/deepxiv-fa-drugs

name: deepxiv-fa-drugs
description: Search ~257k US drug labels (openFDA SPL): indications, contraindications, interactions, boxed warnings, pharmacologic class. Use when a task needs what a US drug label says.

DeepXiv · Drugs (`drugs`)

~257k US drug labels (openFDA SPL, latest version per set_id; Synced daily; exact counts are in corpus (live)). Indications, contraindications, interacting drugs, boxed-warning gist and one-line summaries are model-extracted; route / product type / pharmacologic class come from the openfda mapping block.

Corpus: 256,993 documents, updated 2026-10.

Setup

pip install -U deepxiv-sdk      # deepxiv registers a token on first use

With a registered key (https://data.rag.ac.cn/register), `search` and `read` are fair use: 60/min, 5 at once, 5,000/day; on the auto-registered token they spend the deepxiv daily limit at the credits listed below. `ask` draws on the daily ask allowance (resets 00:00 UTC; a site-wide daily total can run out early at peak times), or 3 lifetime trial asks on the auto-registered token. On 429, back off for `Retry-After` seconds. Data goes to stdout; cost, quota and sources go to stderr. Exit 0 ok, 1 API error, 2 usage error. The general CLI guide is the `deepxiv-cli` skill.

Start here

deepxiv fa search drugs "GLP-1 weight loss" -F has_boxed_warning=true -k 5
deepxiv fa search drugs "anticoagulant" -F route=ORAL -F is_rx=true -k 5
deepxiv fa read drugs f5e548d0-cc79-4c34-a3f5-e20a5b8b6564 -l brief
deepxiv fa ask "Which drugs interact with warfarin according to their labels?" -d drugs

Free samples: ids `f5e548d0-cc79-4c34-a3f5-e20a5b8b6564`; queries `semaglutide weight loss`.

Search

deepxiv fa search drugs "query" [-F FILTER]... [-k N] [--offset N] [--mode M] [--head] [--json]

Modes: hybrid, dense, bm25. Up to 100 hits. Cost 2 (with `--head`: 3). An empty query is rejected; use `"*"` to list by filters only. Filters combine with AND; an undeclared field exits 2.

| filter | type | `-F` syntax | meaning | |---|---|---|---| | `route` | keyword | `k=v`, `k=a,b` | Route of administration Values: `ORAL`, `TOPICAL`, `INTRAVENOUS`, `INTRAMUSCULAR`, `SUBCUTANEOUS`, `OPHTHALMIC`, `NASAL`, `RESPIRATORY (INHALATION)` …. | | `product_type` | keyword | `k=v`, `k=a,b` | Product type; UNMAPPED = the SPL has no openfda mapping block Values: `HUMAN PRESCRIPTION DRUG`, `HUMAN OTC DRUG`, `CELLULAR THERAPY`, `UNMAPPED`. | | `is_rx` | bool | `k=v` | Prescription-only | | `has_boxed_warning` | bool | `k=v` | Has a boxed warning | | `pharm_class_epc` | keyword | `k=v`, `k=a,b` | Pharmacologic class (EPC) | | `effective_year` | integer | `k=v`, `k>=n`, `k=n..m` | Label version year, range |

Advanced filters (see `deepxiv fa spec drugs`): `generic_name`, `substance_names`, `pharm_class_moa`, `manufacturer`, `rxcui`, `unii`, `product_ndc`, `application_number`.

Read

deepxiv fa read drugs ID [ID...] [-l brief|detail|full] [-e EXTRA] [-p k=v]... [-f json|md|html]

| level | credits | returns | |---|---|---| | `brief` | 1 | Card: the fields needed to triage, same as in search hits | | `detail` (default) | 2 | Every structured field (rule-derived plus model-generated; model fields are listed in _enrich.fields) | | `full` | 5 | Full text (not available yet: the label sections live on NAS (openfda/label); the index carries only section names and token counts) |

At `-l full`, `-p section=NAME` reads one section and `-p characters=N` the first N characters.

Facets

`deepxiv fa facets drugs FIELD` lists the legal values and counts, free. Use it instead of guessing a spelling. Fields: `route`, `product_type`, `pharm_class_epc`.

Ask

deepxiv fa ask "question" -d drugs [-e low|medium|high] [-p k=v]... [--no-stream] [--json]

Agentic Q&A over this domain: the model turns the question into filters plus keywords from the domain's own self-description, reads the hits and answers with [drugs:<set_id> <title>] citations; /stream is NDJSON with real token deltas

Always pass `-d drugs`: automatic domain picking is still early.

What this corpus will and will not tell you

• 67% (171,903) are product_type=UNMAPPED: those SPLs have no openfda mapping block, so generic name / route / pharmacologic class may be empty — use spl_name for the product name.
• Only the latest version per set_id is kept; no label history.
• Indications and contraindications are extracted highlights; go back to the label for prescribing decisions.
• Not medical advice.
• The index holds no full text: level=full is not available yet (the label sections live on NAS (openfda/label); the index carries only section names and token counts).

Citing

Cite records as `[openFDA SPL f5e548d0…]`. Say plainly when the corpus has nothing.

---

Generated by `scripts/gen_fa_skills.py` from `deepxiv fa spec drugs --json` on 2026-10-19. Field names and prices can change; `deepxiv fa spec drugs` is the live source.