Vectara · Schema

Vectara Agent

A Vectara agent encapsulates instructions, a set of tools, and the corpora it can query, to perform grounded conversational and tool-using workflows.

AIAgentsCorporaEmbeddingsEnterprise SearchGenerative AIGrounded GenerationHallucination DetectionLLMMCPRAGRetrievalSearchSemantic SearchVector Search

Properties

Name Type Description
id string
name string
description string
instructions string System-prompt-style instructions that govern agent behavior.
tool_ids array IDs of tools the agent may call.
corpus_keys array Corpora the agent can retrieve from.
enabled boolean
model object
View JSON Schema on GitHub

JSON Schema

vectara-agent-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/vectara/main/json-schema/vectara-agent-schema.json",
  "title": "Vectara Agent",
  "description": "A Vectara agent encapsulates instructions, a set of tools, and the corpora it can query, to perform grounded conversational and tool-using workflows.",
  "type": "object",
  "required": ["name"],
  "properties": {
    "id": { "type": "string" },
    "name": { "type": "string" },
    "description": { "type": "string" },
    "instructions": {
      "type": "string",
      "description": "System-prompt-style instructions that govern agent behavior."
    },
    "tool_ids": {
      "type": "array",
      "items": { "type": "string" },
      "description": "IDs of tools the agent may call."
    },
    "corpus_keys": {
      "type": "array",
      "items": { "type": "string" },
      "description": "Corpora the agent can retrieve from."
    },
    "enabled": { "type": "boolean" },
    "model": {
      "type": "object",
      "properties": {
        "llm_name": { "type": "string" },
        "max_tokens": { "type": "integer" },
        "temperature": { "type": "number" }
      }
    }
  }
}