Worksport Ltd

AI-native vector embeddings for Worksport Ltd quarterly earnings calls

Get API Access

Ticker

WKSP

Coverage

2018–present

Embedding dims

768

Model

gemini-embedding-2-preview

About WKSP Earnings Embeddings

VectorFin provides vector embeddings for every Worksport Ltd earnings call from 2018 through the present quarter. Each earnings call transcript is chunked into semantically coherent segments and vectorized using Google's gemini-embedding-2-preview model, producing 768-dimensional dense vectors optimized for cosine similarity search.

All data is bitemporal: every embedding chunk carries an effective_ts (when the earnings call occurred) and a knowledge_ts (when VectorFin ingested and vectorized the data). This enables point-in-time backtesting — query the data as it was known at any historical date.

Embedding data is updated within 24 hours of each earnings call. The full history is available via REST API (all plans) or as Apache Iceberg tables on GCS (Pro+ plans), queryable natively from Snowflake, BigQuery, or Databricks.

Available fiscal periods

2024-Q4

2024-Q3

2024-Q2

2024-Q1

2023-Q4

2023-Q3

2023-Q2

2023-Q1

Showing recent 8 quarters. Full history from 2018 available via API.

Access via API

# Fetch WKSP embeddings for the latest quarter
curl https://api.vectorfinancials.com/v1/embeddings/WKSP \
  -H "X-API-Key: vf_sk_your_key_here" \
  -G \
  -d "fiscal_period=2024-Q4" \
  -d "limit=10"

# Response schema
{
  "data": [{
    "ticker": "WKSP",
    "fiscal_period": "2024-Q4",
    "chunk_idx": 0,
    "text": "...",
    "embedding": [0.023, -0.091, ...],
    "effective_ts": "2025-01-30T00:00:00Z",
    "knowledge_ts": "2025-01-31T06:00:00Z",
    "model_version": "gemini-embedding-2-preview"
  }],
  "next_cursor": "..."
}

Related Concepts

Embedding →Cosine Similarity →Bitemporal Data →Effective Timestamp →Knowledge Timestamp →Semantic Search →

Start using WKSP embeddings today

Free tier includes top 100 tickers with 1,000 API calls/month.

Get API Access View Documentation