Qwen-agent流程

最新推荐文章于 2024-08-14 22:29:49 发布
最新推荐文章于 2024-08-14 22:29:49 发布
阅读量225 收藏 3
点赞数 5
文章标签： 人工智能
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/qq_41728178/article/details/140863904
版权

本文章以qwen-agent项目中examples/assistant_add_custom_tool.py的运行过程为切入点，分析其在运行过程中对于后台大模型服务调用时的prompt，来理解agent的实现思路

examples/assistant_add_custom_tool.py期望达到的效果是可以运用代码生成器，图片生成器实现从文本到图片的过程。

代码解析

agent主要的能力来源于各种工具的使用

下面是工具的创建过程

# 设计新的工具，依据工具的注册规范，提供工具功能描述，入参，函数实现功能
@register_tool('my_image_gen')
class MyImageGen(BaseTool):
    description = 'AI painting (image generation) service, input text description, and return the image URL drawn based on text information.'
    parameters = [{
        'name': 'prompt',
        'type': 'string',
        'description': 'Detailed description of the desired image content, in English',
        'required': True,
    }]

    def call(self, params: str, **kwargs) -> str:
        prompt = json5.loads(params)['prompt']
        prompt = urllib.parse.quote(prompt)
        return json.dumps(
            {'image_url': f'https://image.pollinations.ai/prompt/{prompt}'},
            ensure_ascii=False,
        )

bot的创建，设置好使用模型的路径，系统指令，可以使用的工具池

# 大模型服务，工具池，系统指令
def init_agent_service():
    # llm_cfg = {'model': 'qwen-max'}
    llm_cfg = {
        'model': 'Qwen1.5-14B',
        'model_server': 'http://10.112.2.35:8688/v1'
    }
    system = ("According to the user's request, you first draw a picture and then automatically "
              'run code to download the picture and select an image operation from the given document '
              'to process the image')

    tools = [
        'my_image_gen',
        'code_interpreter',
    ]  # code_interpreter is a built-in tool in Qwen-Agent
    bot = Assistant(
        llm=llm_cfg,
        name='AI painting',
        description='AI painting service',
        system_message=system,
        function_list=tools,
        files=[os.path.join(ROOT_RESOURCE, 'doc.pdf')],
    )

    return bot

第一次大模型调用prompt

对输入query进行信息提取和指令提取

<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
Please extract the key information fragments that can help retrieval and the task description in the question, and give them in JSON format:
{"information": ["information fragment 1", "information fragment 2"], "instruction": ["instruction fragment 1", "instruction fragment 2"]}.
If it is a question, the default task description is: Answer the question

Question: What is MMDET.UTILS?
Result: {"information": ["What is MMDET.UTILS"], "instruction": ["Answer the question"]}
Observation: ...

Question: Summarize
Result: {"information": [], "instruction": ["Summarize"]}
Observation: ...

Question: Describe in great detail 2.1 DATA, 2.2 TOKENIZATION, 2.3 ARCHITECTURE. Also, can you incorporate the methods from this paper?
Result: {"information": ["2.1 DATA, 2.2 TOKENIZATION, 2.3 ARCHITECTURE"], "instruction": ["Describe in great detail", "Also, can you incorporate the methods from this paper?"]}
Observation: ... 

Question: Help me count the performance of membership levels.
Result: {"information": ["the performance of membership levels"], "instruction": ["Help me count"]}
Observation: ...

Question: draw a dog
Result:
<|im_end|>
<|im_start|>assistant

第二次大模型调用prompt

对输入query进行关键词提取，呈现时以中文和英文两种方式呈现

<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
Please extract keywords from the question, both in Chinese and English, and supplement them appropriately with relevant keywords that are not in the question.
Try to divide keywords into verb, noun, or adjective types and avoid long phrases (The aim is to better match and retrieve semantically related but differently phrased relevant information).
Keywords are provided in JSON format, such as {"keywords_zh": ["关键词1", "关键词2"], "keywords_en": ["keyword 1", "keyword 2"]}

Question: Who are the authors of this article?
Keywords: {"keywords_zh": ["作者"], "keywords_en": ["author"]}
Observation: ...

Question: Explain Figure 1
Keywords: {"keywords_zh": ["图一", "图 1"], "keywords_en": ["Figure 1"]}
Observation: ...

