vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-03-24 08:21:39 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs(tools): add Exa Search page, align all search provider docs

Browse Source 
New page: tools/exa-search.md
- Neural/keyword/hybrid search modes with content extraction
- Tool parameters including contents (highlights, text, summary)
- Search mode reference table

Rewritten: tools/duckduckgo-search.md
- Aligned to consistent template (Setup, Config, Tool parameters, Notes, Related)
- Simplified from previous version

Aligned across all providers:
- Every search page now ends with a consistent ## Related section
- Replaced 'See [Web tools]' with proper Related links
- Added Exa + DuckDuckGo to web.md overview CardGroup and comparison table
- Added Exa to docs.json nav and redirects
This commit is contained in:
Vincent Koc
2026-03-22 21:27:21 -07:00
parent c11f95eced
commit df3f9bb555
8 changed files with 185 additions and 76 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
docs/docs.json
View File

@@ -92,6 +92,10 @@
"source": "/duckduckgo-search",
"destination": "/tools/duckduckgo-search"
},
{
"source": "/exa-search",
"destination": "/tools/exa-search"
},
{
"source": "/gemini-search",
"destination": "/tools/gemini-search"
@@ -1127,6 +1131,7 @@
"tools/web",
"tools/brave-search",
"tools/duckduckgo-search",
"tools/exa-search",
"tools/firecrawl",
"tools/gemini-search",
"tools/grok-search",

6
docs/tools/brave-search.md
View File

@@ -90,4 +90,8 @@ await web_search({
- The Search plan includes the LLM Context endpoint and AI inference rights. Storing results to train or tune models requires a plan with explicit storage rights. See the Brave [Terms of Service](https://api-dashboard.search.brave.com/terms-of-service).
- Results are cached for 15 minutes by default (configurable via `cacheTtlMinutes`).
See [Web tools](/tools/web) for the full web_search configuration.
## Related
- [Web Search overview](/tools/web) -- all providers and auto-detection
- [Perplexity Search](/tools/perplexity-search) -- structured results with domain filtering
- [Exa Search](/tools/exa-search) -- neural search with content extraction

