Skills tagged: vector-search

• memory-lancedb-pro - Maintenance guide for memory-lancedb-pro OpenClaw plugin

  openclawlancedbmemory-pluginhybrid-retrieval

  ★ 47 · Updated 2026-09-22

  Provides developer guidance for maintaining, debugging, and enhancing the memory-lancedb-pro OpenClaw plugin.

  ⚙ Develop plugin features and bugfixes⚙ Modify retrieval pipeline stages⚙ Configure embedding and rerank providers
• azure-search-documents-dotnet - Build search apps using Azure AI Search .NET SDK.

  azuredotnetsearchvector-search

  ★ 1 · Updated 2026-09-22

  Azure AI Search SDK for .NET supporting full-text, vector, semantic, and hybrid search operations.

  ⚙ Create and manage search indexes⚙ Upload, merge, and delete documents⚙ Perform full-text search queries
• AgentDB Vector Search - Semantic vector search with AgentDB

  vector-searchagentdbsemantic-searchrag

  ★ 2 · Updated 2026-09-20

  Implements vector-based semantic search using AgentDB for document retrieval, similarity matching, and context-aware querying.

  ⚙ Initialize vector database⚙ Query vector database⚙ Export vectors to JSON
• ai-engineer - Build production-ready LLM applications and AI agents

  aillmragagent

  ★ 0 · Updated 2026-09-19

  Develops production-ready LLM applications, advanced RAG systems, vector search, multimodal AI, and agent orchestration.

  ⚙ Build LLM applications⚙ Implement RAG systems⚙ Orchestrate multi-agent workflows
• ai-engineer - Build production LLM applications, RAG, and AI agents.

  llmragai-agentsvector-search

  ★ 0 · Updated 2026-09-19

  Implements LLM applications, RAG systems, vector search, agent orchestration, multimodal AI, and enterprise AI integrations.

  ⚙ Integrate LLM models and serving frameworks⚙ Build multi-stage retrieval RAG pipelines⚙ Orchestrate multi-agent workflows and memory
• ai-engineer - AI Engineer for LLM Applications, RAG, and AI Agents

  llmragai-agentsvector-search

  ★ 1 · Updated 2026-09-19

  Builds production-ready LLM applications, advanced RAG systems, intelligent agents, and multimodal AI integrations.

  ⚙ Integrate LLM models and serving frameworks⚙ Build advanced RAG systems⚙ Orchestrate multi-agent workflows and memory
• fde-kb - FDE Knowledge Base (Obsidian + sqlite-vec)

  obsidianknowledge-basevector-searchsqlite-vec

  ★ 0 · Updated 2026-09-19

  Perform local search, note lookup, ingestion, and evaluation over the team's Obsidian knowledge base vault.

  ⚙ Search Obsidian vault notes⚙ Read vault note content⚙ Ingest new note into vault
• cx-conversation-embedding-pipeline - Design a support conversation vectorisation pipeline

  vector-searchsemantic-searchembedding-pipelinesupport-data

  ★ 1 · Updated 2026-09-18

  Designs a pipeline that vectorises support conversations for semantic search while managing chunking, PII redaction, and deletion.

  ⚙ Chunk conversations on turn boundaries⚙ Attach metadata filters to vectors⚙ Redact PII prior to embedding
• azure-search-documents-ts - Build search apps with Azure AI Search SDK for TypeScript

  azureazure-ai-searchtypescriptvector-search

  ★ 0 · Updated 2026-09-17

  Build search applications, manage indexes, and perform vector, hybrid, and semantic search using the @azure/search-documents package.

  ⚙ Create and update search indexes⚙ Upload and index documents⚙ Execute full-text search queries
• azure-search-documents-ts - Azure AI Search SDK for TypeScript

  azure-ai-searchtypescriptvector-searchhybrid-search

  ★ 0 · Updated 2026-09-17

  Build search applications using Azure AI Search SDK for TypeScript supporting vector, hybrid, and semantic search.

