Conclusão do chat

Atividade Conclusão do chat no conector Perplexity.

Observação:

As of September 30, 2026, this activity uses Perplexity's Agent API. Perplexity is retiring the Sonar Chat Completions API that this activity previously used (supported until September 27, 2026), so UiPath migrated the activity to the Agent API to keep your automations running. Existing workflows keep working: saved Sonar model IDs are mapped to the matching preset automatically. Because the Agent API differs from the Chat Completions API in request and response structure, the output format, citations, or model behavior may differ slightly. Re-test any workflows that parse this activity's output.

Description

Gera uma resposta de conclusão do chat.

Compatibilidade do projeto

Windows | Multiplataforma

Configuração

• Conexão - A conexão estabelecida no Integration Service. Acesse o menu suspenso para escolher, adicionar ou gerenciar conexões.
• Model - The preset that selects the model and research depth: fast, low, medium, high, or xhigh. Deeper presets run more search steps and take longer. Legacy Sonar model IDs are mapped to the matching preset automatically, and a full model ID is also accepted. For details, refer to the Perplexity documentation for presets.
• Prompt - The message to send to the model. This field supports String type input. Provide either Prompt or Message content. If both are set, the prompt is used and the messages are ignored.
• Message content - The text of each message in a multi-turn conversation, in order. Used only when Prompt is empty.

Gerenciar propriedades

Use o assistente Gerenciar Propriedades para configurar ou usar qualquer um dos campos padrão ou personalizados do objeto. Você pode selecionar campos para adicioná-los à tela de atividades. Os campos padrão ou personalizados adicionados estão disponíveis no painel Propriedades (no Studio Desktop) ou em Mostrar propriedades adicionais (no Studio Web).

Propriedades adicionais

Opções

• Instructions - System instructions that steer how the agent approaches the task.
• Maximum steps - The upper bound on the agent research loop, from 1 to 100. Each step is a search or fetch plus a model turn. Lower values reduce latency and cost. If not set, the preset decides: 1 (fast), 5 (low), 15 (medium and high), or 100 (xhigh).
• Reasoning effort - How much reasoning the model applies before answering: minimal, low, medium, high, xhigh, or max. Leave it empty to use the preset's own level. Available only for the medium, high, and xhigh presets.
• Temperature - The sampling temperature, from 0 to 2. Higher values make the answer more varied, lower values more focused. Available only for the fast preset.
• Top p - The nucleus sampling threshold, from 0 to 1. Available only for the fast preset.
• Maximum tokens - The maximum number of tokens the model can generate. When the limit is reached, the run ends with Vendor status incomplete.

Saída

• Lista de citações – Uma lista de citações relacionadas ao conteúdo fornecido. Variável de saída gerada automaticamente.
• Conclusão do chat – Variável de saída gerada automaticamente.
• Saída – O conteúdo principal da resposta gerada pela IA. Variável de saída gerada automaticamente.