Exa Find Similar Pages
View schema →
exa.find_similarFind web pages semantically similar to a reference URL (great for competitor discovery and lookalike sourcing).
Tool ID: helve.web_search
Search the live web across 11 engines (Exa, Tavily, Brave, Serper, Firecrawl, Linkup, Valyu, Perplexity, Jina, Octen, Parallel) or run fusion for cross-engine consensus.
| Parameter | Type | Required | Description |
|---|---|---|---|
query | string | Required | What to search for, in natural language. Keyword engines (Brave, Serper) receive it as typed; neural engines (Exa, Parallel) interpret it semantically. |
provider | string (exa | parallel | tavily | brave | serper | firecrawl | linkup | valyu | jina | octen | perplexity | auto | fusion) | Optional | Which engine serves the request. `auto` (default) picks the first configured provider in Helve's priority order. `fusion` fans out to a panel of engines and merges their top picks by consensus; see the Fusion guide. |
max_results | integer | Optional | Number of results to return, 1–100. Default 10. Engines with a lower ceiling (Tavily and Brave stop at 20) are capped with a `param_approximated` warning. With `fusion` this sizes each member's list, not the merged one. |
mode | string (instant | fast | balanced | deep) | Optional | Speed/quality trade-off, mapped to each engine's tiers (Exa instant/fast/auto/deep, Parallel turbo/fast/basic/advanced, Tavily ultra-fast/fast/basic/advanced). Single-tier engines ignore it with a warning. Default: the engine's own default tier. |
include_domains | array | Optional | Only return pages from these domains. Native on most engines; rewritten into `site:` operators on Brave and Serper. |
exclude_domains | array | Optional | Never return pages from these domains. Native on most engines; rewritten into `-site:` operators on Brave and Serper. |
published_after | string | Optional | Only pages published on or after this date, `YYYY-MM-DD`. Mutually exclusive with `freshness`. |
published_before | string | Optional | Only pages published on or before this date, `YYYY-MM-DD`. Mutually exclusive with `freshness`. |
freshness | string (day | week | month | year) | Optional | Shorthand for a rolling publication window ending now. Mutually exclusive with `published_after` / `published_before`. |
content | object | Optional | What text to return for each result. Every engine returns snippets; full text and summaries depend on the engine. |
locale | object | Optional | Bias results toward a country and language. Native on Brave, Serper, and Tavily. |
category | string (general | news | company | people | research) | Optional | Content category. `news` maps to the engine's news index where one exists; `company`, `people`, and `research` are native on Exa and approximated elsewhere. |
safe_search | string (off | moderate | strict) | Optional | Adult-content filtering. Native on Brave and Serper; ignored with a warning elsewhere. |
offset | integer | Optional | Skip this many results for pagination. Native on Brave and Serper only; other engines ignore it with a warning. |
strict | boolean | Optional | When true, any parameter the serving engine cannot honour is a 400 instead of a warning. Not allowed with `fusion`. Default false. |
provider_options | object | Optional | Escape hatch for provider-native parameters. Each key is a provider id; its value is merged into that provider's request unchanged. Helve never inspects these, except `fusion`, which is Helve's own and typed. |
curl -X POST https://helve.dev/v1/tools/call \
-H "Authorization: Bearer sk_live_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"tool_id": "helve.web_search",
"arguments": {
"query": "latest AI agent benchmarks 2026",
"provider": "auto",
"max_results": 5
}
}'
call_tool){
"name": "call_tool",
"arguments": {
"tool_id": "helve.web_search",
"arguments": {
"query": "latest AI agent benchmarks 2026",
"provider": "auto",
"max_results": 5
}
}
}
exa.find_similarFind web pages semantically similar to a reference URL (great for competitor discovery and lookalike sourcing).
brave.images_searchSearch for images, thumbnails, and visual assets via Brave Images Search API.
brave.videos_searchSearch videos and metadata across the web via Brave Videos Search API.
wayback.availableCheck whether the Internet Archive Wayback Machine has an archived snapshot for a URL (optionally nearest to a timestamp).
devto.articlesFetch developer articles from Dev.to by tag, author username, rising/fresh state, or top N days.