langchain agent

 zero-shot-react-description

代码

from langchain.agents import initialize_agent
from langchain.llms import OpenAI
from langchain.tools import BaseTool
import os
os.environ['OPENAI_API_KEY']="sk-xxx"

# 搜索工具
class SearchTool(BaseTool):
    name = "Search"
    description = "如果我想知道天气，'鸡你太美'这两个问题时，请使用它"
    return_direct = True  # 直接返回结果

    def _run(self, query: str) -> str:
        print("\nSearchTool query: " + query)
        return "这个是一个通用的返回"

    async def _arun(self, query: str) -> str:
        raise NotImplementedError("暂时不支持异步")


# 计算工具
class CalculatorTool(BaseTool):
    name = "Calculator"
    description = "如果是关于数学计算的问题，请使用它"

    def _run(self, query: str) -> str:
        print("\nCalculatorTool query: " + query)
        return "100"

    async def _arun(self, query: str) -> str:
        raise NotImplementedError("暂时不支持异步")


llm = OpenAI(temperature=0.5)
tools = [SearchTool(), CalculatorTool()]
agent = initialize_agent(
    tools, llm, agent="zero-shot-react-description", verbose=True)

print("问题：")
print("答案：" + agent.run("查询这周天气"))
print("问题：")
print("答案：" + agent.run("告诉我'鸡你太美'是什么意思"))
print("问题：")
print("答案：" + agent.run("告诉我'hello world'是什么意思"))
print("问题：")
print("答案：" + agent.run("告诉我10的3次方是多少?"))

 以上代码构造如下prompt

Answer the following questions as best you can. You have access to the following tools:

Search: 如果我想知道天气，'鸡你太美'这两个问题时，请使用它
Calculator: 如果是关于数学计算的问题，请使用它

Use the following format:

Question: the input question you must answer
Thought: you should always think about what to do
Action: the action to take, should be one of [Search, Calculator]
Action Input: the input to the action
Observation: the result of the action
... (this Thought/Action/Action Input/Observation can repeat N times)
Thought: I now know the final answer
Final Answer: the final answer to the original input question

Begin!

Question: 查询这周天气
Thought:

prompt模板：

PREFIX = """Answer the following questions as best you can. You have access to the following tools:"""
FORMAT_INSTRUCTIONS = """Use the following format:

Question: the input question you must answer
Thought: you should always think about what to do
Action: the action to take, should be one of [{tool_names}]
Action Input: the input to the action
Observation: the result of the action
... (this Thought/Action/Action Input/Observation can repeat N times)
Thought: I now know the final answer
Final Answer: the final answer to the original input question"""
SUFFIX = """Begin!

Question: {input}
Thought:{agent_scratchpad}"""

示例二

代码

import os
os.environ['SERPAPI_API_KEY']="xxx"

from langchain.agents import Tool
from langchain.agents import AgentType
from langchain.memory import ConversationBufferMemory
from langchain import OpenAI
from langchain.utilities import SerpAPIWrapper
from langchain.agents import initialize_agent
import os
os.environ['OPENAI_API_KEY']="sk-xxx"
search = SerpAPIWrapper()
tools = [
    Tool(
        name = "Current Search",
        func=search.run,
        description="useful for when you need to answer questions about current events or the current state of the world"
    ),
]

memory = ConversationBufferMemory(memory_key="chat_history")

llm=OpenAI(temperature=0)
agent_chain = initialize_agent(tools, llm, agent=AgentType.CONVERSATIONAL_REACT_DESCRIPTION, verbose=True, memory=memory)
agent_chain.run(input="hi, i am bob")
agent_chain.run(input="what's my name?")
agent_chain.run("what are some good dinners to make this week, if i like thai food?")
agent_chain.run(input="tell me the last letter in my name, and also tell me who won the world cup in 1978?")
agent_chain.run(input="whats the current temperature in pomfret?")

以上代码使用如下的prompt

Assistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

TOOLS:
------

Assistant has access to the following tools:

> Current Search: useful for when you need to answer questions about current events or the current state of the world

To use a tool, please use the following format:

```
Thought: Do I need to use a tool? Yes
Action: the action to take, should be one of [Current Search]
Action Input: the input to the action
Observation: the result of the action
```

When you have a response to say to the Human, or if you do not need to use a tool, you MUST use the format:

```
Thought: Do I need to use a tool? No
AI: [your response here]
```

Begin!

Previous conversation history:
Human: hi, i am bob
AI: Hi Bob, nice to meet you! How can I help you today?
Human: what's my name?
AI: Your name is Bob!

New input: what are some good dinners to make this week, if i like thai food?

prompt 模板：

# flake8: noqa
PREFIX = """Assistant is a large language model trained by OpenAI.

Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.

Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.

TOOLS:
------

Assistant has access to the following tools:"""
FORMAT_INSTRUCTIONS = """To use a tool, please use the following format:

```
Thought: Do I need to use a tool? Yes
Action: the action to take, should be one of [{tool_names}]
Action Input: the input to the action
Observation: the result of the action
```

When you have a response to say to the Human, or if you do not need to use a tool, you MUST use the format:

```
Thought: Do I need to use a tool? No
{ai_prefix}: [your response here]
```"""

SUFFIX = """Begin!

