Skip to content
#

cross-encoder

Star

Here are 135 public repositories matching this topic...

Language: All
Filter by language
All 135 Python 102 Jupyter Notebook 23 Rust 3 TypeScript 3 HTML 2 Shell 1
Sort: Most stars
Sort options
Most stars Fewest stars Most forks Fewest forks Recently updated Least recently updated

lemon07r / Vera

Sponsor
Star 95

Local code search combining BM25, vector similarity, and cross-encoder reranking. Parses 60+ languages with tree-sitter, runs entirely offline, and returns structured results with file paths, line ranges, and symbol metadata. Built in Rust.

rust cli tree-sitter local retrieval skills mcp embeddings code-search semantic-search-engine semantic-search bm25 reranking onnx rag code-search-engine vector-search cross-encoder mcp-server
  • Updated May 13, 2026
  • Rust

cambridgeltl / BLICEr

Star 13

Improving Bilingual Lexicon Induction with Cross-Encoder Reranking (Findings of EMNLP 2022). Keywords: Bilingual Lexicon Induction, Word Translation, Cross-Lingual Word Embeddings.

information-retrieval machine-translation word-embeddings pytorch self-learning word-alignment reranking bilingual-word-embedding bilingual-lexicon-extraction fasttext-embeddings cross-lingual-embeddings xlm-roberta xlm-r low-resource-machine-translation bilingual-lexicon-induction cross-encoder cross-lingual-word-embedding word-translation cross-lingual-word-embeddings bilingual-dictionary-induction
  • Updated Feb 2, 2023
  • Python

MERakram / Advanced-RAG-monorepo

Star 6

🚀 Production-ready modular RAG monorepo: Local LLM inference (vLLM) • Hybrid retrieval with Qdrant • Semantic caching • Docling document parsing • Cross-encoder reranking • DeepEval evaluation • Full observability with Langfuse • Open WebUI chat interface • OpenAI-compatible API • Fully Dockerized

python nlp ai self-hosted reranking rag fastapi vector-database cross-encoder qdrant vllm langfuse open-webui deepeval
  • Updated Jan 28, 2026
  • Python

hwdsl2 / docker-embeddings

Sponsor
Star 4

Docker image to run a self-hosted text embeddings and reranking server powered by Hugging Face TEI, with an OpenAI-compatible API. Supports BGE, Nomic, MiniLM and other models. Features optional reranking via cross-encoder models, API key auth, model management, offline/air-gapped mode, and persistent model cache.

linux docker information-retrieval ai docker-compose docker-image self-hosted embeddings openai semantic-search reranking rag sentence-transformers hugging-face cross-encoder llm langchain retrieval-augmented-generation text-embeddings-inference openai-compatible
  • Updated Jun 6, 2026
  • Shell

Improve this page

Add a description, image, and links to the cross-encoder topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the cross-encoder topic, visit your repo's landing page and select "manage topics."

Learn more