2022-12-30 13:06:57 +00:00
{
"cells": [
{
"cell_type": "markdown",
"id": "6510f51c",
"metadata": {},
"source": [
"# Search Tools\n",
"\n",
"This notebook shows off usage of various search tools."
]
},
{
"cell_type": "code",
2023-03-04 04:57:50 +00:00
"execution_count": 2,
2022-12-30 13:06:57 +00:00
"id": "e6860c2d",
Google Search API integration with serper.dev (wrapper, tests, docs, … (#909)
Adds Google Search integration with [Serper](https://serper.dev) a
low-cost alternative to SerpAPI (10x cheaper + generous free tier).
Includes documentation, tests and examples. Hopefully I am not missing
anything.
Developers can sign up for a free account at
[serper.dev](https://serper.dev) and obtain an api key.
## Usage
```python
from langchain.utilities import GoogleSerperAPIWrapper
from langchain.llms.openai import OpenAI
from langchain.agents import initialize_agent, Tool
import os
os.environ["SERPER_API_KEY"] = ""
os.environ['OPENAI_API_KEY'] = ""
llm = OpenAI(temperature=0)
search = GoogleSerperAPIWrapper()
tools = [
Tool(
name="Intermediate Answer",
func=search.run
)
]
self_ask_with_search = initialize_agent(tools, llm, agent="self-ask-with-search", verbose=True)
self_ask_with_search.run("What is the hometown of the reigning men's U.S. Open champion?")
```
### Output
```
Entering new AgentExecutor chain...
Yes.
Follow up: Who is the reigning men's U.S. Open champion?
Intermediate answer: Current champions Carlos Alcaraz, 2022 men's singles champion.
Follow up: Where is Carlos Alcaraz from?
Intermediate answer: El Palmar, Spain
So the final answer is: El Palmar, Spain
> Finished chain.
'El Palmar, Spain'
```
2023-02-16 06:47:17 +00:00
"metadata": {
"pycharm": {
"is_executing": true
}
},
2022-12-30 13:06:57 +00:00
"outputs": [],
"source": [
"from langchain.agents import load_tools\n",
"from langchain.agents import initialize_agent\n",
2023-04-04 14:21:50 +00:00
"from langchain.agents import AgentType\n",
2022-12-30 13:06:57 +00:00
"from langchain.llms import OpenAI"
]
},
{
"cell_type": "code",
2023-03-04 04:57:50 +00:00
"execution_count": 3,
2022-12-30 13:06:57 +00:00
"id": "dadbcfcd",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)"
]
},
{
"cell_type": "markdown",
2023-02-18 21:40:43 +00:00
"id": "ee251155",
"metadata": {},
Google Search API integration with serper.dev (wrapper, tests, docs, … (#909)
Adds Google Search integration with [Serper](https://serper.dev) a
low-cost alternative to SerpAPI (10x cheaper + generous free tier).
Includes documentation, tests and examples. Hopefully I am not missing
anything.
Developers can sign up for a free account at
[serper.dev](https://serper.dev) and obtain an api key.
## Usage
```python
from langchain.utilities import GoogleSerperAPIWrapper
from langchain.llms.openai import OpenAI
from langchain.agents import initialize_agent, Tool
import os
os.environ["SERPER_API_KEY"] = ""
os.environ['OPENAI_API_KEY'] = ""
llm = OpenAI(temperature=0)
search = GoogleSerperAPIWrapper()
tools = [
Tool(
name="Intermediate Answer",
func=search.run
)
]
self_ask_with_search = initialize_agent(tools, llm, agent="self-ask-with-search", verbose=True)
self_ask_with_search.run("What is the hometown of the reigning men's U.S. Open champion?")
```
### Output
```
Entering new AgentExecutor chain...
Yes.
Follow up: Who is the reigning men's U.S. Open champion?
Intermediate answer: Current champions Carlos Alcaraz, 2022 men's singles champion.
Follow up: Where is Carlos Alcaraz from?
Intermediate answer: El Palmar, Spain
So the final answer is: El Palmar, Spain
> Finished chain.
'El Palmar, Spain'
```
2023-02-16 06:47:17 +00:00
"source": [
"## Google Serper API Wrapper\n",
"\n",
"First, let's try to use the Google Serper API tool."
2023-02-18 21:40:43 +00:00
]
Google Search API integration with serper.dev (wrapper, tests, docs, … (#909)
Adds Google Search integration with [Serper](https://serper.dev) a
low-cost alternative to SerpAPI (10x cheaper + generous free tier).
Includes documentation, tests and examples. Hopefully I am not missing
anything.
Developers can sign up for a free account at
[serper.dev](https://serper.dev) and obtain an api key.
