~/projects/odyssey-rag.md
Odyssey RAG
A retrieval-augmented question-answering system that answers questions about Homer's The Odyssey using relevant passages retrieved from the source text.
- 850chunks (1,000 chars, 200 overlap)
- 768-dGemini embeddings
- top-5cosine retrieval, Recall@K + MRR
Repository (opens in a new tab)All projects
How it works
- Source text
- Chunk
- Embed
- Cosine top-5 ↺ evaluate: back to “Chunk”
- Grounded answer
What it does
- Processes a source document into overlapping chunks and retrieves relevant passages using embedding similarity.
- Uses Gemini embeddings and Gemini for grounded answer generation.
- Includes retrieval inspection and evaluation with metrics such as Recall@K and Mean Reciprocal Rank.