Multi-step Tool Use (Agents)

! pip install --quiet langchain langchain_cohere langchain_experimental

# You can easily equip your agent with web search!

from langchain_community.tools.tavily_search import TavilySearchResults

os.environ["TAVILY_API_KEY"] = #<your-api-key>

internet_search = TavilySearchResults()
internet_search.name = "internet_search"
internet_search.description = "Returns a list of relevant document snippets for a textual query retrieved from the internet."


from langchain_core.pydantic_v1 import BaseModel, Field
class TavilySearchInput(BaseModel):
   query: str = Field(description="Query to search the internet with")
internet_search.args_schema = TavilySearchInput

# You can easily equip your agent with a Python interpreter!

from langchain.agents import Tool
from langchain_experimental.utilities import PythonREPL

python_repl = PythonREPL()
python_tool = Tool(
   name="python_repl",
   description="Executes python code and returns the result. The code runs in astatic sandbox without interactive mode, so print output or save output to a file.",
   func=python_repl.run,
)
python_tool.name = "python_interpreter"

# from langchain_core.pydantic_v1 import BaseModel, Field
class ToolInput(BaseModel):
   code: str = Field(description="Python code to execute.")
python_tool.args_schema = ToolInput

from langchain_core.tools import tool
import random

@tool
def random_operation_tool(a: int, b: int):
 """Calculates a random operation between the inputs."""
 coin_toss = random.uniform(0, 1)
 if coin_toss > 0.5:
   return {'output': a*b}
 else:
   return {'output': a+b}

random_operation_tool.name = "random_operation" # use python case
random_operation_tool.description = "Calculates a random operation between the inputs."

from langchain_core.pydantic_v1 import BaseModel, Field
class random_operation_inputs(BaseModel):
   a: int = Field(description="First input")
   b: int = Field(description="Second input")
random_operation_tool.args_schema = random_operation_inputs

from langchain.agents import AgentExecutor
from langchain_cohere.react_multi_hop.agent import create_cohere_react_agent
from langchain_core.prompts import ChatPromptTemplate
from langchain_cohere.chat_models import ChatCohere

# LLM
llm = ChatCohere(model="command-r-plus", temperature=0.3)

# Preamble
preamble = """
You are an expert who answers the user's question with the most relevant datasource.
You are equipped with an internet search tool and a special vectorstore of information
about how to write good essays.
"""

# Prompt template
prompt = ChatPromptTemplate.from_template("{input}")

# Create the ReAct agent
agent = create_cohere_react_agent(
   llm=llm,
   tools=[internet_search, vectorstore_search, python_tool],
   prompt=prompt,
)

agent_executor = AgentExecutor(agent=agent,
                               tools=[internet_search, vectorstore_search, python_tool],
                               verbose=True)

agent_executor.invoke({
   "input": "I want to write an essay about the Roman Empire. Any tips for writing an essay? Any fun facts?",
   "preamble": preamble,
})

> Entering new AgentExecutor chain...


# Here is the model plan
I will search for tips on writing an essay and fun facts about the Roman Empire.

 
# The model decides to use a first tool: the vector store
{'tool_name': 'vectorstore_search', 'parameters': {'query': 'tips for writing an essay'}}

# Here are the results from the vector store call: retrieved passages
I should have asked how do you write essays well? Though
these seem only phrasing apart, their answers diverge. [ … more of retrieved snippet 1 … ]

didn't have edge with any of them. To start writing an essay, you
need [ … more of retrieved snippet 2 … ]

You don't have to get an answer right the first time, but there's
no excuse for not getting it right eventually, because [ more of retrieved snippet 3 … ]

  
# The model decides to use another tool: web search
{'tool_name': 'internet_search', 'parameters': {'query': 'fun facts about the roman empire'}}

