Skip to main content

RAG Assistant - local knowledge base agent with multi-KB routing

Project description

RAG Assistant

本地知识库智能体系统。基于 ChromaDB + 本地 LLM 的多知识库 RAG 查询引擎。

特性

  • 多知识库路由 — 文档入库/出库均使用嵌入模型做语义路由
  • 穷举组合检索 — LLM 将问题分解为 entities × attrs 元组,多路独立检索
  • 自修正循环 — LLM 输出格式/动作校验失败时自动反馈重试
  • Web 界面 — 配置管理 + 对话窗口,双 Tab 切换
  • CLI 模式--batch / --jsonl 管道模式
  • 完全本地 — 所有数据在本地,不需要任何外部 API

快速开始

pip install rag-assistant-ldxs
python main.py --port 8765

依赖

  • Python ≥ 3.9
  • ChromaDB(向量存储)
  • LM Studio 或 Ollama(LLM 后端)
  • 嵌入模型(BGE / BCE / E5 系列)

协议

Apache 2.0

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

rag_assistant_ldxs-0.6.3-py3-none-any.whl (131.1 kB view details)

Uploaded Python 3

File details

Details for the file rag_assistant_ldxs-0.6.3-py3-none-any.whl.

File metadata

File hashes

Hashes for rag_assistant_ldxs-0.6.3-py3-none-any.whl
Algorithm Hash digest
SHA256 b6aba22f2f227edec7ae74e2487d4029e165cec65a917fe13f528cdfe7bf5c7a
MD5 039751446dda7ea8ae423e2f42ea6464
BLAKE2b-256 c05e50eea3d5cb73d4f0b3e73601c909dcf53a340d5b7a53d2d3db12c77550f7

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page