Previous conversation history:
{chat_history}

New input: {input}
{agent_scratchpad}"""

llm_math_chain

每一步action，可以是另外一个chain，

代码示例：

# Import things that are needed generically
import os
os.environ['SERPAPI_API_KEY']="111xxxx"
os.environ['OPENAI_API_KEY']="sk-xxxxxx"
from langchain import LLMMathChain, SerpAPIWrapper
from langchain.agents import AgentType, initialize_agent
from langchain.chat_models import ChatOpenAI
from langchain.tools import BaseTool, StructuredTool, Tool, tool
from pydantic import BaseModel, Field
llm = ChatOpenAI(temperature=0)


# Load the tool configs that are needed.
search = SerpAPIWrapper()
llm_math_chain = LLMMathChain(llm=llm, verbose=True)

from typing import Optional, Type

from langchain.callbacks.manager import (
    AsyncCallbackManagerForToolRun,
    CallbackManagerForToolRun,
)


class CustomSearchTool(BaseTool):
    name = "custom_search"
    description = "useful for when you need to answer questions about current events"

    def _run(
        self, query: str, run_manager: Optional[CallbackManagerForToolRun] = None
    ) -> str:
        """Use the tool."""
        return search.run(query)

    async def _arun(
        self, query: str, run_manager: Optional[AsyncCallbackManagerForToolRun] = None
    ) -> str:
        """Use the tool asynchronously."""
        raise NotImplementedError("custom_search does not support async")



class CalculatorInput(BaseModel):
    question: str = Field()

class CustomCalculatorTool(BaseTool):
    name = "Calculator"
    description = "useful for when you need to answer questions about math"
    args_schema: Type[BaseModel] = CalculatorInput

    def _run(
        self, query: str, run_manager: Optional[CallbackManagerForToolRun] = None
    ) -> str:
        """Use the tool."""
        return llm_math_chain.run(query)

    async def _arun(
        self, query: str, run_manager: Optional[AsyncCallbackManagerForToolRun] = None
    ) -> str:
        """Use the tool asynchronously."""
        raise NotImplementedError("Calculator does not support async")
tools = [CustomSearchTool(), CustomCalculatorTool()]
agent = initialize_agent(
    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
)

agent.run(
    "Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?"
)

prompt

Translate a math problem into a expression that can be executed using Python's numexpr library. Use the output of running this code to answer the question.

Question: ${Question with math problem.}
```text
${single line mathematical expression that solves the problem}
```
...numexpr.evaluate(text)...
```output
${Output of running the code}
```
Answer: ${Answer}

Begin.

Question: What is 37593 * 67?
```text
37593 * 67
```
...numexpr.evaluate("37593 * 67")...
```output
2518731
```
Answer: 2518731

Question: 37593^(1/5)
```text
37593**(1/5)
```
...numexpr.evaluate("37593**(1/5)")...
```output
8.222831614237718
```
Answer: 8.222831614237718

Question: 19 ^ 0.43

prompt模板：

 """Translate a math problem into a expression that can be executed using Python's numexpr library. Use the output of running this code to answer the question.

Question: ${{Question with math problem.}}
```text
${{single line mathematical expression that solves the problem}}
```
...numexpr.evaluate(text)...
```output
${{Output of running the code}}
```
Answer: ${{Answer}}

Begin.

Question: What is 37593 * 67?
```text
37593 * 67
```
...numexpr.evaluate("37593 * 67")...
```output
2518731
```
Answer: 2518731

Question: 37593^(1/5)
```text
37593**(1/5)
```
...numexpr.evaluate("37593**(1/5)")...
```output
8.222831614237718
```
Answer: 8.222831614237718

Question: {question}
"""

STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION

核心思想：工具如果需要多种输入，也需要将参数一起构建进prompt当中

代码示例

import os
os.environ['SERPAPI_API_KEY']="23123"
os.environ['OPENAI_API_KEY']="sk-232323"
os.environ["LANGCHAIN_TRACING"] = "true"
from langchain import OpenAI
from langchain.agents import initialize_agent, AgentType

llm = OpenAI(temperature=0)
from langchain.tools import StructuredTool


def multiplier(a: float, b: float) -> float:
    """Multiply the provided floats."""
    return a * b


tool = StructuredTool.from_function(multiplier)
# Structured tools are compatible with the STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION agent type.
agent_executor = initialize_agent(
    [tool],
    llm,
    agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION,
    verbose=True,
)

agent_executor.run("What is 3 times 4")

prompt

System: Respond to the human as helpfully and accurately as possible. You have access to the following tools:

multiplier: multiplier(a: float, b: float) -> float - Multiply the provided floats., args: {{'a': {{'title': 'A', 'type': 'number'}}, 'b': {{'title': 'B', 'type': 'number'}}}}

Use a json blob to specify a tool by providing an action key (tool name) and an action_input key (tool input).

Valid "action" values: "Final Answer" or multiplier

Provide only ONE action per $JSON_BLOB, as shown:

```
{
  "action": $TOOL_NAME,
  "action_input": $INPUT
}
```

Follow this format:

Question: input question to answer
Thought: consider previous and subsequent steps
Action:
```
$JSON_BLOB
```
Observation: action result
... (repeat Thought/Action/Observation N times)
Thought: I know what to respond
Action:
```
{
  "action": "Final Answer",
  "action_input": "Final response to human"
}
```

Begin! Reminder to ALWAYS respond with a valid json blob of a single action. Use tools if necessary. Respond directly if appropriate. Format is Action:```$JSON_BLOB```then Observation:.
Thought:
Human: What is 3 times 4

This was your previous work (but I haven't seen any of it! I only see what you return as final answer):
Action:
```
{
  "action": "multiplier",
  "action_input": {"a": 3, "b": 4}
}
```


Observation: 12.0
Thought: