Inqyra
| 开发者 | ipportunities |
|---|---|
| 更新时间 | 2026年3月24日 17:38 |
| 捐献地址: | 去捐款 |
| PHP版本: | 8.1 及以上 |
| WordPress版本: | 6.9 |
| 版权: | GPLv2 or later |
| 版权网址: | 版权信息 |
详情介绍:
- Crawl — Inqyra indexes your pages, posts, and custom post types
- Embed — Content is converted to vector embeddings entirely in your browser (your content never leaves your server)
- Search — When a visitor asks a question, Inqyra finds the most relevant content using vector similarity, keyword matching, and title/path boosting
- Answer — The relevant context is sent to your chosen AI provider, which generates a grounded response
- 5 AI providers — OpenAI, Gemini, Claude, Mistral, DeepSeek
- Browser-based embeddings — Content never leaves your server for indexing
- 29 languages — Dutch, English, German, French, Spanish, Italian, Portuguese, and 22 more
- Customizable widget — Colors, position, greeting, header, powered-by text
- Auto-recrawl — Content re-indexes automatically when you update a post
- Cost & token tracking — Monitor API usage and set budget limits
- Rate limiting — Built-in IP-based rate limiting (20/min, 200/hr)
- API key encryption — Keys encrypted at rest with AES-256-CBC
- No cookies — The plugin does not set any cookies
- Lightweight — Loads asynchronously with minimal impact on Core Web Vitals
- Setup wizard — Live in under 5 minutes with the guided setup
- Floating chat widget with full customization
- Unlimited pages indexed (post type: pages)
- All 5 AI providers (BYOK)
- Browser-based embeddings
- RAG-powered answers
- Conversation tracking (last 30 days)
- Auto-recrawl on content changes
- Cost & token tracking with budget limits
- Query rewriting (LLM-powered query expansion)
- 29-language support
- Index posts, products & custom post types
- Document upload (PDF, DOCX)
- Synonym management for improved search matching
- Webhooks (Zapier, Make, CRM integration)
- Lead extraction (email, phone, name, company)
- Advanced analytics & statistics export
- Page targeting (show widget on specific pages)
- Extended conversation history & analytics
- Escalation & appointment request detection
- Email support
- Embeddings are generated entirely in the browser — your content never leaves your server during indexing
- Only when a visitor asks a question does relevant context go to the AI provider, through your own API key
- No cookies are set by the plugin
- GDPR-friendly architecture
- Built in the Netherlands by Ipportunities B.V.
安装:
- Go to Plugins > Add New in your WordPress admin
- Search for "Inqyra" and click Install Now
- Click Activate — the setup wizard starts automatically
- Choose your AI provider and paste your API key
- Select which content to index and click Index Now
- Customize the chat widget appearance
- Done — the chatbot is live on your site
屏幕截图:
常见问题:
Do I need programming knowledge?
No. Inqyra is fully no-code. Install the plugin, add your API key, and configure everything through the visual interface and setup wizard.
Do I need my own AI account?
Yes. You need an API key from at least one supported provider: OpenAI, Google (Gemini), Anthropic (Claude), Mistral, or DeepSeek. This gives you full control over costs and data.
What does a conversation cost?
With GPT-4o-mini, approximately $0.003 per conversation. With GPT-4o, roughly $0.01–$0.03. With Gemini Flash, as low as $0.001. You pay the AI provider directly — Inqyra adds zero markup.
How is this different from other AI chat plugins?
Most plugins charge per message or mark up API costs. With Inqyra, you pay the AI provider directly at their published rates. Browser-based embeddings mean your content never leaves your server during indexing. You can switch AI providers at any time without re-indexing.
Does it work with WooCommerce?
Yes. With Inqyra Premium, you can index WooCommerce products and any other custom post type. The free version indexes pages.
Is it GDPR compliant?
Inqyra is designed with privacy in mind. Embeddings are generated in the browser (no third-party processing during indexing), no cookies are set, and the plugin is built in the Netherlands. When a visitor chats, only the relevant context is sent to your chosen AI provider through your own API key.
What happens when I hit my budget limit?
The chat widget stops responding for the rest of the day. Limits reset at midnight (server time). You can configure daily token limits, hourly request limits, and cost limits per agent.
Can visitors chat in different languages?
Yes. Inqyra supports 29 languages. The chatbot responds in the language configured for your agent. The multilingual embedding model handles content in any supported language.
What file formats can I upload?
With Inqyra Premium, you can upload PDF and DOCX files (up to 10 MB each). These are chunked and indexed alongside your website content.
更新日志:
- Initial release
- 5 AI providers: OpenAI, Gemini, Claude, Mistral, DeepSeek
- RAG-powered search with vector similarity, keyword matching, and title/path boosting
- Browser-based embeddings via Transformers.js (bundled locally)
- 29-language support with default system prompts
- Customizable floating chat widget
- Auto-recrawl on content changes
- Cost and token tracking with budget limits
- Setup wizard for guided configuration
- API key encryption at rest with AES-256-CBC
- IP-based rate limiting (20/min, 200/hr)
- Query rewriting for improved search accuracy
- Premium: Document upload (PDF, DOCX), synonyms, webhooks, lead extraction, advanced analytics, page targeting