DeepImageSearch
TechyNilesh/DeepImageSearch
DeepImageSearch is a Python library for building multimodal image search engines supporting text, image, and hybrid queries via vector embeddings and LLM captioning. It features built-in agent integrations including a Model Context Protocol (MCP) server and LangChain tool wrappers.
488 93MITUpdated 2026-03-31
82
GreatOverview
DeepImageSearch provides a comprehensive framework for multi-modal image indexing and retrieval using state-of-the-art embedding models like CLIP, SigLIP, and EVA-CLIP. Designed for the agentic era, it integrates vector databases like FAISS, ChromaDB, and Qdrant with robust metadata backends such as JSON and PostgreSQL. Developers can easily query image datasets using natural language, reference images, or hybrid combinations, and connect the search engine directly to AI agents via MCP or LangChain.
Capabilities
- ▸Text-to-image semantic search
- ▸Image-to-image similarity search
- ▸Hybrid weighted search combining text and images
- ▸Automated image captioning with OpenAI-compatible vision providers
- ▸Support for multiple vector databases (FAISS, ChromaDB, Qdrant)
- ▸Metadata management with JSON or PostgreSQL backends
- ▸MCP server and LangChain tool implementations for agent integration
Best for
Building text-to-image and image-to-image search systems for media assets, Integrating visual search capabilities into AI agent pipelines using MCP or LangChain, Auto-generating captions for image datasets using vision-capable LLMs, Managing and querying large image archives with metadata filtering and persistent storage
Works with
Claude CodeCursorGitHub CopilotOpenCodeChatGPT
Evoa Score breakdown= Σ (score × weight)
82Task usefulness20%100 → +20.0
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%90 → +13.5
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%70 → +10.5
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%56 → +6.7
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%80 → +12.0
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%85 → +8.5
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%71 → +5.7
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%100 → +5.0
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total81.9 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Execution of local file indexing and integration with external LLM APIs require standard precautions regarding file system access credentials and API key secrecy.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.