unified_search

🔍 Unified Search - Single entry point for multi-source academic search.

Automatically analyzes your query and searches the best sources. No need to choose between PubMed, OpenAlex, CrossRef, etc.

═══════════════════════════════════════════════════════════════════ WHAT IT DOES: ═══════════════════════════════════════════════════════════════════

1. Analyzes your query (complexity, intent, PICO elements)

2. Automatically selects best sources based on query type

3. Searches multiple sources in parallel

4. Deduplicates and merges results

5. Ranks by configurable criteria

6. Enriches with OA links (Unpaywall)

7. Auto-detects ICD-9/10 codes and expands to MeSH terms

8. Optionally searches preprints (arXiv, medRxiv, bioRxiv)

═══════════════════════════════════════════════════════════════════ EXAMPLES (most calls only need 1-2 params): ═══════════════════════════════════════════════════════════════════

Simple (1 param): unified_search("remimazolam ICU sedation")

With limit (2 params): unified_search("machine learning in anesthesia", limit=20)

Specify sources: unified_search("CRISPR gene therapy", sources="pubmed,openalex")

Auto minus one source: unified_search("sepsis biomarkers", sources="auto,-semantic_scholar")

Search all enabled sources except enrichment-only CrossRef: unified_search("icu sedation", sources="all,-crossref")

Clinical filters: unified_search("diabetes treatment", filters="year:2020-2025,age_group:aged,clinical_query:therapy")

Include preprints + shallow search: unified_search("COVID-19 vaccine", options="preprints,shallow")

Provider-native semantic retrieval (OpenAlex capability): unified_search("mechanisms of treatment resistance", sources="openalex", options="native_semantic")

Reproducible systematic retrieval (bulk/cursor where supported): unified_search("melanoma AND immunotherapy", sources="openalex,semantic_scholar", options="systematic")

Full control: unified_search("propofol vs remimazolam", sources="pubmed,semantic_scholar,europe_pmc", ranking="impact", filters="year:2020-,sex:female,species:humans", options="preprints,no_relax")

ICD Code Auto-Detection: unified_search("E11 complications") → Auto-expands E11 to "Diabetes Mellitus, Type 2"[MeSH]

Args: query: Search query (natural language, ICD codes, or structured). Required unless pipeline is provided. limit: Maximum results per source (default 10, max 100) sources: Comma-separated list of sources to search. Available: "pubmed", "openalex", "semantic_scholar", "europe_pmc", "crossref", "core". Commercial connectors may also appear when enabled via env, e.g. "scopus" when SCOPUS_ENABLED=true and SCOPUS_API_KEY are configured, or "web_of_science" when WEB_OF_SCIENCE_ENABLED=true and WEB_OF_SCIENCE_API_KEY are configured. Default: auto-select based on query complexity. Supports "auto" and "all" with exclusions. Source keys are exact and canonical; legacy hyphenated, spaced, abbreviated, or case-folded aliases are rejected. Examples: "pubmed,openalex", "auto,-semantic_scholar", or "all,-crossref" Global disable env: PUBMED_SEARCH_DISABLED_SOURCES Example: PUBMED_SEARCH_DISABLED_SOURCES=semantic_scholar,core ranking: Ranking strategy: - "balanced": Default, considers all factors - "impact": Prioritize high-citation papers - "recency": Prioritize recent publications - "quality": Prioritize publication-type heuristics (RCTs, meta-analyses); not a quality assessment output_format: "markdown" (human-readable), "json", or "toon" (programmatic) fulltext: "off" (default) or "prefetch" for normal searches. Prefetch prepares open-access XML for up to three top-ranked articles with known PMCIDs in the background. Search does not wait. Later get_fulltext calls reuse ready or in-flight XML; no polling is needed. No speculative PDF, browser or institutional access. Not supported with pipeline; use "off" for pipeline calls. filters: Comma-separated key:value pairs for filtering results. Supported keys: year:2020-2025 → publication year range year:2020- → from 2020 onwards year:-2025 → up to 2025 year:2024 → from 2024 onwards age_group: → age group filter (PubMed). Values: newborn, infant, preschool, child, adolescent, young_adult, adult, middle_aged, aged, aged_80 sex: → sex filter: male, female species: → species filter: humans, animals language: → language filter: english, chinese, etc. clinical_query: → clinical query filter (PubMed EBM). Values: therapy, therapy_narrow, diagnosis, diagnosis_narrow, prognosis, prognosis_narrow, etiology, etiology_narrow, clinical_prediction, clinical_prediction_narrow Tokens, keys, and values use exact canonical spelling with no surrounding whitespace. Example: "year:2020-2025,age_group:aged,sex:female,clinical_query:therapy" options: Comma-separated flags to toggle behaviors. Supported flags: preprints → also search arXiv, medRxiv, bioRxiv include_detected_preprints → retain records identified by the preprint heuristic in otherwise selected sources; this does not establish peer-review status clinical_trials → add a bounded ClinicalTrials.gov adjunct section to Markdown output (explicit opt-in) no_oa → skip Unpaywall OA link enrichment no_analysis → hide query analysis section in output no_scores → hide ranking scores and rank percentiles compact → compact structured JSON/TOON output no_next → hide next-tool suggestions in structured output no_provenance → hide section provenance in structured output no_relax → disable auto-relaxation on 0 results exclude_seen → omit prior session results by PMID/DOI (not supported with pipeline) native_semantic → use provider-native semantic retrieval; currently OpenAlex, max 50 results systematic → use deterministic bulk/cursor retrieval where supported (for example S2 and OpenAlex) shallow → disable deep search (faster, keyword-only) native_semantic and systematic are mutually exclusive Option tokens use exact canonical spelling with no surrounding whitespace. and automatically disable multi-strategy query expansion. Tokens use exact canonical spelling without surrounding whitespace or duplicates. Example: "preprints,shallow" or "no_analysis,no_scores" pipeline: YAML/JSON string defining a multi-step search pipeline. When provided, other parameters (except output_format) are ignored and the pipeline DAG is executed instead.

