information-retrieval

Provide a published slug from GET /v1/logs. Receive JSON with the complete Markdown record of our direct provider attempts, chronological blockers, impact, workarounds, outcomes, and the last-update time.

Provide a published slug from GET /v1/logs. Receive JSON with the complete Markdown record of our direct provider attempts, chronological blockers, impact, workarounds, outcomes, and the last-update time.

Retrieve logos, backdrops, colors, industry, description, and more from any domain

Returns a simplified version of brand data containing only essential information: domain, title, colors, logos, and backdrops. This endpoint is optimized for faster responses and reduced data transfer.

List a Person's external profiles. Returns every known third-party profile (LinkedIn, Wikipedia, social) for the Person.

Returns a list of available languages for accessing real-time news data.

Returns real-time local search ranking data for a specific geographic coordinate.

Extract the title, description and Open Graph metadata of any web page URL — link previews and page metadata. ?url=https://example.com

Look up a current RxNorm, ICD-10-CM, or LOINC display from an exact code. Use when an agent already has a code and must not invent the preferred term.

DNS lookup: A, AAAA, MX, TXT, NS records

Read any public web page as clean readable Markdown for RAG and LLM pipelines — main article text with nav/ads stripped, plus title. The reader/scraper building block for agents. ?url=https://example.com&max_chars=20000

View the roadmap

Screenshot or PDF of any URL over one HTTP GET. Query params: url (required, encoded), format (png|jpeg|pdf, default png), full_page (true|false), width, height, scale (retina), quality (jpeg). Returns the rendered bytes. Drop-in for Urlbox/ScreenshotOne at a fraction of the cost.

Full ISO 13616 structural check plus ISO 7064 mod-97-10 check-digit verification (the same algorithm banks use). Returns valid (boolean), country code, and the normalized IBAN string.

Find the sources where an email was found on the web.

Functions extracted from source with name, repo, file path, arguments, decorators, docstring, line count, and complexity.

Read any public web page as clean readable Markdown for RAG and LLM pipelines — main article text with nav/ads stripped, plus title. The reader/scraper building block for agents. ?url=https://example.com&max_chars=20000

Searches messages and content from Telegram channels and groups.

SYNTHORA sanctions-screen: sanctions screening with MATCH / CLEAR verdict over 4 official downloads (OFAC SDN primary and alias lists, UN, OpenSanctions). Multilingual, tested on Cyrillic transliterations.

SHA-256 of a page or JSON body + change detection vs a baseline hash. Stateless monitoring. Add &json_path=a.b.0 to extract and watch a single JSON field (price, counter). ?url=https://example.com&baseline=<sha256>&json_path=bitcoin.usd

Run Python code in a secure sandbox environment using E2B. Supports Jupyter Notebook syntax and returns execution results and logs.

Extract title, description, OG image from a URL

Compute a SHA-256 fingerprint of any string: full hex digest, colon-separated (like SSH fingerprints), a short 16-char id, and base64. Deterministic, CPU-only. Pass ?text=<content>.

BM25 plus vector search with reciprocal rank fusion over Function and Class nodes, with repository, domain, ontology concept, confidence, and test-coverage filters.