langchain/docs/snippets/get_started/quickstart/agents_llms.mdx
Davis Chase 87e502c6bc
Doc refactor (#6300)
Co-authored-by: jacoblee93 <jacoblee93@gmail.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 11:52:56 -07:00

38 lines
1.5 KiB
Plaintext

```python
from langchain.agents import AgentType, initialize_agent, load_tools
from langchain.llms import OpenAI
# The language model we're going to use to control the agent.
llm = OpenAI(temperature=0)
# The tools we'll give the Agent access to. Note that the 'llm-math' tool uses an LLM, so we need to pass that in.
tools = load_tools(["serpapi", "llm-math"], llm=llm)
# Finally, let's initialize an agent with the tools, the language model, and the type of agent we want to use.
agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
# Let's test it out!
agent.run("What was the high temperature in SF yesterday in Fahrenheit? What is that number raised to the .023 power?")
```
```pycon
> Entering new AgentExecutor chain...
Thought: I need to find the temperature first, then use the calculator to raise it to the .023 power.
Action: Search
Action Input: "High temperature in SF yesterday"
Observation: San Francisco Temperature Yesterday. Maximum temperature yesterday: 57 °F (at 1:56 pm) Minimum temperature yesterday: 49 °F (at 1:56 am) Average temperature ...
Thought: I now have the temperature, so I can use the calculator to raise it to the .023 power.
Action: Calculator
Action Input: 57^.023
Observation: Answer: 1.0974509573251117
Thought: I now know the final answer
Final Answer: The high temperature in SF yesterday in Fahrenheit raised to the .023 power is 1.0974509573251117.
> Finished chain.
```
```pycon
The high temperature in SF yesterday in Fahrenheit raised to the .023 power is 1.0974509573251117.
```