github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-07-04 04:07:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

[docs]: combine tools and toolkits (#25158)

Browse Source
This commit is contained in:
Isaac Francisco 2024-08-08 08:59:02 -07:00 committed by GitHub
parent 249945a572
commit 15a36dd0a2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
59 changed files with 1051 additions and 4213 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
cookbook/databricks_sql_db.ipynb
View File

@ -166,7 +166,7 @@
"source": [ "source": [
"### SQL Database Agent example\n", "### SQL Database Agent example\n",
"\n", "\n",
"This example demonstrates the use of the [SQL Database Agent](/docs/integrations/toolkits/sql_database.html) for answering questions over a Databricks database." "This example demonstrates the use of the [SQL Database Agent](/docs/integrations/tools/sql_database) for answering questions over a Databricks database."
] ]
}, },
{ {

7
docs/Makefile
View File

@ -13,7 +13,12 @@ OUTPUT_NEW_DOCS_DIR = $(OUTPUT_NEW_DIR)/docs
PYTHON = .venv/bin/python PYTHON = .venv/bin/python
PARTNER_DEPS_LIST := $(shell find ../libs/partners -mindepth 1 -maxdepth 1 -type d -exec test -e "{}/pyproject.toml" \; -print | grep -vE "airbyte|ibm|couchbase" | tr '\n' ' ') PARTNER_DEPS_LIST := $(shell find ../libs/partners -mindepth 1 -maxdepth 1 -type d -exec sh -c ' \
for dir; do \
if find "$$dir" -maxdepth 1 -type f \( -name "pyproject.toml" -o -name "setup.py" \) | grep -q .; then \
echo "$$dir"; \
fi \
done' sh {} + | grep -vE "airbyte|ibm|couchbase" | tr '\n' ' ')
PORT ?= 3001 PORT ?= 3001

2
docs/docs/how_to/sql_csv.ipynb
View File

@ -761,7 +761,7 @@
"* [SQL tutorial](/docs/tutorials/sql_qa): Many of the challenges of working with SQL db's and CSV's are generic to any structured data type, so it's useful to read the SQL techniques even if you're using Pandas for CSV data analysis.\n", "* [SQL tutorial](/docs/tutorials/sql_qa): Many of the challenges of working with SQL db's and CSV's are generic to any structured data type, so it's useful to read the SQL techniques even if you're using Pandas for CSV data analysis.\n",
"* [Tool use](/docs/how_to/tool_calling): Guides on general best practices when working with chains and agents that invoke tools\n", "* [Tool use](/docs/how_to/tool_calling): Guides on general best practices when working with chains and agents that invoke tools\n",
"* [Agents](/docs/tutorials/agents): Understand the fundamentals of building LLM agents.\n", "* [Agents](/docs/tutorials/agents): Understand the fundamentals of building LLM agents.\n",
"* Integrations: Sandboxed envs like [E2B](/docs/integrations/tools/e2b_data_analysis) and [Bearly](/docs/integrations/tools/bearly), utilities like [SQLDatabase](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.sql_database.SQLDatabase.html#langchain_community.utilities.sql_database.SQLDatabase), related agents like [Spark DataFrame agent](/docs/integrations/toolkits/spark)." "* Integrations: Sandboxed envs like [E2B](/docs/integrations/tools/e2b_data_analysis) and [Bearly](/docs/integrations/tools/bearly), utilities like [SQLDatabase](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.sql_database.SQLDatabase.html#langchain_community.utilities.sql_database.SQLDatabase), related agents like [Spark DataFrame agent](/docs/integrations/tools/spark_sql)."
] ]
} }
], ],

1
docs/docs/how_to/toolkits.mdx
View File

@ -5,7 +5,6 @@ sidebar_position: 3
Toolkits are collections of tools that are designed to be used together for specific tasks. They have convenient loading methods. Toolkits are collections of tools that are designed to be used together for specific tasks. They have convenient loading methods.
For a complete list of available ready-made toolkits, visit [Integrations](/docs/integrations/toolkits/).
All Toolkits expose a `get_tools` method which returns a list of tools. All Toolkits expose a `get_tools` method which returns a list of tools.
You can therefore do: You can therefore do:

2
docs/docs/how_to/tools_builtin.ipynb
View File

@ -196,8 +196,6 @@
"\n", "\n",
"Toolkits are collections of tools that are designed to be used together for specific tasks. They have convenient loading methods.\n", "Toolkits are collections of tools that are designed to be used together for specific tasks. They have convenient loading methods.\n",
"\n", "\n",
"For a complete list of available ready-made toolkits, visit [Integrations](/docs/integrations/toolkits/).\n",
"\n",
"All Toolkits expose a `get_tools` method which returns a list of tools.\n", "All Toolkits expose a `get_tools` method which returns a list of tools.\n",
"\n", "\n",
"You're usually meant to use them this way:\n", "You're usually meant to use them this way:\n",

2
docs/docs/integrations/document_loaders/apify_dataset.ipynb
View File

@ -13,7 +13,7 @@
"\n", "\n",
"## Prerequisites\n", "## Prerequisites\n",
"\n", "\n",
"You need to have an existing dataset on the Apify platform. If you don't have one, please first check out [this notebook](/docs/integrations/tools/apify) on how to use Apify to extract content from documentation, knowledge bases, help centers, or blogs. This example shows how to load a dataset produced by the [Website Content Crawler](https://apify.com/apify/website-content-crawler)." "You need to have an existing dataset on the Apify platform. This example shows how to load a dataset produced by the [Website Content Crawler](https://apify.com/apify/website-content-crawler)."
] ]
}, },
{ {

2
docs/docs/integrations/platforms/google.mdx
View File

@ -787,7 +787,7 @@ We need to install `langchain-google-community` with required dependencies:
pip install langchain-google-community[gmail] pip install langchain-google-community[gmail]
``` ```
See a [usage example and authorization instructions](/docs/integrations/toolkits/gmail). See a [usage example and authorization instructions](/docs/integrations/tools/gmail).
```python ```python
from langchain_google_community import GmailToolkit from langchain_google_community import GmailToolkit

6
docs/docs/integrations/platforms/microsoft.mdx
View File

@ -370,7 +370,7 @@ We need to install several python packages.
pip install azure-ai-formrecognizer azure-cognitiveservices-speech azure-ai-vision-imageanalysis pip install azure-ai-formrecognizer azure-cognitiveservices-speech azure-ai-vision-imageanalysis
``` ```
See a [usage example](/docs/integrations/toolkits/azure_ai_services). See a [usage example](/docs/integrations/tools/azure_ai_services).
```python ```python
from langchain_community.agent_toolkits import azure_ai_services from langchain_community.agent_toolkits import azure_ai_services
@ -385,7 +385,7 @@ pip install O365
``` ```
See a [usage example](/docs/integrations/toolkits/office365). See a [usage example](/docs/integrations/tools/office365).
```python ```python
from langchain_community.agent_toolkits import O365Toolkit from langchain_community.agent_toolkits import O365Toolkit
@ -399,7 +399,7 @@ We need to install `azure-identity` python package.
pip install azure-identity pip install azure-identity
``` ```
See a [usage example](/docs/integrations/toolkits/powerbi). See a [usage example](/docs/integrations/tools/powerbi).
```python ```python
from langchain_community.agent_toolkits import PowerBIToolkit from langchain_community.agent_toolkits import PowerBIToolkit

