verbatim-rag AI技能包 是 AI Skill Hub 本期精选AI工具之一。综合评分 8.2 分,整体质量较高。我们强烈推荐将其纳入你的 AI 工具库,帮助提升工作效率。
专注于防止大语言模型幻觉的开源RAG系统,通过逐字span提取技术确保生成内容的准确性和可溯源性。适合对检索增强生成精度要求高的开发者和研究人员。
verbatim-rag AI技能包 是一款基于 Python 开发的开源工具,专注于 RAG系统、幻觉防控、文本提取 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
专注于防止大语言模型幻觉的开源RAG系统,通过逐字span提取技术确保生成内容的准确性和可溯源性。适合对检索增强生成精度要求高的开发者和研究人员。
verbatim-rag AI技能包 是一款基于 Python 开发的开源工具,专注于 RAG系统、幻觉防控、文本提取 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
# 方式一:pip 安装(推荐)
pip install verbatim-rag
# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install verbatim-rag
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/KRLabsOrg/verbatim-rag
cd verbatim-rag
pip install -e .
# 验证安装
python -c "import verbatim_rag; print('安装成功')"
# 命令行使用
verbatim-rag --help
# 基本用法
verbatim-rag input_file -o output_file
# Python 代码中调用
import verbatim_rag
# 示例
result = verbatim_rag.process("input")
print(result)
# verbatim-rag 配置文件示例(config.yml) app: name: "verbatim-rag" debug: false log_level: "INFO" # 运行时指定配置文件 verbatim-rag --config config.yml # 或通过环境变量配置 export VERBATIM_RAG_API_KEY="your-key" export VERBATIM_RAG_OUTPUT_DIR="./output"
<p align="center"> <img src="https://github.com/KRLabsOrg/verbatim-rag/blob/main/assets/chiliground.png?raw=true" alt="ChiliGround Logo" width="400"/> <br><em>Chill, I Ground! 🌶 ️</em> </p>
Provenance-first extractive RAG: retrieve documents, select answer-relevant passages, and return source excerpts with citations instead of freely rewriting the evidence.
- Docker with Docker Compose v2.24+ (the stack uses the optional env_file syntax) - An OpenAI-compatible API key (Groq by default, see api/dependencies.py)
The image installs from docker/constraints.txt, a generated lock of one known-working environment. pyproject.toml keeps the library's broad supported ranges; the lock narrows them for the container only, so a resolution that breaks the stack cannot silently reach the image. The hand-maintained input and the regeneration command are documented in docker/overrides.txt; regenerate after changing dependencies in pyproject.toml or bumping packages/core.
```bash
pip install verbatim-rag
For local development:
bash pip install -e packages/core/ pip install -e . ```
Set your OpenAI API key before using the system:
export OPENAI_API_KEY=your_api_key_here
Docker Compose runs the API and the web UI together as a development and demo stack. It is meant for local work and evaluation; it is not a production deployment (no TLS, authentication, tenancy, or scaling).
```bash
docker compose up --build
```python from verbatim_rag import VerbatimIndex, VerbatimRAG from verbatim_rag.ingestion import DocumentProcessor from verbatim_rag.vector_stores import LocalMilvusStore from verbatim_rag.embedding_providers import SpladeProvider
cp .env.example .env
| Variable | Default | Description |
|---|---|---|
OPENAI_API_KEY | (required) | OpenAI-compatible API key |
INDEX_PATH | /data/index.db | Milvus Lite database path in the container |
FRONTEND_PORT | 8080 | Host port the frontend is published on |
All of these can be set in .env (copy .env.example) or exported in the shell. CORS configuration is not needed: the browser only talks to nginx, which proxies /api/ to the backend same-origin (the Vite dev server does the same via its own proxy).
The repository contains a FastAPI API and Vite/React development UI. They are not included in the PyPI wheel and are not yet part of the same compatibility gate as verbatim-core. The Compose stack below runs both locally (#27); the document lifecycle contract is tracked in #31.
verbatim_rag/core.py): Main orchestrator that coordinates document retrieval, span extraction, and response generationverbatim_rag/index.py): Vector-based document indexing and retrievalverbatim_rag/extractors.py): Abstract interface for extracting relevant text spans from documentsverbatim_rag/ingestion/): Docling + Chonkie integration for intelligent document processingverbatim_rag/document.py): Core document representation with metadata创新的幻觉防控方案,通过逐字提取提升RAG可信度。代码活跃度好,解决实际问题,值得关注。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
经综合评估,verbatim-rag AI技能包 在AI工具赛道中表现稳健,质量优秀。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | verbatim-rag |
| 原始描述 | 开源AI工具:Hallucination-prevention RAG system with verbatim span extraction. Ensures all g。⭐174 · Python |
| Topics | RAG系统幻觉防控文本提取LLM优化ModernBERT |
| GitHub | https://github.com/KRLabsOrg/verbatim-rag |
| License | MIT |
| 语言 | Python |
收录时间:2026-05-18 · 更新时间:2026-05-19 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。