rerank library for easy reranking of results
RaBitQ 1-bit quantized vector index in WebAssembly — 32× embedding compression with high-recall rerank, for browsers, Cloudflare Workers, Deno, and Bun
Local cross-encoder reranker for Engram — runs mxbai-rerank-v1 via ONNX Runtime (no API calls)
MemberJunction: Cohere AI Provider - Semantic reranking using Cohere's Rerank API
OpenTelemetry GenAI utility for standardized telemetry collection across LLM, Agent, Embedding, Tool, Retrieval, Rerank, Memory and more
OpenClaw enhanced LanceDB memory plugin with hybrid retrieval (Vector + BM25), cross-encoder rerank, multi-scope isolation, long-context chunking, and management CLI
Jina AI provider for @effect-uai/core (embeddings, rerank).
n8n node for Berget AI rerank models
WASM module for Flash-Rerank — browser and edge inference via tract
BabyAPI client (OpenAI-compatible /v1/completions, /v1/chat/completions, /v1/embeddings, /v1/rerank, plus /docling document conversion).
Reranker nodes for n8n - Custom rerank API (recommended), VL Classifier, Ollama Generate (experimental). Vector Store provider + workflow node.
MCP server for LangSearch Web Search & Semantic Rerank API. Use with Claude Code, Claude Desktop, or any MCP-compatible client.
MergeMind MCP server — read-only доступ к общей памяти команды агентов (markdown vault с гибридным поиском BM25 + vector + rerank). Запускается через `npx -y @agfpd/mergemind-mcp@latest` из .mcp.json плагина MergeMind (gh-репо agfpd/MergeMind).
OpenTelemetry GenAI utility for standardized telemetry collection across LLM, Agent, Embedding, Tool, Retrieval, Rerank, Memory and more
Advanced Hybrid Retriever node for n8n with Rerank support and Metadata passthrough
Provider-neutral reranking contracts and utilities for TekMemo.
RaBitQ 1-bit quantized vector index in WebAssembly — 32× embedding compression with high-recall rerank, for browsers, Cloudflare Workers, Deno, and Bun
OpenClaw enhanced LanceDB memory plugin with hybrid retrieval (Vector + BM25), cross-encoder rerank, multi-scope isolation, long-context chunking, and management CLI
Local ONNX cross-encoder reranking for JavaScript / TypeScript. Vercel AI SDK rerank() but local — zero API costs, edge-runtime ready.
Convenience reexports for TekMemo AI SDK, provider, vector, rerank, and cloud adapters.
Voyage AI reranking adapter for TekMemo.
MCP-first SKILL.md routing for AI agents: local embeddings, SQLite sessions and telemetry, optional LLM rerank paths, regex route policies and project overlays, companion conversation preset, parity CLI.
OpenClaw enhanced LanceDB memory plugin with hybrid retrieval (Vector + BM25), cross-encoder rerank, multi-scope isolation, long-context chunking, and management CLI
MCP server for LanceDB-backed long-term memory with hybrid retrieval (Vector + BM25), cross-encoder rerank, multi-scope isolation, and memory lifecycle management
Fast rank fusion algorithms for hybrid search (RRF, CombMNZ, Borda)
A client for generating embeddings and reranking with Voyage AI
Search result re-ranking — local multi-signal fusion + remote Rerank API
Pure Rust library for local embeddings, reranking, and text generation with MoE-optimized inference and aggressive performance tuning
Cross-encoder reranking for frankensearch (FlashRank + FastEmbed)
Semantic code + document search engine. Cacheless static-embedding + cross-encoder rerank by default; optional ModernBERT/BGE transformer engines with GPU backends. Tree-sitter chunking, hybrid BM25 + PageRank, composable ranking layers.
Local markdown semantic search with hybrid BM25+vector retrieval and LLM reranking
Cross-encoder reranker adapters for mnem (Cohere, Voyage, Jina). Sync, TLS-via-rustls, tokio-free.
Semantic code search CLI — like ripgrep but for meaning
MCP + LSP server for ripvec — semantic code search, PageRank repo maps, and multi-language code intelligence
BM25 reranker for RAG: in-memory term-frequency reranking against a small candidate set. Stateless, zero deps.
Lightweight ndarray-native compute and rerank layer for embedding vectors
A cross-encoder reranking library for Ruby. Supports Cohere, Jina, and local ONNX models. The single biggest quality improvement you can add to a RAG pipeline.
Ruby gem for running state-of-the-art language models locally. Access LLMs, embeddings, rerankers, and NER models directly from Ruby using Rust-powered Candle with Metal/CUDA acceleration.
A lightweight, Fiber-friendly Ruby client for OpenAI-compatible LLM APIs. (chat, embeddings, audio, rerank, health).
OpenRouter Ruby client: chat (streaming SSE), configurable retries for non-streaming completions, optional DB-backed API call logging, Responses API defaults, models listing with filters and free-tier hints, embeddings, rerank, audio, video, OAuth, API keys, guardrails, workspaces, and related REST endpoints.
pikuri-vectordb gives a pikuri-core agent a +vectordb_search+ tool over a local document corpus — agentic search, the agent decides when to retrieve. Ships a swappable backend (a pure-Ruby +Backend::InMemory+ for teaching and a thin +Backend::Chroma+ HTTP client for persistence), a chunker, an embedder wrapper over +RubyLLM.embed+, and an optional +Reranker::LlamaServer+ that speaks +/v1/rerank+ against a cross-encoder model. Text extraction goes through +Pikuri::FileType.read_as_text+ in pikuri-core, which handles plain text / Markdown / PDF; HTML extraction is a deferred follow-up. Hosts wire the feature via +c.add_extension Pikuri::VectorDb::Extension.new(...)+ inside the +Agent.new+ block — same opt-in shape as +pikuri-tasks+ / +pikuri-skills+. The bundled +Pikuri::VectorDb::LIBRARIAN+ persona is the privilege-separated sub-agent counterpart for hosts that want recall to flow through a child rather than the parent's context. Three model endpoints in the full setup — chat (via ruby_llm), an embedder (via +RubyLLM.embed+), and an optional reranker (HTTP +/v1/rerank+). A single +llama-server+ in router mode serves all three by default, loading each cached GGUF on demand; see the gem's README for details.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.