mirror of
https://github.com/ollama/ollama.git
synced 2026-01-29 07:12:03 +03:00
e51dead636
* preserve tool definition and call JSON ordering This is another iteration of <https://github.com/ollama/ollama/pull/12518>, but this time we've simplified things by relaxing the competing requirements of being compatible AND order-preserving with templates (vs. renderers). We maintain backwards compatibility at the cost of not guaranteeing order for templates. We plan on moving more and more models to renderers, which have been updated to use these new data types, and additionally we could add an opt-in way of templates getting an order-preserved list (e.g., via sibling template vars) * orderedmap_test: remove testify
373 lines
12 KiB
Go
373 lines
12 KiB
Go
package renderers
|
|
|
|
import (
|
|
"testing"
|
|
|
|
"github.com/google/go-cmp/cmp"
|
|
"github.com/ollama/ollama/api"
|
|
)
|
|
|
|
func TestQwen3VLThinkingRenderer(t *testing.T) {
|
|
tests := []struct {
|
|
name string
|
|
msgs []api.Message
|
|
images []api.ImageData
|
|
tools []api.Tool
|
|
expected string
|
|
}{
|
|
{
|
|
name: "basic",
|
|
msgs: []api.Message{
|
|
{Role: "system", Content: "You are a helpful assistant."},
|
|
{Role: "user", Content: "Hello, how are you?"},
|
|
},
|
|
expected: `<|im_start|>system
|
|
You are a helpful assistant.<|im_end|>
|
|
<|im_start|>user
|
|
Hello, how are you?<|im_end|>
|
|
<|im_start|>assistant
|
|
<think>
|
|
`,
|
|
},
|
|
{
|
|
name: "With thinking, end assistant.",
|
|
msgs: []api.Message{
|
|
{Role: "user", Content: "Tell me a story in two sentences."},
|
|
{Role: "assistant", Content: "abc", Thinking: "To make this story interesting, I will speak in poetry."},
|
|
},
|
|
expected: `<|im_start|>user
|
|
Tell me a story in two sentences.<|im_end|>
|
|
<|im_start|>assistant
|
|
<think>
|
|
To make this story interesting, I will speak in poetry.
|
|
</think>
|
|
|
|
abc`,
|
|
},
|
|
{
|
|
name: "With thinking, end assistant.",
|
|
msgs: []api.Message{
|
|
{Role: "user", Content: "Tell me a story in two sentences."},
|
|
{Role: "assistant", Thinking: "To make this story interesting, I will speak in poetry."},
|
|
},
|
|
expected: `<|im_start|>user
|
|
Tell me a story in two sentences.<|im_end|>
|
|
<|im_start|>assistant
|
|
<think>
|
|
To make this story interesting, I will speak in poetry.`,
|
|
},
|
|
{
|
|
name: "Multiple thinking",
|
|
msgs: []api.Message{
|
|
{Role: "user", Content: "Tell me a story in two sentences."},
|
|
{Role: "assistant", Content: "abc", Thinking: "To make this story interesting, I will speak in poetry.<think>And I will speak in poetry after the first sentence.</think>"},
|
|
},
|
|
expected: `<|im_start|>user
|
|
Tell me a story in two sentences.<|im_end|>
|
|
<|im_start|>assistant
|
|
<think>
|
|
To make this story interesting, I will speak in poetry.<think>And I will speak in poetry after the first sentence.</think>
|
|
</think>
|
|
|
|
abc`, // NOTE: the second thinking tag is not captured
|
|
},
|
|
{
|
|
name: "Multiple thinking, multiple messages.",
|
|
msgs: []api.Message{
|
|
{Role: "user", Content: "Tell me a story in two sentences."},
|
|
{Role: "assistant", Thinking: "To make this story interesting, I will speak in poetry.", Content: "abc"},
|
|
{Role: "user", Content: "What is the weather like in San Francisco?"},
|
|
{Role: "assistant", Thinking: "Speak poetry after the first sentence.</think><think>Speak poetry after the second sentence."},
|
|
},
|
|
expected: `<|im_start|>user
|
|
Tell me a story in two sentences.<|im_end|>
|
|
<|im_start|>assistant
|
|
abc<|im_end|>
|
|
<|im_start|>user
|
|
What is the weather like in San Francisco?<|im_end|>
|
|
<|im_start|>assistant
|
|
<think>
|
|
Speak poetry after the first sentence.</think><think>Speak poetry after the second sentence.`,
|
|
},
|
|
// NOTE: Servers automatically prepend a [img-<n>] tag
|
|
// {
|
|
// name: "Image",
|
|
// msgs: []api.Message{
|
|
