Result

class Result(url=None, title=None, description=None, netloc=None, published=None, visited=None, author=None, content=None, best_chunk=None, language=None, similarity=None, url_hash=None, brand_safety=None, continent=None, region=None, country=None, sector=None, industry_group=None, industry=None, sub_industry=None, iab_tier_1=None, iab_tier_2=None, iab_tier_3=None, iab_tier_4=None, semantics=None, extra=<factory>)

Bases: object

One losslessly represented Search result.

Attributes

author

content

description

language

netloc

published

similarity

title

url

url_hash

visited

best_chunk

brand_safety

continent

region

country

sector

industry_group

industry

sub_industry

iab_tier_1

iab_tier_2

iab_tier_3

iab_tier_4

semantics

extra

Methods

from_dict(data)

Create a result without discarding unknown response fields.

sentiment(client)

Score this result's content with the configured LLM.

similar(client[, sql_filter, n_results, ...])

Find results similar to this result while excluding the source document.

to_dict()

Convert the result to its lossless dictionary representation.

scrape_url(client)

Scrape the URL associated with this result.
Parameters:

  • url (str | None)

  • title (str | None)

  • description (str | None)

  • netloc (str | None)

  • published (str | None)

  • visited (str | None)

  • author (str | None)

  • content (str | None)

  • best_chunk (str | None)

  • language (str | None)

  • similarity (float | None)

  • url_hash (str | None)

  • brand_safety (str | None)

  • continent (str | None)

  • region (str | None)

  • country (str | None)

  • sector (str | None)

  • industry_group (str | None)

  • industry (str | None)

  • sub_industry (str | None)

  • iab_tier_1 (str | None)

  • iab_tier_2 (str | None)

  • iab_tier_3 (str | None)

  • iab_tier_4 (str | None)

  • semantics (Dict[str, Any] | None)

  • extra (Dict[str, Any])

present_fields: Set[str]
scrape_url(client)

Scrape the URL associated with this result.

Parameters:

  • client (Any) – Configured NOSIBLE client.

  • self (Result)

Returns:

Scraped web-page data.

Return type:

WebPageData

sentiment(client)

Score this result’s content with the configured LLM.

Parameters:

  • client (Any) – Configured NOSIBLE client with an LLM API key.

  • self (Result)

Returns:

Sentiment score from negative one to positive one.

Return type:

float

similar(client, sql_filter=None, n_results=100, n_probes=30, n_contextify=128, algorithm='hybrid-3', publish_start=None, publish_end=None, visited_start=None, visited_end=None, certain=None, include_netlocs=None, exclude_netlocs=None, include_companies=None, exclude_companies=None, include_docs=None, exclude_docs=None, brand_safety=None, language=None, continent=None, region=None, country=None, sector=None, industry_group=None, industry=None, sub_industry=None, iab_tier_1=None, iab_tier_2=None, iab_tier_3=None, iab_tier_4=None, instruction=None, *args, **kwargs)

Find results similar to this result while excluding the source document.

Parameters:

  • client (Any) – Configured NOSIBLE client.

  • sql_filter (str | None) – Optional SQL filter.

  • n_results (int) – Maximum result count.

  • n_probes (int) – Number of search probes.

  • n_contextify (int) – Context size per result.

  • algorithm (str) – Retrieval algorithm.

  • publish_start (str | None) – Earliest publication date.

  • publish_end (str | None) – Latest publication date.

  • visited_start (str | None) – Earliest NOSIBLE visit date.

  • visited_end (str | None) – Latest NOSIBLE visit date.

  • certain (bool | None) – Whether dates must be certain.

  • include_netlocs (List[str] | None) – Domains to include.

  • exclude_netlocs (List[str] | None) – Domains to exclude.

  • include_companies (List[str] | None) – Company identifiers to include.

  • exclude_companies (List[str] | None) – Company identifiers to exclude.

  • include_docs (List[str] | None) – Document hashes to include.

  • exclude_docs (List[str] | None) – Document hashes to exclude.

  • brand_safety (str | None) – Brand-safety filter.

  • language (str | None) – ISO language filter.

  • continent (str | None) – Continent filter.

  • region (str | None) – Region filter.

  • country (str | None) – Country filter.

  • sector (str | None) – GICS sector filter.

  • industry_group (str | None) – GICS industry-group filter.

  • industry (str | None) – GICS industry filter.

  • sub_industry (str | None) – GICS sub-industry filter.

  • iab_tier_1 (str | None) – IAB tier-one filter.

  • iab_tier_2 (str | None) – IAB tier-two filter.

  • iab_tier_3 (str | None) – IAB tier-three filter.

  • iab_tier_4 (str | None) – IAB tier-four filter.

  • instruction (str | None) – Additional retrieval instruction.

  • args (Any) – Ignored legacy positional arguments.

  • kwargs (Any) – Deprecated legacy keyword arguments.

  • self (Result)

Returns:

Similar search results.

Return type:

ResultSet

to_dict()

Convert the result to its lossless dictionary representation.

Returns:

Search result payload.

Parameters:

self (Result)

Return type:

Dict[str, Any]

classmethod from_dict(data)

Create a result without discarding unknown response fields.

Parameters:

data (Dict[str, Any]) – Search result payload.

Returns:

Parsed result.

Return type:

Result