2
docs/docs/integrations/providers/ainetwork.mdx
View File

@ -15,7 +15,7 @@ pip install ain-py
You need to set the `AIN_BLOCKCHAIN_ACCOUNT_PRIVATE_KEY` environmental variable to your AIN Blockchain Account Private Key. You need to set the `AIN_BLOCKCHAIN_ACCOUNT_PRIVATE_KEY` environmental variable to your AIN Blockchain Account Private Key.
## Toolkit ## Toolkit
See a [usage example](/docs/integrations/toolkits/ainetwork). See a [usage example](/docs/integrations/tools/ainetwork).
```python ```python
from langchain_community.agent_toolkits.ainetwork.toolkit import AINetworkToolkit from langchain_community.agent_toolkits.ainetwork.toolkit import AINetworkToolkit

2
docs/docs/integrations/providers/apify.mdx
View File

@ -27,7 +27,7 @@ You can use the `ApifyWrapper` to run Actors on the Apify platform.
from langchain_community.utilities import ApifyWrapper from langchain_community.utilities import ApifyWrapper
``` ```
For a more detailed walkthrough of this wrapper, see [this notebook](/docs/integrations/tools/apify). For more information on this wrapper, see [the API reference](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.apify.ApifyWrapper.html).
## Document loader ## Document loader

2
docs/docs/integrations/providers/cassandra.mdx
View File

@ -80,6 +80,6 @@ from langchain_community.agent_toolkits.cassandra_database.toolkit import (
) )
``` ```
Learn more in the [example notebook](/docs/integrations/toolkits/cassandra_database). Learn more in the [example notebook](/docs/integrations/tools/cassandra_database).

2
docs/docs/integrations/providers/robocorp.mdx
View File

@ -30,7 +30,7 @@ from langchain_robocorp.toolkits import ActionServerRequestTool
## Toolkit ## Toolkit
See a [usage example](/docs/integrations/toolkits/robocorp). See a [usage example](/docs/integrations/tools/robocorp).
```python ```python
from langchain_robocorp import ActionServerToolkit from langchain_robocorp import ActionServerToolkit

