Zai

💡 Tip: Check out example queries or start typing "describe" followed by a species name to see suggestions!

Keep the queries short, no more than 3-5 words long. Focus on a single task and a single species, and include the species name in the query. This allows a more focused context to be presented to the LLM. Here are a few examples to get you started:

←

About

Zai is the Zenodeo ai providing a Q&A access to the ~1M treatments extracted by Plazi and made available on TreatmentBank and BLR on Zenodo.

Zai responds to simple and focused questions with easy-to-understand summaries or pointed answers. It cannot (yet) respond to questions that span many documents, and is best at extracting answers from a single treatment that can be pin-pointed with a full-text search.

Zai is also the Chinese verb 在 (zài) for describing existence in a location, similar to how we say in English, "to be at" or "to be in."

←

Semantic Cache

We use the Supabase/gte-small model for generating vector embeddings of queries.

                                   ┌───────────┐ 
                                   │what is the│ 
   ┌──────────────────────────────▶│meaning of │──┐
   │                               │life?      │  │
 asks                              └───────────┘  │
   │                                     │        │
   │        ┌ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─│─ ─ ─ ─ ┼ 
   │           semantic cache            │        ││
┌────┐      │       ┌─────────┐   ┌──────▼────┐   │ 
│\O/ │              │search   │   │convert    │   ││
│ |  │  42  │       │for exact│   │query to   │   │ 
│/ \ │◀───────found─┤key in   ◀───│unique     │   ││
│user│      │       │cache    │   │cache key  │   │ 
└────┘              └────┬────┘   └───────────┘   ││
   ▲        │            │                        │ 
   │                  not found                   ││
   │        │            │                        │ 
   │                ┌────▼────┐                   ││
   │        │       │convert  │                   │ 
   │                │to       │                   ││
   │        │       │embedding│◀──────────────────┘ 
   │                │vector   │                    │
   │        │       └─────────┘                     
   │                                               │
   │        │       ┌────────────────────┐          
   │                │search for query    │         │
   │        │       │with highest cosine │          
   └──────────found─│similarity above a  │         │
            │       │preset threshold    │          
                    └────────────────────┘         │
            │                  │                    
             ─ ─ ─ ─ ─ ─ ─ ─ ─ ┼ ─ ─ ─ ─ ─ ─ ─ ─ ─ ┘
                              no   
                               │   
                               ▼

←

How this works

                ┌───────────┐
                │what is the│
  ┌────────────▶│meaning of │
  │             │life?      │
asks            └───────────┘
  │                   │      
  │        ┌ ─ ─ ─ ─ ─│─ ─ ─ ─ ── ─ ─ ─ ─ ─ ─ ─ ─ ─ 
┌────┐                │         semantic cache     │
│\O/ │     │    ┌─────▼─────┐                       
│ |  │      yes │is the     │          ┌──────┐    │
│/ \ │◀──42┼────│answer in  │─────────▶│cache │     
│user│          │cache?     │          └───▲──┘    │
└────┘     │    └───────────┘              │        
                     no                    │       │
           └ ─ ─ ─ ─ ─│─ ─ ─ ─ ── ─ ─ ─ ─ ─│─ ─ ─ ─ 
                      │                    │     
             ┌────────▼───────┐            │     
             │remove stopwords│      ┌─────┴────┐
             │"what", "is",   │      │ response │
             │"the", and "of" │      └─────▲────┘
             └────────┬───────┘            │     
                      │              ┌─────┴────┐
             ┌────────▼───────┐      │   LLM    │
             │full text search│      └─────▲────┘
             │of "meaning" and│            │     
             │"life"          │            │     
             └────────┬───────┘   ┌────────┴───────┐
                      │           │question: "what │
                      │           │is the meaning  │
                      │           │of life?"       │
                      │    top  ─▶│                │
                      │   ranked  │context: full   │
                      │   paper   │text of the     │
               ┌──────▼─────┐  │  │paper           │
               │papers      │  │  └────────────────┘
               │ranked by   │──┘ 
               │relevance   │    
               └────────────┘

We are testing various LLMs including Alibaba's Qwen 3:0.6b, Meta's Llama 3.2:1b and 3b, and Google's Gemma 3 to generate answers to questions based on the context provided. The context is chosen from the full text search result of the relevant tokens in your query ranked by their relevance (BM25 score). The generated answers are stored in a semantic cache for fast retrieval for subsequent queries.