Skip to main content
Easily find the most relevant information from trusted sources and your own data. Use it to power agents that give accurate, real-time answers. Ready to start using the Search Service? Let’s dive in!
  • API
  • Python SDK
We will create a sample API request and describe the main request parameters. The best way to try it out is the Developer Platform > Search PlaygroundThe query request object contains the following main parameters:
  • text: Natural-language search string equivalent to the Similarity filter in the SDK. It is not mandatory when filtering by entities, keywords or other filters.
  • filters: It supports equivalent filters as the SDK described in Query Filters. For instance: timestamp, entity, keyword, source, topic, sentiment, reporting_entity, etc
  • ranking_params: Allow customers to control the search ranking algorithm. The Re-ranker is set by default with a threshold between 0.2 and 0.3 depending of the applied filters.
  • max_chunks Maximum number of chunks to retrieve. It must be lower than or equal to 1000. The response might contain a lower number of chunks due to discarding duplicated chunks after the matching phase.
The following example searches for news about Pfizer’s partnerships and returns ten chunks.
curl -X POST 'https://api.bigdata.com/v1/search' \
  -H 'Content-Type: application/json' \
  -H 'X-API-KEY: <your-api-key>' \
  --data '{
  "query": {
    "text": "Partnership",
    "filters": {
      "timestamp": {
        "start": "2025-07-16T22:00:00.000Z",
        "end": "2025-10-14T21:59:59.999Z"
      },
      "entity": {
        "any_of": [
          "267718"
        ]
      }
    },
    "ranking_params": {
      "source_boost": 10,
      "freshness_boost": 1
    },
    "max_chunks": 10
  }
}'
Output:The response contains an array of documents with the text chunks that matched the query criteria.
{
    "results": [
        {
            "id": "62433E4658007ECAD1929C7AF495A658",
            "headline": "Pfizer Deal; Oracle Rising on TikTok News; Alphabet and DOJ",
            "timestamp": "2025-09-22T13:24:08",
            "source": {
                "id": "5E6268",
                "name": "Stock Movers",
                "rank": "RANK_1"
            },
            "url": "https://podtrac.com/pts/redirect.mp3/traffic.omny.fm/d/clips/e73c998e-6e60-432f-8610-ae210140c5b1/deb345cd-6d73-4a24-a6e3-b2a50138dd86/5ab1a963-8b0b-4743-ab3d-b36000da62b9/audio.mp3?utm_source=Podcast&in_playlist=a55c6f22-aa32-4a58-aebd-b2a50138e2b2",
            "chunks": [
                {
                    "cnum": 2,
                    "text": "On this episode of Stock Movers:- Pfizer (PFE) 
                    is moving as it agreed to buy the obesity startup Metsera Inc. 
                    for an enterprise value of about $4.9 billion to bolster its 
                    pipeline after a key weight-loss pill foundered. The US 
                    drugmaker will pay Metsera $47.50 in cash per share, and further 
                    payments of up to $22.50 per share if three specific 
                    and regulatory milestones are met, it said in a statement Monday.
                    The deal represents a 43% premium to Metsera's closing
                    share price on Friday. Oracle (ORCL) is rising his morning on news would recreate and provide security for a new US version of TikTok's algorithm under a deal to sell the app to a consortium of American investors. Oracle will operate in partnership with the US government on everything from algorithm retraining to application development and source code review to ensure content is free from improper manipulation or surveillance. Alphabet (GOOG) shareholders are following news that the Justice Department is heading to court to force a breakup of Alphabet's Google, seeking to divest its advertising exchange AdX, which the department says is the best way to restore competition in the market for online display advertising.",
                    "relevance": 0.38801944336096794,
                    "sentiment": -0.63
                }
            ]
        },
        ... // more documents
    ],
    "metadata": {
        "request_id": "8bd31f92-ca62-4b88-a542-a1394c881eba",
        "timestamp": "2025-10-16T14:50:49.013579+00:00"
    },
    "usage": {
        "api_query_units": 1.0
    }
}
The quickest way to test the Search Service is with the Search PlaygroundThen, you can explore the different search parameters (Query filters, Scope, Date Range, SortBy) on their respective pages.The search will return a list of documents, and the page Response - Document will show you how to access the document content.Finally, but not least, check out the Co-mentions feature. It will tell you which Knowledge Graph Objects (Entities, Topics, Sources, etc.) are mentioned the most in your search. That’s a quick way to see your query’s exposure!
⌘I