Question: core formula
Keywords: {"keywords_zh": ["核心公式", "公式"], "keywords_en": ["core formula", "formula", "equation"]}
Observation: ...

Question: draw a dog
Keywords:
<|im_end|>
<|im_start|>assistant

第一次与第二次大模型调用都是对于输入query的信息改写，已提供更为明确的指令信息，

第三次大模型调用开始都是对于工具的使用，会设置最大工具使用次数，任何一次工具使用结果表现出不再进行工具使用，跳出工具使用循环，结束整个流程

第三次大模型调用prompt

<|im_start|>system
According to the user's request, you first draw a picture and then automatically run code to download the picture and select an image operation from the given document to process the image

# Knowledge Base

## The content from [文件](doc.pdf):

```
# Python Image Processing Tutorial: Downloading Images and Performing Flip Operations 

In  this  tutorial,  we  will  learn  how  to  download  images  using  Python  and  perform  basic  image 
operations such as flipping and rotating using the Pillow library. 
## Prerequisites 
Before we begin, make sure you have the following libraries installed in your Python environment: 
 
- `requests`: for downloading images 
- `Pillow`: for image processing 
If you haven't installed these libraries yet, you can install them using pip: 

```bash 
pip install requests Pillow 
``` 
## Step 1: Downloading an Image 
First, we need to download an image. We will use the `requests` library to accomplish this task. 

``` 
import requests 

def download_image(url, filename): 
    response = requests.get(url) 
    if response.status_code == 200: 
        with open(filename, 'wb') as file: 
        file.write(response.content) 
    else: 
        print(f"Error:Failed to download image from {url}") 
    
# Example usage 
image_url = "https://example.com/image.jpg" # Replace with the URL of the image you want to download 
filename = "downloaded_image.jpg" 
download_image(image_url, filename) 
``` 
## Step 2: Opening and Displaying the Image 
Next, we will use the `Pillow` library to open and display the image we just downloaded. 

``` 
from PIL import Image 

def open_and_show_image(filename): 
    image = Image.open(filename) 
    image.show() 

# Exampleusage 
open_and_show_image(filename) 
``` 
## Step 3: Flipping and Rotating the Image 

Now we can perform flip and rotate operations on the image. The `Pillow` library provides several 
methods for image manipulation. 

``` 
def flip_image(filename, mode='horizontal'): 
    image = Image.open(filename) 
    if mode == 'horizontal': 
        flipped_image = image.transpose(Image.FLIP_LEFT_RIGHT) 
    elif mode == 'vertical': 
        flipped_image = image.transpose(Image.FLIP_TOP_BOTTOM) 
    else: 
        print("Error: Mode should be 'horizontal' or 'vertical'") 
        return 
    flipped_image.show() 
    return flipped_image 
    
def rotate_image(filename, degrees): 
    image = Image.open(filename) 
    rotated_image = image.rotate(degrees) 
    rotated_image.show() 
    return rotated_image 
    
# Example usage 
flipped_image = flip_image(filename, mode='horizontal')    # Horizontally flip 
flipped_image.save("flipped_horizontal.jpg")    # Save the horizontally flipped image 

flipped_image = flip_image(filename, mode='vertical')    # Vertically flip 
flipped_image.save("flipped_vertical.jpg")    # Save the vertically flipped image 

rotated_image = rotate_image(filename, 90)    # Rotate by 90 degrees 
rotated_image.save("rotated_90.jpg")    # Save the rotated image 
    
``` 
## Step 4: Saving the Modified Image 

In the examples above, we have seen how to save flipped and rotated images. You can use the 
`save` method to save any modified image. 

``` 
# Save the image 
def save_image(image, filename): 
    image.save(filename) 
    
# Example usage 
save_image(flipped_image, "flipped_image.jpg") 
save_image(rotated_image, "rotated_image.jpg") 
``` 
        
By  now,  you  have  learned  how  to  download  images  using  Python  and  perform  basic  image 
operations using the Pillow library. You can extend these basics to implement more complex image 
processing functions as needed. 

```

# Tools

## You have access to the following tools:

### my_image_gen

my_image_gen: AI painting (image generation) service, input text description, and return the image URL drawn based on text information. Parameters: [{"name": "prompt", "type": "string", "description": "Detailed description of the desired image content, in English", "required": true}] Format the arguments as a JSON object.