2
docs/docs/integrations/providers/slack.mdx
View File

@ -17,7 +17,7 @@ from langchain_community.document_loaders import SlackDirectoryLoader
## Toolkit ## Toolkit
See a [usage example](/docs/integrations/toolkits/slack). See a [usage example](/docs/integrations/tools/slack).
```python ```python
from langchain_community.agent_toolkits import SlackToolkit from langchain_community.agent_toolkits import SlackToolkit

129
docs/docs/integrations/toolkits/airbyte_structured_qa.ipynb
View File

@ -1,129 +0,0 @@
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# Airbyte Question Answering\n",
"This notebook shows how to do question answering over structured data, in this case using the `AirbyteStripeLoader`.\n",
"\n",
"Vectorstores often have a hard time answering questions that requires computing, grouping and filtering structured data so the high level idea is to use a `pandas` dataframe to help with these types of questions. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%pip install -qU langchain-community"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"1. Load data from Stripe using Airbyte. user the `record_handler` paramater to return a JSON from the data loader."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"import pandas as pd\n",
"from langchain.agents import AgentType\n",
"from langchain_community.document_loaders.airbyte import AirbyteStripeLoader\n",
"from langchain_experimental.agents import create_pandas_dataframe_agent\n",
"from langchain_openai import ChatOpenAI\n",
"\n",
"stream_name = \"customers\"\n",
"config = {\n",
" \"client_secret\": os.getenv(\"STRIPE_CLIENT_SECRET\"),\n",
" \"account_id\": os.getenv(\"STRIPE_ACCOUNT_D\"),\n",
" \"start_date\": \"2023-01-20T00:00:00Z\",\n",
"}\n",
"\n",
"\n",
"def handle_record(record: dict, _id: str):\n",
" return record.data\n",
"\n",
"\n",
"loader = AirbyteStripeLoader(\n",
" config=config,\n",
" record_handler=handle_record,\n",
" stream_name=stream_name,\n",
")\n",
"data = loader.load()"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"2. Pass the data to `pandas` dataframe."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df = pd.DataFrame(data)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"3. Pass the dataframe `df` to the `create_pandas_dataframe_agent` and invoke\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"agent = create_pandas_dataframe_agent(\n",
" ChatOpenAI(temperature=0, model=\"gpt-4\"),\n",
" df,\n",
" verbose=True,\n",
" agent_type=AgentType.OPENAI_FUNCTIONS,\n",
")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"4. Run the agent"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"output = agent.run(\"How many rows are there?\")"
]
}
],
"metadata": {
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 2
}

301
docs/docs/integrations/toolkits/csv.ipynb
View File

@ -1,301 +0,0 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "7094e328",
"metadata": {},
"source": [
"# CSV\n",
"\n",
"This notebook shows how to use agents to interact with data in `CSV` format. It is mostly optimized for question answering.\n",
"\n",
"**NOTE: this agent calls the Pandas DataFrame agent under the hood, which in turn calls the Python agent, which executes LLM generated Python code - this can be bad if the LLM generated Python code is harmful. Use cautiously.**\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "caae0bec",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents.agent_types import AgentType\n",
"from langchain_experimental.agents.agent_toolkits import create_csv_agent\n",
"from langchain_openai import ChatOpenAI, OpenAI"
]
},
{
"cell_type": "markdown",
"id": "bd806175",
"metadata": {},
"source": [
"## Using `ZERO_SHOT_REACT_DESCRIPTION`\n",
"\n",
"This shows how to initialize the agent using the `ZERO_SHOT_REACT_DESCRIPTION` agent type."
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "a1717204",
"metadata": {},
"outputs": [],
"source": [
"agent = create_csv_agent(\n",
" OpenAI(temperature=0),\n",
" \"titanic.csv\",\n",
" verbose=True,\n",
" agent_type=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n",
")"
]
},
{
"cell_type": "markdown",
"id": "c31bb8a6",
"metadata": {},
"source": [
"## Using OpenAI Functions\n",
"\n",
"This shows how to initialize the agent using the OPENAI_FUNCTIONS agent type. Note that this is an alternative to the above."
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "16c4dc59",
"metadata": {},
"outputs": [],
"source": [
"agent = create_csv_agent(\n",
" ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-0613\"),\n",
" \"titanic.csv\",\n",
" verbose=True,\n",
" agent_type=AgentType.OPENAI_FUNCTIONS,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "46b9489d",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Error in on_chain_start callback: 'name'\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[32;1m\u001b[1;3m\n",
"Invoking: `python_repl_ast` with `df.shape[0]`\n",
"\n",
"\n",
"\u001b[0m\u001b[36;1m\u001b[1;3m891\u001b[0m\u001b[32;1m\u001b[1;3mThere are 891 rows in the dataframe.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'There are 891 rows in the dataframe.'"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"how many rows are there?\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "a96309be",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Error in on_chain_start callback: 'name'\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[32;1m\u001b[1;3m\n",
"Invoking: `python_repl_ast` with `df[df['SibSp'] > 3]['PassengerId'].count()`\n",
"\n",
"\n",
"\u001b[0m\u001b[36;1m\u001b[1;3m30\u001b[0m\u001b[32;1m\u001b[1;3mThere are 30 people in the dataframe who have more than 3 siblings.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'There are 30 people in the dataframe who have more than 3 siblings.'"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"how many people have more than 3 siblings\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "964a09f7",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Error in on_chain_start callback: 'name'\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[32;1m\u001b[1;3m\n",
"Invoking: `python_repl_ast` with `import pandas as pd\n",
"import math\n",
"\n",
"# Create a dataframe\n",
"data = {'Age': [22, 38, 26, 35, 35]}\n",
"df = pd.DataFrame(data)\n",
"\n",
"# Calculate the average age\n",
"average_age = df['Age'].mean()\n",
"\n",
"# Calculate the square root of the average age\n",
"square_root = math.sqrt(average_age)\n",
"\n",
"square_root`\n",
"\n",
"\n",
"\u001b[0m\u001b[36;1m\u001b[1;3m5.585696017507576\u001b[0m\u001b[32;1m\u001b[1;3mThe square root of the average age is approximately 5.59.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The square root of the average age is approximately 5.59.'"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"whats the square root of the average age?\")"
]
},
{
"cell_type": "markdown",
"id": "09539c18",
"metadata": {},
"source": [
"### Multi CSV Example\n",
"\n",
"This next part shows how the agent can interact with multiple csv files passed in as a list."
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "15f11fbd",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Error in on_chain_start callback: 'name'\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[32;1m\u001b[1;3m\n",
"Invoking: `python_repl_ast` with `df1['Age'].nunique() - df2['Age'].nunique()`\n",
"\n",
"\n",
"\u001b[0m\u001b[36;1m\u001b[1;3m-1\u001b[0m\u001b[32;1m\u001b[1;3mThere is 1 row in the age column that is different between the two dataframes.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'There is 1 row in the age column that is different between the two dataframes.'"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent = create_csv_agent(\n",
" ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-0613\"),\n",
" [\"titanic.csv\", \"titanic_age_fillna.csv\"],\n",
" verbose=True,\n",
" agent_type=AgentType.OPENAI_FUNCTIONS,\n",
")\n",
"agent.run(\"how many rows in the age column are different between the two dfs?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f2909808",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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",
"version": "3.10.1"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

21
docs/docs/integrations/toolkits/index.mdx
View File

@ -1,21 +0,0 @@
---
sidebar_position: 0
sidebar_class_name: hidden
---
# Toolkits
**Toolkits** are collections of tools that are designed to be used together for specific tasks. They include conveniences for loading tools
that share common authentication, services, or other objects. They can be implemented by subclassing the
[BaseToolkit](https://api.python.langchain.com/en/latest/tools/langchain_core.tools.BaseToolkit.html#langchain_core.tools.BaseToolkit) class.
This table lists common toolkits.
| Toolkit | Package |
|------|---------------|
| [GitHubToolkit](/docs/integrations/toolkits/github) | [langchain_community.agent_toolkits.github](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.github.toolkit.GitHubToolkit.html) |
| [GmailToolkit](/docs/integrations/toolkits/gmail) | [langchain_google_community.gmail.toolkit](https://api.python.langchain.com/en/latest/gmail/langchain_google_community.gmail.toolkit.GmailToolkit.html) |
| [RequestsToolkit](/docs/integrations/toolkits/requests) | [langchain_community.agent_toolkits.openapi](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.openapi.toolkit.RequestsToolkit.html) |
| [SlackToolkit](/docs/integrations/toolkits/slack) | [langchain_community.agent_toolkits.slack](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.slack.toolkit.SlackToolkit.html) |
| [SQLDatabaseToolkit](/docs/integrations/toolkits/sql_database) | [langchain_community.agent_toolkits.sql](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.sql.toolkit.SQLDatabaseToolkit.html) |

382
docs/docs/integrations/toolkits/python.ipynb
View File

@ -1,382 +0,0 @@
{
"cells": [
{
"cell_type": "raw",
"id": "be75cb7e",
"metadata": {},
"source": [
"---\n",
"keywords: [PythonREPLTool]\n",
"---"
]
},
{
"cell_type": "markdown",
"id": "82a4c2cc-20ea-4b20-a565-63e905dee8ff",
"metadata": {},
"source": [
"# Python\n",
"\n",
"This notebook showcases an agent designed to write and execute `Python` code to answer a question."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "f98e9c90-5c37-4fb9-af3e-d09693af8543",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain import hub\n",
"from langchain.agents import AgentExecutor\n",
"from langchain_experimental.tools import PythonREPLTool"
]
},
{
"cell_type": "markdown",
"id": "ba9adf51",
"metadata": {},
"source": [
"## Create the tool(s)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "003bce04",
"metadata": {},
"outputs": [],
"source": [
"tools = [PythonREPLTool()]"
]
},
{
"cell_type": "markdown",
"id": "4aceaeaf",
"metadata": {},
"source": [
"## Using OpenAI Functions Agent\n",
"\n",
"This is probably the most reliable type of agent, but is only compatible with function calling"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "3a054d1d",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import create_openai_functions_agent\n",
"from langchain_openai import ChatOpenAI"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "3454514b",
"metadata": {},
"outputs": [],
"source": [
"instructions = \"\"\"You are an agent designed to write and execute python code to answer questions.\n",
"You have access to a python REPL, which you can use to execute python code.\n",
"If you get an error, debug your code and try again.\n",
"Only use the output of your code to answer the question. \n",
"You might know the answer without running any code, but you should still run the code to get the answer.\n",
"If it does not seem like you can write code to answer the question, just return \"I don't know\" as the answer.\n",
"\"\"\"\n",
"base_prompt = hub.pull(\"langchain-ai/openai-functions-template\")\n",
"prompt = base_prompt.partial(instructions=instructions)"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "2a573e95",
"metadata": {},
"outputs": [],
"source": [
"agent = create_openai_functions_agent(ChatOpenAI(temperature=0), tools, prompt)"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "cae41550",
"metadata": {},
"outputs": [],
"source": [
"agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)"
]
},
{
"cell_type": "markdown",
"id": "ca30d64c",
"metadata": {},
"source": [
"## Using ReAct Agent\n",
"\n",
"This is a less reliable type, but is compatible with most models"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "bcaa0b18",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import create_react_agent\n",
"from langchain_anthropic import ChatAnthropic"
]
},
{
"cell_type": "code",
"execution_count": 29,
"id": "d2470880",
"metadata": {},
"outputs": [],
"source": [
"instructions = \"\"\"You are an agent designed to write and execute python code to answer questions.\n",
"You have access to a python REPL, which you can use to execute python code.\n",
"If you get an error, debug your code and try again.\n",
"Only use the output of your code to answer the question. \n",
"You might know the answer without running any code, but you should still run the code to get the answer.\n",
"If it does not seem like you can write code to answer the question, just return \"I don't know\" as the answer.\n",
"\"\"\"\n",
"base_prompt = hub.pull(\"langchain-ai/react-agent-template\")\n",
"prompt = base_prompt.partial(instructions=instructions)"
]
},
{
"cell_type": "code",
"execution_count": 30,
"id": "cc422f53-c51c-4694-a834-72ecd1e68363",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"agent = create_react_agent(ChatAnthropic(temperature=0), tools, prompt)\n",
"agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)"
]
},
{
"cell_type": "markdown",
"id": "c16161de",
"metadata": {},
"source": [
"## Fibonacci Example\n",
"This example was created by [John Wiseman](https://twitter.com/lemonodor/status/1628270074074398720?s=20)."
]
},
{
"cell_type": "code",
"execution_count": 31,
"id": "25cd4f92-ea9b-4fe6-9838-a4f85f81eebe",
"metadata": {
"scrolled": false,
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m Sure, I can write some Python code to get the 10th Fibonacci number.\n",
"\n",
"```\n",
"Thought: Do I need to use a tool? Yes\n",
"Action: Python_REPL \n",
"Action Input: \n",
"def fib(n):\n",
" a, b = 0, 1\n",
" for i in range(n):\n",
" a, b = b, a + b\n",
" return a\n",
"\n",
"print(fib(10))\n",
"```\n",
"\u001b[0m\u001b[36;1m\u001b[1;3m55\n",
"\u001b[0m\u001b[32;1m\u001b[1;3m Let me break this down step-by-step:\n",
"\n",
"1. I defined a fibonacci function called `fib` that takes in a number `n`. \n",
"2. Inside the function, I initialized two variables `a` and `b` to 0 and 1, which are the first two Fibonacci numbers.\n",
"3. Then I used a for loop to iterate up to `n`, updating `a` and `b` each iteration to the next Fibonacci numbers.\n",
"4. Finally, I return `a`, which after `n` iterations, contains the `n`th Fibonacci number.\n",
"\n",
"5. I called `fib(10)` to get the 10th Fibonacci number and printed the result.\n",
"\n",
"The key parts are defining the fibonacci calculation in the function, and then calling it with the desired input index to print the output.\n",
"\n",
"The observation shows the 10th Fibonacci number is 55, so that is the final answer.\n",
"\n",
"```\n",
"Thought: Do I need to use a tool? No\n",
"Final Answer: 55\n",
"```\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"{'input': 'What is the 10th fibonacci number?', 'output': '55\\n```'}"
