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

Thread

PreviousConversationNextEmbedded API

Last updated 11 months ago

Was this helpful?

A thread is a specialization of Conversation. A conversation can have an optional property id of type string to support ingestion through .

Example:

{
  "id": "Thread1234",
  "messages": [
    {
      "role": "system",
      "message": "You are a LLM providing information about a local football club.",
      "event_timestamp": "2020-02-20T20:20:23Z"
    },
    {
      "role": "user",
      "message": "What time does the team arrive?",
      "event_timestamp": "2020-02-20T20:21:34Z"
    },
    {
      "type": "tool",
      "name": "football_api_tool",
      "thought": "The user asked about the team time arrival, I should use football_api_tool",
      "input": {"event": "team-arrive", "resource": "time"},
      "observation": "Error: could not find event",
      "event_timestamp": "2020-02-20T20:21:34Z"
    },
    {
      "role":"assistant",
      "message": "I'm not sure what time the team arrives.",
      "event_timestamp": "2020-02-20T23:20:40Z",
      "rating": -1
    }
  ],
  "metadata": {
    "model": "gpt-3.5-turbo-16k",
    "user_id": "2947451"
  },
  "feedback": "Agent was not helpful and did not answer my queries."
}
Field Name
Type
Description
Required

id

String

Thread conversation identifier

messages

Array

metadata

Object

feedback

String

Free text feedback from user

Array of or objects

object

Thread Conversation
Chat Message
[deprecated] Tool Message
Metadata