Get your Exa API key
Authorizations
API key can be provided either via x-api-key header or Authorization header with Bearer scheme
Body
The query string for the search.
"Latest developments in LLM capabilities"
The type of search. Neural uses an embeddings-based model, keyword is google-like SERP, and auto (default) intelligently combines the two. Fast uses streamlined versions of the neural and keyword models.
keyword
, neural
, fast
, auto
"auto"
A data category to focus on.
company
, research paper
, news
, pdf
, github
, tweet
, personal site
, linkedin profile
, financial report
"research paper"
The two-letter ISO country code of the user, e.g. US.
"US"
Number of results to return. Limits vary by search type:
- With "keyword": max 10 results
- With "neural": max 100 results
If you want to increase the num results beyond these limits, contact sales ([email protected])
x <= 100
10
List of domains to include in the search. If specified, results will only come from these domains.
["arxiv.org", "paperswithcode.com"]
List of domains to exclude from search results. If specified, no results will be returned from these domains.
Crawl date refers to the date that Exa discovered a link. Results will include links that were crawled after this date. Must be specified in ISO 8601 format.
"2023-01-01T00:00:00.000Z"
Crawl date refers to the date that Exa discovered a link. Results will include links that were crawled before this date. Must be specified in ISO 8601 format.
"2023-12-31T00:00:00.000Z"
Only links with a published date after this will be returned. Must be specified in ISO 8601 format.
"2023-01-01T00:00:00.000Z"
Only links with a published date before this will be returned. Must be specified in ISO 8601 format.
"2023-12-31T00:00:00.000Z"
List of strings that must be present in webpage text of results. Currently, only 1 string is supported, of up to 5 words.
["large language model"]
List of strings that must not be present in webpage text of results. Currently, only 1 string is supported, of up to 5 words. Checks from the first 1000 words of the webpage text.
["course"]
Formats the search results into a context string ready for LLMs.
true
Enable content moderation to filter unsafe content from search results.
true
Response
OK
Unique identifier for the request
"b5947044c4b78efa9552a7c89b306d95"
The search type that was actually used for this request
neural
, keyword
"neural"
A list of search results containing title, URL, published date, and author.
For auto searches, indicates which search type was selected.
neural
, keyword
"auto"
A formatted string of the search results ready for LLMs.