107
docs/tools/duckduckgo-search.md
View File

@@ -13,52 +13,23 @@ OpenClaw supports DuckDuckGo as a **key-free** `web_search` provider. No API
key or account is required.
<Warning>
DuckDuckGo is an **unofficial, HTML-based** integration. It scrapes
DuckDuckGo's non-JavaScript search pages, not an official API or SDK.
Expect occasional breakage from bot-challenge pages or HTML changes.
Use it as a convenient fallback, not a production-grade provider.
DuckDuckGo is an **unofficial, HTML-based** integration, not an official API.
Expect occasional breakage from bot-challenge pages or HTML changes. Use it
as a convenient fallback, not a production-grade provider.
</Warning>
## Quick start
## Setup
DuckDuckGo requires no API key. Just set it as your provider:
No API key needed. Set DuckDuckGo as your provider:
```bash
openclaw configure --section web
# Select "duckduckgo" as the provider
```
Or set the provider directly in config:
```json5
{
tools: {
web: {
search: {
provider: "duckduckgo",
},
},
},
}
```
That's it — no keys, no plugin config, no environment variables.
## How it works
Unlike API-backed providers (Brave, Perplexity, Tavily), DuckDuckGo search
works by:
1. Sending an HTTP request to DuckDuckGo's non-JavaScript search endpoint
2. Parsing the HTML response to extract search results
3. Returning structured results with titles, URLs, and snippets
This approach means:
- **No API key needed** — works out of the box
- **No rate limits from an API plan** — but DuckDuckGo may serve bot-challenge
pages under heavy use
- **Results may differ** from what you see in DuckDuckGo's full web interface
<Steps>
<Step title="Configure">
```bash
openclaw configure --section web
# Select "duckduckgo" as the provider
```
</Step>
</Steps>
## Config
@@ -67,7 +38,6 @@ This approach means:
tools: {
web: {
search: {
enabled: true,
provider: "duckduckgo",
},
},
@@ -75,43 +45,38 @@ This approach means:
}
```
No `plugins.entries` config is needed — DuckDuckGo has no API key or plugin-specific settings.
No `plugins.entries` config is needed — DuckDuckGo has no API key or
plugin-specific settings.
## Supported parameters
## Tool parameters
DuckDuckGo search supports the standard `query` and `count` parameters.
Provider-specific filters like `country`, `language`, `freshness`, and
`domain_filter` are not supported.
| Parameter | Description |
| --------- | ------------------------------ |
| `query` | Search query (required) |
| `count` | Results to return (default: 5) |
## Limitations
DuckDuckGo does not support provider-specific filters like `country`,
`language`, `freshness`, or `domain_filter`.
- **Unofficial integration** — not backed by a DuckDuckGo API or SDK
## Notes
- **No API key** — works out of the box, zero configuration
- **Unofficial** — scrapes DuckDuckGo's non-JavaScript search pages, not an
official API or SDK
- **Bot-challenge risk** — DuckDuckGo may serve CAPTCHAs or block requests
under heavy or automated use
- **HTML parsing** — results depend on DuckDuckGo's page structure, which can
change without notice
- **No advanced filters** — only `query` and `count` are supported
- **Best-effort reliability** — treat this as a fallback, not a primary
provider for production use
- **HTML parsing** — results depend on page structure, which can change without
notice
- **Best-effort reliability** — treat as a fallback for development, demos, or
environments where no API key is available
## When to use DuckDuckGo
<CardGroup cols={2}>
<Card title="Good for" icon="check">
Quick local development, demos, testing, or environments where no API key
is available
</Card>
<Card title="Not recommended for" icon="x">
Production gateways, high-volume search, or workflows requiring reliable
uptime
</Card>
</CardGroup>
For production use, consider [Brave Search](/tools/brave-search) (free tier
available) or another API-backed provider.
<Tip>
For production use, consider [Brave Search](/tools/brave-search) (free tier
available) or another API-backed provider.
</Tip>
## Related
- [Web Search overview](/tools/web) -- all providers and auto-detection
- [Brave Search](/tools/brave-search) -- structured results with free tier
- [Gemini Search](/tools/gemini-search) -- AI-synthesized answers (also no search-specific key if you have a Gemini key)
- [Exa Search](/tools/exa-search) -- neural search with content extraction

119
docs/tools/exa-search.md Normal file
View File

@@ -0,0 +1,119 @@
---
summary: "Exa AI search -- neural and keyword search with content extraction"
read_when:
- You want to use Exa for web_search
- You need an EXA_API_KEY
- You want neural search or content extraction
title: "Exa Search"
---
# Exa Search
OpenClaw supports [Exa AI](https://exa.ai/) as a `web_search` provider. Exa
offers neural, keyword, and hybrid search modes with built-in content
extraction (highlights, text, summaries).
## Get an API key
<Steps>
<Step title="Create an account">
Sign up at [exa.ai](https://exa.ai/) and generate an API key from your
dashboard.
</Step>
<Step title="Store the key">
Set `EXA_API_KEY` in the Gateway environment, or configure via:
```bash
openclaw configure --section web
```
</Step>
</Steps>
## Config
```json5
{
plugins: {
entries: {
exa: {
config: {
webSearch: {
apiKey: "exa-...", // optional if EXA_API_KEY is set
},
},
},
},
},
tools: {
web: {
search: {
provider: "exa",
},
},
},
}
```
**Environment alternative:** set `EXA_API_KEY` in the Gateway environment.
For a gateway install, put it in `~/.openclaw/.env`.
