Paper Reference Assistant (CLI)

Entry point skill. Use papi CLI first; MCP RAG tools only when CLI is insufficient.

For specialized workflows, invoke dedicated skills:

• /papi-ask — RAG queries requiring synthesis
• /papi-verify — verify code against paper
• /papi-compare — compare papers for decision
• /papi-ground — ground responses with citations
• /papi-curate — create project notes

Setup

papi path   # DB location (default ~/.paperpipe/; override via PAPER_DB_PATH)
papi list   # available papers
papi list | grep -i "keyword"  # check if paper exists before searching

When NOT to Use MCP RAG

• Paper name known → papi show <paper> -l summary
• Exact term search → papi search --rg "term"
• Checking equations → papi show <paper> -l eq
• Only use RAG when above methods fail or semantic matching required

Decision Tree

Search Commands

papi search --rg "query"              # exact text (fast, no LLM)
papi search --rg --regex "pattern"    # regex (OR, wildcards)
papi search "query"                   # ranked BM25
papi search --hybrid "query"          # ranked + exact boost
papi ask "question"                   # PaperQA2 RAG
papi ask "question" --backend leann   # LEANN RAG
papi notes {name}                     # open/print implementation notes

Search Escalation (cheapest first)

1. papi search --rg "X" — exact text, fast, no LLM
2. papi search "X" — ranked BM25 (requires papi index --backend search first)
3. papi search --hybrid "X" — ranked + exact boost
4. leann_search() — semantic search, returns file paths for follow-up
5. retrieve_chunks() — formal citations (DOI, page numbers)
6. papi ask "..." — full RAG synthesis

MCP Tool Selection (when papi CLI insufficient)

• Check indexes: leann_list() or list_pqa_indexes()
• Embedding priority: Voyage AI → Google/Gemini → OpenAI → Ollama

Adding Papers

papi add 2303.13476                   # arXiv ID
papi add https://arxiv.org/abs/...    # URL
papi add --pdf /path/to.pdf           # local PDF
papi add --pdf "https://..."          # PDF from URL
papi add --from-file papers.bib       # bulk import

Per-Paper Files

Located at {db}/papers/{name}/:

If agent can't read ~/.paperpipe/, export to repo: papi export <papers...> --level equations --to ./paper-context/ Use --figures to include extracted figures in export.

See commands.md for full reference.