  ⚙ Create and update search indexes⚙ Upload and batch index documents⚙ Execute full text search queries
• azure-search-documents-ts - Azure AI Search SDK for TypeScript

  azure-searchtypescriptvector-searchhybrid-search

  ★ 0 · Updated 2026-09-17

  Build search applications with vector, hybrid, and semantic search capabilities.

  ⚙ Create search index⚙ Upload and index documents⚙ Perform full-text search
• rag-expert - RAG Knowledge Base Management Expert

  ragknowledge-basellamaindexzhipu-ai

  ★ 14 · Updated 2026-09-17

  Provides RAG knowledge base management including document uploading, vector indexing, semantic search, and document maintenance using LlamaIndex and ZhiPu AI.

  ⚙ Upload document to knowledge base⚙ Query knowledge base semantically⚙ List imported documents
• code-refactoring-context-restore - Restore semantic memory and context in AI workflows

  context-restorationsemantic-memoryvector-searchmulti-agent

  ★ 6 · Updated 2026-09-17

  Recovers, reconstructs, and rehydrates project context and semantic memory across multi-agent AI workflows.

  ⚙ Retrieve semantic vectors⚙ Rank context components⚙ Rehydrate project context
• code-refactoring-context-restore - Context Restoration: Advanced Semantic Memory Rehydration

  context-restorationsemantic-memorycode-refactoringrag

  ★ 0 · Updated 2026-09-16

  Recover and reconstruct project context across distributed AI workflows.

  ⚙ Recover and reconstruct project context⚙ Retrieve context vectors semantically⚙ Rank context components by relevance
• rag-expert - Retrieval-Augmented Generation Patterns on OCI

  ragocioracle-cloudvector-search

  ★ 0 · Updated 2026-09-16

  Provides architecture patterns, model selection, vector store options, and retrieval optimization guidance for RAG on Oracle Cloud Infrastructure.

  ⚙ Design RAG architectures on OCI⚙ Select embedding models and vector stores⚙ Optimize retrieval and hybrid search
• rag-expert - RAG Expert for Oracle Cloud Infrastructure

  ragocioracle-cloudvector-search

  ★ 1 · Updated 2026-09-16

  Provides patterns and guidance for building production RAG systems on Oracle Cloud Infrastructure.

  ⚙ Design enterprise RAG architectures⚙ Select embedding models and vector stores⚙ Optimize retrieval quality
• rag-knowledge-management - RAG Knowledge Management

  ragqdrantknowledge-managementvector-search

  ★ 12 · Updated 2026-09-11

  Search, analyze, and save technical facts, project state, and user feedback to Qdrant vector collections.

  ⚙ Search experience and demo collections⚙ Analyze context and user feedback⚙ Save technical facts to Qdrant
• hybrid-search-implementation - Combine vector and keyword search for improved retrieval.

  hybrid-searchvector-searchkeyword-searchrag

  ★ 1 · Updated 2026-09-09

  Provides implementation patterns for combining vector similarity and keyword search in RAG systems.

  ⚙ Combine vector and keyword search⚙ Clarify goals and constraints⚙ Apply search best practices
• hybrid-search-implementation - Hybrid Search Implementation

  hybrid-searchragvector-searchkeyword-search

  ★ 281 · Updated 2026-09-09

  Combines vector similarity and keyword search to improve retrieval recall in RAG systems and search engines.

  ⚙ Combine vector and keyword search⚙ Build high-recall RAG systems⚙ Handle queries with specific terms
• episodic-claw - Local episodic memory engine for OpenClaw

  episodic-memoryopenclawgeminivector-search

  ★ 9 · Updated 2026-09-09

  Local episodic memory engine for OpenClaw using a Go sidecar for Gemini embeddings and vector search.

  ⚙ Retrieve relevant past episodes⚙ Prepend memories to system prompt⚙ Read and write episode files

Scroll to load more