1968 passages indexed
Dense RAG desk
Ask a question about anything in the archive — hearings, documents, sources. Every answer links to the exact passages it came from.
Answer
—
Run a query to see results.
Citations
No citations yet.
Architecture
Dense embeddings (hashed 128-d · MiniLM 384-d). Default offline hashed bi-encoder (concept axes + feature-hashed tokens/char-grams). Optional client MiniLM (Xenova/all-MiniLM-L6-v2) rebuilds the corpus index at 384-d with true neural cosine retrieval.
- Query intake
- Dense embed (hashed 128-d or MiniLM 384-d)
- Cosine top-k retrieve
- Sparse hybrid re-rank fusion
- Context pack + citation binding
- Extractive synthesis or generative Grok (XAI_API_KEY)
Adapters
- embed: hashed (default) · Xenova MiniLM (client toggle)
- store: in-memory corpus index (pgvector-ready)
- generate: extractive · Grok via createServerFn