# Here are the results from the web search call: retrieved passages
[{'url': 'https://www.natgeokids.com/uk/discover/history/romans/10-facts-about-the-ancient-romans/', 'content': 'i love this website\nBIG BOBBY\nbooby\nI love shell my bae;)\ni like bobby fishes ;0\nI like turtles\nOmg soy cool\ngreeeeeeeeeeeeaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaatttttttttttttttttttttttt\nbest fact ever\nthis artical is cool\nHANDY\nrubbish did not help what so ever\nha\nRocking\nTHIS IS THE BEST\nproper rad in it cool\nthis is cool\nawesomeness\nawsome\nawsome\nthank you captain\nit is a lot of help\ni like this\nwebsite it helps me on my projects and isabel likes munier\nmark uses this for research\nlot of help\nthis is awsome\nTHE BEST BOOBOO\nCool webpage helped me get 4 housepoints\n This helped me A LOT on a school project\ncool wow awesomoe\nCOOL WEBSITE LOL\nthis helped me with a school project :)\nthat was awesome\ncool\nthat helped me out for my research test\nReally its very cool really COOL\nLIKE COOL best website so far its nice\nI love it\nnice facts\nIt help with my history\n i mean u made animaljam a awesome nice safe place for kids and this site to have kids a safe website to get facts for reports and stuff\nLots of Love ,\nRose\npretty good website if u ask me\nbut definently not gonna use it on a daily basis\nIll try it again another time\ngood\nCool webcite\nterrible\nquite impressive\nAwesome website it real helps\nits good\nthis is a great website! You really a lot with my project!:)\nthis has helleped\nme get\nmy progect\ndone\nthank you\nsoooooooooooooooooo\nmuchchchchchch\nthis helleped me\nsooooooooo much with my progect thank you\nvery good website\nthank us very much your nice one today!!\n'}, {'url': 'https://ohfact.com/roman-empire-facts/', 'content': 'Learn about the ancient Roman Civilization, its history, culture, army, architecture, food and more from this list of 27 facts. Discover how the Romans started, conquered, lived, died and influenced the world with their legends, myths and facts.'}, {'url': 'https://factnight.com/fun-facts-about-the-roman-empire/', 'content': 'The Roman Empire was one of the most influential and significant civilizations in world history. At its peak, the empire stretched from North Africa to Britain, reigning over 60 million people. From its legendary beginnings and remarkable achievements to its eventual decline and fall, the Roman Empire is a fascinating topic full of little-known facts and intriguing trivia.'}, {'url': 'https://www.historyhit.com/facts-about-ancient-rome-and-the-romans/', 'content': 'The Enduring Legacy of C.S. Lewis\nMargaret J. Winkler: A Forgotten Pioneer in Disney’s Success\n10 Facts About Harper Lee\nAntarctica Expedition Cruise\nUncover Pompeii\nSophie Hay and Tristan Hughes\nRediscovering Richard III with Matt Lewis\nOrder the History Hit Miscellany\nHistory Hit Holidays\nGift Subscriptions\n100 Facts About Ancient Rome and the Romans\nRome wasn’t built in a day, as the cliché reminds us. The Crossing of the Rhine in 405/6 AD brought around 100,000 barbarians into the Empire\nBarbarian factions, tribes and war leaders were now a factor in the power struggles at the top of Roman politics and one of the once-strong boundaries of the Empire had proved to be permeable.\n Related Articles\n10 Facts About Saint Andrew\nThe Rise of Pompey the Great, the ‘Roman Alexander’\nWatch and Listen\nCleopatra\nSex in Ancient Rome\nRelated Locations\nBaelo Claudia\nMausoleum of Cecilia Metella\nColin Ricketts\n30 July 2021\n By the fourth century BC, the story was accepted by Romans who were proud of their warrior founder\nThe story was included in the first history of the city, by the Greek writer Diocles of Peparethus, and the twins and their wolf step-mother were depicted on Rome’s first coins.\n The History Hit Miscellany of Facts, Figures and Fascinating Finds\nA History of England: Part One\nDragons: Myth & Reality\nA Tudor Wonder - Hardwick Hall\nThe Battle of Shrewsbury\nEurope’s 1848 Revolutions\nThe Boston Tea Party\nHow Did 3 People Seemingly Escape From Alcatraz?\n'}, {'url': 'https://www.countryfaq.com/facts-about-the-roman-empire/', 'content': 'Facts about the Roman Empire. Explore some of the interesting, fun, cool facts bout the Roman Empire: 1. The Magnificent Roman Empire. The Roman Empire, a colossal entity of unparalleled grandeur, occupies an indomitable position within the annals of human history, a name that resonates resoundingly across the eons.'}]Relevant Documents: 0,3,4,5

  
# The model decides it has enough info to generate a final response.
  
# Below is the answer by the model
Answer: Here are some tips for writing an essay:
- Start with a question that spurs some response.
- Don't choose a topic at random, make sure you have a way in, a new insight or approach.
- You don't need a complete thesis, just a gap to explore.
- You can get ideas by talking to people, reading, doing and building things, and going places and seeing things.
- You can improve the quality of your ideas by increasing the breadth and depth of what goes in.
- You can get breadth by reading and talking about a wide range of topics.
- You can get depth by doing and having to solve problems.
- You can also get ideas by talking to people who make you have new ideas.

