← 返回 Skills 市场
zhangifonly

Llamaindex

作者 zhangifonly · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
229
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install llamaindex
功能描述
LlamaIndex RAG 框架助手,精通文档索引、检索增强生成、向量存储、查询引擎
使用说明 (SKILL.md)

LlamaIndex RAG 框架助手

你是 LlamaIndex(原 GPT Index)领域的专家,帮助用户构建高质量的检索增强生成系统。

核心概念

概念 说明
Document 原始数据源(PDF、网页、数据库等)的抽象表示
Node Document 切分后的文本块,是索引的基本单元
Index 对 Node 的组织结构,支持向量、摘要、知识图谱等类型
QueryEngine 查询引擎,从 Index 中检索相关内容并生成回答
Retriever 检索器,从 Index 中获取相关 Node

安装

pip install llama-index
pip install llama-index-llms-openai          # OpenAI LLM
pip install llama-index-embeddings-openai    # OpenAI Embedding
pip install llama-index-vector-stores-chroma # Chroma 向量库

快速开始:5 行代码构建 RAG

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader

documents = SimpleDirectoryReader("./data").load_data()
index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine()
response = query_engine.query("这份文档的主要内容是什么?")

数据加载

from llama_index.core import SimpleDirectoryReader

# 通用文件加载,支持 PDF、DOCX、TXT、CSV 等
documents = SimpleDirectoryReader(
    input_dir="./data",
    recursive=True,
    required_exts=[".pdf", ".md"],
    filename_as_id=True
).load_data()

# 专用 Loader(LlamaHub 生态)
from llama_index.readers.web import SimpleWebPageReader
docs = SimpleWebPageReader().load_data(["https://example.com"])

索引类型

索引类型 适用场景 说明
VectorStoreIndex 语义搜索(最常用) 将 Node 转为向量,余弦相似度检索
SummaryIndex 全文摘要 遍历所有 Node 生成摘要
TreeIndex 层级摘要 自底向上构建摘要树
KnowledgeGraphIndex 知识图谱 提取实体关系
KeywordTableIndex 关键词检索 基于关键词匹配

向量存储集成

import chromadb
from llama_index.vector_stores.chroma import ChromaVectorStore
from llama_index.core import StorageContext

chroma_client = chromadb.PersistentClient(path="./chroma_db")
collection = chroma_client.get_or_create_collection("my_docs")
vector_store = ChromaVectorStore(chroma_collection=collection)
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(documents, storage_context=storage_context)

支持的向量数据库

向量库 特点 适用场景
Chroma 轻量嵌入式,零配置 本地开发、小规模
Qdrant 高性能,丰富过滤 生产环境推荐
Pinecone 全托管云服务 免运维需求
Milvus 大规模分布式 亿级向量数据
FAISS Meta 出品,纯内存 高性能本地检索

查询引擎高级配置

query_engine = index.as_query_engine(
    similarity_top_k=5,           # 检索 Top-K 个相关片段
    response_mode="compact",      # compact/refine/tree_summarize
    streaming=True                # 流式输出
)

与 LangChain 对比

特性 LlamaIndex LangChain
核心定位 RAG 专精,数据索引和检索 通用 LLM 应用框架
数据处理 内置丰富的文档加载和切分 需要更多手动配置
索引能力 多种索引类型,开箱即用 依赖向量库直接集成
查询优化 内置 Reranker、路由、子问题分解 需要手动编排 Chain
适用场景 知识库问答、文档分析 Agent、工作流、通用应用
组合使用 可作为 LangChain 的 Retriever 可集成 LlamaIndex 索引
安全使用建议
This skill is an instructional guide for using LlamaIndex and is internally consistent. Before installing or following the instructions: (1) run pip installs inside a virtualenv/container and verify package names and versions; (2) be aware the examples read local files (./data) and create a local Chroma DB (./chroma_db) — only point the agent at data you want indexed; (3) if you plan to use OpenAI (or other LLM/embedding providers), you will need to provide API keys (e.g., OPENAI_API_KEY) — do not share unrelated credentials; (4) review and understand any code/examples before executing them, especially web loaders that fetch remote pages.
功能分析
Type: OpenClaw Skill Name: llamaindex Version: 1.0.0 The skill bundle is a standard educational resource for the LlamaIndex RAG framework. It contains legitimate installation commands, core concept explanations, and boilerplate Python code for document indexing and retrieval (SKILL.md). No indicators of malicious intent, data exfiltration, or prompt injection were found.
能力评估
Purpose & Capability
The name/description match the SKILL.md content: it teaches how to install and use LlamaIndex, vector stores, loaders, and query engines. All commands and examples relate to building RAG pipelines.
Instruction Scope
Instructions legitimately show reading local data (./data), creating a local Chroma DB (./chroma_db), and optionally loading web pages. These are expected for indexing/RAG, but they do mean the agent following these instructions could read and write local files and fetch remote pages — users should only point it at data they want indexed.
Install Mechanism
There is no install spec in the registry (instruction-only). The SKILL.md suggests pip install commands (standard PyPI packages). That is normal, but running them installs third-party packages into the environment, so prefer a virtualenv and verify package names/versions before installing.
Credentials
The skill declares no required environment variables, which is consistent. The docs recommend OpenAI-related packages (llama-index-llms-openai, embeddings-openai) — using those will require provider API keys (e.g., OPENAI_API_KEY) though the skill doesn't declare them. Users should only supply credentials for services they intend to use.
Persistence & Privilege
always:false and no install hooks; the skill does not request persistent platform privileges or override other skills. It only provides instructions the agent could follow when invoked.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install llamaindex
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /llamaindex 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
- Initial release of the LlamaIndex skill, version 1.0.0. - Provides concise documentation and usage examples for LlamaIndex's RAG framework, covering document indexing, retrieval, vector stores, and query engines. - Includes quick start guide, core concepts, supported vector databases, advanced query engine configuration, and comparison with LangChain. - Documentation and commands in Chinese for accessible onboarding and expert guidance.
元数据
Slug llamaindex
版本 1.0.0
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 1
常见问题

Llamaindex 是什么?

LlamaIndex RAG 框架助手,精通文档索引、检索增强生成、向量存储、查询引擎. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 229 次。

如何安装 Llamaindex?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install llamaindex」即可一键安装,无需额外配置。

Llamaindex 是免费的吗?

是的,Llamaindex 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Llamaindex 支持哪些平台?

Llamaindex 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Llamaindex?

由 zhangifonly(@zhangifonly)开发并维护,当前版本 v1.0.0。

💬 留言讨论