JavaScript/TypeScript implementation of LLMLingua-2 (Experimental)
nodejs javascript typescript web tensorflow transformers webgpu hf tensorflowjs prompt-engineering transformer-js prompt-compression llmlingua
- Updated
Sep 14, 2025 - TypeScript
#
prompt-compression
Here are 8 public repositories matching this topic...
Python command-line tool for interacting with AI models through the OpenRouter API/Cloudflare AI Gateway, or local self-hosted Ollama. Optionally support Microsoft LLMLingua prompt token compression
openai linkup opik rag openai-api txtai llms llm-inference openrouter ollama cloudflare-ai ollama-api prompt-compression structured-outputs openai-api-client openrouter-api cloudflare-ai-gateway ai-rag llmlingua
- Updated
Aug 7, 2025
This repository is the official implementation of Generative Context Distillation.
- Updated
May 10, 2025 - Python
Compress LLM Prompts and save 80%+ on GPT-4 in Python
- Updated
Jan 17, 2024 - Python
A fast, Unix-style CLI tool for semantic prompt compression. Cuts LLM prompt tokens by 10-20x with >90% fidelity, saving costs and latency.
- Updated
Sep 19, 2025 - Python
Enhance the performance and cost-efficiency of large-scale Retrieval Augmented Generation (RAG) applications. Learn to integrate vector search with traditional database operations and apply techniques like prefiltering, postfiltering, projection, and prompt compression.
mongodb projection query-optimization search-relevance data-retrieval performance-optimization reranking data-security vector-search developer-advocacy query-processing vector-search-engine database-operations prefiltering cost-efficiency data-retrieval-and-display prompt-compression rag-applications postfiltering large-scale-applications
- Updated
Jul 23, 2024 - Jupyter Notebook
This repository contains the code and data of the paper titled "FrugalPrompt: Reducing Contextual Overhead in Large Language Models via Token Attribution."
- Updated
Oct 30, 2025 - Jupyter Notebook
RL-Prompt-Compression employs graph-enhanced reinforcement learning with a Phi-3 compressor trained via GRPO using a TinyLlama evaluator and a MiniLM cross-encoder feedback model, to optimize prompt compression and improve model efficiency.
- Updated
Oct 31, 2025 - Jupyter Notebook
Improve this page
Add a description, image, and links to the prompt-compression topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the prompt-compression topic, visit your repo's landing page and select "manage topics."