feat(web): add SearXNG as a native search-only backend

Adds SearXNG as a free, self-hosted web search provider.  SearXNG is a
privacy-respecting metasearch engine that requires no API key — just a
running instance and SEARXNG_URL pointing at it.

## What this adds

- `tools/web_providers/searxng.py` — `SearXNGSearchProvider` implementing
  `WebSearchProvider` (search only; no extract capability)
- `_is_backend_available("searxng")` — gates on SEARXNG_URL
- `_get_backend()` — accepts "searxng" as a configured value; adds it to
  auto-detect candidates (lower priority than paid services)
- `web_search_tool` — dispatches to SearXNG when it is the active backend
- `check_web_api_key()` — includes SearXNG in availability check
- `OPTIONAL_ENV_VARS["SEARXNG_URL"]` — registered with tools=["web_search"]
- `tools_config.py` — SearXNG appears in the `hermes tools` provider picker
- `nous_subscription.py` — `direct_searxng` detection, web_active / web_available
- `setup.py` — SEARXNG_URL listed in the missing-credential hint
- 23 tests covering: is_configured, happy-path search, score sorting, limit,
  HTTP/request errors, _is_backend_available, _get_backend, check_web_api_key

## Config

```yaml
# Use SearXNG for search, any paid provider for extract
web:
  search_backend: "searxng"
  extract_backend: "firecrawl"

# Or: SearXNG as the sole backend (web_extract will use the next available)
web:
  backend: "searxng"
```

SearXNG is search-only — it does not implement WebExtractProvider.  Users
who only configure SEARXNG_URL get web_search available; web_extract falls
back to the next available extract provider (or is unavailable if none).

Closes #19198 (Phase 2 Task 4 — SearXNG provider)
Ref: #11562 (original SearXNG PR)
This commit is contained in:
kshitij 2026-05-06 10:05:29 -07:00 committed by GitHub
parent cd2cbc73b7
commit 5c906d7026
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 535 additions and 7 deletions

View file

@ -1832,6 +1832,14 @@ OPTIONAL_ENV_VARS = {
"password": True,
"category": "tool",
},
"SEARXNG_URL": {
"description": "URL of your SearXNG instance for free self-hosted web search",
"prompt": "SearXNG URL (e.g. http://localhost:8080)",
"url": "https://searxng.github.io/searxng/",
"tools": ["web_search"],
"password": False,
"category": "tool",
},
"BROWSERBASE_API_KEY": {
"description": "Browserbase API key for cloud browser (optional — local browser works without this)",
"prompt": "Browserbase API key",

View file

@ -255,6 +255,10 @@ def get_nous_subscription_features(
terminal_cfg = config.get("terminal") if isinstance(config.get("terminal"), dict) else {}
web_backend = str(web_cfg.get("backend") or "").strip().lower()
# Per-capability overrides: if set, they determine which backend is active for
# search/extract independently of web.backend.
web_search_backend = str(web_cfg.get("search_backend") or "").strip().lower()
web_extract_backend = str(web_cfg.get("extract_backend") or "").strip().lower()
tts_provider = str(tts_cfg.get("provider") or "edge").strip().lower()
browser_provider_explicit = "cloud_provider" in browser_cfg
browser_provider = normalize_browser_cloud_provider(
@ -280,6 +284,7 @@ def get_nous_subscription_features(
direct_firecrawl = bool(get_env_value("FIRECRAWL_API_KEY") or get_env_value("FIRECRAWL_API_URL"))
direct_parallel = bool(get_env_value("PARALLEL_API_KEY"))
direct_tavily = bool(get_env_value("TAVILY_API_KEY"))
direct_searxng = bool(get_env_value("SEARXNG_URL"))
direct_fal = fal_key_is_configured()
direct_openai_tts = bool(resolve_openai_audio_api_key())
direct_elevenlabs = bool(get_env_value("ELEVENLABS_API_KEY"))
@ -323,10 +328,18 @@ def get_nous_subscription_features(
or (web_backend == "firecrawl" and direct_firecrawl)
or (web_backend == "parallel" and direct_parallel)
or (web_backend == "tavily" and direct_tavily)
or (web_backend == "searxng" and direct_searxng)
# Per-capability overrides: search_backend or extract_backend may be set
# without web.backend (using the new split config from #20061)
or (web_search_backend == "searxng" and direct_searxng)
or (web_search_backend == "exa" and direct_exa)
or (web_search_backend == "firecrawl" and direct_firecrawl)
or (web_search_backend == "parallel" and direct_parallel)
or (web_search_backend == "tavily" and direct_tavily)
)
)
web_available = bool(
managed_web_available or direct_exa or direct_firecrawl or direct_parallel or direct_tavily
managed_web_available or direct_exa or direct_firecrawl or direct_parallel or direct_tavily or direct_searxng
)
image_managed = image_tool_enabled and managed_image_available and not direct_fal
@ -412,8 +425,8 @@ def get_nous_subscription_features(
managed_by_nous=web_managed,
direct_override=web_active and not web_managed,
toolset_enabled=web_tool_enabled,
current_provider=web_backend or "",
explicit_configured=bool(web_backend),
current_provider=web_backend or web_search_backend or "",
explicit_configured=bool(web_backend or web_search_backend),
),
"image_gen": NousFeatureState(
key="image_gen",

View file

@ -394,7 +394,7 @@ def _print_setup_summary(config: dict, hermes_home):
label = f"Web Search & Extract ({subscription_features.web.current_provider})"
tool_status.append((label, True, None))
else:
tool_status.append(("Web Search & Extract", False, "EXA_API_KEY, PARALLEL_API_KEY, FIRECRAWL_API_KEY/FIRECRAWL_API_URL, or TAVILY_API_KEY"))
tool_status.append(("Web Search & Extract", False, "EXA_API_KEY, PARALLEL_API_KEY, FIRECRAWL_API_KEY/FIRECRAWL_API_URL, TAVILY_API_KEY, or SEARXNG_URL"))
# Browser tools (local Chromium, Camofox, Browserbase, Browser Use, or Firecrawl)
browser_provider = subscription_features.browser.current_provider

View file

@ -299,6 +299,15 @@ TOOL_CATEGORIES = {
{"key": "FIRECRAWL_API_URL", "prompt": "Your Firecrawl instance URL (e.g., http://localhost:3002)"},
],
},
{
"name": "SearXNG",
"badge": "free · self-hosted · search only",
"tag": "Privacy-respecting metasearch engine — search only (pair with any extract provider)",
"web_backend": "searxng",
"env_vars": [
{"key": "SEARXNG_URL", "prompt": "Your SearXNG instance URL (e.g., http://localhost:8080)", "url": "https://searxng.github.io/searxng/"},
],
},
],
},
"image_gen": {