Semantic Search

POST /v1/casestudies/semantic

Search using plain English. The API converts your query to a vector and finds semantically similar case studies.

Request body

Field	Type	Required	Description
`query`	string	Yes	Natural language search query
`company`	string	No	Filter by company slug
`industry`	string	No	Filter by industry
`tag`	string	No	Filter by tag
`limit`	integer	No	Max results (default: 10)
`similarity_threshold`	float	No	Min similarity 0-1 (default: 0.3)

Example

$ curl -X POST https://whatsapp-backend-knd2.onrender.com/v1/casestudies/semantic \
>   -H "X-API-Key: YOUR_KEY" \
>   -H "Content-Type: application/json" \
>   -d '{"query": "companies that improved sales pipeline with better data", "limit": 5}'

Understanding similarity scores

Score	Meaning
0.5+	Strong match
0.35-0.5	Relevant
0.3-0.35	Loosely related
Below 0.3	Filtered out

Tips

Be specific: “SaaS companies that reduced churn by improving onboarding” beats “churn”
Use filters to narrow first, then let semantic ranking sort within the set
For multiple queries at once, use Batch Search