query_optimizer_agent_plan

A planned agent for improving user questions before retrieval-augmented generation (RAG), a method that searches a knowledge base before generating an answer.

In plain words
What is it for?
Use it to plan query rewriting, expansion, decomposition, contextual clarification, spelling correction, and conversion into structured queries such as SQL or Cypher.
Why use it?
It is intended to make vague or incomplete questions clearer so the knowledge-base search can return more relevant results.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/demondamon/agenticx/query_optimizer_agent_plan
Clone the repo
git clone --depth 1 https://github.com/DemonDamon/AgenticX
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,480 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01480
Opus 5 $0.00000 $0.00740
Sonnet 5 $0.00000 $0.00296
Haiku 4.5 $0.00000 $0.00148

Measured 2d ago against content hash fa32dcd0f5e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

query_optimizer_agent_plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agenticx/agents/query_optimizer_agent_plan.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Query Optimizer Agent 建设规划

1. 简介

Query Optimizer Agent 是一个专门用于在 RAG (Retrieval-Augmented Generation) 流程中优化用户查询的智能体。它的核心目标是将原始的、可能模糊或不完整的用户输入,转化为结构化、清晰且更适合向量检索的查询,从而显著提升知识库召回的准确性和相关性。

2. Agent 目标与职责

  • 提升检索准确性: 通过查询重写、扩展和分解,生成高质量的检索指令。
  • 增强语义理解: 理解用户真实意图,处理复杂的、多跳的或隐含的查询。
  • 动态适应: 根据查询的不确定性和上下文,决定是否以及如何触发检索。
  • 结构化转换: 在需要时将自然语言查询转换为结构化查询语言(如 SQL, Cypher)。
  • 反馈优化: 利用初步检索结果迭代式地优化查询。

3. 架构设计

Query Optimizer Agent 将作为 AgenticX 框架中的一个核心组件,嵌入在用户查询和知识库检索之间。

graph TD
    A[用户原始查询] --> B(Query Optimizer Agent);
    B --> C{优化策略选择};
    C -->|查询重写| D1[Query Rewriting Tool];
    C -->|查询扩展| D2[Query Expansion Tool];
    C -->|查询分解| D3[Query Decomposition Tool];
    C -->|结构化转换| D4[Structured Query Tool];

    D1 --> E(优化后的查询);
    D2 --> E;
    D3 --> E;
    D4 --> E;

    E --> F[知识库检索模块];
    F --> G[LLM 生成答案];

4. 核心能力与工具 (Tools)

为了实现上述目标,Query Optimizer Agent 将配备一系列专用工具,这些工具将作为 agenticx.tools 的一部分被实现。

4.1. query_rewriting_tool

  • 功能: 修正和重构查询。
  • 子功能:
    • contextual_rewrite: 结合对话历史,将 "它怎么样了?" 这样的模糊问题重写为 "XX产品2024年的定价方案"。
    • hyde_generate: (Hypothetical Document Embeddings) - 根据原始查询生成一个假设性的答案文档,并使用该文档的向量进行检索。
    • fix_spelling_grammar: 自动进行拼写和语法纠正。

4.2. query_expansion_tool

  • 功能: 扩展查询的语义边界,提高召回率。
  • 子功能:
    • expand_with_synonyms: 利用词向量或同义词词典(如 WordNet)为查询增加同义词或近义词。
    • generate_multiple_queries: 使用 LLM 从单一问题生成多个不同角度的相关问题,进行多路检索。
    • add_term_weights: 识别并增加查询中关键术语的权重。

4.3. query_decomposition_tool

  • 功能: 将复杂问题分解为多个可独立检索的原子查询。
  • 子功能:
    • decompose_multi_hop_question: 将 "为什么健康饮食后仍感觉疲劳?是否应尝试生酮饮食?" 分解为多个子问题。
    • route_sub_queries: (未来规划) 将不同的子查询路由到最合适的数据源(例如,一个子查询发往向量数据库,另一个发往 SQL 数据库)。

4.4. adaptive_retrieval_tool

  • 功能: 智能判断何时需要触发外部知识检索。
  • 子功能:
    • check_uncertainty: 当 Agent 对内部知识的回答置信度较低时,触发此工具进行外部检索。
    • analyze_semantic_importance: 识别查询中需要通过检索来补充信息的关键部分。

4.5. structured_query_tool

Read the full file on GitHub · 100 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 100 lines · 0 tokens per session scan A fa32dcd0f5e0

Subscribe to this mod's changes

query_optimizer_agent_plan is an agent published in the GitHub repository DemonDamon/AgenticX (219 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,480 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.