Results for “retrieval”

Extends effective context capacity through strategic compression, masking, caching, and partitioning techniques.

Build LLM-powered applications with modular components for chains, agents, memory, and retrieval, supporting Python and JavaScript frameworks.

Search personal knowledge bases, notes, docs, and meeting transcripts locally using qmd — a hybrid retrieval engine with BM25, vector search, and LLM reranking. Supports CLI and MCP integration.

Search personal knowledge bases, notes, docs, and meeting transcripts locally using qmd — a hybrid retrieval engine with BM25, vector search, and LLM reranking. Supports CLI and MCP integration.

Design a lesson opening that activates prior knowledge and connects previous learning to today's content. Use when planning lesson starters, retrieval openers, or advance organisers.

Builds or modifies a RAG pipeline with intent-based routing, vector store search, citation rendering, and book fidelity enforcement.

Reranking retrieved documents with cross-encoders and LLM rerankers. Cohere Rerank v3, Voyage rerank-2, BGE reranker, ColBERT late interaction, Jina reranker. Cost and latency tradeoffs, top-K in / top-N out strategy. USE WHEN: user mentions "rerank", "reranker", "cross-encoder", "Cohere Rerank", "Voyage rerank", "BGE reranker", "ColBERT", "Jina reranker", "bi-encoder" DO NOT USE FOR: initial retrieval - use `advanced-retrieval` or `hybrid-search`; query rewriting - use `query-transformations`; agent decisions - use `agentic-rag`

Builds and validates DeepStream GStreamer pipelines through an interactive questionnaire and a BM25 retrieval engine over 270+ verified pipelines.

Automate sports betting odds retrieval and analysis via The Odds API through Composio's Rube MCP integration.

Chunks a book into canonical retrieval units with heading-aware structure splitting, recursive token targets, and contextual prefixes for downstream RAG ingestion.

Generates and manages vector embeddings for semantic search and RAG retrieval across knowledge bases, with self-learning capabilities.

Automate Exa search and data retrieval operations through Composio's Exa toolkit via Rube MCP, with dynamic tool discovery and connection management.

Connects LLMs with user data for RAG applications, document Q&A, and knowledge retrieval using 300+ data connectors and vector indices.

Build a persistent, compounding knowledge base that combines a wiki, knowledge graph, and raw source storage for structured retrieval with provenance.

Automate VirusTotal threat intelligence operations through Composio's toolkit via Rube MCP, including file scanning, URL analysis, and report retrieval.

Provides Qdrant vector database integration patterns with LangChain4j. Handles embedding storage, similarity search, and vector management for Java applications. Use when implementing vector-based retrieval for RAG systems, semantic search, or recommendation engines.

Route Firebase AI feature work into either direct app/client Firebase AI Logic SDK integration or a server-owned Genkit workflow. Use when a web, mobile, backend, or full-stack feature needs model calls, typed outputs, reusable flows, tools, retrieval, prompt files, evals, observability, or deployment. Choose client-ai-logic, flow-foundation, tool-and-agent, retrieval-and-prompt, evaluation-and-observability, deployment-runtime, or comparison-or-fallback; route Firebase platform/operator work to `firebase-cli` and broad framework comparisons to `survey`.

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

Caching strategies across the RAG stack. Semantic caching with GPTCache and LangChain, Redis-based embedding-similarity cache, cache key design, TTL/invalidation, partial caching (cache retrieval only), provider-native prompt caching (Anthropic, OpenAI), and hierarchical L1/L2 caches. USE WHEN: user mentions "semantic cache", "GPTCache", "LLM cache", "prompt caching", "Redis vector cache", "cache invalidation for RAG", "reduce LLM cost", "latency reduction LLM" DO NOT USE FOR: retrieval accuracy - use `rag-patterns`; groundedness checks - use `rag-guardrails`; incremental indexing - use `rag-production`

Guides selection of Qdrant search strategies including hybrid search, reranking, relevance feedback, MMR, and discovery APIs to improve retrieval quality.

Designs persistent memory architectures for AI agents, covering cross-session knowledge retention, entity tracking, temporal validity, graph/vector retrieval, and memory consolidation.

Search local knowledge bases, notes, docs, and meeting transcripts with hybrid retrieval combining BM25, vector search, and LLM reranking, all running on-device.

Benchmarks medical AI agents on synthetic EHR tasks, measuring success rates for data retrieval, temporal aggregation, and threshold-based conditional logic with exact-match scoring.

Knowledge-graph-augmented retrieval. Entity and triple extraction, graph construction (Neo4j, LlamaIndex PropertyGraphIndex), hierarchical community summarization (Microsoft GraphRAG), personalized PageRank (HippoRAG), multi-hop traversal retrieval, and hybrid graph + vector pipelines. USE WHEN: user mentions "GraphRAG", "HippoRAG", "knowledge graph RAG", "entity extraction", "multi-hop reasoning", "Neo4j RAG", "LlamaIndex property graph", "LangChain graph retriever", "triple extraction", "community summarization" DO NOT USE FOR: vanilla vector RAG - use `rag-patterns`; multimodal inputs - use `multimodal-rag`; production indexing ops - use `rag-production`; hallucination checks - use `rag-guardrails`

Provides patterns to build Retrieval-Augmented Generation (RAG) systems for AI applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

Use this skill for search indexing, embeddings, RAG chunking, freshness, retrieval evaluation, source citations. Trigger when the task involves ai engineering work related to Search Indexing RAG, implementation, audits, debugging, strategy, or validation.

Provides persistent, self-hosted semantic memory for AI agents via MCP, storing worklogs, decisions, and notes in PostgreSQL with pgvector for meaning-based retrieval across sessions.

Conducts autonomous multi-source research using a planner/executor architecture and an MCP server, with tools for deep research, quick search, report writing, and source retrieval.

Agent profile for evaluate RAG quality, chunking, retrieval, citations, hallucination risks, freshness, and regression sets. Use when Codex needs a specialist agent perspective for planning, implementation, review, debugging, validation, or handoff in this domain.

Review the week using accumulated session evidence — retrieval rates, hint depths, calibration accuracy, transfer and unassisted results. The learner identifies patterns and sets a strategy goal. Use weekly or after a multi-session period.

Fine-tune, evaluate, run inference, and export Cosmos-Embed1 video-text embedding models for tasks like text-to-video retrieval and semantic deduplication.

Manage design systems in Stitch using MCP tools, including retrieval of assets, creating or updating design systems, and applying them to screens.

Search external documentation (web pages, API docs, papers) and generate useful summaries for development. Use when investigating new technologies, understanding third-party APIs, researching best practices, or gathering information for technical decisions. Reduces hallucinations and expands agent knowledge.

Automates the full lifecycle of agent skills: extracts reusable constraints from user feedback, merges preferences with version bumps, and retrieves relevant skills for new tasks.

Agent profile for design AI/ML features, retrieval, model calls, structured outputs, cost controls, evals, and fallbacks. Use when Codex needs a specialist agent perspective for planning, implementation, review, debugging, validation, or handoff in this domain.

Shares memory between agents at the representation level by compacting the orchestrator's KV cache for efficient worker handoff, reducing token costs without summarization or retrieval.