// {Role: "user", Content: "Describe this image.", Images: []api.ImageData{api.ImageData(IMAGE2_BASE64)}},
|
|
// },
|
|
// expected: `<|im_start|>user
|
|
// [img-0]Describe this image.<|im_end|>
|
|
// <|im_start|>assistant
|
|
// <think>
|
|
// `,
|
|
// },
|
|
|
|
// NOTE: Servers automatically prepend a [img-<n>] tag
|
|
// {
|
|
// name: "Multiple images",
|
|
// msgs: []api.Message{
|
|
// {Role: "user", Content: "Describe these images.", Images: []api.ImageData{api.ImageData(IMAGE1_BASE64), api.ImageData(IMAGE2_BASE64)}},
|
|
// },
|
|
// expected: `<|im_start|>user
|
|
// [img-0][img-1]Describe these images.<|im_end|>
|
|
// <|im_start|>assistant
|
|
// <think>
|
|
// `,
|
|
// },
|
|
|
|
// NOTE: solved with #12518: https://github.com/ollama/ollama/compare/main...drifkin/stable-tool-args
|
|
// {
|
|
// name: "with tools and response",
|
|
// msgs: []api.Message{
|
|
// {Role: "system", Content: "You are a helpful assistant with access to tools."},
|
|
// {Role: "user", Content: "What's the weather like in New York?"},
|
|
// {
|
|
// Role: "assistant",
|
|
// Content: "I'll check the weather in New York for you.",
|
|
// ToolCalls: []api.ToolCall{
|
|
// {
|
|
// Function: api.ToolCallFunction{
|
|
// Name: "get-current-weather",
|
|
// Arguments: testArgs(map[string]any{
|
|
// "location": "New York",
|
|
// "unit": "fahrenheit",
|
|
// }),
|
|
// },
|
|
// },
|
|
// },
|
|
// },
|
|
// {Role: "tool", Content: "80", ToolName: "get-current-weather"},
|
|
// {Role: "user", Content: "That sounds nice! What about San Francisco?"},
|
|
// },
|
|
// tools: []api.Tool{
|
|
// {
|
|
// Type: "function",
|
|
// Function: api.ToolFunction{
|
|
// Name: "get-current-weather",
|
|
// Description: "Get the current weather for a location",
|
|
// Parameters: api.ToolFunctionParameters{
|
|
// Type: "object",
|
|
// Required: []string{"location"},
|
|
// Properties: testPropsMap(map[string]api.ToolProperty{
|
|
// "location": {
|
|
// Type: api.PropertyType{"string"},
|
|
// Description: "The city and state, e.g. San Francisco, CA",
|
|
// },
|
|
// "unit": {
|
|
// Type: api.PropertyType{"string"},
|
|
// Enum: []any{"celsius", "fahrenheit"},
|
|
// Description: "The temperature unit",
|
|
// },
|
|
// }),
|
|
// },
|
|
// },
|
|
// },
|
|
// },
|
|
// expected: `<|im_start|>system
|
|
// You are a helpful assistant with access to 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>
|
|
// {"type": "function", "function": {"name": "get-current-weather", "description": "Get the current weather for a location", "parameters": {"type": "object", "properties": {"location": {"type": "string", "description": "The city and state, e.g. San Francisco, CA"}, "unit": {"type": "string", "enum": ["celsius", "fahrenheit"], "description": "The temperature unit"}}, "required": ["location"]}}}
|
|
// </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 in New York?<|im_end|>
|
|
// <|im_start|>assistant
|
|
// I'll check the weather in New York for you.
|
|
// <tool_call>
|
|
// {"name": "get-current-weather", "arguments": {"location": "New York", "unit": "fahrenheit"}}
|
|
// </tool_call><|im_end|>
|
|
// <|im_start|>user
|
|
// <tool_response>
|
|
// 80
|
|
// </tool_response><|im_end|>
|
|
// <|im_start|>user
|
|
// That sounds nice! What about San Francisco?<|im_end|>
|
|
// <|im_start|>assistant
|
|
// <think>
|
|
// `,
|
|
// },
|
|
|
|
// NOTE: solved with #12518: https://github.com/ollama/ollama/compare/main...drifkin/stable-tool-args
|
|
// {
|
|
// name: "With tools and response, multiple tool calls",
|
|
// msgs: []api.Message{
|
|
// {
|
|
// Role: "system",
|
|
// Content: "You are a helpful assistant with access to tools.",
|
|
// },
|
|
// {
|
|
// Role: "user",
|
|
// Content: "Call two tools for me: add and multiply.",
|
|
// },
|
|
// {
|
|
// Role: "assistant",
|
|
// Content: "Sure, I'll call both tools for you.",
|
|
// ToolCalls: []api.ToolCall{
|
|
// {
|
|
// Function: api.ToolCallFunction{
|
|
// Name: "add",
