dolev31

dolev31/lasagna

Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.

18 good first / help-wanted issues · Python · last activity Oct 26, 2026

20 stars 2 forks 20 watchers Python Apache License 2.0
ablation-study agentic-rag beir benchmark evaluation hybrid-search information-retrieval langgraph llm mcp mcp-server python rag rag-evaluation ragas reproducibility reranking retrieval-augmented-generation semantic-search vector-database
View on GitHub Website
18 Open Issues Need Help Last updated: Oct 26, 2026

Open Issues Need Help

View All on GitHub
The stress suite looks for the Compose files in a directory that does not exist 24 minutes ago
bug good first issue
dolev31/lasagna
20

Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.

Python
#ablation-study#agentic-rag#beir#benchmark#evaluation#hybrid-search#information-retrieval#langgraph#llm#mcp#mcp-server#python#rag#rag-evaluation#ragas#reproducibility#reranking#retrieval-augmented-generation#semantic-search#vector-database
Research: one hierarchical model of a whole sweep, from per-query scores about 1 hour ago
help wanted results research
dolev31/lasagna
20

Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.

Python
#ablation-study#agentic-rag#beir#benchmark#evaluation#hybrid-search#information-retrieval#langgraph#llm#mcp#mcp-server#python#rag#rag-evaluation#ragas#reproducibility#reranking#retrieval-augmented-generation#semantic-search#vector-database
The CLI reference page changes with the installed typer version about 1 hour ago
bug good first issue
dolev31/lasagna
20

Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.

Python
#ablation-study#agentic-rag#beir#benchmark#evaluation#hybrid-search#information-retrieval#langgraph#llm#mcp#mcp-server#python#rag#rag-evaluation#ragas#reproducibility#reranking#retrieval-augmented-generation#semantic-search#vector-database
A benchmark in a Qdrant stack talks to Milvus, and fails about 1 hour ago
bug help wanted deployment
dolev31/lasagna
20

Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.

Python
#ablation-study#agentic-rag#beir#benchmark#evaluation#hybrid-search#information-retrieval#langgraph#llm#mcp#mcp-server#python#rag#rag-evaluation#ragas#reproducibility#reranking#retrieval-augmented-generation#semantic-search#vector-database
The image's Qdrant client is seven minor versions ahead of the stack's Qdrant server about 1 hour ago
bug good first issue deployment
dolev31/lasagna
20

Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.

Python
#ablation-study#agentic-rag#beir#benchmark#evaluation#hybrid-search#information-retrieval#langgraph#llm#mcp#mcp-server#python#rag#rag-evaluation#ragas#reproducibility#reranking#retrieval-augmented-generation#semantic-search#vector-database
Experiment tracking: Weights & Biases and MLflow about 1 hour ago
help wanted deployment
dolev31/lasagna
20

Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.

Python
#ablation-study#agentic-rag#beir#benchmark#evaluation#hybrid-search#information-retrieval#langgraph#llm#mcp#mcp-server#python#rag#rag-evaluation#ragas#reproducibility#reranking#retrieval-augmented-generation#semantic-search#vector-database
An OpenAI-compatible answer endpoint, with streaming about 1 hour ago
help wanted deployment
dolev31/lasagna
20

Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.

Python
#ablation-study#agentic-rag#beir#benchmark#evaluation#hybrid-search#information-retrieval#langgraph#llm#mcp#mcp-server#python#rag#rag-evaluation#ragas#reproducibility#reranking#retrieval-augmented-generation#semantic-search#vector-database
Vector backends: Chroma, LanceDB, Elasticsearch about 1 hour ago
help wanted deployment
dolev31/lasagna
20

Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.

Python
#ablation-study#agentic-rag#beir#benchmark#evaluation#hybrid-search#information-retrieval#langgraph#llm#mcp#mcp-server#python#rag#rag-evaluation#ragas#reproducibility#reranking#retrieval-augmented-generation#semantic-search#vector-database
Research: how well does the judge agree with people? about 1 hour ago
help wanted research
dolev31/lasagna
20

Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.

