Instructions to use Veda-Labs/Vedika-Code-Pro-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Veda-Labs/Vedika-Code-Pro-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Veda-Labs/Vedika-Code-Pro-v1", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Veda-Labs/Vedika-Code-Pro-v1", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Veda-Labs/Vedika-Code-Pro-v1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Veda-Labs/Vedika-Code-Pro-v1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Veda-Labs/Vedika-Code-Pro-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Veda-Labs/Vedika-Code-Pro-v1
- SGLang
How to use Veda-Labs/Vedika-Code-Pro-v1 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Veda-Labs/Vedika-Code-Pro-v1" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Veda-Labs/Vedika-Code-Pro-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Veda-Labs/Vedika-Code-Pro-v1" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Veda-Labs/Vedika-Code-Pro-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Veda-Labs/Vedika-Code-Pro-v1 with Docker Model Runner:
docker model run hf.co/Veda-Labs/Vedika-Code-Pro-v1
Upload 8 files
Browse files- encoding/tests/test_input_1.json +81 -0
- encoding/tests/test_input_2.json +24 -0
- encoding/tests/test_input_3.json +159 -0
- encoding/tests/test_input_4.json +28 -0
- encoding/tests/test_output_1.txt +36 -0
- encoding/tests/test_output_2.txt +1 -0
- encoding/tests/test_output_3.txt +38 -0
- encoding/tests/test_output_4.txt +29 -0
encoding/tests/test_input_1.json
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tools": [
|
| 3 |
+
{
|
| 4 |
+
"type": "function",
|
| 5 |
+
"function": {
|
| 6 |
+
"name": "get_weather",
|
| 7 |
+
"description": "Get the weather for a specific location",
|
| 8 |
+
"parameters": {
|
| 9 |
+
"type": "object",
|
| 10 |
+
"properties": {
|
| 11 |
+
"location": {
|
| 12 |
+
"type": "string",
|
| 13 |
+
"description": "The city name"
|
| 14 |
+
},
|
| 15 |
+
"unit": {
|
| 16 |
+
"type": "string",
|
| 17 |
+
"enum": ["celsius", "fahrenheit"],
|
| 18 |
+
"description": "Temperature unit"
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"required": ["location"]
|
| 22 |
+
}
|
| 23 |
+
}
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"type": "function",
|
| 27 |
+
"function": {
|
| 28 |
+
"name": "search",
|
| 29 |
+
"description": "Search the web for information",
|
| 30 |
+
"parameters": {
|
| 31 |
+
"type": "object",
|
| 32 |
+
"properties": {
|
| 33 |
+
"query": {
|
| 34 |
+
"type": "string",
|
| 35 |
+
"description": "Search query"
|
| 36 |
+
},
|
| 37 |
+
"num_results": {
|
| 38 |
+
"type": "integer",
|
| 39 |
+
"description": "Number of results to return"
|
| 40 |
+
}
|
| 41 |
+
},
|
| 42 |
+
"required": ["query"]
|
| 43 |
+
}
|
| 44 |
+
}
|
| 45 |
+
}
|
| 46 |
+
],
|
| 47 |
+
"messages": [
|
| 48 |
+
{
|
| 49 |
+
"role": "system",
|
| 50 |
+
"content": "You are a helpful assistant."
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"role": "user",
|
| 54 |
+
"content": "What's the weather in Beijing?"
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"role": "assistant",
|
| 58 |
+
"reasoning_content": "The user wants to know the weather in Beijing. I should use the get_weather tool.",
|
| 59 |
+
"tool_calls": [
|
| 60 |
+
{
|
| 61 |
+
"id": "call_001",
|
| 62 |
+
"type": "function",
|
| 63 |
+
"function": {
|
| 64 |
+
"name": "get_weather",
|
| 65 |
+
"arguments": "{\"location\": \"Beijing\", \"unit\": \"celsius\"}"
|
| 66 |
+
}
|
| 67 |
+
}
|
| 68 |
+
]
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"role": "tool",
|
| 72 |
+
"tool_call_id": "call_001",
|
| 73 |
+
"content": "{\"temperature\": 22, \"condition\": \"sunny\", \"humidity\": 45}"
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"role": "assistant",
|
| 77 |
+
"reasoning_content": "Got the weather data. Let me format a nice response.",
|
| 78 |
+
"content": "The weather in Beijing is currently sunny with a temperature of 22°C and 45% humidity."
|
| 79 |
+
}
|
| 80 |
+
]
|
| 81 |
+
}
|
encoding/tests/test_input_2.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"role": "system",
|
| 4 |
+
"content": "You are a helpful assistant."
|
| 5 |
+
},
|
| 6 |
+
{
|
| 7 |
+
"role": "user",
|
| 8 |
+
"content": "Hello"
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"role": "assistant",
|
| 12 |
+
"reasoning_content": "The user said hello, I should greet back.",
|
| 13 |
+
"content": "Hi there! How can I help you?"
