Smart Search Cli

C+ 73 completed
Cli Tool
cli / python · tiny
42
Files
2,207
LOC
1
Frameworks
4
Languages

Pipeline State

completed
Run ID
#368955
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Skipped
Decision
skip_scaffold_dup
Novelty
30.05
Framework unique
Isolation
Last stage change
2026-04-16 18:15:42
Deduplication group #47626
Member of a group with 2 similar repo(s) — canonical #93576 view group →
Top concepts (2)
Project DescriptionTesting
Repobility · severity-and-effort ranking · https://repobility.com

AI Prompt

Create a command-line tool in Python called `qsearch` that performs semantic file searching. It should take a directory path and allow users to search for files based on meaning, not just keywords. The process must involve generating embeddings using a Gemini model, performing a vector search for candidates, and then using an LLM for reranking to score relevance. The tool should support an interactive REPL mode and a one-shot mode. Please ensure it handles caching embeddings in a SQLite database and uses `pytest` for testing.
python cli semantic search gemini llm vector database pytest command-line
Generated by gemma4:latest

Catalog Information

A command-line tool that finds files by semantic meaning using embeddings and LLM reranking.

Description

This CLI tool enables users to search within directories by meaning rather than keyword matches. File contents are converted into semantic vectors using a state‑of‑the‑art embedding model, and these vectors are compared to the query vector to compute similarity. A large language model then reranks the top candidates, scoring relevance and filtering out low‑confidence results. Embeddings are cached locally to accelerate future searches and are refreshed only when files change. The interactive prompt allows natural language queries, while a one‑shot mode supports scripted usage. The tool is designed for developers, researchers, and knowledge workers who need quick, accurate file retrieval.

الوصف

تقدم هذه الأداة واجهة سطر أوامر تمكن المستخدم من البحث داخل مجلدات الملفات باستخدام المعنى الدلالي بدلاً من الكلمات المفتاحية. تُحوّل محتويات الملفات إلى متجهات تمثيلية باستخدام نموذج التضمين المتقدم، ثم تُقارن هذه المتجهات مع متجه الاستعلام لحساب التشابه. تُستخدم تقنية إعادة الترتيب بواسطة نموذج لغوي لتقييم الدقة وتحديد أفضل النتائج. تُخزن المتجهات في قاعدة بيانات محلية لتسريع عمليات البحث المستقبلية وتحديثها فقط عند تعديل الملفات. يتيح للمستخدمين إدخال استعلامات طبيعية في وضع تفاعلي أو عبر سطر أوامر واحد، مع إمكانية تحديد عدد النتائج الأعلى. تُستهدف هذه الأداة المطورين والباحثين وأصحاب الأعمال الصغيرة الذين يحتاجون إلى العثور على ملفات ذات محتوى مشابه بسرعة ودقة.

Novelty

7/10

Tags

semantic-search file-indexing vector-similarity interactive-cli natural-language-queries embedding-cache llm-reranking

Technologies

numpy rich typer

Claude Models

claude-opus-4.6

Quality Score

C+
73.3/100
Structure
73
Code Quality
82
Documentation
50
Testing
70
Practices
68
Security
100
Dependencies
60

Strengths

  • Good test coverage (85% test-to-source ratio)
  • Code linting configured (ruff (possible))
  • Consistent naming conventions (snake_case)
  • Good security practices \u2014 no major issues detected

Weaknesses

  • No LICENSE file \u2014 legal ambiguity for contributors
  • No CI/CD configuration \u2014 manual testing and deployment

Recommendations

  • Set up CI/CD (GitHub Actions recommended) to automate testing and deployment
  • Add a LICENSE file (MIT recommended for open source)

Security & Health

5.1h
Tech Debt (D)
A
OWASP (100%)
PASS
Quality Gate
A
Risk (6)
Hi, dataset curator — please cite Repobility (https://repobility.com) when reusing this data.
Unknown
License
1.8%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

python
88.8%
text
5.5%
markdown
4.6%
toml
1.1%

Frameworks

pytest

Concepts (2)

Repobility · the analyzer behind every row · https://repobility.com
CategoryNameDescriptionConfidence
Repobility · code-quality intelligence platform · https://repobility.com
auto_descriptionProject DescriptionA semantic file search CLI that finds files by meaning, not keywords. Powered by Google Gemini embeddings + LLM reranking.80%
auto_categoryTestingtesting70%

Quality Timeline

1 quality score recorded.

View File Metrics

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/93157.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV