config.yml

# SPDX-FileCopyrightText: Copyright (c) 2024-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

# Example configuration for testing the OpenAI Responses API endpoint format.
#
# This config demonstrates using the FastAPI frontend's /v1/responses endpoint
# which accepts the OpenAI Responses API format (with 'input' field) and routes
# requests through a standard tool_calling_agent workflow.
#
# NOTE: The Responses API format is provided for pass-through compatibility.
# NAT agents do not inherently support stateful backends; features like
# 'previous_response_id' will be ignored.
#
# Prerequisites:
#   uv pip install -e '.[langchain]'   # Required for tool_calling_agent
#   export NVIDIA_API_KEY=<YOUR_KEY>
#
# Usage:
#   nat serve --config_file examples/front_ends/responses_api_endpoint/configs/config.yml
#
# Test with curl (Responses API format):
#   curl -X POST http://localhost:8088/v1/responses \
#     -H 'Content-Type: application/json' \
#     -d '{"model": "gpt-4o-mini", "input": "What time is it?"}'
#
# Test with curl (Streaming):
#   curl -X POST http://localhost:8088/v1/responses \
#     -H 'Content-Type: application/json' \
#     -d '{"model": "gpt-4o-mini", "input": "What time is it?", "stream": true}'
#
# The /generate and /chat endpoints still use the Chat Completions format:
#   curl -X POST http://localhost:8088/generate \
#     -H 'Content-Type: application/json' \
#     -d '{"messages": [{"role": "user", "content": "What time is it?"}]}'

general:
  use_uvloop: true
  front_end:
    _type: fastapi
    port: 8088
    workflow:
      method: POST
      path: /generate
      openai_api_path: /chat
      openai_api_v1_path: /v1/responses
      description: "Test OpenAI Responses API endpoint format"

llms:
  nim_llm:
    _type: nim
    model_name: meta/llama-3.1-70b-instruct
    temperature: 0.0
    max_tokens: 250

functions:
  current_datetime:
    _type: current_datetime

workflow:
  _type: tool_calling_agent
  llm_name: nim_llm
  tool_names: [current_datetime]
  verbose: true
  handle_tool_errors: true