🔎

🔧 Developer Tools

Semantic Search

Natural language search over any content

Vector Index Semantic Embeddings Multi-Query Search Relevance Scoring High Throughput (200 rps)

About

Replace keyword search with meaning-based search powered by vector embeddings. Ingest any text content — articles, docs, product descriptions — and query with natural language. The system understands intent, not just keywords.

Supports multi-query search for complex information needs and returns relevance-scored results with metadata.

API Endpoints

POST /ingest Ingest content for semantic search

POST /search Semantic search

POST /search/multi Multi-query search

GET /docs List indexed documents

GET /health Health check

How It Works

Content Ingestion

POST /ingest — text content chunked, embedded, and indexed in the vector database.

Query Embedding

Search query converted to a vector in the same embedding space as your content.

Vector Search

Top-k nearest neighbors retrieved with relevance scores (configurable threshold).

Result Ranking

Results ranked by cosine similarity and returned with metadata and scores.

Use Cases

📚

Documentation Search

Let users search your docs with natural language instead of exact keyword matches.

🏷️

Product Catalog Search

Find products by describing what you need rather than knowing exact names or SKUs.

🔬

Research Assistant

Search across a corpus of papers, articles, or reports by meaning.

🗂️

Content Discovery

Surface related content across your site or app based on semantic similarity.

Quick Launch arrow_forward

Opens Aerostack dashboard to deploy this template

What's Included

check Vector Index

check Semantic Embeddings

check Multi-Query Search

check Relevance Scoring

check High Throughput (200 rps)

check 5 API endpoints

check Edge deployed

Pipeline

database RAG — Vector search + retrieval

Billing Model

metered

Pay per token used. Free tier included.