@font-face {
  font-family: 'NBInternationalPro';
  src: url('https://www.truestate.io/fonts/NBInternationalProRegularWeb/nbinternationalpro-regular-webfont.woff2') format('woff2');
  font-weight: normal;
  font-style: normal;
  font-display: swap;
}

@font-face {
  font-family: 'PerfectlyNineties';
  src: url('https://www.truestate.io/fonts/PerfectlyNineties/PerfectlyNineties-Regular.woff') format('woff');
  font-weight: normal;
  font-style: normal;
}

/* Then you can use it in your CSS like this: */
body {
  font-family: 'NBInternationalPro', sans-serif;
}

h1, h2, h3{
  font-family: 'NBInternationalPro', sans-serif;
  font-weight: 400;
}

.bold-text {
  font-weight: 700;  /* Bold */
}

.semibold-text {
  font-weight: 600;  /* Semi-bold */
}

.regular-text {
  font-weight: 400;  /* Regular */
}


Succeeding with AI analytics

What can you do with TrueState?

Exploring the largest disruption to analytics in history

Home

TrueState Documentation

Get started with AI-driven analytics in under 5 minutes

Quickstart guide

AI-driven analytics

A guide to forming an impact-oriented strategy for AI-driven analytics

Finding the right use-cases

A guide to the current capabilities of AI-driven analytics

Capabilities

Best practices for prompting across the TrueState platform

Prompting guide

Using AI as a tool to accelerate and improve the exploration of data

Exploratory analysis

Lightweight AI-driven analytics with TrueState

Data cleaning

Link mission-critical data into your AI-driven analytics engine

Integrating data

Using AI-driven analytics to predict and classify outcomes

Predictive analytics

Extracting insights from unstructured text using TrueState’s natural language tools

Text analytics

Building AI-powered automations with TrueState

Automations

Creating interactive dashboards to explore and showcase your data

Dashboards

Get Assistants

Create Assistant

List Assistants

Get Assistant

Update Assistant

Delete Assistant

Get all API keys for the member

Create a new API key for this user and organisation in the **api_keys** table.

Add a new API key for this member

Delete member's API key

Update member's API key

Get Model

Get Models

Retrieves the figure file stored in GCP for a given model.

Steps:
  1) Retrieve the model (same as get_model).
  2) Read the annotations property from the model.
  3) If the annotations do not satisfy the figure condition, raise a 400 error.
  4) If the condition is met, compute the final GCP file path.
     - If the stored GCP path is a directory, append 'figure.png'.
     - Use the organisation_id and sanitize_gcp_bucket_name to compute the bucket name.
  5) Read the file from GCP and return it as an image.

Get Figure

Retrieves the figure.png file from a given GCS URI provided directly in the path.

Get Figure By Path

List Conversations

Create Conversation

Generate Title

Get Conversation

Delete Conversation

Update Conversation

Handles chatbot queries by incorporating conversation history.

Query a Chatbot with conversation history

Retrieve messages based on user, organisation, and conversation_id.

Retrieve messages for a specific conversation

Handles chatbot queries with a single user message, without conversation history.

Query a Chatbot with a single message

Execute Query

Embedding Search

Fuzzy Search

Hybrid Search

Executes a retrieval augmented generation (RAG) query on a dataset.

Request Payload:
- **dataset_id**: The dataset ID to query.
- **messages**: A list of messages that form the conversation. Each message must have a `sender` field (either 'assistant' or 'user') and a `content` field. The conversation must end with a user message.
- **top_k**: The number of documents to retrieve from the underlying search.
- **keyword_column**: (Optional) If provided (and not null), a hybrid search is used based on the specified column. If omitted or null, a vector search is performed.

RAG Query Endpoint

Executes a collection query by retrieving all rows from the dataset (excluding the _embedding_vec column) and building an XML context from the query results. The context is then passed to the chatbot for response generation.

Request payload:
- **dataset_id**: The dataset ID to query.
- **messages**: A list of messages forming the conversation. The conversation must end with a user message.

Query Collection Endpoint

Executes a collection query by retrieving all rows from the chosen dataset (excluding the _embedding_vec column) and building an XML context from the query results. The chatbot is first asked to choose which dataset to use based on a mapping of dataset IDs to criteria. The chatbot must respond with exactly one dataset ID or None within <dataset> tags. If extraction fails or an invalid option is chosen, the query will proceed without any retrieved data.

Request payload:
- **dataset_id_to_criteria**: A mapping of dataset id to a criteria for selecting the dataset.
- **messages**: A list of messages forming the conversation. The conversation must end with a user message.

Query Collection Router Endpoint

Get Data Dictionary

Update Data Dictionary

Get Dataset

Delete Dataset

Update Dataset

Get Datasets

Create Hosted Dataset

Handle completion of dataset upload

Provides a signed URL to download the dataset file

Args:
- **body**: The request body containing the ID.
- **user**: The current user, obtained via dependency injection.
- **db**: The database session, obtained via dependency injection.

Returns:
- A JSON response containing the status and signed URL for the output file.

Get a signed URL to download the dataset

Get Dashboards

Create Dashboard

Get Dashboard

Delete Dashboard

Patch Dashboard

Creates a secret from stripe to send to the frontend that allows the customer to talk directly to stripe.

