Context.ai
  • What is Context.ai?
  • List of Trackable Metrics
  • Product Analytics
    • Overview
    • Topic Categorisation
      • LLM Topics
    • User Engagement Tracking
    • Foreign Language Support
    • PII Filtering
    • Custom Metadata Filtering
    • Backfill Analytics Data
    • Custom Events
    • API Ingestion Methods
      • Log Conversation
      • [deprecated] Upsert Conversation
      • Thread Conversation
      • Patch Thread Message
      • API Resources
        • Chat Message
        • [deprecated] Tool Message
        • Custom Event
        • Metadata
        • Conversation
        • Thread
    • Embedded API
      • Multi-Tenancy
      • Conversations
        • Series Data
  • Integrations
    • Getting Started
    • Python SDK
    • Javascript SDK
    • LangChain Plugin
    • Haystack Plugin
    • Authorization
Powered by GitBook
On this page

Was this helpful?

  1. Product Analytics
  2. API Ingestion Methods
  3. API Resources

Chat Message

PreviousAPI ResourcesNext[deprecated] Tool Message

Last updated 10 months ago

Was this helpful?

A chat message describes a user's interaction with an LLM within the context of a conversation.

Example:

{
   "role": "assistant",
   "message": "The football club is open from 8am to 4pm today.",
   "event_timestamp": "2020-02-20T20:20:23Z",
   "rating": -1
   "metadata": {
     "state": "advancing",
   }
}
Field Name
Type
Description
Required

type

String

Chat message identifier. Defaults to message.

role

String

The role of who sent the message.

message

String

The text of this chat message.

event_timestamp

Timestamp

(ISO 8601)

The timestamp of when this message was sent or received.

rating

Integer

The user rating of this message, given by a 'thumbs up' or 'thumbs down' scoring system.

This should be set to one of -1 (for thumbs down), 0 (for no rating given), or 1 (for a thumbs up rating).

metadata

A hash of arbitrary key-value pairs.

Metadata