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"role": "user",
|
| 17 |
+
"content": "What is the capital of France?"
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"role": "assistant",
|
| 21 |
+
"reasoning_content": "The user asks about the capital of France. It is Paris.",
|
| 22 |
+
"content": "The capital of France is Paris."
|
| 23 |
+
}
|
| 24 |
+
]
|
encoding/tests/test_input_3.json
ADDED
|
@@ -0,0 +1,159 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"role": "system",
|
| 4 |
+
"content": "该助手为Vedika-Code-Pro-v1,由Veda Labs创造。"
|
| 5 |
+
},
|
| 6 |
+
{
|
| 7 |
+
"role": "latest_reminder",
|
| 8 |
+
"content": "2026-02-21,星期六,广州,App,中文"
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"role": "developer",
|
| 12 |
+
"content": "小柴胡冲剂和布洛芬能一起吃吗?\n\nCITATION FORMAT: 【{cursor_id}†L{start_line_id}(-L{end_line_id})?】",
|
| 13 |
+
"tools": [
|
| 14 |
+
{
|
| 15 |
+
"type": "function",
|
| 16 |
+
"function": {
|
| 17 |
+
"name": "search",
|
| 18 |
+
"description": "Web search. Split multiple queries with '||'.",
|
| 19 |
+
"parameters": {
|
| 20 |
+
"type": "object",
|
| 21 |
+
"properties": {
|
| 22 |
+
"queries": {
|
| 23 |
+
"type": "string",
|
| 24 |
+
"description": "query1||query2"
|
| 25 |
+
}
|
| 26 |
+
},
|
| 27 |
+
"required": [
|
| 28 |
+
"queries"
|
| 29 |
+
],
|
| 30 |
+
"additionalProperties": false,
|
| 31 |
+
"$schema": "http://json-schema.org/draft-07/schema#"
|
| 32 |
+
}
|
| 33 |
+
}
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"type": "function",
|
| 37 |
+
"function": {
|
| 38 |
+
"name": "open",
|
| 39 |
+
"description": "Batch open IDs (format 【{id}†...】) or URLs.",
|
| 40 |
+
"parameters": {
|
| 41 |
+
"type": "object",
|
| 42 |
+
"properties": {
|
| 43 |
+
"open_list": {
|
| 44 |
+
"type": "array",
|
| 45 |
+
"items": {
|
| 46 |
+
"type": "object",
|
| 47 |
+
"properties": {
|
| 48 |
+
"id": {
|
| 49 |
+
"description": "ID or URL",
|
| 50 |
+
"anyOf": [
|
| 51 |
+
{
|
| 52 |
+
"type": "integer"
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"type": "string"
|
| 56 |
+
}
|
| 57 |
+
],
|
| 58 |
+
"default": -1
|
| 59 |
+
},
|
| 60 |
+
"cursor": {
|
| 61 |
+
"type": "integer",
|
| 62 |
+
"description": "",
|
| 63 |
+
"default": -1
|
| 64 |
+
},
|
| 65 |
+
"loc": {
|
| 66 |
+
"type": "integer",
|
| 67 |
+
"description": "Start line",
|
| 68 |
+
"default": -1
|
| 69 |
+
},
|
| 70 |
+
"num_lines": {
|
| 71 |
+
"type": "integer",
|
| 72 |
+
"description": "",
|
| 73 |
+
"default": -1
|
| 74 |
+
},
|
| 75 |
+
"view_source": {
|
| 76 |
+
"type": "boolean",
|
| 77 |
+
"description": "",
|
| 78 |
+
"default": false
|
| 79 |
+
}
|
| 80 |
+
},
|
| 81 |
+
"additionalProperties": false
|
| 82 |
+
},
|
| 83 |
+
"description": ""
|
| 84 |
+
}
|
| 85 |
+
},
|
| 86 |
+
"required": [
|
| 87 |
+
"open_list"
|
| 88 |
+
],
|
| 89 |
+
"additionalProperties": false,
|
| 90 |
+
"$schema": "http://json-schema.org/draft-07/schema#"
|
| 91 |
+
}
|
| 92 |
+
}
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"type": "function",
|
| 96 |
+
"function": {
|
| 97 |
+
"name": "find",
|
| 98 |
+
"description": "Find exact text pattern in pages.",
|
| 99 |
+
"parameters": {
|
| 100 |
+
"type": "object",
|
| 101 |
+
"properties": {
|
| 102 |
+
"find_list": {
|
| 103 |
+
"type": "array",
|
| 104 |
+
"items": {
|
| 105 |
+
"type": "object",
|
| 106 |
+
"properties": {
|
| 107 |
+
"pattern": {
|
| 108 |
+
"type": "string",
|
| 109 |
+
"description": ""
|
| 110 |
+
},
|
| 111 |
+
"cursor": {
|
| 112 |
+
"type": "integer",
|
| 113 |
+
"description": "",
|
| 114 |
+
"default": -1
|
| 115 |
+
}
|
| 116 |
+
},
|
| 117 |
+
"required": [
|
| 118 |
+
"pattern"
|
| 119 |
+
],
|
| 120 |
+
"additionalProperties": false
|
| 121 |
+
},
|
| 122 |
+
"description": ""
|
| 123 |
+
}
|
| 124 |
+
},
|
| 125 |
+
"required": [
|
| 126 |
+
"find_list"
|
| 127 |
+
],
|
| 128 |
+
"additionalProperties": false,
|
| 129 |
+
"$schema": "http://json-schema.org/draft-07/schema#"
|
| 130 |
+
}
|
| 131 |
+
}
|
| 132 |
+
}
|
| 133 |
+
]
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"role": "assistant",
|
| 137 |
+
"content": "",
|
| 138 |
+
"reasoning_content": "用户想知道小柴胡冲剂和布洛芬能否一起服用。",
|
| 139 |
+
"tool_calls": [
|
| 140 |
+
{
|
| 141 |
+
"type": "function",
|
| 142 |
+
"function": {
|
| 143 |
+
"name": "search",
|
| 144 |
+
"arguments": "{\"queries\": \"小柴胡冲剂 布洛芬 相互作用 一起吃\"}"
|
| 145 |
+
}
|
| 146 |
+
}
|
| 147 |
+
]
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"role": "tool",
|
| 151 |
+
"content": "[0]"
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"role": "assistant",
|
| 155 |
+
"content": "请及时就医。",
|
| 156 |
+
"reasoning_content": "现在开始组织回答。",
|
| 157 |
+
"tool_calls": []
|
| 158 |
+
}
|
| 159 |
+
]
|
encoding/tests/test_input_4.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"role": "system",
|
| 4 |
+
"content": "该助手为Vedika-Code-Pro-v1,由Veda Labs创造。\n今天是2025年10月17日,星期五。"
|
| 5 |
+
},
|
| 6 |
+
{
|
| 7 |
+
"role": "latest_reminder",
|
| 8 |
+
"content": "2024-11-15,上海市,App,中文"
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"role": "user",
|
| 12 |
+
"content": "热海大滚锅是世界著名温泉吗"
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"role": "assistant",
|
| 16 |
+
