Reranker Python Packages

pymilvus-model

A library integrating embedding and reranker models from OpenAI, SentenceTransformers etc for semantic search in vector database.

ms-swift

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).

milvus-model

A library integrating embedding and reranker models from OpenAI, SentenceTransformers etc for semantic search in vector database.

adalflow

AdalFlow: The library to build & auto-optimize LLM applications.

llama-index-postprocessor-jev

LlamaIndex reranker + router powered by TypeSafe Jev - typed scores/choices, cheaper than LLM-as-judge.

llama-index-selectors-jev

LlamaIndex reranker + router powered by TypeSafe Jev - typed scores/choices, cheaper than LLM-as-judge.

lightrag

AdalFlow: The library to build & auto-optimize LLM applications.

eeane

Run text embedding and reranking models on the Apple Neural Engine of Apple Silicon Macs. OpenAI-compatible server; ModernBERT, BERT, and XLM-RoBERTa.

langchain-localai

Langchain integration package with LocalAI. It provides embeddings and reranker support

code-rag-mcp

An MCP server that add semantic code search to your coding agent

easyrerank

A premium, self-contained Python module for local (llama.cpp) and remote (Jina AI, OpenRouter) semantic document reranking with automatic chunk splitting and vision/image reranking support.

artifex

Small Language Model Inference, Fine-Tuning and Observability.

agent-memory-engine-ljf

Long-term memory engine for coding agents: two-stage retrieval + gating, hybrid BM25+vector, Ebbinghaus decay, single SQLite file, MCP-ready. Dogfooded daily: 3,300+ memories across 4.5 months.

krino

Krino (κρίνω) — probing, analysis, and replication toolkit for JEV-class decision models

ryrank-mcp

Cohere-compatible reranker over MCP — pay-per-call in USDC, no account, no GPU, no model download.

lexilux

Unified LLM API client library for Python. Simple API for Chat, Embedding, Rerank, and Tokenizer. OpenAI-compatible with streaming support and unified usage tracking.

smaran-openai-sdk

Smaran is a state-of-the-art memory infrastructure layer designed from the ground up for AI agents. It acts as the ultimate long-term memory engine for agents like Claude Desktop, Cursor, and custom LLM workflows, allowing them to instantly recall your knowledge with perfect context.

graxon

Graxon: Open-Source Agentic Hybrid RAG to eliminate hallucinations through a persistent Knowledge Graph layer.

rag7

rag7 🕵️🍸🚗🎯 — Licensed to Retrieve

raglan-retrieval

A lightweight, highly configurable RAG retrieval engine. Framework-free, protocol-driven.

smaran-agent-framework

Smaran is a state-of-the-art memory infrastructure layer designed from the ground up for AI agents. It acts as the ultimate long-term memory engine for agents like Claude Desktop, Cursor, and custom LLM workflows, allowing them to instantly recall your knowledge with perfect context.

smaran-pipecat

Smaran is a state-of-the-art memory infrastructure layer designed from the ground up for AI agents. It acts as the ultimate long-term memory engine for agents like Claude Desktop, Cursor, and custom LLM workflows, allowing them to instantly recall your knowledge with perfect context.

smaran-cartesia

Smaran is a state-of-the-art memory infrastructure layer designed from the ground up for AI agents. It acts as the ultimate long-term memory engine for agents like Claude Desktop, Cursor, and custom LLM workflows, allowing them to instantly recall your knowledge with perfect context.