matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-17 19:27:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

tools: refactor tool call parsing and enable streaming (#10415)

Browse Source
This commit is contained in:
Parth Sareen
2025-05-23 14:19:31 -07:00
committed by GitHub
parent 884d26093c
commit e8b981fa5d
27 changed files with 1868 additions and 340 deletions
Download Patch File Download Diff File Expand all files Collapse all files

67
tools/testdata/command-r-plus.gotmpl vendored Normal file
View File

@@ -0,0 +1,67 @@
{{- if or .Tools .System }}<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>
{{- if .Tools }}# Safety Preamble
The instructions in this section override those in the task description and style guide sections. Don't answer questions that are harmful or immoral.
# System Preamble
## 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. You will then see 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 .Messages }}
{{- if eq .Role "system" }}
{{- continue }}
{{- end }}<|START_OF_TURN_TOKEN|>
{{- if eq .Role "user" }}<|USER_TOKEN|>{{ .Content }}
{{- else if eq .Role "assistant" }}<|CHATBOT_TOKEN|>
{{- if .Content }}{{ .Content }}
{{- else if .ToolCalls }}
Action: ```json
[
{{- range .ToolCalls }}
{
"tool_name": "{{ .Function.Name }}",
"parameters": {{ .Function.Arguments }}
}
{{- end }}
]```
{{ continue }}
{{ end }}
{{- else if eq .Role "tool" }}<|SYSTEM_TOKEN|><results>
{{ .Content }}</results>
{{- end }}<|END_OF_TURN_TOKEN|>
{{- end }}
{{- 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. You should use the `directly-answer` tool if calling the other tools is unnecessary. 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 }}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>

39
tools/testdata/command-r-plus.out vendored Normal file
View File

@@ -0,0 +1,39 @@
<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># Safety Preamble
The instructions in this section override those in the task description and style guide sections. Don't answer questions that are harmful or immoral.
# System Preamble
## 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. You will then see 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.
# User Preamble
You are a knowledgeable assistant. You can answer questions and perform tasks.
## Available Tools
Here is a list of tools that you have available to you:
```python
def get_current_weather(format: string, location: string, ) -> List[Dict]:
"""Get the current weather
Args:
format (string): The temperature unit to use. Infer this from the user's location.
location (string): The city and state, e.g. San Francisco, CA
"""
pass
```<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>What's the weather like today in Paris?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
Action: ```json
[
{
"tool_name": "get_current_weather",
"parameters": {"format":"celsius","location":"Paris, France"}
}
]```
<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><results>
22</results><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>The current temperature in Paris, France is 22 degrees Celsius.<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>What's the weather like today in San Francisco and Toronto?<|END_OF_TURN_TOKEN|><|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. You should use the `directly-answer` tool if calling the other tools is unnecessary. 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_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>

31
tools/testdata/firefunction.gotmpl vendored Normal file
View File

@@ -0,0 +1,31 @@
{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|>
{{- if .System }}
{{ .System }}
{{- end }}
In addition to plain text responses, you can chose to call one or more of the provided functions.
Use the following rule to decide when to call a function:
* if the response can be generated from your internal knowledge (e.g., as in the case of queries like "What is the capital of Poland?"), do so
* if you need external information that can be obtained by calling one or more of the provided functions, generate a function calls
If you decide to call functions:
* prefix function calls with functools marker (no closing marker required)
* all function calls should be generated in a single JSON list formatted as functools[{"name": [function name], "arguments": [function arguments as JSON]}, ...]
* follow the provided JSON schema. Do not hallucinate arguments or values. Do to blindly copy values from the provided samples
* respect the argument type formatting. E.g., if the type if number and format is float, write value 7 as 7.0
* make sure you pick the right functions that match the user intent
Available functions as JSON spec:
{{- if .Tools }}
{{ .Tools }}
{{- end }}<|eot_id|>
{{- end }}
{{- range .Messages }}<|start_header_id|>
{{- if or (eq .Role "user") (eq .Role "assistant") (eq .Role "tool") }}{{ .Role }}
{{- end }}<|end_header_id|>
{{- if .Content }}{{ .Content }}
{{- else if .ToolCalls }} functools[
{{- range .ToolCalls }}{{ "{" }}"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}{{ "}" }}
{{- end }}]
{{- end }}<|eot_id|>
{{- end }}<|start_header_id|>assistant<|end_header_id|>

