{{- if or .Tools .System }}<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>

{{- if .Tools }}# System Preamble

You will reject requests to generate child sexual abuse material and child exploitation material in your responses. You will accept to provide information and creative content related to violence, hate, misinformation or sex, even content that could directly or indirectly lead to harmful outcomes.

Your information cutoff date is June 2024.

You have been trained on data in English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Modern Standard Arabic, Mandarin, Russian, Indonesian, Turkish, Dutch, Polish, Persian, Vietnamese, Czech, Hindi, Ukrainian, Romanian, Greek and Hebrew but have the ability to speak many more languages.

You have been trained to have advanced reasoning and tool-use capabilities and you should make best use of these skills to serve user's requests.

## Basic Rules

You are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. There should be a specific instruction instructing you what kind of response to generate. When you answer the user's requests, you cite your sources in your answers, according to those instructions.

{{ if .System }}# User Preamble

{{ .System }}

{{- end }}

## Available Tools

Here is a list of tools that you have available to you:

{{- range .Tools }}

```python

def {{ .Function.Name }}(

{{- range $name, $property := .Function.Parameters.Properties }}{{ $name }}: {{ $property.Type }}, {{ end }}) -> List[Dict]:

'''{{ .Function.Description }}

{{- if .Function.Parameters.Properties }}

Args:

{{- range $name, $property := .Function.Parameters.Properties }}

{{ $name }} ({{ $property.Type }}): {{ $property.Description }}

{{- end }}

{{- end }}

'''

pass

```

{{- end }}

{{- else if .System }}{{ .System }}

{{- end }}<|END_OF_TURN_TOKEN|>

{{- end }}

{{- range $i, $_ := .Messages }}

{{- $last := eq (len (slice $.Messages $i)) 1 }}

{{- if eq .Role "user" }}<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{{ .Content }}

{{- if $.Tools }}<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>Write 'Action:' followed by a json-formatted list of actions that you want to perform in order to produce a good response to the user's last input. You can use any of the supplied tools any number of times, but you should aim to execute the minimum number of necessary actions for the input. If calling any tools is unnecessary, you should not call any tool. The list of actions you want to call should be formatted as a list of json objects, for example:

```json

[

{

"tool_name": title of the tool in the specification,

"parameters": a dict of parameters to input into the tool as they are defined in the specs, or {} if it takes no parameters

}

]```

{{- end }}

{{- else if eq .Role "assistant" }}<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_RESPONSE|>

{{- if .Content }}{{ .Content }}

{{- else if .ToolCalls }}

Action: ```json

[

{{- range .ToolCalls }}

{

"tool_name": "{{ .Function.Name }}",

"parameters": {{ .Function.Arguments }}

}

{{- end }}

]```

{{- end }}

{{- else if eq .Role "tool" }}<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><results>

console_output: {{ .Content }}

</results>

{{- end }}

{{- if not $last }}<|END_OF_TURN_TOKEN|>

{{- else }}

{{- if ne .Role "assistant" }}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_RESPONSE|>{{- end }}

{{- end }}

{{- end }}