Official code for ACL2025 "🔍 Retrieval Models Aren’t Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models"
-
Updated
Dec 22, 2025 - JavaScript
#
retrieval-evaluation
Here are 59 public repositories matching this topic...
smallevals — CPU-fast, GPU-blazing fast offline retrieval evaluation for RAG systems with tiny QA models.
qa chroma question-generation weaviate qa-generation milvus vector-database qdrant chromadb rag-evaluation tiny-llm retrieval-evaluation offline-evaluation retrieval-metrics
-
Updated
Dec 4, 2025 - Python
Official codebase for the ACL 2025 Findings paper: Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrieval.
information-retrieval bert bm25 passage-retrieval ndcg text-embedding amharic-corpus mrr roberta amharic-nlp huggingface-transformers colbert multilingual-nlp low-resource-nlp dense-retrieval amharic-language retrieval-evaluation academic-benchmark
-
Updated
Jul 26, 2025 - Jupyter Notebook
面向智能清洁设备售前咨询、故障诊断与用户运营的企业级多智能体服务平台。基于 LangChain/LangGraph、通义千问、Chroma RAG、FastAPI、React 与 SQLite，集成调度 Agent、受控 Skill、知识库安全运营、JWT/RBAC、分层记忆与用户可控遗忘、定位天气、流式执行摘要及 Recall@K/MRR 评测。
sqlite geolocation customer-support rag streamlit vector-database ai-agent open-meteo langchain prompt-injection chromadb qwen langgraph dashscope retrieval-evaluation
-
Updated
Sep 2, 2026 - Python
Validate TREC qrels and runs in CI; explore a MiniLM browser lab and FAISS + DeBERTa product-search pipeline.
information-retrieval validator e-commerce reproducibility semantic-search reranking trec trec-eval faiss github-actions github-action product-search pyodide neural-search qrels browser-demo transformers-js retrieval-evaluation evaluation-tools amazon-esci
-
Updated
Jul 29, 2026 - Python
Hybrid RAG (BM25 + NumPy in-memory vector store) with LLM-as-a-Judge response scoring and a retrieval evaluation harness. Built with Gemini 2.5 Flash.
python information-retrieval evaluation gemini bm25 rag streamlit hybrid-search llm llm-as-a-judge retrieval-evaluation
-
Updated
Aug 20, 2026 - Python
Published PyPI package for ArXiv embedding benchmarks, retrieval evaluation, and scientific RAG experiments.
nlp benchmarking retrieval embeddings arxiv model-evaluation rag pypi-package scientific-ml retrieval-evaluation
-
Updated
May 22, 2026 - Python
Human-verified evaluation for RAG, policies, search quality, model versions, and AI agents.
electron python macos evaluation policy-evaluation human-in-the-loop ai-agents llmops llm-evaluation rag-evaluation agent-evaluation retrieval-evaluation goldset
-
Updated
Jul 16, 2026 - Python
image-reconstruction neuroscience pytorch medical-imaging neuroimaging nsd fmri representation-learning clip uncertainty-estimation probabilistic-modeling multimodal-learning self-supervised-learning brain-decoding contrastive-learning stable-diffusion openclip retrieval-evaluation vision-reconstruction
-
Updated
Sep 9, 2026 - Python
Open-source retrieval diagnostics toolkit for enterprise RAG pipelines
python open-source information-retrieval retrieval haystack rag vector-search llm langchain llmops llamaindex retrieval-augmented-generation rag-evaluation retrieval-evaluation enterprise-rag rag-diagnostics
-
Updated
Jul 23, 2026 - Python
RAG retrieval benchmark runner with JSON reports, Pareto plots, and regression gates for retrieval quality changes.
python nlp benchmark information-retrieval embeddings regression-testing bm25 reranking quality-gates rag llm llmops retrieval-augmented-generation retrieval-evaluation retrieval-benchmark
-
Updated
May 20, 2026 - Python
Bilingual RAG evaluation benchmark for culturally grounded English/Uzbek retrieval
multilingual nlp benchmark information-retrieval evaluation uzbek low-resource-languages rag retrieval-augmented-generation enterprise-ai retrieval-evaluation multilingual-ai corpus-engineering
-
Updated
Sep 5, 2026 - Python
Hybrid legal search over 83,706 U.S. Code chunks combining BM25 and HNSW pgvector, with LLM query rewriting and a Precision@3/Recall@5/MRR evaluation harness. FastAPI backend, Next.js frontend.
-
Updated
Sep 2, 2026 - TypeScript
YouTube transcript retrieval lab comparing E5 + FAISS, Japanese BM25, hybrid, and agentic search with timestamped evidence and evaluation.
python information-retrieval semantic-search bm25 faiss youtube-transcripts multilingual-nlp hybrid-search cross-encoder agentic-search retrieval-evaluation
-
Updated
Aug 22, 2026 - Python
Hybrid (dense + BM25) RAG retrieval service on Qdrant/PostgreSQL with offline evaluation and a web console
-
Updated
Sep 7, 2026 - Python
Deterministic RAG evaluation toolkit -- retrieval metrics (recall, precision, MRR), corpus overlap detection, and CI regression gating without model calls.
-
Updated
May 26, 2026 - Python
Local-first memory infrastructure for coding workflows: deterministic retrieval, explainable traces, MCP/REST/SDK interfaces, and standalone browser-first operation.
python knowledge-graph python-sdk observability codex rag local-first standalone-app hybrid-search local-ai ollama ai-memory gemini-cli mcp-server agent-memory claude-code retrieval-evaluation context-engineering mcp-memory memory-infrastructure
-
Updated
Aug 24, 2026 - Python
A minimal RAG pipeline with a labelled retrieval eval set, testing whether query rewriting and routing actually improve retrieval. They didn't.
-
Updated
Aug 24, 2026 - Jupyter Notebook
Cited RAG over a product manual — hybrid BM25 + dense retrieval, cross-encoder re-ranking, 25-question eval harness.
python retrieval rag streamlit llm llms retrieval-augmented llm-tools retrieval-augmented-generation rag-evaluation rag-pipeline rag-chatbot retrieval-evaluation retrieval-augmented-generation-rag
-
Updated
Sep 5, 2026 - Python
Score chunking configs by whether gold answer spans stay retrievable, in character span space
-
Updated
Aug 15, 2026 - TypeScript
Add this topic to your repo
To associate your repository with the retrieval-evaluation topic, visit your repo's landing page and select "manage topics."