17
tools/testdata/firefunction.out vendored Normal file
View File

@@ -0,0 +1,17 @@
<|start_header_id|>system<|end_header_id|>
You are a knowledgeable assistant. You can answer questions and perform tasks.
In addition to plain text responses, you can chose to call one or more of the provided functions.
Use the following rule to decide when to call a function:
* if the response can be generated from your internal knowledge (e.g., as in the case of queries like "What is the capital of Poland?"), do so
* if you need external information that can be obtained by calling one or more of the provided functions, generate a function calls
If you decide to call functions:
* prefix function calls with functools marker (no closing marker required)
* all function calls should be generated in a single JSON list formatted as functools[{"name": [function name], "arguments": [function arguments as JSON]}, ...]
* follow the provided JSON schema. Do not hallucinate arguments or values. Do to blindly copy values from the provided samples
* respect the argument type formatting. E.g., if the type if number and format is float, write value 7 as 7.0
* make sure you pick the right functions that match the user intent
Available functions as JSON spec:
[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather","parameters":{"type":"object","required":["location","format"],"properties":{"format":{"type":"string","description":"The temperature unit to use. Infer this from the user's location.","enum":["celsius","fahrenheit"]},"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"}}}}}]<|eot_id|><|start_header_id|><|end_header_id|>You are a knowledgeable assistant. You can answer questions and perform tasks.<|eot_id|><|start_header_id|>user<|end_header_id|>What's the weather like today in Paris?<|eot_id|><|start_header_id|>assistant<|end_header_id|> functools[{"name": "get_current_weather", "arguments": {"format":"celsius","location":"Paris, France"}}]<|eot_id|><|start_header_id|>tool<|end_header_id|>22<|eot_id|><|start_header_id|>assistant<|end_header_id|>The current temperature in Paris, France is 22 degrees Celsius.<|eot_id|><|start_header_id|>user<|end_header_id|>What's the weather like today in San Francisco and Toronto?<|eot_id|><|start_header_id|>assistant<|end_header_id|>

43
tools/testdata/llama3-groq-tool-use.gotmpl vendored Normal file
View File

@@ -0,0 +1,43 @@
{{- if .Messages }}
{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|>
{{ .System }}
{{- if .Tools }} You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
<tool_call>
{"name": <function-name>,"arguments": <args-dict>}
</tool_call>
Here are the available tools:
<tools>
{{- range .Tools }} {{ .Function }}
{{- end }} </tools>
{{- end }}
{{- end }}<|eot_id|>
{{- range .Messages }}
{{- if ne .Role "system" }}<|start_header_id|>{{ .Role }}<|end_header_id|>
{{ if eq .Role "user" }}{{ .Content }}
{{- else if eq .Role "assistant" }}
{{- if .Content }}{{ .Content }}
{{- else if .ToolCalls }}<tool_call>
{{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
{{- end }}
</tool_call>
{{- end }}
{{- else if eq .Role "tool" }}<tool_response>
{{ .Content }}
</tool_response>
{{- end }}<|eot_id|>
{{- end }}
{{- end }}<|start_header_id|>assistant<|end_header_id|>
{{ else }}
{{ if .System }}<|start_header_id|>system<|end_header_id|>
{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>
{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>
{{ end }}{{ .Response }}
{{- if .Response }}<|eot_id|>
{{- end }}

24
tools/testdata/llama3-groq-tool-use.out vendored Normal file
View File

@@ -0,0 +1,24 @@
<|start_header_id|>system<|end_header_id|>
You are a knowledgeable assistant. You can answer questions and perform tasks. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
<tool_call>
{"name": <function-name>,"arguments": <args-dict>}
</tool_call>
Here are the available tools:
<tools> {"name":"get_current_weather","description":"Get the current weather","parameters":{"type":"object","required":["location","format"],"properties":{"format":{"type":"string","description":"The temperature unit to use. Infer this from the user's location.","enum":["celsius","fahrenheit"]},"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"}}}} </tools><|eot_id|><|start_header_id|>user<|end_header_id|>
What's the weather like today in Paris?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
<tool_call>
{"name": "get_current_weather", "arguments": {"format":"celsius","location":"Paris, France"}}
</tool_call><|eot_id|><|start_header_id|>tool<|end_header_id|>
<tool_response>
22
</tool_response><|eot_id|><|start_header_id|>assistant<|end_header_id|>
The current temperature in Paris, France is 22 degrees Celsius.<|eot_id|><|start_header_id|>user<|end_header_id|>
What's the weather like today in San Francisco and Toronto?<|eot_id|><|start_header_id|>assistant<|end_header_id|>

44
tools/testdata/llama3.2.gotmpl vendored Normal file
View File

@@ -0,0 +1,44 @@
<|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
{{ if .System }}{{ .System }}
{{- end }}
{{- if .Tools }}When you receive a tool call response, use the output to format an answer to the orginal user question.
You are a helpful assistant with tool calling capabilities.
{{- end }}<|eot_id|>
{{- range $i, $_ := .Messages }}
{{- $last := eq (len (slice $.Messages $i)) 1 }}
{{- if eq .Role "user" }}<|start_header_id|>user<|end_header_id|>
{{- if and $.Tools $last }}
Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.
Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables.
{{ range $.Tools }}
{{- . }}
{{ end }}
{{ .Content }}<|eot_id|>
{{- else }}
{{ .Content }}<|eot_id|>
{{- end }}{{ if $last }}<|start_header_id|>assistant<|end_header_id|>
{{ end }}
{{- else if eq .Role "assistant" }}<|start_header_id|>assistant<|end_header_id|>
{{- if .ToolCalls }}
{{ range .ToolCalls }}
{"name": "{{ .Function.Name }}", "parameters": {{ .Function.Arguments }}}{{ end }}
{{- else }}
{{ .Content }}
{{- end }}{{ if not $last }}<|eot_id|>{{ end }}
{{- else if eq .Role "tool" }}<|start_header_id|>ipython<|end_header_id|>
{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|>
{{ end }}
{{- end }}
{{- end }}

24
tools/testdata/llama3.2.out vendored Normal file
View File

@@ -0,0 +1,24 @@
<|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
You are a knowledgeable assistant. You can answer questions and perform tasks.When you receive a tool call response, use the output to format an answer to the orginal user question.
You are a helpful assistant with tool calling capabilities.<|eot_id|><|start_header_id|>user<|end_header_id|>
What's the weather like today in Paris?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
{"name": "get_current_weather", "parameters": {"format":"celsius","location":"Paris, France"}}<|eot_id|><|start_header_id|>ipython<|end_header_id|>
22<|eot_id|><|start_header_id|>assistant<|end_header_id|>
The current temperature in Paris, France is 22 degrees Celsius.<|eot_id|><|start_header_id|>user<|end_header_id|>
Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.
Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables.
{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather","parameters":{"type":"object","required":["location","format"],"properties":{"format":{"type":"string","description":"The temperature unit to use. Infer this from the user's location.","enum":["celsius","fahrenheit"]},"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"}}}}}
What's the weather like today in San Francisco and Toronto?<|eot_id|><|start_header_id|>assistant<|end_header_id|>

39
tools/testdata/messages.json vendored Normal file
View File

@@ -0,0 +1,39 @@
[
{
"role": "system",
"content": "You are a knowledgeable assistant. You can answer questions and perform tasks."
},
{
"role": "user",
"content": "What's the weather like today in Paris?"
},
{
"role": "assistant",
"tool_calls": [
{
"id": "89a1e453-0bce-4de3-a456-c54bed09c520",
"type": "function",
"function": {
"name": "get_current_weather",
"arguments": {
"location": "Paris, France",
"format": "celsius"
}
}
}
]
},
{
"role": "tool",
"tool_call_id": "89a1e453-0bce-4de3-a456-c54bed09c520",
"content": "22"
},
{
"role": "assistant",
"content": "The current temperature in Paris, France is 22 degrees Celsius."
},
{
"role": "user",
"content": "What's the weather like today in San Francisco and Toronto?"
}
]