"content": "关于热海大滚锅是否是世界著名温泉,可以这样总结:它在**中国乃至全球的地热奇观中占有重要地位**,但“世界著名”的称号更侧重于它作为**独特的地质现象和旅游景点**,而非普遍的温泉疗养体验。\n\n为了让你快速了解,我整理了一个简要的表格:\n\n| 维度 | 热海大滚锅的地位与特点 |\n| :--- | :--- |\n| **地质奇观** | **世界罕见**的高温地热系统,泉眼多、水温高、形态多样。 |\n| **国内声誉** | **中国三大地热区之一**,**国家5A级旅游景区**,自古闻名(徐霞客曾游历并记载)。 |\n| **国际知名度** | 在一些旅游平台被提及为“世界六大温泉”之一,但此说法流传不广,其国际声誉更多建立在地质独特性上。 |\n| **核心体验** | **观赏地热奇观**(如97℃沸腾的“大滚锅”)、**体验温泉煮鸡蛋**。 |\n\n### 💡 游玩攻略与温馨提示\n\n如果你计划前往热海大滚锅,这里有一些实用信息供你参考:\n\n- **门票与开放时间**:\n - **门票**:景区门票约为**50元/人**。如果选择包含温泉沐浴的套餐,价格会更高,例如约**288元**。\n - **开放时间**:景区一般**08:00-18:00**开放,但具体时间可能变动,建议提前核实。\n\n- **特色体验**:\n - **温泉煮鸡蛋**:这几乎是必试项目。可以在景区门口购买用草绳串起的生鸡蛋(约5-8元/串),然后到“大滚锅”旁的指定区域蒸煮,几分钟便可熟食,趣味十足。\n - **金汤足浴**:可以直接用从“大滚锅”流出的温泉水泡脚,缓解旅途疲劳。\n\n- **注意事项**:\n - **安全第一**:“大滚锅”水温极高,务必遵守游览规则,在指定区域内观赏,切勿随意触碰泉水。\n - **规划行程**:建议为热海景区预留**3-4小时**的游览时间。景区内步道不走回头路,出入口有观光车接送。\n\n希望这些信息能帮助你更好地了解热海大滚锅。如果你对腾冲的其他景点或者行程规划有更多疑问,我很乐意提供进一步的信息。",
|
| 17 |
+
"mask": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"role": "user",
|
| 21 |
+
"content": "世界著名温泉有哪些",
|
| 22 |
+
"task": "action"
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"role": "assistant",
|
| 26 |
+
"content": "Search"
|
| 27 |
+
}
|
| 28 |
+
]
|
encoding/tests/test_output_1.txt
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<|begin▁of▁sentence|>You are a helpful assistant.
|
| 2 |
+
|
| 3 |
+
## Tools
|
| 4 |
+
|
| 5 |
+
You have access to a set of tools to help answer the user's question. You can invoke tools by writing a "<|DSML|tool_calls>" block like the following:
|
| 6 |
+
|
| 7 |
+
<|DSML|tool_calls>
|
| 8 |
+
<|DSML|invoke name="$TOOL_NAME">
|
| 9 |
+
<|DSML|parameter name="$PARAMETER_NAME" string="true|false">$PARAMETER_VALUE</|DSML|parameter>
|
| 10 |
+
...
|
| 11 |
+
</|DSML|invoke>
|
| 12 |
+
<|DSML|invoke name="$TOOL_NAME2">
|
| 13 |
+
...
|
| 14 |
+
</|DSML|invoke>
|
| 15 |
+
</|DSML|tool_calls>
|
| 16 |
+
|
| 17 |
+
String parameters should be specified as is and set `string="true"`. For all other types (numbers, booleans, arrays, objects), pass the value in JSON format and set `string="false"`.
|
| 18 |
+
|
| 19 |
+
If thinking_mode is enabled (triggered by <think>), you MUST output your complete reasoning inside <think>...</think> BEFORE any tool calls or final response.
|
| 20 |
+
|
| 21 |
+
Otherwise, output directly after </think> with tool calls or final response.
|
| 22 |
+
|
| 23 |
+
### Available Tool Schemas
|
| 24 |
+
|
| 25 |
+
{"name": "get_weather", "description": "Get the weather for a specific location", "parameters": {"type": "object", "properties": {"location": {"type": "string", "description": "The city name"}, "unit": {"type": "string", "enum": ["celsius", "fahrenheit"], "description": "Temperature unit"}}, "required": ["location"]}}
|
| 26 |
+
{"name": "search", "description": "Search the web for information", "parameters": {"type": "object", "properties": {"query": {"type": "string", "description": "Search query"}, "num_results": {"type": "integer", "description": "Number of results to return"}}, "required": ["query"]}}
|
| 27 |
+
|
| 28 |
+
You MUST strictly follow the above defined tool name and parameter schemas to invoke tool calls.
