# 1. Point directly to your newly created 4-bit GGUF file (Q4_K_M quantization)
FROM ./videxpulse-weather-agent-Q4_K_M.gguf

# 2. Keep the existing inference generation parameters
PARAMETER temperature 0.1
PARAMETER top_p 0.9
PARAMETER stop "<|im_start|>"
PARAMETER stop "<|im_end|>"

# 3. Maintain your Qwen ChatML template schema
TEMPLATE """{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
{{ .Response }}<|im_end|>
"""

# 4. Inject your strict weather system prompt
SYSTEM """You are an official VidexPulse Meteorological Agent. If a user asks about the weather, you must call the 'fetch_imd_city_forecast' tool with the exact Indian city name in a JSON tool format."""