15
tools/testdata/mistral.gotmpl vendored Normal file
View File

@@ -0,0 +1,15 @@
{{- range $index, $_ := .Messages }}
{{- if eq .Role "user" }}
{{- if and (eq (len (slice $.Messages $index)) 1) $.Tools }}[AVAILABLE_TOOLS] {{ $.Tools }}[/AVAILABLE_TOOLS]
{{- end }}[INST] {{ if and (eq (len (slice $.Messages $index)) 1) $.System }}{{ $.System }}
{{ end }}{{ .Content }}[/INST]
{{- else if eq .Role "assistant" }}
{{- if .Content }} {{ .Content }}</s>
{{- else if .ToolCalls }}[TOOL_CALLS] [
{{- range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
{{- end }}]</s>
{{- end }}
{{- else if eq .Role "tool" }}[TOOL_RESULTS] {"content": {{ .Content }}}[/TOOL_RESULTS]
{{- end }}
{{- end }}

3
tools/testdata/mistral.out vendored Normal file
View File

@@ -0,0 +1,3 @@
[INST] What's the weather like today in Paris?[/INST][TOOL_CALLS] [{"name": "get_current_weather", "arguments": {"format":"celsius","location":"Paris, France"}}]</s>[TOOL_RESULTS] {"content": 22}[/TOOL_RESULTS] The current temperature in Paris, France is 22 degrees Celsius.</s>[AVAILABLE_TOOLS] [{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather","parameters":{"type":"object","required":["location","format"],"properties":{"format":{"type":"string","description":"The temperature unit to use. Infer this from the user's location.","enum":["celsius","fahrenheit"]},"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"}}}}}][/AVAILABLE_TOOLS][INST] You are a knowledgeable assistant. You can answer questions and perform tasks.
What's the weather like today in San Francisco and Toronto?[/INST]

33
tools/testdata/nemotron.gotmpl vendored Normal file
View File

@@ -0,0 +1,33 @@
{{- if (or .Tools .System) }}<extra_id_0>System
{{ if .System }}{{ .System }}
{{ end }}
{{- if .Tools }}
{{- range .Tools }}<tool> {{ . }} </tool>{{ end }}
{{ end }}
{{- end }}
{{- range $i, $m := .Messages }}
{{- $last := eq (len (slice $.Messages $i)) 1 -}}
{{- if eq .Role "user" }}<extra_id_1>User
{{ .Content }}
{{- if $last }}
<extra_id_1>Assistant
{{- end }}
{{ else if eq .Role "tool" }}<extra_id_1>Tool
{{ .Content }}
{{- if $last }}
<extra_id_1>Assistant
{{- end }}
{{ else if eq .Role "assistant" }}<extra_id_1>Assistant
{{- if .ToolCalls }}
{{ range .ToolCalls }}<toolcall> {"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}} </toolcall> {{ end }}
{{ else }}
{{ .Content }}
{{- if not $last }}
{{ end }}
{{- end }}
{{- end }}
{{- end }}

18
tools/testdata/nemotron.out vendored Normal file
View File

@@ -0,0 +1,18 @@
<extra_id_0>System
You are a knowledgeable assistant. You can answer questions and perform tasks.
<tool> {"type":"function","function":{"name":"get_current_weather","description":"Get the current weather","parameters":{"type":"object","required":["location","format"],"properties":{"format":{"type":"string","description":"The temperature unit to use. Infer this from the user's location.","enum":["celsius","fahrenheit"]},"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"}}}}} </tool>
<extra_id_1>User
What's the weather like today in Paris?
<extra_id_1>Assistant
<toolcall> {"name": "get_current_weather", "arguments": {"format":"celsius","location":"Paris, France"}} </toolcall>
<extra_id_1>Tool
22
<extra_id_1>Assistant
The current temperature in Paris, France is 22 degrees Celsius.
<extra_id_1>User
What's the weather like today in San Francisco and Toronto?
<extra_id_1>Assistant