## Usage
```python
from langchain.utilities import GoogleSerperAPIWrapper
from langchain.llms.openai import OpenAI
from langchain.agents import initialize_agent, Tool
import os
os.environ["SERPER_API_KEY"] = ""
os.environ['OPENAI_API_KEY'] = ""
llm = OpenAI(temperature=0)
search = GoogleSerperAPIWrapper()
tools = [
Tool(
name="Intermediate Answer",
func=search.run
)
]
self_ask_with_search = initialize_agent(tools, llm, agent="self-ask-with-search", verbose=True)
self_ask_with_search.run("What is the hometown of the reigning men's U.S. Open champion?")
```
### Output
```
Entering new AgentExecutor chain...
Yes.
Follow up: Who is the reigning men's U.S. Open champion?
Intermediate answer: Current champions Carlos Alcaraz, 2022 men's singles champion.
Follow up: Where is Carlos Alcaraz from?
Intermediate answer: El Palmar, Spain
So the final answer is: El Palmar, Spain
> Finished chain.
'El Palmar, Spain'
```
2023-02-16 06:47:17 +00:00
},
{
"cell_type": "code",
2023-02-18 21:40:43 +00:00
"execution_count": 6,
"id": "0cdaa487",
"metadata": {},
Google Search API integration with serper.dev (wrapper, tests, docs, … (#909)
Adds Google Search integration with [Serper](https://serper.dev) a
low-cost alternative to SerpAPI (10x cheaper + generous free tier).
Includes documentation, tests and examples. Hopefully I am not missing
anything.
Developers can sign up for a free account at
[serper.dev](https://serper.dev) and obtain an api key.
## Usage
```python
from langchain.utilities import GoogleSerperAPIWrapper
from langchain.llms.openai import OpenAI
from langchain.agents import initialize_agent, Tool
import os
os.environ["SERPER_API_KEY"] = ""
os.environ['OPENAI_API_KEY'] = ""
llm = OpenAI(temperature=0)
search = GoogleSerperAPIWrapper()
tools = [
Tool(
name="Intermediate Answer",
func=search.run
)
]
self_ask_with_search = initialize_agent(tools, llm, agent="self-ask-with-search", verbose=True)
self_ask_with_search.run("What is the hometown of the reigning men's U.S. Open champion?")
```
### Output
```
Entering new AgentExecutor chain...
Yes.
Follow up: Who is the reigning men's U.S. Open champion?
Intermediate answer: Current champions Carlos Alcaraz, 2022 men's singles champion.
Follow up: Where is Carlos Alcaraz from?
Intermediate answer: El Palmar, Spain
So the final answer is: El Palmar, Spain
> Finished chain.
'El Palmar, Spain'
```
2023-02-16 06:47:17 +00:00
"outputs": [],
"source": [
"tools = load_tools([\"google-serper\"], llm=llm)"
2023-02-18 21:40:43 +00:00
]
Google Search API integration with serper.dev (wrapper, tests, docs, … (#909)
Adds Google Search integration with [Serper](https://serper.dev) a
low-cost alternative to SerpAPI (10x cheaper + generous free tier).
Includes documentation, tests and examples. Hopefully I am not missing
anything.
Developers can sign up for a free account at
[serper.dev](https://serper.dev) and obtain an api key.
## Usage
```python
from langchain.utilities import GoogleSerperAPIWrapper
from langchain.llms.openai import OpenAI
from langchain.agents import initialize_agent, Tool
import os
os.environ["SERPER_API_KEY"] = ""
os.environ['OPENAI_API_KEY'] = ""
llm = OpenAI(temperature=0)
search = GoogleSerperAPIWrapper()
tools = [
Tool(
name="Intermediate Answer",
func=search.run
)
]
self_ask_with_search = initialize_agent(tools, llm, agent="self-ask-with-search", verbose=True)
self_ask_with_search.run("What is the hometown of the reigning men's U.S. Open champion?")
```
### Output
```
Entering new AgentExecutor chain...
Yes.
Follow up: Who is the reigning men's U.S. Open champion?
Intermediate answer: Current champions Carlos Alcaraz, 2022 men's singles champion.
Follow up: Where is Carlos Alcaraz from?
Intermediate answer: El Palmar, Spain
So the final answer is: El Palmar, Spain
> Finished chain.
'El Palmar, Spain'
```
2023-02-16 06:47:17 +00:00
},
{
"cell_type": "code",
2023-02-18 21:40:43 +00:00
"execution_count": 7,
"id": "01b1ab4a",
"metadata": {},
Google Search API integration with serper.dev (wrapper, tests, docs, … (#909)
Adds Google Search integration with [Serper](https://serper.dev) a
low-cost alternative to SerpAPI (10x cheaper + generous free tier).
Includes documentation, tests and examples. Hopefully I am not missing
anything.
Developers can sign up for a free account at
[serper.dev](https://serper.dev) and obtain an api key.
## Usage
```python
from langchain.utilities import GoogleSerperAPIWrapper
from langchain.llms.openai import OpenAI
from langchain.agents import initialize_agent, Tool
import os
os.environ["SERPER_API_KEY"] = ""
os.environ['OPENAI_API_KEY'] = ""
llm = OpenAI(temperature=0)
search = GoogleSerperAPIWrapper()
tools = [
Tool(
name="Intermediate Answer",
func=search.run
)
]
self_ask_with_search = initialize_agent(tools, llm, agent="self-ask-with-search", verbose=True)
self_ask_with_search.run("What is the hometown of the reigning men's U.S. Open champion?")
```
### Output
```
Entering new AgentExecutor chain...
Yes.
Follow up: Who is the reigning men's U.S. Open champion?
Intermediate answer: Current champions Carlos Alcaraz, 2022 men's singles champion.
Follow up: Where is Carlos Alcaraz from?
Intermediate answer: El Palmar, Spain
So the final answer is: El Palmar, Spain
> Finished chain.
'El Palmar, Spain'
```
2023-02-16 06:47:17 +00:00
"outputs": [],
"source": [
2023-04-04 04:56:20 +00:00
"agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)"
2023-02-18 21:40:43 +00:00
]
Google Search API integration with serper.dev (wrapper, tests, docs, … (#909)
Adds Google Search integration with [Serper](https://serper.dev) a
low-cost alternative to SerpAPI (10x cheaper + generous free tier).
Includes documentation, tests and examples. Hopefully I am not missing
anything.
Developers can sign up for a free account at
[serper.dev](https://serper.dev) and obtain an api key.
## Usage
```python
from langchain.utilities import GoogleSerperAPIWrapper
from langchain.llms.openai import OpenAI
from langchain.agents import initialize_agent, Tool
import os
os.environ["SERPER_API_KEY"] = ""
os.environ['OPENAI_API_KEY'] = ""
llm = OpenAI(temperature=0)
search = GoogleSerperAPIWrapper()
tools = [
Tool(
name="Intermediate Answer",
func=search.run
)
]
self_ask_with_search = initialize_agent(tools, llm, agent="self-ask-with-search", verbose=True)
self_ask_with_search.run("What is the hometown of the reigning men's U.S. Open champion?")
```
### Output
```
Entering new AgentExecutor chain...
Yes.
Follow up: Who is the reigning men's U.S. Open champion?
Intermediate answer: Current champions Carlos Alcaraz, 2022 men's singles champion.
Follow up: Where is Carlos Alcaraz from?
Intermediate answer: El Palmar, Spain
So the final answer is: El Palmar, Spain
> Finished chain.
'El Palmar, Spain'
```
2023-02-16 06:47:17 +00:00
},
{
"cell_type": "code",
2023-02-18 21:40:43 +00:00
"execution_count": 8,
"id": "5cf44ec0",
"metadata": {},
Google Search API integration with serper.dev (wrapper, tests, docs, … (#909)
Adds Google Search integration with [Serper](https://serper.dev) a
low-cost alternative to SerpAPI (10x cheaper + generous free tier).
Includes documentation, tests and examples. Hopefully I am not missing
anything.
Developers can sign up for a free account at
[serper.dev](https://serper.dev) and obtain an api key.
## Usage
```python
from langchain.utilities import GoogleSerperAPIWrapper
from langchain.llms.openai import OpenAI
from langchain.agents import initialize_agent, Tool
import os
os.environ["SERPER_API_KEY"] = ""
os.environ['OPENAI_API_KEY'] = ""
llm = OpenAI(temperature=0)
search = GoogleSerperAPIWrapper()
tools = [
Tool(
name="Intermediate Answer",
func=search.run
)
]
self_ask_with_search = initialize_agent(tools, llm, agent="self-ask-with-search", verbose=True)
self_ask_with_search.run("What is the hometown of the reigning men's U.S. Open champion?")
```
### Output
```
Entering new AgentExecutor chain...
Yes.
Follow up: Who is the reigning men's U.S. Open champion?
Intermediate answer: Current champions Carlos Alcaraz, 2022 men's singles champion.
Follow up: Where is Carlos Alcaraz from?
Intermediate answer: El Palmar, Spain
So the final answer is: El Palmar, Spain
> Finished chain.
'El Palmar, Spain'
```
2023-02-16 06:47:17 +00:00
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
2023-02-18 21:40:43 +00:00
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I should look up the current weather conditions.\n",
Google Search API integration with serper.dev (wrapper, tests, docs, … (#909)
Adds Google Search integration with [Serper](https://serper.dev) a
low-cost alternative to SerpAPI (10x cheaper + generous free tier).
Includes documentation, tests and examples. Hopefully I am not missing
anything.
Developers can sign up for a free account at
[serper.dev](https://serper.dev) and obtain an api key.
## Usage
```python
from langchain.utilities import GoogleSerperAPIWrapper
from langchain.llms.openai import OpenAI
from langchain.agents import initialize_agent, Tool
import os
os.environ["SERPER_API_KEY"] = ""
os.environ['OPENAI_API_KEY'] = ""
llm = OpenAI(temperature=0)
search = GoogleSerperAPIWrapper()
tools = [
Tool(
name="Intermediate Answer",
func=search.run
)
]
self_ask_with_search = initialize_agent(tools, llm, agent="self-ask-with-search", verbose=True)
self_ask_with_search.run("What is the hometown of the reigning men's U.S. Open champion?")
```
### Output
```
Entering new AgentExecutor chain...
Yes.
Follow up: Who is the reigning men's U.S. Open champion?
Intermediate answer: Current champions Carlos Alcaraz, 2022 men's singles champion.
Follow up: Where is Carlos Alcaraz from?
Intermediate answer: El Palmar, Spain
So the final answer is: El Palmar, Spain
> Finished chain.
'El Palmar, Spain'
```
2023-02-16 06:47:17 +00:00
"Action: Search\n",
2023-02-18 21:40:43 +00:00
"Action Input: \"weather in Pomfret\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m37°F\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the current temperature in Pomfret.\n",
"Final Answer: The current temperature in Pomfret is 37°F.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
Google Search API integration with serper.dev (wrapper, tests, docs, … (#909)
Adds Google Search integration with [Serper](https://serper.dev) a
low-cost alternative to SerpAPI (10x cheaper + generous free tier).
Includes documentation, tests and examples. Hopefully I am not missing
anything.
Developers can sign up for a free account at
[serper.dev](https://serper.dev) and obtain an api key.
## Usage
```python
from langchain.utilities import GoogleSerperAPIWrapper
from langchain.llms.openai import OpenAI
from langchain.agents import initialize_agent, Tool
import os
os.environ["SERPER_API_KEY"] = ""
os.environ['OPENAI_API_KEY'] = ""
llm = OpenAI(temperature=0)
search = GoogleSerperAPIWrapper()
tools = [
Tool(
name="Intermediate Answer",
func=search.run
)
]
self_ask_with_search = initialize_agent(tools, llm, agent="self-ask-with-search", verbose=True)
self_ask_with_search.run("What is the hometown of the reigning men's U.S. Open champion?")
```
### Output
```
Entering new AgentExecutor chain...
Yes.
Follow up: Who is the reigning men's U.S. Open champion?
Intermediate answer: Current champions Carlos Alcaraz, 2022 men's singles champion.
Follow up: Where is Carlos Alcaraz from?
Intermediate answer: El Palmar, Spain
So the final answer is: El Palmar, Spain
> Finished chain.
'El Palmar, Spain'
```
2023-02-16 06:47:17 +00:00
]
},
{
"data": {
"text/plain": [
2023-02-18 21:40:43 +00:00
"'The current temperature in Pomfret is 37°F.'"
Google Search API integration with serper.dev (wrapper, tests, docs, … (#909)
Adds Google Search integration with [Serper](https://serper.dev) a
low-cost alternative to SerpAPI (10x cheaper + generous free tier).
Includes documentation, tests and examples. Hopefully I am not missing
anything.
Developers can sign up for a free account at
[serper.dev](https://serper.dev) and obtain an api key.
## Usage
```python
from langchain.utilities import GoogleSerperAPIWrapper
from langchain.llms.openai import OpenAI
from langchain.agents import initialize_agent, Tool
import os
os.environ["SERPER_API_KEY"] = ""
os.environ['OPENAI_API_KEY'] = ""
llm = OpenAI(temperature=0)
search = GoogleSerperAPIWrapper()
tools = [
Tool(
name="Intermediate Answer",
func=search.run
)
]
self_ask_with_search = initialize_agent(tools, llm, agent="self-ask-with-search", verbose=True)
self_ask_with_search.run("What is the hometown of the reigning men's U.S. Open champion?")
```
### Output
```
Entering new AgentExecutor chain...
Yes.
Follow up: Who is the reigning men's U.S. Open champion?
Intermediate answer: Current champions Carlos Alcaraz, 2022 men's singles champion.
Follow up: Where is Carlos Alcaraz from?
Intermediate answer: El Palmar, Spain
So the final answer is: El Palmar, Spain
> Finished chain.
'El Palmar, Spain'
```
2023-02-16 06:47:17 +00:00
]
},
2023-02-18 21:40:43 +00:00
"execution_count": 8,
Google Search API integration with serper.dev (wrapper, tests, docs, … (#909)
Adds Google Search integration with [Serper](https://serper.dev) a
low-cost alternative to SerpAPI (10x cheaper + generous free tier).
Includes documentation, tests and examples. Hopefully I am not missing
anything.
Developers can sign up for a free account at
[serper.dev](https://serper.dev) and obtain an api key.
## Usage
```python
from langchain.utilities import GoogleSerperAPIWrapper
from langchain.llms.openai import OpenAI
from langchain.agents import initialize_agent, Tool
import os
os.environ["SERPER_API_KEY"] = ""
os.environ['OPENAI_API_KEY'] = ""
llm = OpenAI(temperature=0)
search = GoogleSerperAPIWrapper()
tools = [
Tool(
name="Intermediate Answer",
func=search.run
)
]
self_ask_with_search = initialize_agent(tools, llm, agent="self-ask-with-search", verbose=True)
self_ask_with_search.run("What is the hometown of the reigning men's U.S. Open champion?")
```
### Output
```
Entering new AgentExecutor chain...
Yes.
Follow up: Who is the reigning men's U.S. Open champion?
Intermediate answer: Current champions Carlos Alcaraz, 2022 men's singles champion.
Follow up: Where is Carlos Alcaraz from?
Intermediate answer: El Palmar, Spain
So the final answer is: El Palmar, Spain
> Finished chain.
'El Palmar, Spain'
```
2023-02-16 06:47:17 +00:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"What is the weather in Pomfret?\")"
2023-02-18 21:40:43 +00:00
]
Google Search API integration with serper.dev (wrapper, tests, docs, … (#909)
Adds Google Search integration with [Serper](https://serper.dev) a
low-cost alternative to SerpAPI (10x cheaper + generous free tier).
Includes documentation, tests and examples. Hopefully I am not missing
anything.
Developers can sign up for a free account at
[serper.dev](https://serper.dev) and obtain an api key.
## Usage
```python
from langchain.utilities import GoogleSerperAPIWrapper
from langchain.llms.openai import OpenAI
from langchain.agents import initialize_agent, Tool
import os
os.environ["SERPER_API_KEY"] = ""
os.environ['OPENAI_API_KEY'] = ""
llm = OpenAI(temperature=0)
search = GoogleSerperAPIWrapper()
tools = [
Tool(
name="Intermediate Answer",
func=search.run
)
]
self_ask_with_search = initialize_agent(tools, llm, agent="self-ask-with-search", verbose=True)
self_ask_with_search.run("What is the hometown of the reigning men's U.S. Open champion?")
```
### Output
```
Entering new AgentExecutor chain...
Yes.
Follow up: Who is the reigning men's U.S. Open champion?
Intermediate answer: Current champions Carlos Alcaraz, 2022 men's singles champion.
Follow up: Where is Carlos Alcaraz from?
Intermediate answer: El Palmar, Spain
So the final answer is: El Palmar, Spain
> Finished chain.
'El Palmar, Spain'
```
2023-02-16 06:47:17 +00:00
},
{
"cell_type": "markdown",
2023-02-18 21:40:43 +00:00
"id": "0e39fc46",
"metadata": {},
2022-12-30 13:06:57 +00:00
"source": [
"## SerpAPI\n",
"\n",
Google Search API integration with serper.dev (wrapper, tests, docs, … (#909)
Adds Google Search integration with [Serper](https://serper.dev) a
low-cost alternative to SerpAPI (10x cheaper + generous free tier).
Includes documentation, tests and examples. Hopefully I am not missing
anything.
Developers can sign up for a free account at
[serper.dev](https://serper.dev) and obtain an api key.
## Usage
```python
from langchain.utilities import GoogleSerperAPIWrapper
from langchain.llms.openai import OpenAI
from langchain.agents import initialize_agent, Tool
import os
os.environ["SERPER_API_KEY"] = ""
os.environ['OPENAI_API_KEY'] = ""
llm = OpenAI(temperature=0)
search = GoogleSerperAPIWrapper()
tools = [
Tool(
name="Intermediate Answer",
func=search.run
)
]
self_ask_with_search = initialize_agent(tools, llm, agent="self-ask-with-search", verbose=True)
self_ask_with_search.run("What is the hometown of the reigning men's U.S. Open champion?")
```
### Output
```
Entering new AgentExecutor chain...
Yes.
Follow up: Who is the reigning men's U.S. Open champion?
Intermediate answer: Current champions Carlos Alcaraz, 2022 men's singles champion.
Follow up: Where is Carlos Alcaraz from?
Intermediate answer: El Palmar, Spain
So the final answer is: El Palmar, Spain
> Finished chain.
'El Palmar, Spain'
```
2023-02-16 06:47:17 +00:00
"Now, let's use the SerpAPI tool."
