Understanding the core components of Artemis Search
Artemis Search is built on several interconnected components that work together to provide powerful, reasoning-based searches. The following diagram illustrates how these components relate to each other:
Artemis Search Component Relationship
This diagram illustrates the structure of Artemis Search, highlighting key relationships:
embedding
and tags
), and only one at a time may be activated.Let’s explore each of these components in more detail.
What makes our search 'intelligent'?
Artemis Search goes beyond traditional keyword matching or semantic similarity. Our technology uses task-specialized ML ranking models to enable us to bake “reasoning” and “context” into searches.
For example, when searching for “companies that require HIPAA compliance”, our system doesn’t just find companies related to medicine or HIPAA compliance. It actually reasons about which companies would be subject to HIPAA regulations based on their descriptions and activities.
Projects are the top-level entities in Artemis Search. Each project is dedicated to a particular search task.
What defines a project?
A project consists of:
Think of a project as a self-contained environment for a specific search use case.
Datasets are the foundation of your searches. They contain the information that Artemis Search will process and query.
What's in a dataset?
Each dataset is a pandas DataFrame saved as a parquet file with two essential columns:
embedding
: Contains OpenAI text-large-3 embeddings of the text you want to search through.tag
: Contains string values associated with each embedding, which will be returned as the content associated with each search result.You can have multiple datasets in a project, but only one can be active at a time.
Machines are the computational resources that power your searches.
How do machines work?
Each machine runs our ML model on the active dataset when responding to search requests.
The playground is where you can experiment with and fine-tune your searches. Under the hood, it uses the API to perform searches.
What can you do in the playground?
In the playground, you can:
What parameters can you adjust?
Adjusting these parameters allows you to fine-tune the balance between search accuracy and performance.
Artemis Search provides a RESTful API for seamless integration with your applications.
How to use the API?
/search
, which accepts parameters like search_query
, num_batches
, top_k
, filter_query
, and project_id
.For detailed API documentation, check out our API Reference section.
Understanding these key concepts will help you leverage the full power of Artemis Search in your projects. If you’re ready to start building, head over to our Quickstart Guide to set up your first project.
Understanding the core components of Artemis Search
Artemis Search is built on several interconnected components that work together to provide powerful, reasoning-based searches. The following diagram illustrates how these components relate to each other:
Artemis Search Component Relationship
This diagram illustrates the structure of Artemis Search, highlighting key relationships:
embedding
and tags
), and only one at a time may be activated.Let’s explore each of these components in more detail.
What makes our search 'intelligent'?
Artemis Search goes beyond traditional keyword matching or semantic similarity. Our technology uses task-specialized ML ranking models to enable us to bake “reasoning” and “context” into searches.
For example, when searching for “companies that require HIPAA compliance”, our system doesn’t just find companies related to medicine or HIPAA compliance. It actually reasons about which companies would be subject to HIPAA regulations based on their descriptions and activities.
Projects are the top-level entities in Artemis Search. Each project is dedicated to a particular search task.
What defines a project?
A project consists of:
Think of a project as a self-contained environment for a specific search use case.
Datasets are the foundation of your searches. They contain the information that Artemis Search will process and query.
What's in a dataset?
Each dataset is a pandas DataFrame saved as a parquet file with two essential columns:
embedding
: Contains OpenAI text-large-3 embeddings of the text you want to search through.tag
: Contains string values associated with each embedding, which will be returned as the content associated with each search result.You can have multiple datasets in a project, but only one can be active at a time.
Machines are the computational resources that power your searches.
How do machines work?
Each machine runs our ML model on the active dataset when responding to search requests.
The playground is where you can experiment with and fine-tune your searches. Under the hood, it uses the API to perform searches.
What can you do in the playground?
In the playground, you can:
What parameters can you adjust?
Adjusting these parameters allows you to fine-tune the balance between search accuracy and performance.
Artemis Search provides a RESTful API for seamless integration with your applications.
How to use the API?
/search
, which accepts parameters like search_query
, num_batches
, top_k
, filter_query
, and project_id
.For detailed API documentation, check out our API Reference section.
Understanding these key concepts will help you leverage the full power of Artemis Search in your projects. If you’re ready to start building, head over to our Quickstart Guide to set up your first project.