载大模型,qwen15-32B-AWQ,不能使用GPU,请问要如何配置 HOT 3
- [FEATURE] 增加对非OpenXML格式的Word文件(.doc)的识别
- 设置CHUNK_SIZE 检索知识库返回content长度无变化 HOT 1
- 知识库检索的代码 HOT 2
- 没有报错,URL正确输出,点击后无法显示,加载不出UI界面 HOT 2
- [BUG] 简洁阐述问题 / 使用命令 python startup.py -a启动时出错 HOT 1
- 0.2.10,对话报错 HOT 1
- 对话正常,切换到知识库,报错:UnicodeEncodeError: 'utf-8' codec can't encode characters in position 4-5: surrogates not allowed HOT 1
- 切换milvus向量库,初始化数据报错 HOT 1
- 使用milvus数据库,初始化数据库的时候,显存爆炸。 HOT 2
- windows 上启动后进行交互,请求地址出现https://api.segment.io/v1/t,请问这是在哪配置的 HOT 1
- 对Qwen1.5以上模型使用vllm加速推理依赖问题 HOT 1
- 对Qwen1.5以上模型使用vllm加速推理依赖问题 HOT 1
- 上传文件后对话正常,返回知识库时报错:Bad message format Tried to use SessionInfo before it was initialized HOT 1
- 连接milvus数据库,进行初始化数据库,报错 HOT 3
- cannot import name 'AutoTokenizer' from 'transformers'错误 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from langchain-chatchat.