2023-02-18 21:40:43 +00:00
]
2022-12-30 13:06:57 +00:00
},
{
"cell_type": "code",
2023-02-18 21:40:43 +00:00
"execution_count": 9,
"id": "e1c39a0f",
"metadata": {},
2022-12-30 13:06:57 +00:00
"outputs": [],
"source": [
"tools = load_tools([\"serpapi\"], llm=llm)"
2023-02-18 21:40:43 +00:00
]
2022-12-30 13:06:57 +00:00
},
{
"cell_type": "code",
2023-02-18 21:40:43 +00:00
"execution_count": 10,
"id": "900dd6cb",
"metadata": {},
2022-12-30 13:06:57 +00:00
"outputs": [],
"source": [
2023-04-04 04:56:20 +00:00
"agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)"
2023-02-18 21:40:43 +00:00
]
2022-12-30 13:06:57 +00:00
},
{
"cell_type": "code",
2023-02-18 21:40:43 +00:00
"execution_count": 11,
"id": "342ee8ec",
"metadata": {},
2022-12-30 13:06:57 +00:00
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
2023-02-18 21:40:43 +00:00
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to find out what the current weather is in Pomfret.\n",
2022-12-30 13:06:57 +00:00
"Action: Search\n",
2023-02-18 21:40:43 +00:00
"Action Input: \"weather in Pomfret\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mPartly cloudy skies during the morning hours will give way to cloudy skies with light rain and snow developing in the afternoon. High 42F. Winds WNW at 10 to 15 ...\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the current weather in Pomfret.\n",
"Final Answer: Partly cloudy skies during the morning hours will give way to cloudy skies with light rain and snow developing in the afternoon. High 42F. Winds WNW at 10 to 15 mph.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
2022-12-30 13:06:57 +00:00
]
},
{
"data": {
"text/plain": [
2023-02-18 21:40:43 +00:00
"'Partly cloudy skies during the morning hours will give way to cloudy skies with light rain and snow developing in the afternoon. High 42F. Winds WNW at 10 to 15 mph.'"
2022-12-30 13:06:57 +00:00
]
},
2023-02-18 21:40:43 +00:00
"execution_count": 11,
2022-12-30 13:06:57 +00:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"What is the weather in Pomfret?\")"
2023-02-18 21:40:43 +00:00
]
2022-12-30 13:06:57 +00:00
},
{
"cell_type": "markdown",
2023-02-18 21:40:43 +00:00
"id": "adc8bb68",
"metadata": {},
2022-12-30 13:06:57 +00:00
"source": [
"## GoogleSearchAPIWrapper\n",
"\n",
"Now, let's use the official Google Search API Wrapper."
2023-02-18 21:40:43 +00:00
]
2022-12-30 13:06:57 +00:00
},
{
"cell_type": "code",
Docs refactor (#480)
Big docs refactor! Motivation is to make it easier for people to find
resources they are looking for. To accomplish this, there are now three
main sections:
- Getting Started: steps for getting started, walking through most core
functionality
- Modules: these are different modules of functionality that langchain
provides. Each part here has a "getting started", "how to", "key
concepts" and "reference" section (except in a few select cases where it
didnt easily fit).
- Use Cases: this is to separate use cases (like summarization, question
answering, evaluation, etc) from the modules, and provide a different
entry point to the code base.
There is also a full reference section, as well as extra resources
(glossary, gallery, etc)
Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>
2023-01-02 16:24:09 +00:00
"execution_count": 13,
2023-02-18 21:40:43 +00:00
"id": "ef24f92d",
"metadata": {},
2022-12-30 13:06:57 +00:00
"outputs": [],
"source": [
"tools = load_tools([\"google-search\"], llm=llm)"
2023-02-18 21:40:43 +00:00
]
2022-12-30 13:06:57 +00:00
},
{
"cell_type": "code",
Docs refactor (#480)
Big docs refactor! Motivation is to make it easier for people to find
resources they are looking for. To accomplish this, there are now three
main sections:
- Getting Started: steps for getting started, walking through most core
functionality
- Modules: these are different modules of functionality that langchain
provides. Each part here has a "getting started", "how to", "key
concepts" and "reference" section (except in a few select cases where it
didnt easily fit).
- Use Cases: this is to separate use cases (like summarization, question
answering, evaluation, etc) from the modules, and provide a different
entry point to the code base.
