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

[deprecated] Tool Message

Tool messages are used to describe agent-tool usage events within the context of a conversation. Typically a user will prompt an agent who will decide which tool name to use (if any), an optional input and an optional Chain-of-Thought thought.

After running the tool an additional observation is generated.

Example:

{
   "type": "tool"
   "name": "football_api_tool",
   "thought": "I should check what time the football club is open today using football_api_tool",
   "input": {"event": "opening_hours", "filter": "day_of_week=Tuesday"},
   "observation": "0800-1600",
   "event_timestamp": "2020-02-20T20:20:23Z"
}
Field Name
Type
Description
Required

type

String

Tool identifier.

name

String

Tool name

thought

String

Chain-of-Thought reasoning.

input

Object

Collection of tool arguments.

observation

String

Tool execution result.

event_timestamp

Timestamp

(ISO 8601)

The timestamp of when this message was sent or received.

PreviousChat MessageNextCustom Event

Last updated 11 months ago

Was this helpful?