]
},
"execution_count": 31,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.invoke({\"input\": \"What is the 10th fibonacci number?\"})"
]
},
{
"cell_type": "markdown",
"id": "7caa30de",
"metadata": {},
"source": [
"## Training neural net\n",
"This example was created by [Samee Ur Rehman](https://twitter.com/sameeurehman/status/1630130518133207046?s=20)."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "4b9f60e7-eb6a-4f14-8604-498d863d4482",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mCould not parse tool input: {'name': 'python', 'arguments': 'import torch\\nimport torch.nn as nn\\nimport torch.optim as optim\\n\\n# Define the neural network\\nclass SingleNeuron(nn.Module):\\n def __init__(self):\\n super(SingleNeuron, self).__init__()\\n self.linear = nn.Linear(1, 1)\\n \\n def forward(self, x):\\n return self.linear(x)\\n\\n# Create the synthetic data\\nx_train = torch.tensor([[1.0], [2.0], [3.0], [4.0]], dtype=torch.float32)\\ny_train = torch.tensor([[2.0], [4.0], [6.0], [8.0]], dtype=torch.float32)\\n\\n# Create the neural network\\nmodel = SingleNeuron()\\n\\n# Define the loss function and optimizer\\ncriterion = nn.MSELoss()\\noptimizer = optim.SGD(model.parameters(), lr=0.01)\\n\\n# Train the neural network\\nfor epoch in range(1, 1001):\\n # Forward pass\\n y_pred = model(x_train)\\n \\n # Compute loss\\n loss = criterion(y_pred, y_train)\\n \\n # Backward pass and optimization\\n optimizer.zero_grad()\\n loss.backward()\\n optimizer.step()\\n \\n # Print the loss every 100 epochs\\n if epoch % 100 == 0:\\n print(f\"Epoch {epoch}: Loss = {loss.item()}\")\\n\\n# Make a prediction for x = 5\\nx_test = torch.tensor([[5.0]], dtype=torch.float32)\\ny_pred = model(x_test)\\ny_pred.item()'} because the `arguments` is not valid JSON.\u001b[0mInvalid or incomplete response\u001b[32;1m\u001b[1;3m\n",
"Invoking: `Python_REPL` with `import torch\n",
"import torch.nn as nn\n",
"import torch.optim as optim\n",
"\n",
"# Define the neural network\n",
"class SingleNeuron(nn.Module):\n",
" def __init__(self):\n",
" super(SingleNeuron, self).__init__()\n",
" self.linear = nn.Linear(1, 1)\n",
" \n",
" def forward(self, x):\n",
" return self.linear(x)\n",
"\n",
"# Create the synthetic data\n",
"x_train = torch.tensor([[1.0], [2.0], [3.0], [4.0]], dtype=torch.float32)\n",
"y_train = torch.tensor([[2.0], [4.0], [6.0], [8.0]], dtype=torch.float32)\n",
"\n",
"# Create the neural network\n",
"model = SingleNeuron()\n",
"\n",
"# Define the loss function and optimizer\n",
"criterion = nn.MSELoss()\n",
"optimizer = optim.SGD(model.parameters(), lr=0.01)\n",
"\n",
"# Train the neural network\n",
"for epoch in range(1, 1001):\n",
" # Forward pass\n",
" y_pred = model(x_train)\n",
" \n",
" # Compute loss\n",
" loss = criterion(y_pred, y_train)\n",
" \n",
" # Backward pass and optimization\n",
" optimizer.zero_grad()\n",
" loss.backward()\n",
" optimizer.step()\n",
" \n",
" # Print the loss every 100 epochs\n",
" if epoch % 100 == 0:\n",
" print(f\"Epoch {epoch}: Loss = {loss.item()}\")\n",
"\n",
"# Make a prediction for x = 5\n",
"x_test = torch.tensor([[5.0]], dtype=torch.float32)\n",
"y_pred = model(x_test)\n",
"y_pred.item()`\n",
"\n",
"\n",
"\u001b[0m\u001b[36;1m\u001b[1;3mEpoch 100: Loss = 0.03825576975941658\n",
"Epoch 200: Loss = 0.02100197970867157\n",
"Epoch 300: Loss = 0.01152981910854578\n",
"Epoch 400: Loss = 0.006329738534986973\n",
"Epoch 500: Loss = 0.0034749575424939394\n",
"Epoch 600: Loss = 0.0019077073084190488\n",
"Epoch 700: Loss = 0.001047312980517745\n",
"Epoch 800: Loss = 0.0005749554838985205\n",
"Epoch 900: Loss = 0.0003156439634039998\n",
"Epoch 1000: Loss = 0.00017328384274151176\n",
"\u001b[0m\u001b[32;1m\u001b[1;3m\n",
"Invoking: `Python_REPL` with `x_test.item()`\n",
"\n",
"\n",
"\u001b[0m\u001b[36;1m\u001b[1;3m\u001b[0m\u001b[32;1m\u001b[1;3mThe prediction for x = 5 is 10.000173568725586.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The prediction for x = 5 is 10.000173568725586.'"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.invoke(\n",
" {\n",
" \"input\": \"\"\"Understand, write a single neuron neural network in PyTorch.\n",
"Take synthetic data for y=2x. Train for 1000 epochs and print every 100 epochs.\n",
"Return prediction for x = 5\"\"\"\n",
" }\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "eb654671",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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",
"version": "3.10.1"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

361
docs/docs/integrations/toolkits/requests.ipynb
View File

@ -1,361 +0,0 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "050c5580-2c85-4763-8783-59dbd20395a5",
"metadata": {},
"source": [
"---\n",
"sidebar_label: Requests\n",
"---"
]
},
{
"cell_type": "markdown",
"id": "cfe4185a-34dc-4cdc-b831-001954f2d6e8",
"metadata": {},
"source": [
"# Requests Toolkit\n",
"\n",
"We can use the Requests [toolkit](/docs/concepts/#toolkits) to construct agents that generate HTTP requests.\n",
"\n",
"For detailed documentation of all API toolkit features and configurations head to the API reference for [RequestsToolkit](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.openapi.toolkit.RequestsToolkit.html).\n",
"\n",
"## ⚠️ Security note ⚠️\n",
"There are inherent risks in giving models discretion to execute real-world actions. Take precautions to mitigate these risks:\n",
"\n",
"- Make sure that permissions associated with the tools are narrowly-scoped (e.g., for database operations or API requests);\n",
"- When desired, make use of human-in-the-loop workflows."
]
},
{
"cell_type": "markdown",
"id": "d968e982-f370-4614-8469-c1bc71ee3e32",
"metadata": {},
"source": [
"## Setup\n",
"\n",
"### Installation\n",
"\n",
"This toolkit lives in the `langchain-community` package:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f74f05fb-3f24-4c0b-a17f-cf4edeedbb9a",
"metadata": {},
"outputs": [],
"source": [
"%pip install -qU langchain-community"
]
},
{
"cell_type": "markdown",
"id": "36a178eb-1f2c-411e-bf25-0240ead4c62a",
"metadata": {},
"source": [
"Note that if you want to get automated tracing from runs of individual tools, you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8e68d0cd-6233-481c-b048-e8d95cba4c35",
"metadata": {},
"outputs": [],
"source": [
"# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
"# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
]
},
{
"cell_type": "markdown",
"id": "a7e2f64a-a72e-4fef-be52-eaf7c5072d24",
"metadata": {},
"source": [
"## Instantiation\n",
"\n",
"First we will demonstrate a minimal example.\n",
"\n",
"**NOTE**: There are inherent risks in giving models discretion to execute real-world actions. We must \"opt-in\" to these risks by setting `allow_dangerous_request=True` to use these tools.\n",
"**This can be dangerous for calling unwanted requests**. Please make sure your custom OpenAPI spec (yaml) is safe and that permissions associated with the tools are narrowly-scoped."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "018bd070-9fc8-459b-8d28-b4a3e283e640",
"metadata": {},
"outputs": [],
"source": [
"ALLOW_DANGEROUS_REQUEST = True"
]
},
{
"cell_type": "markdown",
"id": "a024f7b3-5437-4878-bd16-c4783bff394c",
"metadata": {},
"source": [
"We can use the [JSONPlaceholder](https://jsonplaceholder.typicode.com) API as a testing ground.\n",
"\n",
"Let's create (a subset of) its API spec:"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "2dcbcf92-2ad5-49c3-94ac-91047ccc8c5b",
"metadata": {},
"outputs": [],
"source": [
"from typing import Any, Dict, Union\n",
"\n",
"import requests\n",
"import yaml\n",
"\n",
"\n",
"def _get_schema(response_json: Union[dict, list]) -> dict:\n",
" if isinstance(response_json, list):\n",
" response_json = response_json[0] if response_json else {}\n",
" return {key: type(value).__name__ for key, value in response_json.items()}\n",
"\n",
"\n",
"def _get_api_spec() -> str:\n",
" base_url = \"https://jsonplaceholder.typicode.com\"\n",
" endpoints = [\n",
" \"/posts\",\n",
" \"/comments\",\n",
" ]\n",
" common_query_parameters = [\n",
" {\n",
" \"name\": \"_limit\",\n",
" \"in\": \"query\",\n",
" \"required\": False,\n",
" \"schema\": {\"type\": \"integer\", \"example\": 2},\n",
" \"description\": \"Limit the number of results\",\n",
" }\n",
" ]\n",
" openapi_spec: Dict[str, Any] = {\n",
" \"openapi\": \"3.0.0\",\n",
" \"info\": {\"title\": \"JSONPlaceholder API\", \"version\": \"1.0.0\"},\n",
" \"servers\": [{\"url\": base_url}],\n",
" \"paths\": {},\n",
" }\n",
" # Iterate over the endpoints to construct the paths\n",
" for endpoint in endpoints:\n",
" response = requests.get(base_url + endpoint)\n",
" if response.status_code == 200:\n",
" schema = _get_schema(response.json())\n",
" openapi_spec[\"paths\"][endpoint] = {\n",
" \"get\": {\n",
" \"summary\": f\"Get {endpoint[1:]}\",\n",
" \"parameters\": common_query_parameters,\n",
" \"responses\": {\n",
" \"200\": {\n",
" \"description\": \"Successful response\",\n",
" \"content\": {\n",
" \"application/json\": {\n",
" \"schema\": {\"type\": \"object\", \"properties\": schema}\n",
" }\n",
" },\n",
" }\n",
" },\n",
" }\n",
" }\n",
" return yaml.dump(openapi_spec, sort_keys=False)\n",
"\n",
"\n",
"api_spec = _get_api_spec()"
]
},
{
"cell_type": "markdown",
"id": "db3d6148-ae65-4a1d-91a6-59ee3e4e6efa",
"metadata": {},
"source": [
"Next we can instantiate the toolkit. We require no authorization or other headers for this API:"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "63a630b3-45bb-4525-865b-083f322b944b",
"metadata": {},
"outputs": [],
"source": [
"from langchain_community.agent_toolkits.openapi.toolkit import RequestsToolkit\n",
"from langchain_community.utilities.requests import TextRequestsWrapper\n",
"\n",
"toolkit = RequestsToolkit(\n",
" requests_wrapper=TextRequestsWrapper(headers={}),\n",
" allow_dangerous_requests=ALLOW_DANGEROUS_REQUEST,\n",
")"
]
},
{
"cell_type": "markdown",
"id": "f4224a64-843a-479d-8a7b-84719e4b9d0c",
"metadata": {},
"source": [
"## Tools\n",
"\n",
"View available tools:"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "70ea0f4e-9f10-4906-894b-08df832fd515",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[RequestsGetTool(requests_wrapper=TextRequestsWrapper(headers={}, aiosession=None, auth=None, response_content_type='text', verify=True), allow_dangerous_requests=True),\n",
" RequestsPostTool(requests_wrapper=TextRequestsWrapper(headers={}, aiosession=None, auth=None, response_content_type='text', verify=True), allow_dangerous_requests=True),\n",
" RequestsPatchTool(requests_wrapper=TextRequestsWrapper(headers={}, aiosession=None, auth=None, response_content_type='text', verify=True), allow_dangerous_requests=True),\n",
" RequestsPutTool(requests_wrapper=TextRequestsWrapper(headers={}, aiosession=None, auth=None, response_content_type='text', verify=True), allow_dangerous_requests=True),\n",
" RequestsDeleteTool(requests_wrapper=TextRequestsWrapper(headers={}, aiosession=None, auth=None, response_content_type='text', verify=True), allow_dangerous_requests=True)]"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tools = toolkit.get_tools()\n",
"\n",
"tools"
]
},
{
"cell_type": "markdown",
"id": "a21a6ca4-d650-4b7d-a944-1a8771b5293a",
"metadata": {},
"source": [
"- [RequestsGetTool](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.requests.tool.RequestsGetTool.html)\n",
"- [RequestsPostTool](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.requests.tool.RequestsPostTool.html)\n",
"- [RequestsPatchTool](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.requests.tool.RequestsPatchTool.html)\n",
"- [RequestsPutTool](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.requests.tool.RequestsPutTool.html)\n",
"- [RequestsDeleteTool](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.requests.tool.RequestsDeleteTool.html)"
]
},
{
"cell_type": "markdown",
"id": "e2dbb304-abf2-472a-9130-f03150a40549",
"metadata": {},
"source": [
"## Use within an agent"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "db062da7-f22c-4f36-9df8-1da96c9f7538",
"metadata": {},
"outputs": [],
"source": [
"from langchain_openai import ChatOpenAI\n",
"from langgraph.prebuilt import create_react_agent\n",
"\n",
"llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\")\n",
"\n",
"system_message = \"\"\"\n",
"You have access to an API to help answer user queries.\n",
"Here is documentation on the API:\n",
"{api_spec}\n",
"\"\"\".format(api_spec=api_spec)\n",
"\n",
"agent_executor = create_react_agent(llm, tools, state_modifier=system_message)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "c1e47be9-374a-457c-928a-48f02b5530e3",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"================================\u001b[1m Human Message \u001b[0m=================================\n",
"\n",
"Fetch the top two posts. What are their titles?\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
"Tool Calls:\n",
" requests_get (call_RV2SOyzCnV5h2sm4WPgG8fND)\n",
" Call ID: call_RV2SOyzCnV5h2sm4WPgG8fND\n",
" Args:\n",
" url: https://jsonplaceholder.typicode.com/posts?_limit=2\n",
"=================================\u001b[1m Tool Message \u001b[0m=================================\n",
"Name: requests_get\n",
"\n",
"[\n",
" {\n",
" \"userId\": 1,\n",
" \"id\": 1,\n",
" \"title\": \"sunt aut facere repellat provident occaecati excepturi optio reprehenderit\",\n",
" \"body\": \"quia et suscipit\\nsuscipit recusandae consequuntur expedita et cum\\nreprehenderit molestiae ut ut quas totam\\nnostrum rerum est autem sunt rem eveniet architecto\"\n",
" },\n",
" {\n",
" \"userId\": 1,\n",
" \"id\": 2,\n",
" \"title\": \"qui est esse\",\n",
" \"body\": \"est rerum tempore vitae\\nsequi sint nihil reprehenderit dolor beatae ea dolores neque\\nfugiat blanditiis voluptate porro vel nihil molestiae ut reiciendis\\nqui aperiam non debitis possimus qui neque nisi nulla\"\n",
" }\n",
"]\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
"\n",
"The titles of the top two posts are:\n",
"1. \"sunt aut facere repellat provident occaecati excepturi optio reprehenderit\"\n",
"2. \"qui est esse\"\n"
]
}
],
"source": [
"example_query = \"Fetch the top two posts. What are their titles?\"\n",
"\n",
"events = agent_executor.stream(\n",
" {\"messages\": [(\"user\", example_query)]},\n",
" stream_mode=\"values\",\n",
")\n",
"for event in events:\n",
" event[\"messages\"][-1].pretty_print()"
]
},
{
"cell_type": "markdown",
"id": "01ec4886-de3d-4fda-bd05-e3f254810969",
"metadata": {},
"source": [
"## API reference\n",
"\n",
"For detailed documentation of all API toolkit features and configurations head to the API reference for [RequestsToolkit](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.openapi.toolkit.RequestsToolkit.html)."
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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",
"version": "3.10.4"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

419
docs/docs/integrations/toolkits/spark.ipynb
View File

@ -1,419 +0,0 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Spark Dataframe\n",
"\n",
"This notebook shows how to use agents to interact with a `Spark DataFrame` and `Spark Connect`. It is mostly optimized for question answering.\n",
"\n",
