| 12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394 |
- """Keenable (https://keenable.ai) web search + fetch — keyless-ring member.
- Env: ``KEENABLE_API_KEY`` (optional; keyless free tier works without it).
- Config: ``web.provider_tier.keenable: free|paid`` pins the tier (unset = auto).
- """
- from __future__ import annotations
- import logging
- from typing import Any, Dict, List
- from agent.ssl_verify import requests_verify
- from plugins.web._common import (
- SEARCH_LIMIT_CAP, BaseWebSearchProvider, document, http_status_detail, keenable_origin_error, keyless_extract, keyless_search,
- keyless_variant_schema, page_error, provider_env, run_extract, run_search, search_fail, search_ok, use_keyless, web_hit,
- )
- logger = logging.getLogger(__name__)
- _KEENABLE_API_URL = "https://api.keenable.ai"
- def _keenable_headers(api_key: str) -> dict[str, str]:
- # The keyless tier structurally requires an app-identifier header; no user identifiers are sent.
- headers = {"X-Keenable-Title": "hermes-agent"}
- if api_key:
- headers["Authorization"] = f"Bearer {api_key}"
- return headers
- class KeenableWebSearchProvider(BaseWebSearchProvider):
- """Keenable search + extract provider (keyed or keyless)."""
- NAME = "keenable"
- DISPLAY_NAME = "Keenable"
- KEY_ENV = "KEENABLE_API_KEY"
- EXTRACT = True
- KEYLESS = True
- def search(self, query: str, limit: int = 5) -> dict[str, Any]:
- def _body() -> dict[str, Any]:
- api_key = provider_env("KEENABLE_API_KEY")
- if use_keyless("keenable", api_key):
- return keyless_search("Keenable", "keenable", query, limit, logger)
- import requests
- logger.info("Keenable search: '%s' (limit=%d)", query, limit)
- # requests freezes its default CA bundle path at its own import; a replaced
- # install environment leaves it dangling, so hand over a live bundle.
- response = requests.post(
- f"{_KEENABLE_API_URL}/v1/search",
- json={"query": query, "max_results": min(max(1, int(limit)), SEARCH_LIMIT_CAP)},
- headers=_keenable_headers(api_key), timeout=30, verify=requests_verify(),
- )
- if response.status_code >= 400:
- return search_fail(f"Keenable search failed: {http_status_detail(response)}")
- return search_ok([
- web_hit(r.get("url") or "", r.get("title") or "", r.get("snippet") or r.get("description") or "", i + 1)
- for i, r in enumerate(response.json().get("results") or [])
- ])
- return run_search("Keenable", logger, _body, verbatim_value_error=False)
- def extract(self, urls: list[str], **kwargs: Any) -> list[dict[str, Any]]:
- def _body() -> list[dict[str, Any]]:
- api_key = provider_env("KEENABLE_API_KEY")
- if use_keyless("keenable", api_key):
- return keyless_extract("Keenable", "keenable", urls, logger)
- import requests
- logger.info("Keenable extract: %d URL(s)", len(urls))
- results: list[dict[str, Any]] = []
- for url in urls:
- try:
- response = requests.get(f"{_KEENABLE_API_URL}/v1/fetch", params={"url": url}, headers=_keenable_headers(api_key), timeout=30, verify=requests_verify())
- if response.status_code >= 400:
- if origin := keenable_origin_error(response.status_code, response.text):
- results.append(page_error(url, origin))
- continue
- raise ValueError(http_status_detail(response))
- data = response.json()
- results.append(document(data.get("url") or url, data.get("title") or "", data.get("content") or "", source_url=url))
- except Exception as exc:
- results.append(page_error(url, f"Keenable extract failed: {exc}"))
- return results
- return run_extract("Keenable", logger, urls, _body, verbatim_value_error=False)
- def get_setup_schema(self) -> dict[str, Any]:
- return keyless_variant_schema(
- "Keenable", "KEENABLE_API_KEY", "https://keenable.ai",
- free_tag="Independent web index for AI apps — fast search + page fetch on Keenable's anonymous free tier.",
- paid_tag="Independent web index for AI apps. Keyed access with higher limits and guaranteed service.",
- )
|