Query Assistant For Polling

Submit a question to the scite Assistant. Returns a task ID that you poll via GET /api_partner/assistant/tasks/{task_id}.

Required Fields

turns — Conversation History

The conversation history as a list of turn objects. Each turn has a role ("user" or "assistant") and content. For a new conversation, provide a single user turn:

{
  "turns": [{"role": "user", "content": "How does protein structure affect function?"}]
}

For multi-turn conversations, include the full history. Assistant turns should include references, searchStrategy, model, settings, and publicationsConsulted from previous responses.

userInput — Current Question

The current user question (should match the last user turn's content). Used independently for search strategy generation and tool selection.

---

Reference Behavior Control

---

Search Filtering

---

Paper Selection

---

Result Ranking — rankBy

Controls how retrieved results are ranked before being passed to the LLM. Default: "all".

---

Response Configuration

Available Models

If one provider fails, the system automatically falls back to the other. Unsupported or retired model strings automatically fall back to the default (gpt-5-nano-2025-08-07).

---

Structured Response Mode

---

Patent Modes

---

Session Management

---

Response

Returns {"id": "<task_id>"}. If the user is rate-limited, also includes "usage": {"used": N, "max": M}.

---

Examples

Basic single question:

{
  "turns": [{"role": "user", "content": "What is the effect of exercise on depression?"}],
  "userInput": "What is the effect of exercise on depression?"
}

DOI-scoped question:

{
  "turns": [{"role": "user", "content": "Summarize the key findings"}],
  "userInput": "Summarize the key findings",
  "dois": ["10.1002/cepa.3344", "10.1002/hsr2.70931"]
}

Filtered search:

{
  "turns": [{"role": "user", "content": "What do systematic reviews say about mindfulness for anxiety?"}],
  "userInput": "What do systematic reviews say about mindfulness for anxiety?",
  "publicationTypes": ["systematic review", "meta-analysis"],
  "yearFrom": "2020",
  "rankBy": "supporting-citations",
  "answerLength": "long"
}

Structured response (table mode):

{
  "turns": [{"role": "user", "content": "Does each paper support the hypothesis that X causes Y?"}],
  "userInput": "Does each paper support the hypothesis that X causes Y?",
  "useStructuredResponse": true,
  "jsonResponseType": "boolean",
  "dois": ["10.1234/a", "10.1234/b", "10.1234/c"]
}