看了下有 gptel-tools 但没搜到具体例子，有没人分享下让我抄下
1 个赞
一个不算直接的回答，如果用的 Openrouter，可以直接加上:online Web Search | Add Real-time Web Data to AI Model Responses — OpenRouter | Documentation
注册一个 Tavily，搞到一个 Tavily API key，然后做如下配置：
(defun tavily-search-async (callback query &optional search-depth max-results)
"Perform a search using the Tavily API and return results as JSON string.
API-KEY is your Tavily API key.
QUERY is the search query string.
Optional SEARCH-DEPTH is either \"basic\" (default) or \"advanced\".
Optional MAX-RESULTS is the maximum number of results (default 5)."
(let* ((url "https://api.tavily.com/search")
(search-depth (or search-depth "basic"))
(max-results (or max-results 5))
(request-data
`(("api_key" . ,(tavily-api-key))
("query" . ,query)
("search_depth" . ,search-depth)
("max_results" . ,max-results))))
(plz 'post url
:headers '(("Content-Type" . "application/json"))
:body (json-encode request-data)
:as 'string
:then (lambda (result) (funcall callback result)))))
(defun fetch-url-text-async (callback url)
"Fetch text content from URL."
(interactive "sEnter URL: ")
(require 'plz)
(require 'shr)
(plz 'get url
:as 'string
:then (lambda (html)
(with-temp-buffer
(insert html)
(shr-render-region (point-min) (point-max))
(funcall callback (buffer-substring-no-properties (point-min) (point-max)))))))
(gptel-make-tool
:category "web"
:name "search"
:async t
:function (lambda (cb keyword)
(tavily-search-async cb keyword))
:description "Search the Internet; If you used any search results, be sure to include the references in your response."
:args (list '(:name "keyword"
:type string
:description "The keyword to search")))
(gptel-make-tool
:category "web"
:name "fetch_url_text"
:async t
:description "Fetch the plaintext contents from an HTML page specified by its URL"
:args (list '(:name "url"
:type string
:description "The url of the web page"))
:function (lambda (cb url)
(fetch-url-text-async cb url)))
然后在发送请求的时候启用这两个 tool 就可以了。效果：
（我的完整配置 emacs-config/modules/prelude-ai.el at master · ksqsf/emacs-config · GitHub ）
1 个赞