Ingest Data
Profile API
Ingest Data
Extract traits and memories from arbitrary text data
POST
Ingest Data
Overview
Ingest arbitrary text data and extract user traits and memories synchronously. This endpoint allows you to process historical data, CRM notes, chat logs, emails, or any text containing user information. Unlike the LLM proxy which processes conversations in real-time, this endpoint provides immediate extraction results, making it ideal for batch imports and offline processing.Use Cases
- Historical chat log import - Bulk import past conversations
- CRM integration - Extract user info from Salesforce/HubSpot notes
- Email thread processing - Analyze support ticket histories
- Batch migrations - Import user data from other systems
- Offline processing - Extract traits without live LLM calls
Path Parameters
string
required
Profile ID (internal UUID or external ID)
Request Body
string
required
The text data to ingest (max 100KB). Can be any text containing user
information.
string
Optional source identifier (e.g., “crm”, “chat_log”, “email”, “salesforce”)
object
Optional metadata object for tracking (e.g.,
{ "salesforceId": "abc123" })boolean
default:true
Whether to extract traits from the data
boolean
default:true
Whether to extract memories from the data
Response
object
The updated profile information
object
Extraction results
string | null
The source passed in the request
object | null
The metadata passed in the request
Response Example
Examples
Basic Usage
CRM Data Import
Chat Log Import
Extract Only Traits
Error Responses
Best Practices
- Data Size - Keep data under 100KB per request. For larger datasets, split into multiple requests.
-
Source Tracking - Use the
sourcefield to track where data originated for audit trails. - Metadata - Include relevant metadata to link back to source systems (CRM IDs, session IDs, etc.).
- Batch Processing - For bulk imports, process profiles sequentially to avoid rate limits.
- Error Handling - Implement retry logic for transient failures (500 errors).