deepxiv/deepxiv_sdk/deepxiv-fa-trials

DeepXiv · Trials (trials)

All ~607k studies on ClinicalTrials.gov (one per NCT; Synced daily; exact counts are in corpus (live)). Phase / status / enrolment / countries / MeSH come from the ctgov record; eligibility highlights, biomarkers, prior therapy, ECOG and one-line summaries are model-extracted.

Corpus: 607,168 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 trials "GLP-1 obesity" -F phase=PHASE3 -F overall_status=RECRUITING -k 5
deepxiv fa read trials NCT02082496 -l brief
deepxiv fa ask "recruiting phase 3 trials for pancreatic cancer" -d trials

Free samples: ids NCT02082496; queries glp-1 obesity phase 3.

Search

deepxiv fa search trials "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.

Advanced filters (see deepxiv fa spec trials): sex, sponsor, intervention_mesh, biomarker_names, performance_status, treatment_naive, enrollment, age_min_years, age_max_years, completion_year.

Read

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

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

Facets

deepxiv fa facets trials FIELD lists the legal values and counts, free. Use it instead of guessing a spelling. Fields: phase, overall_status, study_type, intervention_type, sponsor_class, sex, countries, condition_mesh.

Ask

deepxiv fa ask "question" -d trials [-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 [trials:<nct_id> <title>] citations; /stream is NDJSON with real token deltas

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

What this corpus will and will not tell you

• Filter by condition_mesh (controlled terms); conditions is free text as entered by the registrant.
• Eligibility highlights, biomarkers, prior therapy and ECOG are model-extracted from the eligibility text — verify against the record before acting.
• 97k studies carry overall_status=UNKNOWN: the registrant stopped updating, which does not mean the trial ended.
• The index holds no full text: level=full is not available yet (the full registry record lives on NAS (ctgov/bulk) and is not in the index).

Citing

Cite records as [NCT02082496]. Say plainly when the corpus has nothing.

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