There is also a full reference section, as well as extra resources
(glossary, gallery, etc)
Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>
2023-01-02 16:24:09 +00:00
"execution_count": 14,
2023-02-18 21:40:43 +00:00
"id": "909cd28b",
"metadata": {},
2022-12-30 13:06:57 +00:00
"outputs": [],
"source": [
2023-04-04 04:56:20 +00:00
"agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)"
2023-02-18 21:40:43 +00:00
]
2022-12-30 13:06:57 +00:00
},
{
"cell_type": "code",
Docs refactor (#480)
Big docs refactor! Motivation is to make it easier for people to find
resources they are looking for. To accomplish this, there are now three
main sections:
- Getting Started: steps for getting started, walking through most core
functionality
- Modules: these are different modules of functionality that langchain
provides. Each part here has a "getting started", "how to", "key
concepts" and "reference" section (except in a few select cases where it
didnt easily fit).
- Use Cases: this is to separate use cases (like summarization, question
answering, evaluation, etc) from the modules, and provide a different
entry point to the code base.
There is also a full reference section, as well as extra resources
(glossary, gallery, etc)
Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>
2023-01-02 16:24:09 +00:00
"execution_count": 17,
2023-02-18 21:40:43 +00:00
"id": "46515d2a",
"metadata": {},
2022-12-30 13:06:57 +00:00
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
2023-02-18 21:40:43 +00:00
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I should look up the current weather conditions.\n",
2022-12-30 13:06:57 +00:00
"Action: Google Search\n",
2023-02-18 21:40:43 +00:00
"Action Input: \"weather in Pomfret\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mShowers early becoming a steady light rain later in the day. Near record high temperatures. High around 60F. Winds SW at 10 to 15 mph. Chance of rain 60%. Pomfret, CT Weather Forecast, with current conditions, wind, air quality, and what to expect for the next 3 days. Hourly Weather-Pomfret, CT. As of 12:52 am EST. Special Weather Statement +2 ... Hazardous Weather Conditions. Special Weather Statement ... Pomfret CT. Tonight ... National Digital Forecast Database Maximum Temperature Forecast. Pomfret Center Weather Forecasts. Weather Underground provides local & long-range weather forecasts, weatherreports, maps & tropical weather conditions for ... Pomfret, CT 12 hour by hour weather forecast includes precipitation, temperatures, sky conditions, rain chance, dew-point, relative humidity, wind direction ... North Pomfret Weather Forecasts. Weather Underground provides local & long-range weather forecasts, weatherreports, maps & tropical weather conditions for ... Today's Weather - Pomfret, CT. Dec 31, 2022 4:00 PM. Putnam MS. --. Weather forecast icon. Feels like --. Hi --. Lo --. Pomfret, CT temperature trend for the next 14 Days. Find daytime highs and nighttime lows from TheWeatherNetwork.com. Pomfret, MD Weather Forecast Date: 332 PM EST Wed Dec 28 2022. The area/counties/county of: Charles, including the cites of: St. Charles and Waldorf.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the current weather conditions in Pomfret.\n",
"Final Answer: Showers early becoming a steady light rain later in the day. Near record high temperatures. High around 60F. Winds SW at 10 to 15 mph. Chance of rain 60%.\u001b[0m\n",
"\u001b[1m> Finished AgentExecutor chain.\u001b[0m\n"
2022-12-30 13:06:57 +00:00
]
},
{
"data": {
"text/plain": [
Docs refactor (#480)
Big docs refactor! Motivation is to make it easier for people to find
resources they are looking for. To accomplish this, there are now three
main sections:
- Getting Started: steps for getting started, walking through most core
functionality
- Modules: these are different modules of functionality that langchain
provides. Each part here has a "getting started", "how to", "key
concepts" and "reference" section (except in a few select cases where it
didnt easily fit).
- Use Cases: this is to separate use cases (like summarization, question
answering, evaluation, etc) from the modules, and provide a different
entry point to the code base.
There is also a full reference section, as well as extra resources
(glossary, gallery, etc)
Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>
2023-01-02 16:24:09 +00:00
"'Showers early becoming a steady light rain later in the day. Near record high temperatures. High around 60F. Winds SW at 10 to 15 mph. Chance of rain 60%.'"
2022-12-30 13:06:57 +00:00
]
},
Docs refactor (#480)
Big docs refactor! Motivation is to make it easier for people to find
resources they are looking for. To accomplish this, there are now three
main sections:
- Getting Started: steps for getting started, walking through most core
functionality
- Modules: these are different modules of functionality that langchain
provides. Each part here has a "getting started", "how to", "key
concepts" and "reference" section (except in a few select cases where it
didnt easily fit).
- Use Cases: this is to separate use cases (like summarization, question
answering, evaluation, etc) from the modules, and provide a different
entry point to the code base.
