Responses

POST https://api.tensoras.ai/v1/responses
GET  https://api.tensoras.ai/v1/responses/{response_id}

Authorization: Bearer tns_your_key_here

{
  "model": "llama-3.3-70b",
  "input": "What is machine learning?"
}

{
  "model": "llama-3.3-70b",
  "input": [
    { "role": "system", "content": "You are a helpful research assistant." },
    { "role": "user", "content": "Summarize the latest findings on RAG." }
  ]
}

{
  "type": "file_search",
  "file_search": {
    "knowledge_base_ids": ["kb_abc123", "kb_def456"],
    "max_results": 10,
    "search_type": "hybrid",
    "score_threshold": 0.0,
    "rerank": false
  }
}

{
  "type": "function",
  "function": {
    "name": "get_weather",
    "description": "Get the current weather for a city.",
    "parameters": {
      "type": "object",
      "properties": {
        "city": { "type": "string" }
      },
      "required": ["city"]
    }
  }
}

{
  "id": "resp_abc123def456",
  "object": "response",
  "created_at": 1709123456,
  "model": "llama-3.3-70b",
  "status": "completed",
  "output": [
    {
      "type": "file_search_call",
      "id": "fs_abc123",
      "queries": ["machine learning fundamentals"],
      "results": [
        {
          "kb_id": "kb_abc123",
          "document_id": "doc_123",
          "document_name": "ml-overview.pdf",
          "text": "Machine learning is a subset of artificial intelligence...",
          "score": 0.95
        }
      ],
      "status": "completed"
    },
    {
      "type": "message",
      "id": "msg_xyz789",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Machine learning is a subset of artificial intelligence that enables systems to learn from data...",
          "annotations": []
        }
      ],
      "status": "completed"
    }
  ],
  "usage": {
    "input_tokens": 250,
    "output_tokens": 120,
    "total_tokens": 370
  },
  "metadata": null,
  "tool_call_count": 1,
  "turn_count": 2
}

from tensoras import Tensoras
import json
 
client = Tensoras(api_key="tns_...")
 
# 1. Create a response with a custom function tool
response = client.responses.create(
    model="llama-3.3-70b",
    input="What is the weather in Paris?",
    tools=[{
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get the current weather for a city.",
            "parameters": {
                "type": "object",
                "properties": {
                    "city": {"type": "string"}
                },
                "required": ["city"]
            }
        }
    }],
)
 
# 2. Inspect output for function_call items
for item in response.output:
    if item["type"] == "function_call":
        fn_name = item["name"]
        fn_args = json.loads(item["arguments"])
        call_id = item["call_id"]
 
        # 3. Execute the function client-side
        if fn_name == "get_weather":
            result = {"temperature": "15°C", "condition": "cloudy"}
 
        # 4. (Optional) Re-submit with the result for further model reasoning
        follow_up = client.responses.create(
            model="llama-3.3-70b",
            input=[
                {"role": "user", "content": "What is the weather in Paris?"},
                {"role": "assistant", "tool_calls": [{"id": call_id, "type": "function",
                    "function": {"name": fn_name, "arguments": item["arguments"]}}]},
                {"role": "tool", "tool_call_id": call_id, "content": json.dumps(result)},
            ],
        )
        for follow_item in follow_up.output:
            if follow_item["type"] == "message":
                print(follow_item["content"][0]["text"])

{
  "error": {
    "message": "Field 'model' is required.",
    "type": "invalid_request_error",
    "param": "model",
    "code": "missing_required_field"
  }
}

{
  "error": {
    "message": "Insufficient credits. Please add credits to your account.",
    "type": "billing_error",
    "param": null,
    "code": "insufficient_credits"
  }
}

{
  "error": {
    "message": "Rate limit exceeded. Please slow down your requests.",
    "type": "rate_limit_error",
    "param": null,
    "code": "rate_limit_exceeded"
  }
}

GET https://api.tensoras.ai/v1/responses/{response_id}

curl https://api.tensoras.ai/v1/responses \
  -H "Authorization: Bearer $TENSORAS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3.3-70b",
    "input": "What is retrieval-augmented generation?"
  }'

curl https://api.tensoras.ai/v1/responses \
  -H "Authorization: Bearer $TENSORAS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3.3-70b",
    "input": "Summarize our Q4 financial results.",
    "instructions": "Answer based only on the provided documents.",
    "tools": [
      {
        "type": "file_search",
        "file_search": {
          "knowledge_base_ids": ["kb_finance_2024"],
          "max_results": 10,
          "rerank": true
        }
      }
    ]
  }'

from tensoras import Tensoras
 
client = Tensoras(api_key="tns_...")
 
response = client.responses.create(
    model="llama-3.3-70b",
    input="What are the key findings in our research docs?",
    tools=[{
        "type": "file_search",
        "file_search": {
            "knowledge_base_ids": ["kb_research"],
        },
    }],
)
 
for item in response.output:
    if item["type"] == "message":
        print(item["content"][0]["text"])

import Tensoras from "@tensoras/sdk";
 
const client = new Tensoras({ apiKey: "tns_..." });
 
const response = await client.responses.create({
  model: "llama-3.3-70b",
  input: "What are the key findings in our research docs?",
  tools: [{
    type: "file_search",
    file_search: {
      knowledge_base_ids: ["kb_research"],
    },
  }],
});
 
for (const item of response.output) {
  if (item.type === "message") {
    console.log(item.content[0].text);
  }
}