Retrieve

from gildea import Gildea

gildea = Gildea()

# Your scope from the previous recipe, inlined so this block runs on its own.
scope = {"themes": ["Infrastructure"], "entities": ["NVIDIA"], "window": "6m"}

# 1. Semantic + faceted retrieval: a natural-language query narrowed to your
#    territory (entity + theme + window). Retrieval is semantic, not keyword.
hits = gildea.search(
    "data center moat durability and competitive threats",
    entity=scope["entities"][0], theme=scope["themes"][0], window=scope["window"],
    limit=10,
)["results"]
print(f"{len(hits)} verified units in scope. top:")
for h in hits[:5]:
    u, c = h["unit"], h["citation"]
    print(f"  [{u['role']:9}] {u['text'][:62]}  <- {c['domain']}")

# 2. Role facet: pull one layer of the decomposition -- thesis/synopsis (the
#    central position), argument (reasoning), claim (atomic factual assertions).
theses = gildea.search("AI infrastructure spending", role="thesis", window="3m", limit=5)["results"]
print(f"\n{len(theses)} thesis-level units (positions experts are taking):")
for h in theses[:3]:
    print(f"  - {h['unit']['text'][:80]}")

# 3. similar_to: embedding-backed "more like this" off any unit id. Find the
#    cluster making the same point, across sources.
seed = hits[0]["unit"]["id"]
similar = gildea.search(similar_to=seed, limit=5)["results"]
print(f"\nunits similar to the top hit ({len(similar)} found):")
for h in similar[:3]:
    print(f"  ~ {h['unit']['text'][:66]}  <- {h['citation']['domain']}")

# 4. Tune the ranking: recency_boost favors newer signals; diversity_cap limits
#    units per source so one prolific author can't dominate the page.
fresh = gildea.search(
    "frontier model competition", recency_boost=1, diversity_cap=1, window="1m", limit=8,
)["results"]
print(f"\nrecency-boosted, source-diversified: {len(fresh)} hits across "
      f"{len({h['citation']['domain'] for h in fresh})} domains")

# 5. Split the feed by content_type -- event (what happened) vs analysis (what
#    experts think) -- then drill a signal to its full verified decomposition
#    as a flat units[] with roles + evidence.
theme = scope["themes"][0]
events = gildea.signals.list(theme=theme, content_type="event", window="3w", limit=5)["signals"]
analyses = gildea.signals.list(theme=theme, content_type="analysis", window="3w", limit=5)["signals"]
print(f"\n{len(events)} event / {len(analyses)} analysis signals in '{theme}'")
detail = gildea.signals.get((events or analyses)[0]["signal_id"])
roles = ", ".join(sorted({u["role"] for u in detail["units"]}))
print(f"drilled '{detail['title'][:48]}' -> {len(detail['units'])} units ({roles})")