### code_interpreter

code_interpreter: Python代码沙盒，可用于执行Python代码。 Parameters: [{"name": "code", "type": "string", "description": "待执行的代码", "required": true}] 此工具的输入应为Markdown代码块。

## When you need to call a tool, please insert the following command in your reply, which can be called zero or multiple times according to your needs:

✿FUNCTION✿: The tool to use, should be one of [my_image_gen,code_interpreter]
✿ARGS✿: The input of the tool
✿RESULT✿: Tool results
✿RETURN✿: Reply based on tool results. Images need to be rendered as ![](url)<|im_end|>
<|im_start|>user
draw a dog<|im_end|>
<|im_start|>assistant

prompt中有相当大的一分部在以COT的方式介绍如何完成画图的整个流程，第一步，第二步，第三步的方式告知应该怎么思考解决方案，同时如何在了解工具的功能，工具的入参的情况下，怎么给输出工具的入参以使用工具的功能。

后半段可以看到是对工具池中工具的说明，提到了功能，入参，输出

最后几行告知了大模型的输出格式

第四次大模型调用prompt

第四次和第三次的prompt差别主要在最后添加上了第三部的执行结果，后续大模型调用都是如此

<|im_start|>system
According to the user's request, you first draw a picture and then automatically run code to download the picture and select an image operation from the given document to process the image

# Knowledge Base

## The content from [文件](doc.pdf):

```
# Python Image Processing Tutorial: Downloading Images and Performing Flip Operations 

In  this  tutorial,  we  will  learn  how  to  download  images  using  Python  and  perform  basic  image 
operations such as flipping and rotating using the Pillow library. 
 ## Prerequisites 
 Before we begin, make sure you have the following libraries installed in your Python environment: 
 
 - `requests`: for downloading images 
 - `Pillow`: for image processing 
If you haven't installed these libraries yet, you can install them using pip: 

```bash 
pip install requests Pillow 
``` 
## Step 1: Downloading an Image 
First, we need to download an image. We will use the `requests` library to accomplish this task. 

``` 
import requests 
 
def download_image(url, filename): 
    response = requests.get(url) 
    if response.status_code == 200: 
        with open(filename, 'wb') as file: 
            file.write(response.content) 
    else: 
        print(f"Error:Failed to download image from {url}") 
        
# Example usage 
image_url = "https://example.com/image.jpg" # Replace with the URL of the image you want to download 
filename = "downloaded_image.jpg" 
download_image(image_url, filename) 
``` 
## Step 2: Opening and Displaying the Image 
Next, we will use the `Pillow` library to open and display the image we just downloaded. 

``` 
from PIL import Image 

def open_and_show_image(filename): 
    image = Image.open(filename) 
    image.show() 
    
# Example usage 
open_and_show_image(filename) 
``` 
## Step 3: Flipping and Rotating the Image 
Now we can perform flip and rotate operations on the image. The `Pillow` library provides several 
methods for image manipulation. 

``` 
def flip_image(filename, mode='horizontal'): 
    image = Image.open(filename) 
    if mode == 'horizontal': 
        flipped_image = image.transpose(Image.FLIP_LEFT_RIGHT) 
    elif mode == 'vertical': 
        flipped_image = image.transpose(Image.FLIP_TOP_BOTTOM) 
    else: 
        print("Error: Mode should be 'horizontal' or 'vertical'") 
        return 

    flipped_image.show() 
    return flipped_image 
    
def rotate_image(filename, degrees): 
    image = Image.open(filename) 
    rotated_image = image.rotate(degrees) 
    rotated_image.show() 
    return rotated_image 
    
# Example usage 
flipped_image = flip_image(filename, mode='horizontal')    # Horizontally flip 
flipped_image.save("flipped_horizontal.jpg")    # Save the horizontally flipped image 
flipped_image = flip_image(filename, mode='vertical')    # Vertically flip 
flipped_image.save("flipped_vertical.jpg")    # Save the vertically flipped image 

rotated_image = rotate_image(filename, 90)    # Rotate by 90 degrees 
rotated_image.save("rotated_90.jpg")    # Save the rotated image 

``` 
## Step 4: Saving the Modified Image 

In the examples above, we have seen how to save flipped and rotated images. You can use the `save` method to save any modified image. 