"**NOTE: this agent calls the Python agent under the hood, which executes LLM generated Python code - this can be bad if the LLM generated Python code is harmful. Use cautiously.**"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"os.environ[\"OPENAI_API_KEY\"] = \"...input your openai api key here...\""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## `Spark DataFrame` example"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"23/05/15 20:33:10 WARN Utils: Your hostname, Mikes-Mac-mini.local resolves to a loopback address: 127.0.0.1; using 192.168.68.115 instead (on interface en1)\n",
"23/05/15 20:33:10 WARN Utils: Set SPARK_LOCAL_IP if you need to bind to another address\n",
"Setting default log level to \"WARN\".\n",
"To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).\n",
"23/05/15 20:33:10 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"+-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+\n",
"|PassengerId|Survived|Pclass| Name| Sex| Age|SibSp|Parch| Ticket| Fare|Cabin|Embarked|\n",
"+-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+\n",
"| 1| 0| 3|Braund, Mr. Owen ...| male|22.0| 1| 0| A/5 21171| 7.25| null| S|\n",
"| 2| 1| 1|Cumings, Mrs. Joh...|female|38.0| 1| 0| PC 17599|71.2833| C85| C|\n",
"| 3| 1| 3|Heikkinen, Miss. ...|female|26.0| 0| 0|STON/O2. 3101282| 7.925| null| S|\n",
"| 4| 1| 1|Futrelle, Mrs. Ja...|female|35.0| 1| 0| 113803| 53.1| C123| S|\n",
"| 5| 0| 3|Allen, Mr. Willia...| male|35.0| 0| 0| 373450| 8.05| null| S|\n",
"| 6| 0| 3| Moran, Mr. James| male|null| 0| 0| 330877| 8.4583| null| Q|\n",
"| 7| 0| 1|McCarthy, Mr. Tim...| male|54.0| 0| 0| 17463|51.8625| E46| S|\n",
"| 8| 0| 3|Palsson, Master. ...| male| 2.0| 3| 1| 349909| 21.075| null| S|\n",
"| 9| 1| 3|Johnson, Mrs. Osc...|female|27.0| 0| 2| 347742|11.1333| null| S|\n",
"| 10| 1| 2|Nasser, Mrs. Nich...|female|14.0| 1| 0| 237736|30.0708| null| C|\n",
"| 11| 1| 3|Sandstrom, Miss. ...|female| 4.0| 1| 1| PP 9549| 16.7| G6| S|\n",
"| 12| 1| 1|Bonnell, Miss. El...|female|58.0| 0| 0| 113783| 26.55| C103| S|\n",
"| 13| 0| 3|Saundercock, Mr. ...| male|20.0| 0| 0| A/5. 2151| 8.05| null| S|\n",
"| 14| 0| 3|Andersson, Mr. An...| male|39.0| 1| 5| 347082| 31.275| null| S|\n",
"| 15| 0| 3|Vestrom, Miss. Hu...|female|14.0| 0| 0| 350406| 7.8542| null| S|\n",
"| 16| 1| 2|Hewlett, Mrs. (Ma...|female|55.0| 0| 0| 248706| 16.0| null| S|\n",
"| 17| 0| 3|Rice, Master. Eugene| male| 2.0| 4| 1| 382652| 29.125| null| Q|\n",
"| 18| 1| 2|Williams, Mr. Cha...| male|null| 0| 0| 244373| 13.0| null| S|\n",
"| 19| 0| 3|Vander Planke, Mr...|female|31.0| 1| 0| 345763| 18.0| null| S|\n",
"| 20| 1| 3|Masselmani, Mrs. ...|female|null| 0| 0| 2649| 7.225| null| C|\n",
"+-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+\n",
"only showing top 20 rows\n",
"\n"
]
}
],
"source": [
"from langchain_experimental.agents.agent_toolkits import create_spark_dataframe_agent\n",
"from langchain_openai import OpenAI\n",
"from pyspark.sql import SparkSession\n",
"\n",
"spark = SparkSession.builder.getOrCreate()\n",
"csv_file_path = \"titanic.csv\"\n",
"df = spark.read.csv(csv_file_path, header=True, inferSchema=True)\n",
"df.show()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"agent = create_spark_dataframe_agent(llm=OpenAI(temperature=0), df=df, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to find out how many rows are in the dataframe\n",
"Action: python_repl_ast\n",
"Action Input: df.count()\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m891\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: There are 891 rows in the dataframe.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'There are 891 rows in the dataframe.'"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"how many rows are there?\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to find out how many people have more than 3 siblings\n",
"Action: python_repl_ast\n",
"Action Input: df.filter(df.SibSp > 3).count()\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m30\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: 30 people have more than 3 siblings.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'30 people have more than 3 siblings.'"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"how many people have more than 3 siblings\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to get the average age first\n",
"Action: python_repl_ast\n",
"Action Input: df.agg({\"Age\": \"mean\"}).collect()[0][0]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m29.69911764705882\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now have the average age, I need to get the square root\n",
"Action: python_repl_ast\n",
"Action Input: math.sqrt(29.69911764705882)\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mname 'math' is not defined\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to import math first\n",
"Action: python_repl_ast\n",
"Action Input: import math\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now have the math library imported, I can get the square root\n",
"Action: python_repl_ast\n",
"Action Input: math.sqrt(29.69911764705882)\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m5.449689683556195\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: 5.449689683556195\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'5.449689683556195'"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"whats the square root of the average age?\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"spark.stop()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## `Spark Connect` example"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# in apache-spark root directory. (tested here with \"spark-3.4.0-bin-hadoop3 and later\")\n",
"# To launch Spark with support for Spark Connect sessions, run the start-connect-server.sh script.\n",
"!./sbin/start-connect-server.sh --packages org.apache.spark:spark-connect_2.12:3.4.0"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"23/05/08 10:06:09 WARN Utils: Service 'SparkUI' could not bind on port 4040. Attempting port 4041.\n"
]
}
],
"source": [
"from pyspark.sql import SparkSession\n",
"\n",
"# Now that the Spark server is running, we can connect to it remotely using Spark Connect. We do this by\n",
"# creating a remote Spark session on the client where our application runs. Before we can do that, we need\n",
"# to make sure to stop the existing regular Spark session because it cannot coexist with the remote\n",
"# Spark Connect session we are about to create.\n",
"SparkSession.builder.master(\"local[*]\").getOrCreate().stop()"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"# The command we used above to launch the server configured Spark to run as localhost:15002.\n",
"# So now we can create a remote Spark session on the client using the following command.\n",
"spark = SparkSession.builder.remote(\"sc://localhost:15002\").getOrCreate()"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"+-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+\n",
"|PassengerId|Survived|Pclass| Name| Sex| Age|SibSp|Parch| Ticket| Fare|Cabin|Embarked|\n",
"+-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+\n",
"| 1| 0| 3|Braund, Mr. Owen ...| male|22.0| 1| 0| A/5 21171| 7.25| null| S|\n",
"| 2| 1| 1|Cumings, Mrs. Joh...|female|38.0| 1| 0| PC 17599|71.2833| C85| C|\n",
"| 3| 1| 3|Heikkinen, Miss. ...|female|26.0| 0| 0|STON/O2. 3101282| 7.925| null| S|\n",
"| 4| 1| 1|Futrelle, Mrs. Ja...|female|35.0| 1| 0| 113803| 53.1| C123| S|\n",
"| 5| 0| 3|Allen, Mr. Willia...| male|35.0| 0| 0| 373450| 8.05| null| S|\n",
"| 6| 0| 3| Moran, Mr. James| male|null| 0| 0| 330877| 8.4583| null| Q|\n",
"| 7| 0| 1|McCarthy, Mr. Tim...| male|54.0| 0| 0| 17463|51.8625| E46| S|\n",
"| 8| 0| 3|Palsson, Master. ...| male| 2.0| 3| 1| 349909| 21.075| null| S|\n",
"| 9| 1| 3|Johnson, Mrs. Osc...|female|27.0| 0| 2| 347742|11.1333| null| S|\n",
"| 10| 1| 2|Nasser, Mrs. Nich...|female|14.0| 1| 0| 237736|30.0708| null| C|\n",
"| 11| 1| 3|Sandstrom, Miss. ...|female| 4.0| 1| 1| PP 9549| 16.7| G6| S|\n",