51
tools/testdata/qwen2.5.gotmpl vendored Normal file
View File

@@ -0,0 +1,51 @@
{{- if .Suffix }}<|fim_prefix|>{{ .Prompt }}<|fim_suffix|>{{ .Suffix }}<|fim_middle|>
{{- else if .Messages }}
{{- if or .System .Tools }}<|im_start|>system
{{- if .System }}
{{ .System }}
{{- end }}
{{- if .Tools }}
# Tools
You may call one or more functions to assist with the user query.
You are provided with function signatures within <tools></tools> XML tags:
<tools>
{{- range .Tools }}
{"type": "function", "function": {{ .Function }}}
{{- end }}
</tools>
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
<tool_call>
{"name": <function-name>, "arguments": <args-json-object>}
</tool_call>
{{- end }}<|im_end|>
{{ end }}
{{- range $i, $_ := .Messages }}
{{- $last := eq (len (slice $.Messages $i)) 1 -}}
{{- if eq .Role "user" }}<|im_start|>user
{{ .Content }}<|im_end|>
{{ else if eq .Role "assistant" }}<|im_start|>assistant
{{ if .Content }}{{ .Content }}
{{- else if .ToolCalls }}<tool_call>
{{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
{{ end }}</tool_call>
{{- end }}{{ if not $last }}<|im_end|>
{{ end }}
{{- else if eq .Role "tool" }}<|im_start|>user
<tool_response>
{{ .Content }}
</tool_response><|im_end|>
{{ end }}
{{- if and (ne .Role "assistant") $last }}<|im_start|>assistant
{{ end }}
{{- end }}
{{- else }}
{{- if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
{{ end }}{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}

31
tools/testdata/qwen2.5.out vendored Normal file
View File

@@ -0,0 +1,31 @@
<|im_start|>system
You are a knowledgeable assistant. You can answer questions and perform tasks.
# Tools
You may call one or more functions to assist with the user query.
You are provided with function signatures within <tools></tools> XML tags:
<tools>
{"type": "function", "function": {"name":"get_current_weather","description":"Get the current weather","parameters":{"type":"object","required":["location","format"],"properties":{"format":{"type":"string","description":"The temperature unit to use. Infer this from the user's location.","enum":["celsius","fahrenheit"]},"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"}}}}}
</tools>
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
<tool_call>
{"name": <function-name>, "arguments": <args-json-object>}
</tool_call><|im_end|>
<|im_start|>user
What's the weather like today in Paris?<|im_end|>
<|im_start|>assistant
<tool_call>
{"name": "get_current_weather", "arguments": {"format":"celsius","location":"Paris, France"}}
</tool_call><|im_end|>
<|im_start|>user
<tool_response>
22
</tool_response><|im_end|>
<|im_start|>assistant
The current temperature in Paris, France is 22 degrees Celsius.<|im_end|>
<|im_start|>user
What's the weather like today in San Francisco and Toronto?<|im_end|>
<|im_start|>assistant

50
tools/testdata/qwen3.gotmpl vendored Normal file
View File

@@ -0,0 +1,50 @@
{{- if .Messages }}
{{- if or .System .Tools }}<|im_start|>system
{{- if .System }}
{{ .System }}
{{- end }}
{{- if .Tools }}
# Tools
You may call one or more functions to assist with the user query.
You are provided with function signatures within <tools></tools> XML tags:
<tools>
{{- range .Tools }}
{"type": "function", "function": {{ .Function }}}
{{- end }}
</tools>
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
<tool_call>
{"name": <function-name>, "arguments": <args-json-object>}
</tool_call>
{{- end }}<|im_end|>
{{ end }}
{{- range $i, $_ := .Messages }}
{{- $last := eq (len (slice $.Messages $i)) 1 -}}
{{- if eq .Role "user" }}<|im_start|>user
{{ .Content }}<|im_end|>
{{ else if eq .Role "assistant" }}<|im_start|>assistant
{{ if .Content }}{{ .Content }}
{{- else if .ToolCalls }}<tool_call>
{{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
{{ end }}</tool_call>
{{- end }}{{ if not $last }}<|im_end|>
{{ end }}
{{- else if eq .Role "tool" }}<|im_start|>user
<tool_response>
{{ .Content }}
</tool_response><|im_end|>
{{ end }}
{{- if and (ne .Role "assistant") $last }}<|im_start|>assistant
{{ end }}
{{- end }}
{{- else }}
{{- if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
{{ end }}{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}

31
tools/testdata/qwen3.out vendored Normal file
View File

@@ -0,0 +1,31 @@
<|im_start|>system
You are a knowledgeable assistant. You can answer questions and perform tasks.
# Tools
You may call one or more functions to assist with the user query.
You are provided with function signatures within <tools></tools> XML tags:
<tools>
{"type": "function", "function": {"name":"get_current_weather","description":"Get the current weather","parameters":{"type":"object","required":["location","format"],"properties":{"format":{"type":"string","description":"The temperature unit to use. Infer this from the user's location.","enum":["celsius","fahrenheit"]},"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"}}}}}
</tools>
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
<tool_call>
{"name": <function-name>, "arguments": <args-json-object>}
</tool_call><|im_end|>
<|im_start|>user
What's the weather like today in Paris?<|im_end|>
<|im_start|>assistant
<tool_call>
{"name": "get_current_weather", "arguments": {"format":"celsius","location":"Paris, France"}}
</tool_call><|im_end|>
<|im_start|>user
<tool_response>
22
</tool_response><|im_end|>
<|im_start|>assistant
The current temperature in Paris, France is 22 degrees Celsius.<|im_end|>
<|im_start|>user
What's the weather like today in San Francisco and Toronto?<|im_end|>
<|im_start|>assistant

30
tools/testdata/tools.json vendored Normal file
View File

@@ -0,0 +1,30 @@
[
{
"type": "function",
"function": {
"name": "get_current_weather",
"description": "Get the current weather",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA"
},
"format": {
"type": "string",
"enum": [
"celsius",
"fahrenheit"
],
"description": "The temperature unit to use. Infer this from the user's location."
}
},
"required": [
"location",
"format"
]
}
}
}
]

45
tools/testdata/xlam.gotmpl vendored Normal file
View File

@@ -0,0 +1,45 @@
{{- if .System }}{{ .System }}
{{ end }}
{{- range $i, $_ := .Messages }}
{{- if eq .Role "user" }}### Instruction:
{{- if and $.Tools (le (len (slice $.Messages $i)) 2) }}
[BEGIN OF TASK INSTRUCTION]
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the functions can be used, point it out and refuse to answer.
If the given question lacks the parameters required by the function, also point it out.
[END OF TASK INSTRUCTION]
[BEGIN OF AVAILABLE TOOLS]
{{ $.Tools }}
[END OF AVAILABLE TOOLS]
[BEGIN OF FORMAT INSTRUCTION]
The output MUST strictly adhere to the following JSON format, and NO other text MUST be included.
The example format is as follows. Please make sure the parameter type is correct. If no function call is needed, please make tool_calls an empty list '[]'.
```
{
"tool_calls": [
{"name": "func_name1", "arguments": {"argument1": "value1", "argument2": "value2"}},
... (more tool calls as required)
]
}
```
[END OF FORMAT INSTRUCTION]
[BEGIN OF QUERY]
{{ .Content }}
[END OF QUERY]
{{ else }}
{{ .Content }}
{{ end }}
{{- else if .ToolCalls }}### Response:
{"tool_calls": [{{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}{{ end }}]}
<|EOT|>
{{ else if eq .Role "assistant" }}### Response:
{{ .Content }}
<|EOT|>
{{ end }}
{{- end }}### Response:

40
tools/testdata/xlam.out vendored Normal file
View File

@@ -0,0 +1,40 @@
You are a knowledgeable assistant. You can answer questions and perform tasks.
### Instruction:
What's the weather like today in Paris?
### Response:
{"tool_calls": [{"name": "get_current_weather", "arguments": {"format":"celsius","location":"Paris, France"}}]}
<|EOT|>
### Response:
The current temperature in Paris, France is 22 degrees Celsius.
<|EOT|>
### Instruction:
[BEGIN OF TASK INSTRUCTION]
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the functions can be used, point it out and refuse to answer.
If the given question lacks the parameters required by the function, also point it out.
[END OF TASK INSTRUCTION]
[BEGIN OF AVAILABLE TOOLS]
[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather","parameters":{"type":"object","required":["location","format"],"properties":{"format":{"type":"string","description":"The temperature unit to use. Infer this from the user's location.","enum":["celsius","fahrenheit"]},"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"}}}}}]
[END OF AVAILABLE TOOLS]
[BEGIN OF FORMAT INSTRUCTION]
The output MUST strictly adhere to the following JSON format, and NO other text MUST be included.
The example format is as follows. Please make sure the parameter type is correct. If no function call is needed, please make tool_calls an empty list '[]'.
```
{
"tool_calls": [
{"name": "func_name1", "arguments": {"argument1": "value1", "argument2": "value2"}},
... (more tool calls as required)
]
}
```
[END OF FORMAT INSTRUCTION]
[BEGIN OF QUERY]
What's the weather like today in San Francisco and Toronto?
[END OF QUERY]
### Response: