基于Llama 3的AI代理开发实战演练 原创

from haystack import Pipeline, Document
from haystack.document_stores.in_memory import InMemoryDocumentStore
from haystack.components.writers import DocumentWriter
from haystack.components.embedders import SentenceTransformersDocumentEmbedder
from haystack.components.generators import OpenAIGenerator
from haystack.utils import Secret
from haystack.components.generators.chat import OpenAIChatGenerator
from haystack.components.builders import PromptBuilder
from haystack.components.embedders import SentenceTransformersTextEmbedder
from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever
from haystack.dataclasses import ChatMessage
import pandas as pd

#从CSV加载产品数据
df = pd.read_csv("product_sample.csv")

#初始化内存中的文档存储区
document_store = InMemoryDocumentStore()

#将产品数据转换为Haystack文档对象
documents = [
Document(
content=item.product_name, 
meta={
"id": item.uniq_id, 
"price": item.selling_price, 
"url": item.product_url
}
) for item in df.itertuples()
]

#创建一个用于编制文档索引的管道
indexing_pipeline = Pipeline()

#使用句子转换器模型向管道中添加一个文档嵌入器
indexing_pipeline.add_component(
instance=SentenceTransformersDocumentEmbedder(model="sentence-transformers/all-MiniLM-L6-v2"), name="doc_embedder"
)

# 向管道中添加文档写入器，以便在文档存储区中存储文档
indexing_pipeline.add_component(instance=DocumentWriter(document_store=document_store), name="doc_writer")

#将嵌入器的输出连接到写入器的输入
indexing_pipeline.connect("doc_embedder.documents", "doc_writer.documents")

#运行索引管道来处理和存储文档
indexing_pipeline.run({"doc_embedder": {"documents": documents}})

template = """
Understand the user query and list of products the user is interested in and return product names as list.
You should always return a Python list. Do not return any explanation.

Examples:
Question: I am interested in camping boots, charcoal and disposable rain jacket.
Answer: ["camping_boots","charcoal","disposable_rain_jacket"]

Question: Need a laptop, wireless mouse, and noise-cancelling headphones for work.
Answer: ["laptop","wireless_mouse","noise_cancelling_headphones"]

Question: {{ question }}
Answer:
"""

product_identifier = Pipeline()

product_identifier.add_component("prompt_builder", PromptBuilder(template=template))
product_identifier.add_component("llm", generator())

product_identifier.connect("prompt_builder", "llm")

template = """
Return product name, price, and url as a python dictionary. 
You should always return a Python dictionary with keys price, name and url for single product.
You should always return a Python list of dictionaries with keys price, name and url for multiple products.
Do not return any explanation.

Legitimate Response Schema:
{"price": "float", "name": "string", "url": "string"}
Legitimate Response Schema for multiple products:
[{"price": "float", "name": "string", "url": "string"},{"price": "float", "name": "string", "url": "string"}]

Context:
{% for document in documents %}
product_price: {{ document.meta['price'] }}
product_url: {{ document.meta['url'] }}
product_id: {{ document.meta['id'] }}
product_name: {{ document.content }}
{% endfor %}
Question: {{ question }}
Answer:
"""

rag_pipe = Pipeline()
rag_pipe.add_component("embedder", SentenceTransformersTextEmbedder(model="sentence-transformers/all-MiniLM-L6-v2"))
rag_pipe.add_component("retriever", InMemoryEmbeddingRetriever(document_store=document_store, top_k=5))
rag_pipe.add_component("prompt_builder", PromptBuilder(template=template))
rag_pipe.add_component("llm", generator())

rag_pipe.connect("embedder.embedding", "retriever.query_embedding")
rag_pipe.connect("retriever", "prompt_builder.documents")
rag_pipe.connect("prompt_builder", "llm")

def product_identifier_func(query: str):
"""
根据给定的查询来标识产品，并检索每个已标识的产品的相关详细信息。

参数:
query (str): 用于标识产品的查询字符串。

返回值:
dict: 一个字典，其中键是产品名称，值是每个产品的详细信息。如果没有找到产品，则返回“No product found”。
"""
product_understanding = product_identifier.run({"prompt_builder": {"question": query}})

try:
product_list = literal_eval(product_understanding["llm"]["replies"][0])
except:
return "No product found"

results = {}

for product in product_list:
response = rag_pipe.run({"embedder": {"text": product}, "prompt_builder": {"question": product}})
try:
results[product] = literal_eval(response["llm"]["replies"][0])
except:
results[product] = {}

return results

query = "I want crossbow and woodstock puzzle"
#执行函数
product_identifier_func(query)

# {'crossbow': {'name': 'DB Longboards CoreFlex Crossbow 41" Bamboo Fiberglass '
#                        'Longboard Complete',
#                'price': 237.68,
#                'url': 'https://www.amazon.com/DB-Longboards-CoreFlex-Fiberglass-Longboard/dp/B07KMVJJK7'},
#  'woodstock_puzzle': {'name': 'Woodstock- Collage 500 pc Puzzle',
#                       'price': 17.49,
#                       'url': 'https://www.amazon.com/Woodstock-Collage-500-pc-Puzzle/dp/B07MX21WWX'}}

{
"product_key": {
"name": "string",
"price": "float",
"url": "string"
}
}

def find_budget_friendly_option(selected_product_details):
"""
为每一类产品找到最经济友好的选择。

参数:
selected_product_details (dict): 一个字典，其中的键是产品类别和值是列表的产品细节。每个产品的细节都应该是一个包含一个“price”键的字典。

返回结果:
dict: 一个字典，其中键是产品类别，值是每个类别的最经济友好的产品详细信息。
"""
budget_friendly_options = {}

for category, items in selected_product_details.items():
if isinstance(items, list):
lowest_price_item = min(items, key=lambda x: x['price'])
else:
lowest_price_item = items

budget_friendly_options[category] = lowest_price_item

return budget_friendly_options

chat_template = '''<|start_header_id|>system<|end_header_id|>

You are a function calling AI model. 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": "product_identifier_func",
"description": "To understand user interested products and its details",
"parameters": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The query to use in the search. Infer this from the user's message. It should be a question or a statement"
}
},
"required": ["query"]
}
},
{
"name": "find_budget_friendly_option",
"description": "Get the most cost-friendly option. If selected_product_details has morethan one key this should return most cost-friendly options",
"parameters": {
"type": "object",
"properties": {
"selected_product_details": {
"type": "dict",
"description": "Input data is a dictionary where each key is a category name, and its value is either a single dictionary with 'price', 'name', and 'url' keys or a list of such dictionaries; example: {'category1': [{'price': 10.5, 'name': 'item1', 'url': 'http://example.com/item1'}, {'price': 8.99, 'name': 'item2', 'url': 'http://example.com/item2'}], 'category2': {'price': 15.0, 'name': 'item3', 'url': 'http://example.com/item3'}}"
}
},
"required": ["selected_product_details"]
}
}
</tools><|eot_id|><|start_header_id|>user<|end_header_id|>

I need to buy a crossbow<|eot_id|><|start_header_id|>assistant<|end_header_id|>

<tool_call>
{"id":"call_deok","name":"product_identifier_func","arguments":{"query":"I need to buy a crossbow"}}
</tool_call><|eot_id|><|start_header_id|>tool<|end_header_id|>

<tool_response>
{"id":"call_deok","result":{'crossbow': {'price': 237.68,'name': 'crossbow','url': 'https://www.amazon.com/crossbow/dp/B07KMVJJK7'}}}
</tool_response><|eot_id|><|start_header_id|>assistant<|end_header_id|>
'''

##测试代理
messages = [
ChatMessage.from_system(
chat_template
),
ChatMessage.from_user("I need to buy a crossbow for my child and Pokémon for myself."),
]

chat_generator = get_chat_generator()
response = chat_generator.run(messages=messages)
pprint(response)

## 响应结果
{'replies': [ChatMessage(content='<tool_call>\n'
'{"id": 0, "name": "product_identifier_func", '
'"arguments": {"query": "I need to buy a '
'crossbow for my child"}}\n'
'</tool_call>\n'
'<tool_call>\n'
'{"id": 1, "name": "product_identifier_func", '
'"arguments": {"query": "I need to buy a '
'Pokemon for myself"}}\n'
'</tool_call>',
role=<ChatRole.ASSISTANT: 'assistant'>,
name=None,
meta={'finish_reason': 'stop',
'index': 0,
'model': 'llama3-groq-70b-8192-tool-use-preview',
'usage': {'completion_time': 0.217823967,
'completion_tokens': 70,
'prompt_time': 0.041348261,
'prompt_tokens': 561,
'total_time': 0.259172228,
'total_tokens': 631}})]}

def extract_tool_calls(tool_calls_str):
json_objects = re.findall(r'<tool_call>(.*?)</tool_call>', tool_calls_str, re.DOTALL)

result_list = [json.loads(obj) for obj in json_objects]

return result_list

available_functions = {
"product_identifier_func": product_identifier_func, 
"find_budget_friendly_option": find_budget_friendly_option
}

messages.append(ChatMessage.from_user(message))
response = chat_generator.run(messages=messages)

if response and "<tool_call>" in response["replies"][0].content:
function_calls = extract_tool_calls(response["replies"][0].content)
for function_call in function_calls:
# 解析函数调用信息
function_name = function_call["name"]
function_args = function_call["arguments"]

#找到相应的函数并用给定的参数调用它
function_to_call = available_functions[function_name]
function_response = function_to_call(**function_args)

# 使用`ChatMessage.from_function`在消息列表中附加函数响应
messages.append(ChatMessage.from_function(content=json.dumps(function_response), name=function_name))
response = chat_generator.run(messages=messages)

import gradio as gr

messages = [ChatMessage.from_system(chat_template)]
chat_generator = get_chat_generator()

def chatbot_with_fc(message, messages):
messages.append(ChatMessage.from_user(message))
response = chat_generator.run(messages=messages)

while True:
if response and "<tool_call>" in response["replies"][0].content:
function_calls = extract_tool_calls(response["replies"][0].content)
for function_call in function_calls:
#解析函数调用信息
function_name = function_call["name"]
function_args = function_call["arguments"]

#找到相应的函数并用给定的参数调用它
function_to_call = available_functions[function_name]
function_response = function_to_call(**function_args)

# 使用`ChatMessage.from_function`在消息列表中附加函数响应
messages.append(ChatMessage.from_function(content=json.dumps(function_response), name=function_name))
response = chat_generator.run(messages=messages)

# 定期对话
else:
messages.append(response["replies"][0])
break
return response["replies"][0].content


def chatbot_interface(user_input, state):
response_content = chatbot_with_fc(user_input, state)
return response_content, state

with gr.Blocks() as demo:
gr.Markdown("# AI Purchase Assistant")
gr.Markdown("Ask me about products you want to buy!")

state = gr.State(value=messages)

with gr.Row():
user_input = gr.Textbox(label="Your message:")
response_output = gr.Markdown(label="Response:")

user_input.submit(chatbot_interface, [user_input, state], [response_output, state])
gr.Button("Send").click(chatbot_interface, [user_input, state], [response_output, state])


demo.launch()