``` 
# Save the image 
def save_image(image, filename): 
    image.save(filename) 
    
# Example usage 
save_image(flipped_image, "flipped_image.jpg") 
save_image(rotated_image, "rotated_image.jpg") 
``` 

By  now,  you  have  learned  how  to  download  images  using  Python  and  perform  basic  image 
operations using the Pillow library. You can extend these basics to implement more complex image 
processing functions as needed. 

```

# Tools

## You have access to the following tools:

### my_image_gen

my_image_gen: AI painting (image generation) service, input text description, and return the image URL drawn based on text information. Parameters: [{"name": "prompt", "type": "string", "description": "Detailed description of the desired image content, in English", "required": true}] Format the arguments as a JSON object.

### code_interpreter
code_interpreter: Python代码沙盒，可用于执行Python代码。 Parameters: [{"name": "code", "type": "string", "description": "待执行的代码", "required": true}] 此工具的输入应为Markdown代码块。

## When you need to call a tool, please insert the following command in your reply, which can be called zero or multiple times according to your needs:

✿FUNCTION✿: The tool to use, should be one of [my_image_gen,code_interpreter]
✿ARGS✿: The input of the tool
✿RESULT✿: Tool results
✿RETURN✿: Reply based on tool results. Images need to be rendered as ![](url)<|im_end|>
<|im_start|>user
draw a dog

✿FUNCTION✿: code_interpreter
✿ARGS✿: 
```py
from PIL import Image, ImageDraw

# Create a new image with a white background
width, height = 400, 400
image = Image.new('RGB', (width, height), (255, 255, 255))
draw = ImageDraw.Draw(image)

# Draw a simple dog using a rectangle and a couple of ovals
# The dog
✿RESULT✿: error:

```
Cell In[2], line 2
```py ^SyntaxError: invalid syntax```
✿RETURN✿<|im_end|>
<|im_start|>assistant

第五次大模型调用prompt

<|im_start|>system
According to the user's request, you first draw a picture and then automatically run code to download the picture and select an image operation from the given document to process the image

# Knowledge Base

## The content from [文件](doc.pdf):

```
# Python Image Processing Tutorial: Downloading Images and Performing Flip Operations 

In  this  tutorial,  we  will  learn  how  to  download  images  using  Python  and  perform  basic  image 
operations such as flipping and rotating using the Pillow library. 
 ## Prerequisites 
 Before we begin, make sure you have the following libraries installed in your Python environment: 

- `requests`: for downloading images 
- `Pillow`: for image processing 
 If you haven't installed these libraries yet, you can install them using pip: 
```bash 
pip install requests Pillow 
``` 
 ## Step 1: Downloading an Image 
 First, we need to download an image. We will use the `requests` library to accomplish this task. 

``` 
import requests 

def download_image(url, filename): 
    response = requests.get(url) 
    if response.status_code == 200: 
        with open(filename, 'wb') as file: 
            file.write(response.content) 
    else: 
        print(f"Error:Failed to download image from {url}") 
        
# Example usage 
image_url = "https://example.com/image.jpg" # Replace with the URL of the image you want to download 
filename = "downloaded_image.jpg" 
download_image(image_url, filename) 
``` 
## Step 2: Opening and Displaying the Image 
Next, we will use the `Pillow` library to open and display the image we just downloaded. 
 
``` 
from PIL import Image 

def open_and_show_image(filename): 
image = Image.open(filename) 
image.show() 
# Example usage 
open_and_show_image(filename) 
``` 
## Step 3: Flipping and Rotating the Image 
Now we can perform flip and rotate operations on the image. The `Pillow` library provides several 
methods for image manipulation. 

``` 
def flip_image(filename, mode='horizontal'): 
    image = Image.open(filename) 
    if mode == 'horizontal': 
        flipped_image = image.transpose(Image.FLIP_LEFT_RIGHT) 
    elif mode == 'vertical': 
        flipped_image = image.transpose(Image.FLIP_TOP_BOTTOM) 
    else: 
        print("Error: Mode should be 'horizontal' or 'vertical'") 
        return 
        
    flipped_image.show()     
    return flipped_image 

def rotate_image(filename, degrees): 
    image = Image.open(filename) 
    rotated_image = image.rotate(degrees) 
    rotated_image.show() 
    return rotated_image 

# Example usage 
flipped_image = flip_image(filename, mode='horizontal')    # Horizontally flip 
flipped_image.save("flipped_horizontal.jpg")    # Save the horizontally flipped image 

flipped_image = flip_image(filename, mode='vertical')    # Vertically flip 
flipped_image.save("flipped_vertical.jpg")    # Save the vertically flipped image 

rotated_image = rotate_image(filename, 90)    # Rotate by 90 degrees 
rotated_image.save("rotated_90.jpg")    # Save the rotated image 

``` 
## Step 4: Saving the Modified Image 

In the examples above, we have seen how to save flipped and rotated images. You can use the `save` method to save any modified image. 
``` 
# Save the image 
def save_image(image, filename): 
    image.save(filename) 

# Example usage 
save_image(flipped_image, "flipped_image.jpg") 
save_image(rotated_image, "rotated_image.jpg") 
``` 

By  now,  you  have  learned  how  to  download  images  using  Python  and  perform  basic  image 
operations using the Pillow library. You can extend these basics to implement more complex image 
processing functions as needed. 

```

# Tools
## You have access to the following tools:

### my_image_gen

my_image_gen: AI painting (image generation) service, input text description, and return the image URL drawn based on text information. Parameters: [{"name": "prompt", "type": "string", "description": "Detailed description of the desired image content, in English", "required": true}] Format the arguments as a JSON object.

### code_interpreter

code_interpreter: Pyth on代码沙盒，可用于执行Python代码。 Parameters: [{"name": "code", "type": "string", "description": "待执行的代码", "required": true}] 此工具的输入应为Markdown代码块。

## When you need to call a tool, please insert the following command in your reply, which can be called zero or multiple times according to your needs:

✿FUNCTION✿: The tool to use, should be one of [my_image_gen,code_interpreter]
✿ARGS✿: The input of the tool
✿RESULT✿: Tool results
✿RETURN✿: Reply based on tool results. Images need to be rendered as ![](url)<|im_end|>
<|im_start|>user
draw a dog

✿FUNCTION✿: code_interpreter
✿ARGS✿: 
```py
from PIL import Image, ImageDraw

# Create a new image with a white background
width, height = 400, 400
image = Image.new('RGB', (width, height), (255, 255, 255))
draw = ImageDraw.Draw(image)

# Draw a simple dog using a rectangle and a couple of ovals
# The dog
✿RESULT✿: error:

```
  Cell In[2], line 2
```py
    ^
    SyntaxError: invalid syntax
```
✿RETURN✿: Apologies for the error. Let's try a different approach to draw a dog using the `PIL` library. Since it's quite complex to draw adetailed dog using Python code directly, I'll use the `my_image_gen` tool instead to generate an image of a dog for you.
✿FUNCTION✿: my_image_gen
✿ARGS✿: {"prompt": "a friendly dog running on a grassy field"}
✿RESULT✿: {"image_url": "https://image.pollinations.ai/prompt/a%20friendly%20dog%20running%20on%20a%20grassy%20field"}
✿RETURN✿<|im_end|>
<|im_start|>assistant

到这个时候我们发现其实整个过程已经可以结束了，因为我们想要的图片已经生成，得到imgae_url。

这次大模型调用得到的结果大致如下：

✿FUNCTION✿: 
✿ARGS✿: 
✿RESULT✿: 
✿RETURN✿:

qwen-agent的判断是否继续执行代码如下：

可以发现主要根据是否有function_name也就是模型输出中的✿FUNCTION✿: 是否有值来判断是否还继续使用工具

use_tool, tool_name, tool_args, _ = self._detect_tool(out)
print(use_tool, tool_name, tool_args)
print(type(use_tool), type(tool_name), type(tool_args))
if use_tool:
    tool_result = self._call_tool(tool_name, tool_args, messages=messages, **kwargs)
    fn_msg = Message(
                     role=FUNCTION,
                     name=tool_name,
                     content=tool_result,)
    messages.append(fn_msg)
    response.append(fn_msg)
    yield response
    used_any_tool = True



def _detect_tool(self, message: Message) -> Tuple[bool, str, str, str]:
    """A built-in tool call detection for func_call format message.

    Args:
        message: one message generated by LLM.

    Returns:
        Need to call tool or not, tool name, tool args, text replies.
    """
    func_name = None
    func_args = None

    if message.function_call:
        func_call = message.function_call
        func_name = func_call.name
        func_args = func_call.arguments
    text = message.content
    if not text:
        text = ''

    return (func_name is not None), func_name, func_args, text

lucky_append
关注
  • 5
    点赞
  • 踩
  • 3
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
【AI大模型Agent探索】深入探索实践 Qwen-Agent 的 Function Calling
寻道码路，探索编程之路的无限可能。
07-19 2120
本文将深入探讨 Qwen-Agent 的核心特性之一——功能调用（Function Calling）。这是一种允许 AI 模型直接与外部工具和API进行交互的能力，极大地扩展了 AI 模型的应用范围。通过实际的编码实践，我们将展示如何利用这一机制，将 AI 的决策能力和外部工具的功能性紧密结合，以实现更加丰富和高效的自动化服务。
Qwen-Agent
liuzhenghua66的博客
07-23 565
一个智能体用于理解包含百万字词的文档，使用了支持8k上下文的模型，但效果超过RAG和长序列原生模型。智能体包含三个复杂度级别，每一层都建立在前一层的基础上。官方介绍：https://qwenlm.github.io/zh/blog/qwen-agent-2405/代码库：https://github.com/QwenLM/Qwen-Agent。
【通义千问—Qwen-Agent系列1】Qwen-Agent 快速开始&使用和开发过程
艰难困苦，玉汝于成。
05-11 6852
Qwen-Agent是一个开发框架。开发者可基于本框架开发Agent应用，充分利用基于通义千问模型（Qwen）的指令遵循、工具使用、规划、记忆能力。本项目也提供了浏览器助手、代码解释器、自定义助手等示例应用。
基于Qwen-Agent与OpenVINOTM构建本地AI智能体
英特尔开发人员专区
07-22 1089
AI智能体作为通用人工智能的核心载体，可以模仿人类的思维逻辑，将复杂任务进行拆解，并借助外部工具解决任务。通过利用OpenVINOTM和Qwen-Agent这样的工具，我们可以非常快捷地在本地构建一个AI智能体应用，在保护用户数据隐私的同时，更快速地响应任务需求，简单任务调用本地工具处理，复杂任务调用云端资源处理。
基于 Qwen-Agent 与 OpenVINO™ 构建本地 AI 智能体
OpenVINOCC的博客
07-18 526
点击蓝字关注我们,让开发变得更有趣作者 | 杨亦诚排版 | 吴紫琴Qwen2 是阿里巴巴集团 Qwen 团队研发的大语言模型和大型多模态模型系列。Qwen2 具备自然语言理解、文本生成、视觉理解、音频理解、工具使用、角色扮演、作为 AI Agent 进行互动等多种能力。图：智能体中工具使用执行逻辑Qwen-Agent 是一个 AI 智能体的开发框架。开发者可基于本框架开发 Agent 应用，充分利...
使用 Qwen-Agent 将 8k 上下文记忆扩展到百万量级
机器学习社区
06-09 1374
我们在本文中介绍了利用智能体扩展模型上下文记忆的关键思路。一旦智能体准备就绪，如何合成数据便显而易见。例如，我们可以招募志愿者与智能体互动，并记录结果来构建微调数据集。此外，我们还可以利用智能体对其他方法生成的数据进行交叉验证，以确保数据质量。此外，用智能体的结果去微调模型，这个思路也适用于其他领域，比如提升模型解决大规模任务的能力。
【AI大模型Agent探索】Qwen-Agent之RAG智能助手实践
寻道码路，探索编程之路的无限可能。
07-15 2598
在人工智能的不断演进中，大模型如雨后春笋般涌现，它们在处理语言、生成内容、辅助决策等方面展现出令人瞩目的能力。Qwen-Agent，作为这一领域的新星，以其独特的架构和功能，为开发者提供了与这些强大模型互动的新途径。特别是其RAG（Retrieval-Augmented Generation）能力，它允许模型在生成回答前检索相关信息，极大地增强了AI助手的智能性和实用性。本文将深入探讨Qwen-Agent的RAG智能助手实践，揭示其如何通过结合AI大模型与外部工具，实现更深层次的自动化服务。
【LLM & Agent & 长文本】Chain-of-Agents与Qwen-Agent引领智能体长文本处理革命
余俊晖，NLP炼丹师，目前专注自然语言处理领域研究。曾获得国内外自然语言处理算法竞赛TOP奖项近二十项。
06-12 1073
输入长度减少：RAG的方法可以减少输入长度，但这可能导致所需信息的部分丢失，影响任务解决性能。扩展LLMs的上下文长度：通过微调的方式来扩展LLMs的上下文窗口，以便处理整个输入。当窗口变长时，LLMs难以集中注意力在解决任务所需的信息上，导致上下文利用效率低下。下面来看看两个有趣的另辟蹊径的方法，使用Agent协同来处理长上下文。
【通义千问—Qwen-Agent系列2】案例分析（图像理解&图文生成Agent||多模态助手|| 基于ReAct范式的数据分析Agent）
艰难困苦，玉汝于成。
05-24 1563
Qwen-Agent是一个开发框架。开发者可基于本框架开发Agent应用，充分利用基于通义千问模型（Qwen）的指令遵循、工具使用、规划、记忆能力。本框架也提供了浏览器助手、代码解释器、自定义助手等示例应用，该篇为系列2。
langchain-chatchat在window上使用cpu运行Qwen-1-8B-Chat时遇到ERROR: object
04-26
langchain-chatchat在window上使用cpu运行Qwen-1_8B-Chat时遇到ERROR: object of type ‘NoneType‘ has no len()，这个问题其实是因为"addmm_impl_cpu_" not implemented for 'Half’这个根本原因导致的，也就是cpu...
算法部署-使用TensorRT-LLM部署通义千问Qwen-7B大模型-附详细优化+分析流程教程-优质大模型部署项目实战.zip
03-06
算法部署_使用TensorRT-LLM部署通义千问Qwen-7B大模型_附详细优化+分析流程教程_优质大模型部署项目实战
Qwen-VL 远程GPU服务器部署实战
07-14
Qwen-VL 远程GPU服务器部署实战
Qwen-main.zip
02-21
【Qwen-main.zip】是一个压缩包文件，其中包含的资源很可能与一个名为“Qwen”的项目或软件有关。从文件名来看，“Qwen”可能是该项目的核心名称或主体部分。这个压缩包可能是为了方便用户下载、存储或传输Qwen的...
C/C++开发，opencv内置背景减除算法与运动检测
最新发布
技术需要分享
08-14 661
C/C++开发，opencv内置背景减除算法的完整代码及编译过程示例
Spark MLlib 特征工程(上)
08-14 1812
特征选择的动机，在于提取与预测标的关联度更高的特征，从而精简模型尺寸、提升模型泛化能力。特征选择可以从两方面入手，业务出发的专家经验和基于数据的统计分析。归一化的目的，在于去掉不同特征之间量纲的影响，避免量纲不一致而导致的梯度下降震荡、模型收敛效率低下等问题。归一化的具体做法，是把不同特征都缩放到同一个值域。在这方面，Spark MLlib 提供了多种归一化方法供开发者选择。
GraphRAG：复杂查询的知识图谱新框架
YeJuliaLi的博客
08-14 522
微软最近发布了名为 GraphRAG（Graphs + Retrieval Augmented Generation）的创新 RAG 框架，这是一个将文本提取、语义网络分析，与大语言模型（LLM）的提示和总结功能结合在一起的端到端系统，用于深入理解文本数据集。在对私有数据中的复杂文本信息进行文档分析时，GrahRAG 使用 LLM 生成的知识图谱来大幅提高问答性能。这里的私有数据集是指 LLM 没...
一键生成民谣的AI音乐工具来了！
Nonsense_man的博客
08-12 247
今天分享一个可以在线免费生成音乐的AI工具。 工具使用的是「豆包」 很多人可能用过豆包写作，或者作图，但最近上线了AI音乐生成功能。
ubuntu22.04 安装 ros1
qq_35547879的博客
08-14 223
原先只知道ros1 noetic 只支持到ubuntu20.04。现在系统必须升级到ubuntu22.04。
Qwen-Audio-Chat微调
05-10
Qwen-Audio-Chat微调是基于Qwen音频AI技术的一种应用场景，它可以通过微调Qwen模型，实现特定领域的音频智能交互。例如，将Qwen-Audio-Chat微调到医疗领域，可以实现医生与患者之间的智能语音交互，帮助医生快速准确地诊断病情。在微调Qwen模型时，我们可以根据具体的应用场景来调整模型结构、训练数据和超参数等，以达到更好的效果。
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值