There is also a full reference section, as well as extra resources
(glossary, gallery, etc)
Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>
2023-01-02 16:24:09 +00:00
"execution_count": 17,
2022-12-30 13:06:57 +00:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"What is the weather in Pomfret?\")"
2023-02-18 21:40:43 +00:00
]
2023-03-04 04:57:50 +00:00
},
{
"cell_type": "markdown",
"id": "eabad3af",
"metadata": {},
"source": [
"## SearxNG Meta Search Engine\n",
"\n",
"Here we will be using a self hosted SearxNG meta search engine."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "b196c704",
"metadata": {},
"outputs": [],
"source": [
"tools = load_tools([\"searx-search\"], searx_host=\"http://localhost:8888\", llm=llm)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "9023eeaa",
"metadata": {},
"outputs": [],
"source": [
2023-04-04 04:56:20 +00:00
"agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)"
2023-03-04 04:57:50 +00:00
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "3aad92c1",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I should look up the current weather\n",
"Action: SearX Search\n",
"Action Input: \"weather in Pomfret\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mMainly cloudy with snow showers around in the morning. High around 40F. Winds NNW at 5 to 10 mph. Chance of snow 40%. Snow accumulations less than one inch.\n",
"\n",
"10 Day Weather - Pomfret, MD As of 1:37 pm EST Today 49°/ 41° 52% Mon 27 | Day 49° 52% SE 14 mph Cloudy with occasional rain showers. High 49F. Winds SE at 10 to 20 mph. Chance of rain 50%....\n",
"\n",
"10 Day Weather - Pomfret, VT As of 3:51 am EST Special Weather Statement Today 39°/ 32° 37% Wed 01 | Day 39° 37% NE 4 mph Cloudy with snow showers developing for the afternoon. High 39F....\n",
"\n",
"Pomfret, CT ; Current Weather. 1:06 AM. 35°F · RealFeel® 32° ; TODAY'S WEATHER FORECAST. 3/3. 44°Hi. RealFeel® 50° ; TONIGHT'S WEATHER FORECAST. 3/3. 32°Lo.\n",
"\n",
"Pomfret, MD Forecast Today Hourly Daily Morning 41° 1% Afternoon 43° 0% Evening 35° 3% Overnight 34° 2% Don't Miss Finally, Here’ s Why We Get More Colds and Flu When It’ s Cold Coast-To-Coast...\n",
"\n",
"Pomfret, MD Weather Forecast | AccuWeather Current Weather 5:35 PM 35° F RealFeel® 36° RealFeel Shade™ 36° Air Quality Excellent Wind E 3 mph Wind Gusts 5 mph Cloudy More Details WinterCast...\n",
"\n",
"Pomfret, VT Weather Forecast | AccuWeather Current Weather 11:21 AM 23° F RealFeel® 27° RealFeel Shade™ 25° Air Quality Fair Wind ESE 3 mph Wind Gusts 7 mph Cloudy More Details WinterCast...\n",
"\n",
"Pomfret Center, CT Weather Forecast | AccuWeather Daily Current Weather 6:50 PM 39° F RealFeel® 36° Air Quality Fair Wind NW 6 mph Wind Gusts 16 mph Mostly clear More Details WinterCast...\n",
"\n",
"12:00 pm · Feels Like36° · WindN 5 mph · Humidity43% · UV Index3 of 10 · Cloud Cover65% · Rain Amount0 in ...\n",
"\n",
"Pomfret Center, CT Weather Conditions | Weather Underground star Popular Cities San Francisco, CA 49 °F Clear Manhattan, NY 37 °F Fair Schiller Park, IL (60176) warning39 °F Mostly Cloudy...\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The current weather in Pomfret is mainly cloudy with snow showers around in the morning. The temperature is around 40F with winds NNW at 5 to 10 mph. Chance of snow is 40%.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The current weather in Pomfret is mainly cloudy with snow showers around in the morning. The temperature is around 40F with winds NNW at 5 to 10 mph. Chance of snow is 40%.'"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"What is the weather in Pomfret\")"
]
2022-12-30 13:06:57 +00:00
}
],
"metadata": {
"kernelspec": {
2023-02-18 21:40:43 +00:00
"display_name": "Python 3 (ipykernel)",
2022-12-30 13:06:57 +00:00
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
2023-03-04 04:57:50 +00:00
"version": "3.9.11"
Docs refactor (#480)
Big docs refactor! Motivation is to make it easier for people to find
resources they are looking for. To accomplish this, there are now three
main sections:
- Getting Started: steps for getting started, walking through most core
functionality
- Modules: these are different modules of functionality that langchain
provides. Each part here has a "getting started", "how to", "key
concepts" and "reference" section (except in a few select cases where it
didnt easily fit).
- Use Cases: this is to separate use cases (like summarization, question
answering, evaluation, etc) from the modules, and provide a different
entry point to the code base.
There is also a full reference section, as well as extra resources
(glossary, gallery, etc)
Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>
2023-01-02 16:24:09 +00:00
},
"vscode": {
"interpreter": {
"hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
}
2022-12-30 13:06:57 +00:00
}
},
"nbformat": 4,
"nbformat_minor": 5
}