Evaluating-RAG-systems

building a process for evaluating different rag systems, in terms of two main apsects, the retrieval, and the generation

This project is configured to use local Ollama for generation. Default chat model: llama3.2 Default Ollama URL: http://127.0.0.1:11434

Name		Name	Last commit message	Last commit date
Latest commit History 9 Commits
.fastembed_cache/models--Qdrant--bge-small-en-v1.5-onnx-Q		.fastembed_cache/models--Qdrant--bge-small-en-v1.5-onnx-Q
__pycache__		__pycache__
lancedb/pdf_chunks.lance/_versions		lancedb/pdf_chunks.lance/_versions
pdfs		pdfs
rag_rust		rag_rust
.gitignore		.gitignore
.rag_cache.json		.rag_cache.json
README.md		README.md
_		_
agents.py		agents.py
api.py		api.py
batch_download_pdfs.py		batch_download_pdfs.py
evaluate.py		evaluate.py
evaluate_batch.py		evaluate_batch.py
evaluate_multi_agent.py		evaluate_multi_agent.py
mise.toml		mise.toml
naive_rag.py		naive_rag.py
prepare_eval.py		prepare_eval.py
qasper_paper_1.txt		qasper_paper_1.txt
requirements.txt		requirements.txt
save_paper.py		save_paper.py
scores_evaluations.md		scores_evaluations.md
script_opt.py		script_opt.py
txt_to_pdf.py		txt_to_pdf.py

Provide feedback