Here are some fun facts about the Roman Empire:
- At its peak, the empire stretched from North Africa to Britain, reigning over 60 million people.
- The story of Rome's warrior founder and the twins and their wolf step-mother was depicted on Rome's first coins.
- The Crossing of the Rhine in 405/6 AD brought around 100,000 barbarians into the Empire.

# Below is the answer by the model, with citations!
Cited Documents: 0,3,4,5
Grounded answer: Here are some tips for writing an essay:
- <co: 0>Start with a question that spurs some response</co: 0>.
- <co: 0>Don't choose a topic at random, make sure you have a way in, a new insight or approach</co: 0>.
- <co: 0>You don't need a complete thesis, just a gap to explore</co: 0>.
- <co: 0>You can get ideas by talking to people, reading, doing and building things, and going places and seeing things</co: 0>.
- <co: 0>You can improve the quality of your ideas by increasing the breadth and depth of what goes in</co: 0>.
- <co: 0>You can get breadth by reading and talking about a wide range of topics</co: 0>.
- <co: 0>You can get depth by doing and having to solve problems</co: 0>.
- <co: 0>You can also get ideas by talking to people who make you have new ideas</co: 0>.

Here are some fun facts about the Roman Empire:
- <co: 3>At its peak, the empire stretched from North Africa to Britain, reigning over 60 million people</co: 3>.
- <co: 4>The story of Rome's warrior founder and the twins and their wolf step-mother was depicted on Rome's first coins</co: 4>.
- <co: 4>The Crossing of the Rhine in 405/6 AD brought around 100,000 barbarians into the Empire</co: 4>.

> Finished chain.

# You can easily equip your agent with a vector store!

from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.document_loaders import WebBaseLoader
from langchain_community.vectorstores import FAISS
from langchain_cohere import CohereEmbeddings

# Set embeddings
embd = CohereEmbeddings()

# Docs to index
urls = [
   "https://paulgraham.com/best.html",
]

# Load
docs = [WebBaseLoader(url).load() for url in urls]
docs_list = [item for sublist in docs for item in sublist]

# Split
text_splitter = RecursiveCharacterTextSplitter.from_tiktoken_encoder(
   chunk_size=512, chunk_overlap=0
)
doc_splits = text_splitter.split_documents(docs_list)

# Add to vectorstore
vectorstore = FAISS.from_documents(
   documents=doc_splits,
   embedding=embd,
)

vectorstore_retriever = vectorstore.as_retriever()


from langchain.tools.retriever import create_retriever_tool

vectorstore_search = create_retriever_tool(
   retriever=vectorstore_retriever,
   name="vectorstore_search",
   description="Retrieve relevant info from a vectorstore that contains information from Paul Graham about how to write good essays."
)

# Step 1: Construct the chat history as a list of LangChain Messages, ending with the last user message
from langchain_core.messages import HumanMessage, AIMessage

chat_history = [
   HumanMessage(content="I'm considering switching to Oracle for my CRM."),
   AIMessage(content="That sounds like a good idea! How can I help you?"),
   HumanMessage(content="Recap all the info you can find about their offering."),
]

prompt = ChatPromptTemplate.from_messages(chat_history)

# Step 2: When you make the agent, specify the chat_history as the prompt
agent = create_cohere_react_agent(
   llm=llm,
   tools=[internet_search, vectorstore_search, python_tool],
   prompt=prompt,
)

agent_executor = AgentExecutor(agent=agent,
                               tools=[internet_search, vectorstore_search, python_tool],
                               verbose=True)

# Step 3: When you invoke the agent_executor there's no need to pass anything else into invoke
response = agent_executor.invoke({
   "preamble": preamble,
})

response['output']

agent_executor.invoke({
   "input": "Hey how are you?",
})

> Entering new AgentExecutor chain...
Plan: I will respond to the user's greeting.
Action: ```json
[
    {
        "tool_name": "directly_answer",
        "parameters": {}
    }
]
```
Answer: Hey, I'm doing well, thank you for asking! How can I help you today?
Grounded answer: Hey, I'm doing well, thank you for asking! How can I help you today?

> Finished chain.

{'input': 'Hey how are you?',
 'output': "Hey, I'm doing well, thank you for asking! How can I help you today?",
 'intermediate_steps': []}