|
| 29 |
+
<|User|>What's the weather in Beijing?<|Assistant|><think>The user wants to know the weather in Beijing. I should use the get_weather tool.</think>
|
| 30 |
+
|
| 31 |
+
<|DSML|tool_calls>
|
| 32 |
+
<|DSML|invoke name="get_weather">
|
| 33 |
+
<|DSML|parameter name="location" string="true">Beijing</|DSML|parameter>
|
| 34 |
+
<|DSML|parameter name="unit" string="true">celsius</|DSML|parameter>
|
| 35 |
+
</|DSML|invoke>
|
| 36 |
+
</|DSML|tool_calls><|end▁of▁sentence|><|User|><tool_result>{"temperature": 22, "condition": "sunny", "humidity": 45}</tool_result><|Assistant|><think>Got the weather data. Let me format a nice response.</think>The weather in Beijing is currently sunny with a temperature of 22°C and 45% humidity.<|end▁of▁sentence|>
|
encoding/tests/test_output_2.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
<|begin▁of▁sentence|>You are a helpful assistant.<|User|>Hello<|Assistant|></think>Hi there! How can I help you?<|end▁of▁sentence|><|User|>What is the capital of France?<|Assistant|><think>The user asks about the capital of France. It is Paris.</think>The capital of France is Paris.<|end▁of▁sentence|>
|
encoding/tests/test_output_3.txt
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<|begin▁of▁sentence|>该助手为Vedika-Code-Pro-v1,由Veda Labs创造。<|latest_reminder|>2026-02-21,星期六,广州,App,中文<|User|>小柴胡冲剂和布洛芬能一起吃吗?
|
| 2 |
+
|
| 3 |
+
CITATION FORMAT: 【{cursor_id}†L{start_line_id}(-L{end_line_id})?】
|
| 4 |
+
|
| 5 |
+
## Tools
|
| 6 |
+
|
| 7 |
+
You have access to a set of tools to help answer the user's question. You can invoke tools by writing a "<|DSML|tool_calls>" block like the following:
|
| 8 |
+
|
| 9 |
+
<|DSML|tool_calls>
|
| 10 |
+
<|DSML|invoke name="$TOOL_NAME">
|
| 11 |
+
<|DSML|parameter name="$PARAMETER_NAME" string="true|false">$PARAMETER_VALUE</|DSML|parameter>
|
| 12 |
+
...
|
| 13 |
+
</|DSML|invoke>
|
| 14 |
+
<|DSML|invoke name="$TOOL_NAME2">
|
| 15 |
+
...
|
| 16 |
+
</|DSML|invoke>
|
| 17 |
+
</|DSML|tool_calls>
|
| 18 |
+
|
| 19 |
+
String parameters should be specified as is and set `string="true"`. For all other types (numbers, booleans, arrays, objects), pass the value in JSON format and set `string="false"`.
|
| 20 |
+
|
| 21 |
+
If thinking_mode is enabled (triggered by <think>), you MUST output your complete reasoning inside <think>...</think> BEFORE any tool calls or final response.
|
| 22 |
+
|
| 23 |
+
Otherwise, output directly after </think> with tool calls or final response.
|
| 24 |
+
|
| 25 |
+
### Available Tool Schemas
|
| 26 |
+
|
| 27 |
+
{"name": "search", "description": "Web search. Split multiple queries with '||'.", "parameters": {"type": "object", "properties": {"queries": {"type": "string", "description": "query1||query2"}}, "required": ["queries"], "additionalProperties": false, "$schema": "http://json-schema.org/draft-07/schema#"}}
|
| 28 |
+
{"name": "open", "description": "Batch open IDs (format 【{id}†...】) or URLs.", "parameters": {"type": "object", "properties": {"open_list": {"type": "array", "items": {"type": "object", "properties": {"id": {"description": "ID or URL", "anyOf": [{"type": "integer"}, {"type": "string"}], "default": -1}, "cursor": {"type": "integer", "description": "", "default": -1}, "loc": {"type": "integer", "description": "Start line", "default": -1}, "num_lines": {"type": "integer", "description": "", "default": -1}, "view_source": {"type": "boolean", "description": "", "default": false}}, "additionalProperties": false}, "description": ""}}, "required": ["open_list"], "additionalProperties": false, "$schema": "http://json-schema.org/draft-07/schema#"}}
|
| 29 |
+
{"name": "find", "description": "Find exact text pattern in pages.", "parameters": {"type": "object", "properties": {"find_list": {"type": "array", "items": {"type": "object", "properties": {"pattern": {"type": "string", "description": ""}, "cursor": {"type": "integer", "description": "", "default": -1}}, "required": ["pattern"], "additionalProperties": false}, "description": ""}}, "required": ["find_list"], "additionalProperties": false, "$schema": "http://json-schema.org/draft-07/schema#"}}
|
| 30 |
+
|
| 31 |
+
You MUST strictly follow the above defined tool name and parameter schemas to invoke tool calls.
