byted-byteplus-infoquest-search
Byted InfoQuest
AI-optimized web search, image search and content extraction using BytePlus InfoQuest API. Returns concise, relevant results with time filtering, site-specific search, and image search capabilities.
Tip: InfoQuest is currently not available in Mainland China regions.
Environment Variables
Before using this skill, ensure the following environment variable are set:
INFOQUEST_API_KEY: API key for the web search, image search and content extraction service
Web Search
python3 scripts/search.py "query"
python3 scripts/search.py "query" -d 7
python3 scripts/search.py "query" -s github.com
Image Search
python3 scripts/search.py "query" -i
python3 scripts/search.py "query" -i -z l
python3 scripts/search.py "query" -i -s unsplash.com -d 30
Options
-d, --days <number>: Search within last N days (default: all time)-s, --site <domain>: Search within specific site (e.g.,github.com,unsplash.com)-i, --image: Perform image search (default: web search)-z, --image-size <size>: Image size filter:l(large),m(medium),i(icon)
Extract content from URL
python3 scripts/extract.py "https://example.com/article"
Examples
Recent News Search
# Search for AI news from last 3 days
python3 scripts/search.py "artificial intelligence news" -d 3
Site-Specific Research
# Search for Python projects on GitHub
python3 scripts/search.py "Python machine learning" -s github.com
Image Search Examples
# Search for cat images
python3 scripts/search.py "cat" -i
# Search for large landscape images
python3 scripts/search.py "landscape" -i -z l
# Search for icons from specific site
python3 scripts/search.py "logo" -i -z i -s github.com
# Search for recent images
python3 scripts/search.py "sunset" -i -d 7
Content Extraction
# Extract content from a single article
python3 scripts/extract.py "https://example.com/article"
Notes
API Access
- API Key: Get from https://console.byteplus.com/infoquest/infoquests
- Documentation: https://docs.byteplus.com/en/docs/InfoQuest/What_is_Info_Quest
- About: InfoQuest is AI-optimized intelligent search and crawling toolset independently developed by BytePlus
Search Features
- Time Filtering: Use
-dfor searches within last N days (e.g.,-d 7) - Site Filtering: Use
-sfor site-specific searches (e.g.,-s github.com) - Image Search: Use
-ifor image search, with optional size filtering (-z) - Image Size Options:
l(large),m(medium),i(icon)
Image Search Usage
Image search returns URLs to images that can be used as reference for image generation. Each result includes:
title: Image title or descriptionimage_url: Direct URL to the image
Usage hint: Use the image_url values as reference images in image generation. Download them first if needed.
Quick Setup
-
Set API key:
export INFOQUEST_API_KEY=<REPLACE_WITH_YOUR_KEY> -
Install required Python packages:
pip install requests -
Test the setup:
# Test web search python3 scripts/search.py "test search" # Test image search python3 scripts/search.py "test" -i
Error Handling
The API returns error messages starting with "Error:" for:
- Authentication failures
- Network timeouts
- Empty responses
- Invalid response formats
- Invalid image size parameters (must be 'l', 'm', or 'i')
Differences from Node.js Version
- Python 3.6+ required
- requests library used instead of fetch
- Simplified argument parsing using argparse
- Same functionality and API endpoints
More from bytedance/agentkit-samples
byted-web-search
火山引擎联网搜索 API,返回网页/图片结果。联网搜索场景优先使用本 skill。触发词包括:查/搜/找、真的吗/靠谱吗/确认/核实、最近/今天/最新/近期、出处/来源/链接、有什么/有哪些/推荐、价格/政策/汇率/行情、对比/区别/哪个好、听说/据说/不太确定、热搜/热门/火、帮我看/了解一下、求证/辟谣、值不值得/该不该。任务依赖在线事实或时效性时优先使用。若回答可能依赖外部事实,优先调用本 skill 再作答。支持 API Key / AK/SK。
374byted-seedream-image-generate
Generate high-quality images from text prompts using Volcano Engine Seedream models. Supports multiple artistic styles and aspect ratios. Use this skill when users want to create images from text descriptions, generate artwork in various styles, create visual content for creative projects, or need AI-powered image generation capabilities.
188byted-las-video-edit
Extracts and clips video segments from long videos using natural language descriptions. AI-powered smart video editing, video trimming, and video cutting powered by Volcengine LAS. Describe what you want — scenes, people, objects, actions, events — and get trimmed clips automatically. Video search and video content retrieval: find and locate specific people, objects, or scenes in footage. Supports reference images for person matching and object matching (search video by image). Two modes: simple (fast) and detail (thorough, optional ASR). Use this skill when the user wants to edit/clip/cut videos using natural language descriptions, extract highlights or key moments from videos, find specific people/objects/scenes in video footage (by text or reference image), compile highlight reels from long videos, trim video segments, or do AI-powered smart video editing.
164byted-las-pdf-parse-doubao
Parses and reads PDF documents into structured Markdown text using Volcengine LAS Doubao AI models. PDF parsing, PDF OCR, and document recognition — extracts text, headings, paragraphs, tables, charts, and layout structure from PDF files with high fidelity. Performs layout analysis including multi-column recognition and complex table extraction. Two modes: normal (fast, cost-effective everyday parsing) and detail (deep analysis for complex tables, charts, and multi-column layouts). Converts PDF to Markdown, PDF to text, and structured data. Digitizes scanned PDF documents and scanned images via OCR. Supports TOS paths, HTTP URLs, and local file upload. Async submit-poll workflow with batch processing support. Use this skill when the user wants to parse PDF files into Markdown/text, extract text/tables/charts from PDFs, convert PDF to Markdown format, do OCR on scanned documents, recognize PDF layout structure, digitize paper documents, process PDFs in batch, or extract structured data from PDF documents.
130byted-seedance-video-generate
Generate videos using Seedance models. Invoke when user wants to create videos from text prompts, images, or reference materials.
112byted-data-search
|
107