         Accepts **YAML** (recommended, human-friendly) or **JSON** format.

         **Template mode — YAML** (shortcut for common workflows):
           template: pico
           template_params:
             P: ICU patients
             I: remimazolam
             C: propofol
             O: sedation

         Other templates:
           template: comprehensive
           template_params:
             query: CRISPR gene therapy

           template: exploration
           template_params:
             pmid: "12345678"

           template: gene_drug
           template_params:
             term: BRCA1

           template: snowball
           template_params:
             query: CRISPR gene therapy
             seed_limit: 5
             limit: 20

         **Custom pipeline — YAML** (full DAG control, max 20 steps):
           name: My Custom Search
           steps:
             - id: s1
               action: search
               params:
                 query: remimazolam ICU
                 sources: [pubmed, europe_pmc]
                 limit: 50
             - id: s2
               action: search
               params:
                 query: propofol ICU
                 sources: [pubmed]
                 limit: 50
             - id: merged
               action: merge
               inputs: [s1, s2]
               params:
                 method: rrf
             - id: enriched
               action: metrics
               inputs: [merged]
           output:
             format: markdown
             limit: 20
             ranking: impact

         Shared params:
           globals: default params inherited only by actions that
                    declare the same canonical parameter key
           variables: typed values available as ${name} placeholders;
                      embedded replacements must be strings

         Debugging controls:
           dry_run: validate/preview the pipeline without searches
           stop_at: execute through one step id, e.g. "merged"

         **JSON also supported** (for programmatic use):
           {"template": "pico", "template_params": {"P": "ICU patients", "I": "remimazolam"}}

         Available actions:
           search      — literature search (params: query, sources, limit, min_year, max_year)
           pico        — PICO elements (params: P, I, C, O)
           expand      — MeSH/synonym expansion (params: topic)
           details     — fetch article details (params: pmids)
           related     — find related articles (params: pmid OR seed_limit, limit)
           citing      — find citing articles (params: pmid OR seed_limit, limit)
           references  — get article references (params: pmid OR seed_limit, limit)
           metrics     — enrich with iCite citation metrics (inputs only)
           merge       — combine results (params: method=union|intersection|rrf)
           filter      — post-filter (params: min_year, max_year, article_types, min_citations, has_abstract)
         seed_limit (1-10) snowballs from the first unique input PMIDs;
         it needs inputs, is exclusive with pmid, and excludes seeds.

Returns: Formatted search results with: - Query analysis (complexity, intent, PICO) - ICD code expansions (if detected) - Search statistics (sources, dedup count) - Ranked articles with metadata - Open access links where available - Preprints (if options includes "preprints") - Relaxation info (if auto_relax triggered) - Pipeline step summary (if pipeline mode)