Semantic Search

Search webpages or entered text for the answers you need.

Hvad er Semantic Search?

Semantic Search er en Chrome-udvidelse udviklet af Luke Sutor, og dens hovedfunktion er "Search webpages or entered text for the answers you need.".

Udvidelsesskærmbilleder

screenshot
screenshot
screenshot

Download Semantic Search-udvidelses-CRX-fil

Download Semantic Search-udvidelsesfiler i crx-format, installer Chrome-udvidelser manuelt i browseren eller del crx-filer med venner for nemt at installere Chrome-udvidelser.

Brugsanvisning til Udvidelsen

                        If you've ever been to pages like Wikipedia, you know finding simple answers in the vast amounts of text can be a pain. The semantic search extension makes finding answers to your questions easy and painless. This extension gathers the text from your current webpage, takes a question as input from you, the user, and passes it into a natural language processing model to answer your question using artificial intelligence.

Even if you don't word your question exactly as the answer appears on the website, you don't need to worry because the  NLP model can still answer your hardest questions accurately.



How to use:
•  This extension has two tabs, "Scan Webpage" and "Manually Enter." 
•  To parse the text of your current tab for an answer, use the "Scan Webpage" tab and simply ask the question you want answered. 
•  If you want to parse a specific block of text for an answer, you can use the "Manually Enter" tab by pasting the text block you want scanned into the "Text to Scan" field, and your question into the "Question" field.


Updates:
•  1.2.0: The extension has switched to a new backend service for model inference. It now uses banana.dev and a custom-built model inference pipeline. The extension performed slower in testing, but the answers and server reliability were greatly improved.
•  1.3.0: The extension has switched to using ChatGPT for question answering. Due to now using OpenAI's servers, the maximum context length is 11,000 words. Also, webpages cannot be chunked into smaller pieces automatically due to ChatGPT not reliably giving a confidence score along with its answer. Despite this, model inference is now faster than ever and the answers generated are much more reliable.
•  1.3.1: Minor big fixes.
•  1.3.2: Added support for searching text in Google Docs.
•  1.3.3: Made all extension requests route through a Cloudflare Worker server to act as a proxy.


Feedback:
[email protected]

Website:
lukesutor.com                    

Grundlæggende oplysninger om udvidelsen

Navn Semantic Search Semantic Search
ID moknadjgghaffcedafbafjfjgnaanalm
Officiel URL https://chromewebstore.google.com/detail/semantic-search/moknadjgghaffcedafbafjfjgnaanalm
Beskrivelse Search webpages or entered text for the answers you need.
Filstørrelse 78.26 KB
Antal Installationer 179
Nuværende Version 1.3.3
Senest Opdateret 2023-12-18
Udgivelsesdato 2021-05-17
Bedømmelse 5.00/5 Samlet 2 Bedømmelser
Udvikler Luke Sutor
E-mail [email protected]
Betalingsmetode free
Understøttede Sprog en-US
manifest.json
{
    "update_url": "https:\/\/clients2.google.com\/service\/update2\/crx",
    "manifest_version": 3,
    "name": "Semantic Search",
    "version": "1.3.3",
    "description": "Search webpages or entered text for the answers you need.",
    "options_page": "src\/pages\/options\/index.html",
    "background": {
        "service_worker": "src\/pages\/background\/index.js",
        "type": "module"
    },
    "action": {
        "default_popup": "src\/pages\/popup\/index.html",
        "default_icon": "icon-34.png"
    },
    "icons": {
        "128": "icon-128.png"
    },
    "content_scripts": [
        {
            "matches": [
                "http:\/\/*\/*",
                "https:\/\/*\/*",
                ""
            ],
            "js": [
                "src\/pages\/content\/index.js"
            ],
            "css": [
                "assets\/css\/contentStyle17027899008.chunk.css"
            ]
        }
    ],
    "web_accessible_resources": [
        {
            "resources": [
                "assets\/js\/*.js",
                "assets\/css\/*.css",
                "icon-128.png",
                "icon-34.png"
            ],
            "matches": [
                "*:\/\/*\/*"
            ]
        }
    ]
}