|
|
// Arguments: testArgs(map[string]any{
|
|
// "a": 2,
|
|
// "b": 3,
|
|
// }),
|
|
// },
|
|
// },
|
|
// {
|
|
// Function: api.ToolCallFunction{
|
|
// Name: "multiply",
|
|
// Arguments: testArgs(map[string]any{
|
|
// "x": 4,
|
|
// "y": 5,
|
|
// }),
|
|
// },
|
|
// },
|
|
// },
|
|
// },
|
|
// {
|
|
// Role: "tool",
|
|
// Content: "5",
|
|
// ToolName: "add",
|
|
// },
|
|
// {
|
|
// Role: "tool",
|
|
// Content: "20",
|
|
// ToolName: "multiply",
|
|
// },
|
|
// {
|
|
// Role: "user",
|
|
// Content: "Thanks! What are the results?",
|
|
// },
|
|
// },
|
|
// tools: []api.Tool{
|
|
// {
|
|
// Type: "function",
|
|
// Function: api.ToolFunction{
|
|
// Name: "add",
|
|
// Description: "Add two numbers",
|
|
// Parameters: api.ToolFunctionParameters{
|
|
// Type: "object",
|
|
// Required: []string{"a", "b"},
|
|
// Properties: testPropsMap(map[string]api.ToolProperty{
|
|
// "a": {Type: api.PropertyType{"integer"}, Description: "First number"},
|
|
// "b": {Type: api.PropertyType{"integer"}, Description: "Second number"},
|
|
// }),
|
|
// },
|
|
// },
|
|
// },
|
|
// {
|
|
// Type: "function",
|
|
// Function: api.ToolFunction{
|
|
// Name: "multiply",
|
|
// Description: "Multiply two numbers",
|
|
// Parameters: api.ToolFunctionParameters{
|
|
// Type: "object",
|
|
// Required: []string{"x", "y"},
|
|
// Properties: testPropsMap(map[string]api.ToolProperty{
|
|
// "x": {Type: api.PropertyType{"integer"}, Description: "First factor"},
|
|
// "y": {Type: api.PropertyType{"integer"}, Description: "Second factor"},
|
|
// }),
|
|
// },
|
|
// },
|
|
// },
|
|
// },
|
|
// expected: `<|im_start|>system
|
|
// You are a helpful assistant with access to 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>
|
|
// {"type": "function", "function": {"name": "add", "description": "Add two numbers", "parameters": {"type": "object", "properties": {"a": {"type": "integer"}, "b": {"type": "integer"}}, "required": ["a", "b"]}}}
|
|
// {"type": "function", "function": {"name": "multiply", "description": "Multiply two numbers", "parameters": {"type": "object", "properties": {"x": {"type": "integer"}, "y": {"type": "integer"}}, "required": ["x", "y"]}}}
|
|
// </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
|
|
// Call two tools for me: add and multiply.<|im_end|>
|
|
// <|im_start|>assistant
|
|
// Sure, I'll call both tools for you.
|
|
// <tool_call>
|
|
// {"name": "add", "arguments": {"a": 2, "b": 3}}
|
|
// </tool_call>
|
|
// <tool_call>
|
|
// {"name": "multiply", "arguments": {"x": 4, "y": 5}}
|
|
// </tool_call><|im_end|>
|
|
// <|im_start|>user
|
|
// <tool_response>
|
|
// 5
|
|
// </tool_response>
|
|
// <tool_response>
|
|
// 20
|
|
// </tool_response><|im_end|>
|
|
// <|im_start|>user
|
|
// Thanks! What are the results?<|im_end|>
|
|
// <|im_start|>assistant
|
|
// <think>
|
|
// `,
|
|
// },
|
|
}
|
|
for _, tt := range tests {
|
|
t.Run(tt.name, func(t *testing.T) {
|
|
rendered, err := (&Qwen3VLRenderer{isThinking: true}).Render(tt.msgs, tt.tools, nil)
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
if diff := cmp.Diff(rendered, tt.expected); diff != "" {
|
|
t.Errorf("mismatch (-got +want):\n%s", diff)
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestFormatToolCallArgumentThinkingVL(t *testing.T) {
|
|
tests := []struct {
|
|
name string
|
|
arg any
|
|
expected string
|
|
}{
|
|
{
|
|
name: "string",
|
|
arg: "foo",
|
|
expected: "foo",
|
|
},
|
|
{
|
|
name: "map",
|
|
arg: map[string]any{"foo": "bar"},
|
|
expected: "{\"foo\":\"bar\"}",
|
|
},
|
|
{
|
|
name: "number",
|
|
arg: 1,
|
|
expected: "1",
|
|
},
|
|
{
|
|
name: "boolean",
|
|
arg: true,
|
|
expected: "true",
|
|
},
|
|
}
|
|
for _, tt := range tests {
|
|
t.Run(tt.name, func(t *testing.T) {
|
|
got := formatToolCallArgument(tt.arg)
|
|
if got != tt.expected {
|
|
t.Errorf("formatToolCallArgument(%v) = %v, want %v", tt.arg, got, tt.expected)
|
|
}
|
|
})
|
|
}
|
|
}
|