Skip to main content
POST
/
api
/
news
/
v1
/
summarize-article
SummarizeArticle
curl --request POST \
  --url https://api.example.com/api/news/v1/summarize-article \
  --header 'Content-Type: application/json' \
  --data '
{
  "provider": "<string>",
  "headlines": [
    "<string>"
  ],
  "mode": "<string>",
  "geoContext": "<string>",
  "variant": "<string>",
  "lang": "<string>",
  "systemAppend": "<string>",
  "bodies": [
    "<string>"
  ]
}
'
{
  "summary": "<string>",
  "model": "<string>",
  "provider": "<string>",
  "tokens": 123,
  "fallback": true,
  "error": "<string>",
  "errorType": "<string>",
  "statusDetail": "<string>"
}

Body

application/json

SummarizeArticleRequest specifies parameters for LLM article summarization.

​
provider
string
required

LLM provider: "ollama", "groq", "openrouter"

Minimum string length: 1
​
headlines
string[]
Minimum array length: 1

Headlines to summarize. Up to 10 raw headlines are used for request identity/cache matching; the LLM prompt uses up to 5 unique, non-empty sanitized headline/body pairs.

​
mode
string

Summarization mode: "brief", "analysis", "translate", "" (default).

​
geoContext
string

Geographic signal context to include in the prompt.

​
variant
string

Variant: "full", "tech", or target language for translate mode.

​
lang
string

Output language code, default "en".

​
systemAppend
string

Optional system prompt append for analytical framework instructions.

​
bodies
string[]

Optional article bodies paired 1:1 with headlines. When bodies[i] is non-empty, the prompt interleaves it as grounding context under headlines[i]; when empty, behavior is identical to headline-only today. Callers may supply a shorter array; missing entries are treated as empty. Each body is subject to the same sanitisation as headlines before reaching the LLM prompt.

Response

Successful response

SummarizeArticleResponse contains the LLM summarization result.

​
summary
string

The generated summary text.

​
model
string

Model identifier used for generation.

​
provider
string

Provider that produced the result (or "cache").

​
tokens
integer<int32>

Token count from the LLM response.

​
fallback
boolean

Whether the client should try the next provider in the fallback chain.

​
error
string

Error message if the request failed.

​
errorType
string

Error type/name (e.g. "TypeError").

​
status
enum<string>

SummarizeStatus indicates the outcome of a summarization request.

Available options:
SUMMARIZE_STATUS_UNSPECIFIED,
SUMMARIZE_STATUS_SUCCESS,
SUMMARIZE_STATUS_CACHED,
SUMMARIZE_STATUS_SKIPPED,
SUMMARIZE_STATUS_ERROR
​
statusDetail
string

Human-readable detail for non-success statuses (skip reason, etc.).