Create Payment Method

Updates the customer's billing details and attaches the new payment method

Confirm Setup Intent

Get Payment Method

Get Credits

Purchase Credits

Get Price Preview

Get Auto Recharge Settings

Update Auto Recharge Settings

Post Dashboard Element

Patch Dashboard Elements

Delete Dashboard Element

Patch Dashboard Element

Post Dashboard Filter

Delete Dashboard Filter

Delete Dashboard Embedding Searches

Run Query

Fetch Query Result

Get Deployments

Create Deployment

This route specifically queries a text based category deployment.
It accepts a string and returns a category response from the deployment.

Query Text Category

This route specifically queries a text based entity-match deployment.

Query Text Entity Match

This route specifically queries a text based zero shot classification deployment.
It accepts a string and returns a dictionary of categories from the deployment.

Query Text Zero Shot Classification

This route specifically queries a text based continuous deployment.
It accepts a string and returns a float response from the deployment.

Query Text Continuous

Query Chatbot

Delete an existing deployment

Get Messages

Create Message

Retrieve metadata for a secret

Delete an existing secret entry in the database.

Args:
- **body**: The request body containing the secret id to delete.
- **user**: The current user, obtained via dependency injection.
- **db**: The database session, obtained via dependency injection.

Returns:
- The status of the operation.

Delete an existing secret entry in the DB. This will also delete the associated secret in the cloud provider's secret manager.

Get all secrets for the current user's organization.

Args:
- **user**: The current user, obtained via dependency injection.
- **db**: The database session, obtained via dependency injection.

Returns:
- A list of all secrets for the current user's organization.

Retrieve all secrets for an organization.

Create a new secret entry in the database.

Secrets are typically used/needed to access datasets in protected cloud storage and can be different for each platform (e.g. GCP, AWS, Azure).

Args:
- **body**: The request body containing the new secret details.
- **user**: The current user, obtained via dependency injection.
- **db**: The database session, obtained via dependency injection.

Returns:
- The newly created secret details as a JSON response.

Create a new secret entry in the DB. These are typically used/needed to access datasets in protected cloud storage.

Retrieve all workflows associated with the user's organization.

Args:
- db: Database session.
- user: Authenticated user.

Returns:
- List[WorkflowRead]: List of workflows.

Get Workflows

Create a new workflow.

Args:
- workflow: Workflow creation object.
- db: Database session.
- user: Authenticated user.

Returns:
- WorkflowRead: The created workflow.

Create Workflow

Transfer Workflow Between Organisations

Retrieve a specific workflow by ID.

Args:
- workflow_id: ID of the workflow to retrieve.
- db: Database session.
- user: Authenticated user.

Returns:
- WorkflowRead: The requested workflow.

Get Workflow

Delete a specific workflow.

Args:
- workflow_id: ID of the workflow to delete.
- db: Database session.
- user: Authenticated user.

Delete Workflow

Update Workflow Metadata

Update Workflow

Duplicate Workflow

Update Workflow Schedule

Get Runs

Create Workflow Run

Get Run

Get Run Logs

Cancel Workflow Run

Get Live Flows

Create Live Flow

Get Live Flow

Update Live Flow

Delete Live Flow

Update Live Flow Metadata

Duplicate Live Flow

Get Sessions

Create Session

Get Session

Cancel Session

Add User Input To Session

Get a list of all available classification class hierarchies

Create a classification class hierarchy

Get an existing classification class hierarchy

Delete an existing classification class hierarchy

Update a classification class hierarchy

Create a classification class hierarchy from a CSV file

Get User

Get Organisations

Create Organisation

Get Current Organisation

Get Members

Create Member

Remove Member

Update Permissions

Upgrade Or Renew Subscription

Sets Seats Num

Toggle Seat Renewal

Generate embeddings for sentences

Generate a zero shot classification for an input text string

Score the truth value of an input text string

Get a list of all available tagging lists

Create a tagging list

Get an existing tagging list

Delete an existing tagging list

Update a tagging list

Get Notebooks

Create Notebook

Get Notebook

Delete Notebook

Update Notebook

Is Service Running

Create Service

Get Service Sessions

Activate New Service Session

Get Api Sessions

Post Api Sessions

Patch Api Sessions

Get Api Kernels

Get Api Kernel

Interrupt Api Kernel

Restart Api Kernel

Get Api Kernelspecs

Get Api Me

if no group_id provided, get the top-level tasks i.e. task.group_id == task.id
else get all tasks in the group

Get Tasks

Create Task

Get Task

Delete Task

Get Started

Essentials

Guides

Home

Explore the power of AI analytics in less than 5 minutes

Succeeding with AI analytics

What is AI analytics?

Finding your first use-case

Prompting guides

What can AI do?

What can you do with TrueState?

Exploratory Analytics

Dashboards

Data Cleaning

Predictive Analytics

Text Analytics

Automations

Get Started

Essentials

Guides

Explore the power of AI analytics in less than 5 minutes

​Succeeding with AI analytics

What is AI analytics?

Finding your first use-case

Prompting guides

What can AI do?

​What can you do with TrueState?

Exploratory Analytics

Dashboards

Data Cleaning

Predictive Analytics

Text Analytics

Automations

Succeeding with AI analytics

What can you do with TrueState?