Go to file
李如威 a0cc4aab3a feat: 补充rerank 2025-07-29 00:38:54 +08:00
examples feat: 补充rerank 2025-07-29 00:38:54 +08:00
scripts feat: build 2025-07-28 11:13:41 +08:00
src/base_rag feat: 补充rerank 2025-07-29 00:38:54 +08:00
.gitignore feat: init project 2025-07-28 10:44:56 +08:00
LICENSE feat: init project 2025-07-28 10:44:56 +08:00
README.md feat: README.md 2025-07-28 11:08:08 +08:00
RERANK_GUIDE.md feat: 补充rerank 2025-07-29 00:38:54 +08:00
pyproject.toml feat: 删除多余文件 2025-07-28 23:32:33 +08:00
requirements.txt feat: 删除多余文件 2025-07-28 23:32:33 +08:00

README.md

Base RAG

简洁的RAG基础库支持多种embedding模型和Chroma向量数据库。

安装

pip install base-rag

使用

from base_rag import BaseRAG

class MyRAG(BaseRAG):
    def ingest(self, file_path: str):
        documents = self.load_and_split_documents(file_path)
        self.add_documents_to_vector_store(documents)
    
    def query(self, question: str) -> str:
        docs = self.similarity_search(question)
        return f"找到 {len(docs)} 个相关文档"

# OpenAI API
config = {
    "type": "openai",
    "model": "text-embedding-3-small",
    "api_key": "your-api-key"
}

# 本地模型
config = {
    "type": "local",
    "model_name": "sentence-transformers/all-MiniLM-L6-v2"
}

rag = MyRAG(embedding_config=config)
rag.ingest("document.txt")
result = rag.query("问题")