
Feishu-OpenAI × Private Knowledge Base
Feishu Vector Knowledge Management
In addition to Feishu-OpenAI supporting internal functions, knowledge base functions have been added, including:
Knowledge Base Q&A: Use /faq or knowledge base as query instructions
? Knowledge Base CSV Import: Support importing CSV format vector data
? Knowledge Base CSV creation: Supports reconstruction of CSV format vector files to reduce token costs
Knowledge Base Management: Support importing URL web pages and file data?
Knowledge base management: Support querying database records and adding, deleting and modifying records?
? Cache problem vector: reduce token cost and reduce duplicate queries
git clone https://github.com/ConnectAI-E/Feishu-Vector-Knowledge-Management
cd Feishu-Vector-Knowledge-Management # 切割qa数据为csv文件 demo:raw.txt
go run ./cmd - prepare split -f ./data/demo/raw.txt -o ./data/demo/raw.csv
# 将csv文件转换为向量数据(调用openai-embedding-api), raw.csv 必须包含title和content字段
go run ./cmd - prepare analyze -f ./data/demo/raw.csv -o ./data/demo/vector.csv
# 导入数据csv(向量)数据
go run ./cmd - prepare import -f ./data/demo/vector.csv id,url,title,content,title_vector,content_vector,vector_id
Sample data download
Online swagger documentation: https://ui.qdrant.tech/#/
Edit docker-compose.yaml, configure the corresponding environment variables through environment (or mount the corresponding configuration file through volumes), and then run the following command
# 构建镜像
docker compose build
# 启动服务
docker compose up -d
# 停止服务
docker compose downEvent callback address: http://IP:9000/webhook/event Card callback address: http://IP:9000/webhook/card
For more nodules, please visit the project Feishu-OpenAI
Thank you to 'Find My Ai' for some funding sponsorship!