## Tool parameters
| Parameter | Description |
| ------------- | ----------------------------------------------------------------------------- |
| `query` | Search query (required) |
| `count` | Results to return (1-100) |
| `type` | Search mode: `auto`, `neural`, `fast`, `deep`, `deep-reasoning`, or `instant` |
| `freshness` | Time filter: `day`, `week`, `month`, or `year` |
| `date_after` | Results after this date (YYYY-MM-DD) |
| `date_before` | Results before this date (YYYY-MM-DD) |
| `contents` | Content extraction options (see below) |
### Content extraction
Exa can return extracted content alongside search results. Pass a `contents`
object to enable:
```javascript
await web_search({
query: "transformer architecture explained",
type: "neural",
contents: {
text: true, // full page text
highlights: { numSentences: 3 }, // key sentences
summary: true, // AI summary
},
});
```
| Contents option | Type | Description |
| --------------- | --------------------------------------------------------------------- | ---------------------- |
| `text` | `boolean \| { maxCharacters }` | Extract full page text |
| `highlights` | `boolean \| { maxCharacters, query, numSentences, highlightsPerUrl }` | Extract key sentences |
| `summary` | `boolean \| { query }` | AI-generated summary |
### Search modes
| Mode | Description |
| ---------------- | --------------------------------- |
| `auto` | Exa picks the best mode (default) |
| `neural` | Semantic/meaning-based search |
| `fast` | Quick keyword search |
| `deep` | Thorough deep search |
| `deep-reasoning` | Deep search with reasoning |
| `instant` | Fastest results |
## Notes
- `freshness` and `date_after`/`date_before` cannot be combined — use one
time-filter mode
- Results are cached for 15 minutes by default (configurable via
`cacheTtlMinutes`)
- Exa is an official API integration with structured JSON responses
## Related
- [Web Search overview](/tools/web) -- all providers and auto-detection
- [Brave Search](/tools/brave-search) -- structured results with country/language filters
- [Perplexity Search](/tools/perplexity-search) -- structured results with domain filtering

6
docs/tools/firecrawl.md
View File

@@ -137,4 +137,8 @@ than basic-only scraping.
2. Firecrawl (if configured)
3. Basic HTML cleanup (last fallback)
See [Web Search](/tools/web) for the full provider setup and comparison.
## Related
- [Web Search overview](/tools/web) -- all providers and auto-detection
- [Web Fetch](/tools/web-fetch) -- web_fetch tool with Firecrawl fallback
- [Tavily](/tools/tavily) -- search + extract tools

8
docs/tools/perplexity-search.md
View File

@@ -170,5 +170,9 @@ await web_search({
- OpenRouter or explicit `plugins.entries.perplexity.config.webSearch.baseUrl` / `model` switches Perplexity back to Sonar chat completions for compatibility
- Results are cached for 15 minutes by default (configurable via `cacheTtlMinutes`)
See [Web tools](/tools/web) for the full web_search configuration.
See [Perplexity Search API docs](https://docs.perplexity.ai/docs/search/quickstart) for more details.
## Related
- [Web Search overview](/tools/web) -- all providers and auto-detection
- [Perplexity Search API docs](https://docs.perplexity.ai/docs/search/quickstart) -- official Perplexity documentation
- [Brave Search](/tools/brave-search) -- structured results with country/language filters
- [Exa Search](/tools/exa-search) -- neural search with content extraction

6
docs/tools/tavily.md
View File

@@ -122,4 +122,8 @@ Tips:
| Search with depth, topic, AI answers | `tavily_search` |
| Extract content from specific URLs | `tavily_extract` |
See [Web Search](/tools/web) for the full provider setup and comparison.
## Related
- [Web Search overview](/tools/web) -- all providers and auto-detection
- [Firecrawl](/tools/firecrawl) -- search + scraping with content extraction
- [Exa Search](/tools/exa-search) -- neural search with content extraction

4
docs/tools/web.md
View File

@@ -52,6 +52,9 @@ returns results. Results are cached by query for 15 minutes (configurable).
<Card title="DuckDuckGo" icon="bird" href="/tools/duckduckgo-search">
Key-free fallback. No API key needed. Unofficial HTML-based integration.
</Card>
<Card title="Exa" icon="brain" href="/tools/exa-search">
Neural + keyword search with content extraction (highlights, text, summaries).
</Card>
<Card title="Firecrawl" icon="flame" href="/tools/firecrawl">
Structured results. Best paired with `firecrawl_search` and `firecrawl_scrape` for deep extraction.
</Card>
@@ -78,6 +81,7 @@ returns results. Results are cached by query for 15 minutes (configurable).
| -------------------------------------- | -------------------------- | ------------------------------------------------ | ------------------------------------------- |
| [Brave](/tools/brave-search) | Structured snippets | Country, language, time, `llm-context` mode | `BRAVE_API_KEY` |
| [DuckDuckGo](/tools/duckduckgo-search) | Structured snippets | -- | None (key-free) |
| [Exa](/tools/exa-search) | Structured + extracted | Neural/keyword mode, date, content extraction | `EXA_API_KEY` |
| [Firecrawl](/tools/firecrawl) | Structured snippets | Via `firecrawl_search` tool | `FIRECRAWL_API_KEY` |
| [Gemini](/tools/gemini-search) | AI-synthesized + citations | -- | `GEMINI_API_KEY` |
| [Grok](/tools/grok-search) | AI-synthesized + citations | -- | `XAI_API_KEY` |