Python
#ablation-study#agentic-rag#beir#benchmark#evaluation#hybrid-search#information-retrieval#langgraph#llm#mcp#mcp-server#python#rag#rag-evaluation#ragas#reproducibility#reranking#retrieval-augmented-generation#semantic-search#vector-database
Research: corpus scaling with out-of-domain distractors about 1 hour ago
help wanted research
dolev31/lasagna
20

Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.

Python
#ablation-study#agentic-rag#beir#benchmark#evaluation#hybrid-search#information-retrieval#langgraph#llm#mcp#mcp-server#python#rag#rag-evaluation#ragas#reproducibility#reranking#retrieval-augmented-generation#semantic-search#vector-database
Research: does composition hold with an open-weight generator? about 1 hour ago
help wanted research
dolev31/lasagna
20

Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.

Python
#ablation-study#agentic-rag#beir#benchmark#evaluation#hybrid-search#information-retrieval#langgraph#llm#mcp#mcp-server#python#rag#rag-evaluation#ragas#reproducibility#reranking#retrieval-augmented-generation#semantic-search#vector-database
Record what each built-in component's paper reports (claims) about 1 hour ago
good first issue
dolev31/lasagna
20

Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.

Python
#ablation-study#agentic-rag#beir#benchmark#evaluation#hybrid-search#information-retrieval#langgraph#llm#mcp#mcp-server#python#rag#rag-evaluation#ragas#reproducibility#reranking#retrieval-augmented-generation#semantic-search#vector-database
Benchmark adapter: BRIGHT (reasoning-intensive retrieval) about 1 hour ago
good first issue benchmark
dolev31/lasagna
20

Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.

Python
#ablation-study#agentic-rag#beir#benchmark#evaluation#hybrid-search#information-retrieval#langgraph#llm#mcp#mcp-server#python#rag#rag-evaluation#ragas#reproducibility#reranking#retrieval-augmented-generation#semantic-search#vector-database
Benchmark adapter: MIRACL (multilingual retrieval, 18 languages) about 1 hour ago
good first issue benchmark
dolev31/lasagna
20

Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.

Python
#ablation-study#agentic-rag#beir#benchmark#evaluation#hybrid-search#information-retrieval#langgraph#llm#mcp#mcp-server#python#rag#rag-evaluation#ragas#reproducibility#reranking#retrieval-augmented-generation#semantic-search#vector-database
Wanted: your paper's component, in Lasagna about 1 hour ago
help wanted component-wanted
dolev31/lasagna
20

Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.

Python
#ablation-study#agentic-rag#beir#benchmark#evaluation#hybrid-search#information-retrieval#langgraph#llm#mcp#mcp-server#python#rag#rag-evaluation#ragas#reproducibility#reranking#retrieval-augmented-generation#semantic-search#vector-database
Two services starting together race to create the collection, and one fails to start 4 days ago
bug good first issue deployment
dolev31/lasagna
20

Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.

Python
#ablation-study#agentic-rag#beir#benchmark#evaluation#hybrid-search#information-retrieval#langgraph#llm#mcp#mcp-server#python#rag#rag-evaluation#ragas#reproducibility#reranking#retrieval-augmented-generation#semantic-search#vector-database
Benchmark adapter: 2WikiMultihopQA, with its distractor paragraphs 5 days ago
help wanted benchmark
dolev31/lasagna
20

Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.

Python
#ablation-study#agentic-rag#beir#benchmark#evaluation#hybrid-search#information-retrieval#langgraph#llm#mcp#mcp-server#python#rag#rag-evaluation#ragas#reproducibility#reranking#retrieval-augmented-generation#semantic-search#vector-database
`lasagna component validate` rejects an `agentic_pipeline` 7 days ago
good first issue stage:agentic_pipeline
dolev31/lasagna
20

Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.

Python
#ablation-study#agentic-rag#beir#benchmark#evaluation#hybrid-search#information-retrieval#langgraph#llm#mcp#mcp-server#python#rag#rag-evaluation#ragas#reproducibility#reranking#retrieval-augmented-generation#semantic-search#vector-database