How it works
Four search modes share the same Bigdata.com POST /v1/search endpoint
but ask for very different things. This page shows the plain-English flow and the exact payload shape
for each mode.
1. Company Topic News
Pick a ticker (or several). The app resolves it to a Bigdata entity ID, then runs
one natural-language query per editable topic. Each topic template contains
{company}, which is replaced with the company name before search.
- Scoped to that company via an entity filter
- Keeps positive and negative sentiment (drops neutral)
- Sources: public news and transcripts
- Optional AI query expansion multiplies each topic into more phrases
- UI relevance dropdown drops weak hits after results return
Search payload (one call per topic):
{
"query": {
"text": "Apple Inc. reported earnings results beating or missing revenue and profit expectations",
"filters": {
"timestamp": { "start": "...", "end": "..." },
"entity": { "all_of": ["<entity_id>"] },
"category": {
"mode": "INCLUDE",
"values": ["news_public", "transcripts"]
},
"sentiment": {
"values": ["positive", "negative"]
}
},
"max_chunks": 10
}
}2. Company Negative News
Same company desk, different question: show strongly negative public news where the company appears in the headline, grouped by risk categories (litigation, regulatory, credit stress, governance, cyber / product).
- Filter-only search — no query text
search_mode: "fast"- Sources: public news and transcripts (
news_public,transcripts) - Entity matched in the headline (avoids drive-by body mentions)
- Sentiment score in range
[-1, -0.1] - Bigdata taxonomy topics in
topic.any_of(editable per category) - One entity ID per request (clean ticker attribution on multi-ticker runs)
Search payload (one call per category × company):
{
"search_mode": "fast",
"query": {
"filters": {
"timestamp": { "start": "...", "end": "..." },
"category": {
"mode": "INCLUDE",
"values": ["news_public", "transcripts"]
},
"entity": {
"search_in": "HEADLINE",
"any_of": ["<entity_id>"]
},
"sentiment": {
"ranges": [{ "min": -1, "max": -0.1 }]
},
"topic": {
"search_in": "ALL",
"any_of": [
"society,legal,fraud,,",
"business,regulatory,regulatory-investigation,,"
]
}
},
"max_chunks": 10
}
}3. Sector / Commodity News
Commodities desk: pick Energy, Power, Shipping & Freight, or Metals. Each desk ships with editable theme phrases. Every phrase is searched verbatim — there is no company / entity filter, so the feed follows the theme, not a single issuer.
- Natural-language
query.text(desk phrase as written) - No entity filter, no taxonomy topic filter
- Positive + negative sentiment (neutral excluded)
- Sources: public news and transcripts
- Optional AI expansion uses a desk-specific prompt
Search payload (one call per theme phrase):
{
"query": {
"text": "Brent and WTI crude oil prices rise or fall on shifting supply and demand outlook",
"filters": {
"timestamp": { "start": "...", "end": "..." },
"category": {
"mode": "INCLUDE",
"values": ["news_public", "transcripts"]
},
"sentiment": {
"values": ["positive", "negative"]
}
},
"max_chunks": 20
}
}4. Location News
Location desk: pick a place (country, region or city) and one or more event topics, both looked up in the Bigdata Knowledge Graph. The feed shows chunks (passages), not whole articles, that mention that place and carry that event.
- Place lookup:
POST /v1/knowledge-graph/placeswith{"query": "Texas"}returns entity IDs (State of Texas =C1BA53, not Texas City or Texas County, Missouri) - Topic lookup:
POST /v1/knowledge-graph/topicswith{"query": "protest"}returns taxonomy IDs such associety,civil-unrest,protest,, - Place in
entity.any_of, one taxonomy topic intopic.any_ofper request - Optional TEXT box (default
Data Center): sent asquery.textto rank chunks and askeyword.any_ofso every result mentions it (case, plural and "centre" variants match). Clear it for a filter-only search - Reranker off (with a topic filter it drops results)
- Sources: public news and transcripts; no sentiment filter (each chunk's score is shown)
- One row per chunk, deduplicated by document ID + chunk number; SECTOR is the taxonomy's top level (Business, Society, Environment…)
- Bigdata applies filters per document, so other chunks of a matching article come back too. Chunk must mention place + topic (on by default) keeps only chunks whose own detections include both, and the expanded row highlights them
- Chunk budget is split across topics unless CHUNKS / TOPIC is set (max 500); PAYLOAD shows the exact bodies sent
Example: Texas (the desk's default) × TEXT Data Center × the data center campus taxonomy: build-out
(business,assets,facility-construction,,), community opposition
(society,civil-unrest,protest,,, society,civil-unrest,civil-unrest,,,
society,legal,legal-issues,,) and regulation
(business,regulatory,regulatory-investigation,,). Topic filters find the event, not the industry:
without TEXT, one month of Texas returns about 220 chunks but only 14 about data centers (the Protest feed
is every protest that mentions Texas). With Data Center, three months returns 114 chunks, all of
them on data centers, e.g. Regulatory Investigation → "Abbott Orders Temporary Halt For All Data Center Permits In Texas"
and Protest → "US Data Center New Construction Bans Surge in July, Protests Erupt in 142 Cities".
Search payload (one call per topic, Protest shown; drop text and keyword when TEXT is empty):
{
"search_mode": "fast",
"query": {
"text": "Data Center",
"filters": {
"timestamp": { "start": "...", "end": "..." },
"category": {
"mode": "INCLUDE",
"values": ["news_public", "transcripts"]
},
"entity": { "any_of": ["C1BA53"] },
"topic": { "any_of": ["society,civil-unrest,protest,,"] },
"keyword": { "any_of": ["Data Center"] }
},
"max_chunks": 50,
"ranking_params": { "reranker": { "enabled": false } }
}
}Quick compare
| Topic News | Negative News | Sector / Commodity | Location | |
|---|---|---|---|---|
| Page | / |
/ |
/sector |
/location |
| API | POST /api/news/{ticker} |
POST /api/news/{ticker}negative_news: true |
POST /api/sector-news |
POST /api/location-news |
| Query text | Yes — topic with company name | No — filters only | Yes — theme phrase verbatim | Optional — default "Data Center", also a keyword filter |
| Entity | all_of company |
Headline any_of (1 ID) |
None | any_of place (Knowledge Graph) |
| Taxonomy topics | No | Yes — risk categories | No | Yes — one per request |
| Sentiment | positive + negative | range −1 … −0.1 | positive + negative | none (score shown per chunk) |
| Result row | Article (best chunk) | Article (best chunk) | Article (best chunk) | Chunk |
| Sources | news_public, transcripts | news_public, transcripts | news_public, transcripts | news_public, transcripts |