OpenAI 多功能代理
这个笔记本展示了使用一个代理，该代理使用OpenAI的函数能力 来响应用户使用大型语言模型的提示。
安装openai和google-search-results包，因为langchain包在内部调用它们。
pip install openai google-search-results
代理被赋予了使用相应工具执行搜索功能的能力。
from langchain import SerpAPIWrapper
from langchain.agents import initialize_agent, Tool
from langchain.agents import AgentType
from langchain.chat_models import ChatOpenAI
import getpass
import os
os.environ["SERPAPI_API_KEY"] = getpass.getpass()
# Initialize the OpenAI language model
# Replace <your_api_key> in openai_api_key="<your_api_key>" with your actual OpenAI key.
llm = ChatOpenAI(temperature=0, model="gpt-3.5-turbo-0613")
# Initialize the SerpAPIWrapper for search functionality
# Replace <your_api_key> in openai_api_key="<your_api_key>" with your actual SerpAPI key.
search = SerpAPIWrapper()
# Define a list of tools offered by the agent
tools = [
Tool(
name="Search",
func=search.run,
description="Useful when you need to answer questions about current events. You should ask targeted questions.",
),
]
mrkl = initialize_agent(
tools, llm, agent=AgentType.OPENAI_MULTI_FUNCTIONS, verbose=True
)
# 打开调试开关，这样可以更清楚地知道发生了什么
import langchain
langchain.debug = True
# 输入提问
mrkl.run("What is the weather in LA and SF?")
[chain/start] [1:chain:AgentExecutor] Entering Chain run with input:
{
"input": "What is the weather in LA and SF?"
}
[llm/start] [1:chain:AgentExecutor > 2:llm:ChatOpenAI] Entering LLM run with input:
{
"prompts": [
"System: You are a helpful AI assistant.\nHuman: What is the weather in LA and SF?"
]
}
[llm/end] [1:chain:AgentExecutor > 2:llm:ChatOpenAI] [2.91s] Exiting LLM run with output:
{
"generations": [
[
{
"text": "",
"generation_info": null,
"message": {
"content": "",
"additional_kwargs": {
"function_call": {
"name": "tool_selection",
"arguments": "{\n \"actions\": [\n {\n \"action_name\": \"Search\",\n \"action\": {\n \"tool_input\": \"weather in Los Angeles\"\n }\n },\n {\n \"action_name\": \"Search\",\n \"action\": {\n \"tool_input\": \"weather in San Francisco\"\n }\n }\n ]\n}"
}
},
"example": false
}
}
]
],
"llm_output": {
"token_usage": {
"prompt_tokens": 81,
"completion_tokens": 75,
"total_tokens": 156
},
"model_name": "gpt-3.5-turbo-0613"
},
"run": null
}
[tool/start] [1:chain:AgentExecutor > 3:tool:Search] Entering Tool run with input:
"{'tool_input': 'weather in Los Angeles'}"
[tool/end] [1:chain:AgentExecutor > 3:tool:Search] [608.693ms] Exiting Tool run with output:
"Mostly cloudy early, then sunshine for the afternoon. High 76F. Winds SW at 5 to 10 mph. Humidity59%."
[tool/start] [1:chain:AgentExecutor > 4:tool:Search] Entering Tool run with input:
"{'tool_input': 'weather in San Francisco'}"
[tool/end] [1:chain:AgentExecutor > 4:tool:Search] [517.475ms] Exiting Tool run with output:
"Partly cloudy this evening, then becoming cloudy after midnight. Low 53F. Winds WSW at 10 to 20 mph. Humidity83%."
[llm/start] [1:chain:AgentExecutor > 5:llm:ChatOpenAI] Entering LLM run with input:
{
"prompts": [
"System: You are a helpful AI assistant.\nHuman: What is the weather in LA and SF?\nAI: {'name': 'tool_selection', 'arguments': '{\\n \"actions\": [\\n {\\n \"action_name\": \"Search\",\\n \"action\": {\\n \"tool_input\": \"weather in Los Angeles\"\\n }\\n },\\n {\\n \"action_name\": \"Search\",\\n \"action\": {\\n \"tool_input\": \"weather in San Francisco\"\\n }\\n }\\n ]\\n}'}\nFunction: Mostly cloudy early, then sunshine for the afternoon. High 76F. Winds SW at 5 to 10 mph. Humidity59%.\nAI: {'name': 'tool_selection', 'arguments': '{\\n \"actions\": [\\n {\\n \"action_name\": \"Search\",\\n \"action\": {\\n \"tool_input\": \"weather in Los Angeles\"\\n }\\n },\\n {\\n \"action_name\": \"Search\",\\n \"action\": {\\n \"tool_input\": \"weather in San Francisco\"\\n }\\n }\\n ]\\n}'}\nFunction: Partly cloudy this evening, then becoming cloudy after midnight. Low 53F. Winds WSW at 10 to 20 mph. Humidity83%."
]
}
[llm/end] [1:chain:AgentExecutor > 5:llm:ChatOpenAI] [2.33s] Exiting LLM run with output:
{
"generations": [
[
{
"text": "The weather in Los Angeles is mostly cloudy with a high of 76°F and a humidity of 59%. The weather in San Francisco is partly cloudy in the evening, becoming cloudy after midnight, with a low of 53°F and a humidity of 83%.",
"generation_info": null,
"message": {
"content": "The weather in Los Angeles is mostly cloudy with a high of 76°F and a humidity of 59%. The weather in San Francisco is partly cloudy in the evening, becoming cloudy after midnight, with a low of 53°F and a humidity of 83%.",
"additional_kwargs": {},
"example": false
}
}
]
],
"llm_output": {
"token_usage": {
"prompt_tokens": 307,
"completion_tokens": 54,
"total_tokens": 361
},
"model_name": "gpt-3.5-turbo-0613"
},
"run": null
}
[chain/end] [1:chain:AgentExecutor] [6.37s] Exiting Chain run with output:
{
"output": "The weather in Los Angeles is mostly cloudy with a high of 76°F and a humidity of 59%. The weather in San Francisco is partly cloudy in the evening, becoming cloudy after midnight, with a low of 53°F and a humidity of 83%."
}
'The weather in Los Angeles is mostly cloudy with a high of 76°F and a humidity of 59%. The weather in San Francisco is partly cloudy in the evening, becoming cloudy after midnight, with a low of 53°F and a humidity of 83%.'
配置最大迭代行为
为确保我们的代理不会陷入过长的循环中，我们 可以设置max_iterations。我们还可以设置一个提前停止的方法，该方法将 决定我们的代理在达到最大迭代次数时的行为。默认情况下，提前停止使用方法force，它只是返回那个常数字符串。或者，您可以指定方法generate，然后 进行一次LLM的FINAL遍历以生成输出。
mrkl = initialize_agent(
tools,
llm,
agent=AgentType.OPENAI_FUNCTIONS,
verbose=True,
max_iterations=2,
early_stopping_method="generate",
)
mrkl.run("What is the weather in NYC today, yesterday, and the day before?")
[chain/start] [1:chain:AgentExecutor] Entering Chain run with input:
{
"input": "What is the weather in NYC today, yesterday, and the day before?"
}
[llm/start] [1:chain:AgentExecutor > 2:llm:ChatOpenAI] Entering LLM run with input:
{
"prompts": [
"System: You are a helpful AI assistant.\nHuman: What is the weather in NYC today, yesterday, and the day before?"
]
}
[llm/end] [1:chain:AgentExecutor > 2:llm:ChatOpenAI] [1.27s] Exiting LLM run with output:
{
"generations": [
[
{
"text": "",
"generation_info": null,
"message": {
"lc": 1,
"type": "constructor",
"id": [
"langchain",
"schema",
"messages",
"AIMessage"
],
"kwargs": {
"content": "",
"additional_kwargs": {
"function_call": {
"name": "Search",
"arguments": "{\n \"query\": \"weather in NYC today\"\n}"
}
}
}
}
}
]
],
"llm_output": {
"token_usage": {
"prompt_tokens": 79,
"completion_tokens": 17,
"total_tokens": 96
},
"model_name": "gpt-3.5-turbo-0613"
},
"run": null
}
[tool/start] [1:chain:AgentExecutor > 3:tool:Search] Entering Tool run with input:
"{'query': 'weather in NYC today'}"
[tool/end] [1:chain:AgentExecutor > 3:tool:Search] [3.84s] Exiting Tool run with output:
"10:00 am · Feels Like85° · WindSE 4 mph · Humidity78% · UV Index3 of 11 · Cloud Cover81% · Rain Amount0 in ..."
[llm/start] [1:chain:AgentExecutor > 4:llm:ChatOpenAI] Entering LLM run with input:
{
"prompts": [
"System: You are a helpful AI assistant.\nHuman: What is the weather in NYC today, yesterday, and the day before?\nAI: {'name': 'Search', 'arguments': '{\\n \"query\": \"weather in NYC today\"\\n}'}\nFunction: 10:00 am · Feels Like85° · WindSE 4 mph · Humidity78% · UV Index3 of 11 · Cloud Cover81% · Rain Amount0 in ..."
]
}
[llm/end] [1:chain:AgentExecutor > 4:llm:ChatOpenAI] [1.24s] Exiting LLM run with output:
{
"generations": [
[
{
"text": "",
"generation_info": null,
"message": {
"lc": 1,
"type": "constructor",
"id": [
"langchain",
"schema",
"messages",
"AIMessage"
],
"kwargs": {
"content": "",
"additional_kwargs": {
"function_call": {
"name": "Search",
"arguments": "{\n \"query\": \"weather in NYC yesterday\"\n}"
}
}
}
}
}
]
],
"llm_output": {
"token_usage": {
"prompt_tokens": 142,
"completion_tokens": 17,
"total_tokens": 159
},
"model_name": "gpt-3.5-turbo-0613"
},
"run": null
}
[tool/start] [1:chain:AgentExecutor > 5:tool:Search] Entering Tool run with input:
"{'query': 'weather in NYC yesterday'}"
[tool/end] [1:chain:AgentExecutor > 5:tool:Search] [1.15s] Exiting Tool run with output:
"New York Temperature Yesterday. Maximum temperature yesterday: 81 °F (at 1:51 pm) Minimum temperature yesterday: 72 °F (at 7:17 pm) Average temperature ..."
[llm/start] [1:llm:ChatOpenAI] Entering LLM run with input:
{
"prompts": [
"System: You are a helpful AI assistant.\nHuman: What is the weather in NYC today, yesterday, and the day before?\nAI: {'name': 'Search', 'arguments': '{\\n \"query\": \"weather in NYC today\"\\n}'}\nFunction: 10:00 am · Feels Like85° · WindSE 4 mph · Humidity78% · UV Index3 of 11 · Cloud Cover81% · Rain Amount0 in ...\nAI: {'name': 'Search', 'arguments': '{\\n \"query\": \"weather in NYC yesterday\"\\n}'}\nFunction: New York Temperature Yesterday. Maximum temperature yesterday: 81 °F (at 1:51 pm) Minimum temperature yesterday: 72 °F (at 7:17 pm) Average temperature ..."
]
}
[llm/end] [1:llm:ChatOpenAI] [2.68s] Exiting LLM run with output:
{
"generations": [
[
{
"text": "Today in NYC, the weather is currently 85°F with a southeast wind of 4 mph. The humidity is at 78% and there is 81% cloud cover. There is no rain expected today.\n\nYesterday in NYC, the maximum temperature was 81°F at 1:51 pm, and the minimum temperature was 72°F at 7:17 pm.\n\nFor the day before yesterday, I do not have the specific weather information.",
"generation_info": null,
"message": {
"lc": 1,
"type": "constructor",
"id": [
"langchain",
"schema",
"messages",
"AIMessage"
],
"kwargs": {
"content": "Today in NYC, the weather is currently 85°F with a southeast wind of 4 mph. The humidity is at 78% and there is 81% cloud cover. There is no rain expected today.\n\nYesterday in NYC, the maximum temperature was 81°F at 1:51 pm, and the minimum temperature was 72°F at 7:17 pm.\n\nFor the day before yesterday, I do not have the specific weather information.",
"additional_kwargs": {}
}
}
}
]
],
"llm_output": {
"token_usage": {
"prompt_tokens": 160,
"completion_tokens": 91,
"total_tokens": 251
},
"model_name": "gpt-3.5-turbo-0613"
},
"run": null
}
[chain/end] [1:chain:AgentExecutor] [10.18s] Exiting Chain run with output:
{
"output": "Today in NYC, the weather is currently 85°F with a southeast wind of 4 mph. The humidity is at 78% and there is 81% cloud cover. There is no rain expected today.\n\nYesterday in NYC, the maximum temperature was 81°F at 1:51 pm, and the minimum temperature was 72°F at 7:17 pm.\n\nFor the day before yesterday, I do not have the specific weather information."
}
'Today in NYC, the weather is currently 85°F with a southeast wind of 4 mph. The humidity is at 78% and there is 81% cloud cover. There is no rain expected today.\n\nYesterday in NYC, the maximum temperature was 81°F at 1:51 pm, and the minimum temperature was 72°F at 7:17 pm.\n\nFor the day before yesterday, I do not have the specific weather information.'
这里请注意，由于达到了 max_iterations 限制，我们从来没有时间去查找前天的天气。