|
| 32 |
+
<|Assistant|><think>用户想知道小柴胡冲剂和布洛芬能否一起服用。</think>
|
| 33 |
+
|
| 34 |
+
<|DSML|tool_calls>
|
| 35 |
+
<|DSML|invoke name="search">
|
| 36 |
+
<|DSML|parameter name="queries" string="true">小柴胡冲剂 布洛芬 相互作用 一起吃</|DSML|parameter>
|
| 37 |
+
</|DSML|invoke>
|
| 38 |
+
</|DSML|tool_calls><|end▁of▁sentence|><|User|><tool_result>[0]</tool_result><|Assistant|><think>现在开始组织回答。</think>请及时就医。<|end▁of▁sentence|>
|
encoding/tests/test_output_4.txt
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<|begin▁of▁sentence|>该助手为Vedika-Code-Pro-v1,由Veda Labs创造。
|
| 2 |
+
今天是2025年10月17日,星期五。<|latest_reminder|>2024-11-15,上海市,App,中文<|User|>热海大滚锅是世界著名温泉吗<|Assistant|></think>关于热海大滚锅是否是世界著名温泉,可以这样总结:它在**中国乃至全球的地热奇观中占有重要地位**,但“世界著名”的称号更侧重于它作为**独特的地质现象和旅游景点**,而非普遍的温泉疗养体验。
|
| 3 |
+
|
| 4 |
+
为了让你快速了解,我整理了一个简要的表格:
|
| 5 |
+
|
| 6 |
+
| 维度 | 热海大滚锅的地位与特点 |
|
| 7 |
+
| :--- | :--- |
|
| 8 |
+
| **地质奇观** | **世界罕见**的高温地热系统,泉眼多、水温高、形态多样。 |
|
| 9 |
+
| **国内声誉** | **中国三大地热区之一**,**国家5A级旅游景区**,自古闻名(徐霞客曾游历并记载)。 |
|
| 10 |
+
| **国际知名度** | 在一些旅游平台被提及为“世界六大温泉”之一,但此说法流传不广,其国际声誉更多建立在地质独特性上。 |
|
| 11 |
+
| **核心体验** | **观赏地热奇观**(如97℃沸腾的“大滚锅”)、**体验温泉煮鸡蛋**。 |
|
| 12 |
+
|
| 13 |
+
### 💡 游玩攻略与温馨提示
|
| 14 |
+
|
| 15 |
+
如果你计划前往热海大滚锅,这里有一些实用信息供你参考:
|
| 16 |
+
|
| 17 |
+
- **门票与开放时间**:
|
| 18 |
+
- **门票**:景区门票约为**50元/人**。如果选择包含温泉沐浴的套餐,价格会更高,例如约**288元**。
|
| 19 |
+
- **开放时间**:景区一般**08:00-18:00**开放,但具体时间可能变动,建议提前核实。
|
| 20 |
+
|
| 21 |
+
- **特色体验**:
|
| 22 |
+
- **温泉煮鸡蛋**:这几乎是必试项目。可以在景区门口购买用草绳串起的生鸡蛋(约5-8元/串),然后到“大滚锅”旁的指定区域蒸煮,几分钟便可熟食,趣味十足。
|
| 23 |
+
- **金汤足浴**:可以直接用从“大滚锅”流出的温泉水泡脚,缓解旅途疲劳。
|
| 24 |
+
|
| 25 |
+
- **注意事项**:
|
| 26 |
+
- **安全第一**:“大滚锅”水温极高,务必遵守游览规则,在指定区域内观赏,切勿随意触碰泉水。
|
| 27 |
+
- **规划行程**:建议为热海景区预留**3-4小时**的游览时间。景区内步道不走回头路,出入口有观光车接送。
|
| 28 |
+
|
| 29 |
+
希望这些信息能帮助你更好地了解热海大滚锅。如果你对腾冲的其他景点或者行程规划有更多疑问,我很乐意提供进一步的信息。<|end▁of▁sentence|><|User|>世界著名温泉有哪些<|Assistant|></think><|action|>Search<|end▁of▁sentence|>
|