"| 12| 1| 1|Bonnell, Miss. El...|female|58.0| 0| 0| 113783| 26.55| C103| S|\n",
"| 13| 0| 3|Saundercock, Mr. ...| male|20.0| 0| 0| A/5. 2151| 8.05| null| S|\n",
"| 14| 0| 3|Andersson, Mr. An...| male|39.0| 1| 5| 347082| 31.275| null| S|\n",
"| 15| 0| 3|Vestrom, Miss. Hu...|female|14.0| 0| 0| 350406| 7.8542| null| S|\n",
"| 16| 1| 2|Hewlett, Mrs. (Ma...|female|55.0| 0| 0| 248706| 16.0| null| S|\n",
"| 17| 0| 3|Rice, Master. Eugene| male| 2.0| 4| 1| 382652| 29.125| null| Q|\n",
"| 18| 1| 2|Williams, Mr. Cha...| male|null| 0| 0| 244373| 13.0| null| S|\n",
"| 19| 0| 3|Vander Planke, Mr...|female|31.0| 1| 0| 345763| 18.0| null| S|\n",
"| 20| 1| 3|Masselmani, Mrs. ...|female|null| 0| 0| 2649| 7.225| null| C|\n",
"+-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+\n",
"only showing top 20 rows\n",
"\n"
]
}
],
"source": [
"csv_file_path = \"titanic.csv\"\n",
"df = spark.read.csv(csv_file_path, header=True, inferSchema=True)\n",
"df.show()"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"from langchain_experimental.agents import create_spark_dataframe_agent\n",
"from langchain_openai import OpenAI\n",
"\n",
"os.environ[\"OPENAI_API_KEY\"] = \"...input your openai api key here...\"\n",
"\n",
"agent = create_spark_dataframe_agent(llm=OpenAI(temperature=0), df=df, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"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\n",
"Thought: I need to find the row with the highest fare\n",
"Action: python_repl_ast\n",
"Action Input: df.sort(df.Fare.desc()).first()\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mRow(PassengerId=259, Survived=1, Pclass=1, Name='Ward, Miss. Anna', Sex='female', Age=35.0, SibSp=0, Parch=0, Ticket='PC 17755', Fare=512.3292, Cabin=None, Embarked='C')\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the name of the person who bought the most expensive ticket\n",
"Final Answer: Miss. Anna Ward\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'Miss. Anna Ward'"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\n",
" \"\"\"\n",
"who bought the most expensive ticket?\n",
"You can find all supported function types in https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/dataframe\n",
"\"\"\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"spark.stop()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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",
"version": "3.10.1"
}
},
"nbformat": 4,
"nbformat_minor": 4
}

624
docs/docs/integrations/toolkits/sql_database.ipynb
View File

@ -1,624 +0,0 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "757e7780-b89a-4a87-b10c-cfa42337a8e0",
"metadata": {},
"source": [
"---\n",
"sidebar_label: SQLDatabaseToolkit\n",
"---"
]
},
{
"cell_type": "markdown",
"id": "0e499e90-7a6d-4fab-8aab-31a4df417601",
"metadata": {},
"source": [
"# SQLDatabaseToolkit\n",
"\n",
"This will help you getting started with the SQL Database [toolkit](/docs/concepts/#toolkits). For detailed documentation of all `SQLDatabaseToolkit` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.sql.toolkit.SQLDatabaseToolkit.html).\n",
"\n",
"Tools within the `SQLDatabaseToolkit` are designed to interact with a `SQL` database. \n",
"\n",
"A common application is to enable agents to answer questions using data in a relational database, potentially in an iterative fashion (e.g., recovering from errors).\n",
"\n",
"**⚠️ Security note ⚠️**\n",
"\n",
"Building Q&A systems of SQL databases requires executing model-generated SQL queries. There are inherent risks in doing this. Make sure that your database connection permissions are always scoped as narrowly as possible for your chain/agent's needs. This will mitigate though not eliminate the risks of building a model-driven system. For more on general security best practices, [see here](/docs/security).\n",
"\n",
"## Setup\n",
"\n",
"If you want to get automated tracing from runs of individual tools, you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3de6e3be-1fd9-42a3-8564-8ca7dca11e1c",
"metadata": {},
"outputs": [],
"source": [
"# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
"# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
]
},
{
"cell_type": "markdown",
"id": "31896b61-68d2-4b4d-be9d-b829eda327d1",
"metadata": {},
"source": [
"### Installation\n",
"\n",
"This toolkit lives in the `langchain-community` package:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c4933e04-9120-4ccc-9ef7-369987823b0e",
"metadata": {},
"outputs": [],
"source": [
"%pip install --upgrade --quiet langchain-community"
]
},
{
"cell_type": "markdown",
"id": "6ad08dbe-1642-448c-b58d-153810024375",
"metadata": {},
"source": [
"For demonstration purposes, we will access a prompt in the LangChain [Hub](https://smith.langchain.com/hub). We will also require `langgraph` to demonstrate the use of the toolkit with an agent. This is not required to use the toolkit."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f3dead45-9908-497d-a5a3-bce30642e88f",
"metadata": {},
"outputs": [],
"source": [
"%pip install --upgrade --quiet langchainhub langgraph"
]
},
{
"cell_type": "markdown",
"id": "804533b1-2f16-497b-821b-c82d67fcf7b6",
"metadata": {},
"source": [
"## Instantiation\n",
"\n",
"The `SQLDatabaseToolkit` toolkit requires:\n",
"\n",
"- a [SQLDatabase](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.sql_database.SQLDatabase.html) object;\n",
"- a LLM or chat model (for instantiating the [QuerySQLCheckerTool](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.sql_database.tool.QuerySQLCheckerTool.html) tool).\n",
"\n",
"Below, we instantiate the toolkit with these objects. Let's first create a database object.\n",
"\n",
"This guide uses the example `Chinook` database based on [these instructions](https://database.guide/2-sample-databases-sqlite/).\n",
"\n",
"Below we will use the `requests` library to pull the `.sql` file and create an in-memory SQLite database. Note that this approach is lightweight, but ephemeral and not thread-safe. If you'd prefer, you can follow the instructions to save the file locally as `Chinook.db` and instantiate the database via `db = SQLDatabase.from_uri(\"sqlite:///Chinook.db\")`."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "40d05f9b-5a8f-4307-8f8b-4153db0fdfa9",
"metadata": {},
"outputs": [],
"source": [
"import sqlite3\n",
"\n",
"import requests\n",
"from langchain_community.utilities.sql_database import SQLDatabase\n",
"from sqlalchemy import create_engine\n",
"from sqlalchemy.pool import StaticPool\n",
"\n",
"\n",
"def get_engine_for_chinook_db():\n",
" \"\"\"Pull sql file, populate in-memory database, and create engine.\"\"\"\n",
" url = \"https://raw.githubusercontent.com/lerocha/chinook-database/master/ChinookDatabase/DataSources/Chinook_Sqlite.sql\"\n",
" response = requests.get(url)\n",
" sql_script = response.text\n",
"\n",
" connection = sqlite3.connect(\":memory:\", check_same_thread=False)\n",
" connection.executescript(sql_script)\n",
" return create_engine(\n",
" \"sqlite://\",\n",
" creator=lambda: connection,\n",
" poolclass=StaticPool,\n",
" connect_args={\"check_same_thread\": False},\n",
" )\n",
"\n",
"\n",
"engine = get_engine_for_chinook_db()\n",
"\n",
"db = SQLDatabase(engine)"
]
},
{
"cell_type": "markdown",
"id": "2b9a6326-78fd-4c42-a1cb-4316619ac449",
"metadata": {},
"source": [
"We will also need a LLM or chat model:\n",
"\n",
"```{=mdx}\n",
"import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
"\n",
"<ChatModelTabs customVarName=\"llm\" />\n",
"```"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "cc6e6108-83d9-404f-8f31-474c2fbf5f6c",
"metadata": {},
"outputs": [],
"source": [
"# | output: false\n",
"# | echo: false\n",
"\n",
"from langchain_openai import ChatOpenAI\n",
"\n",
"llm = ChatOpenAI(temperature=0)"
]
},
{
"cell_type": "markdown",
"id": "77925e72-4730-43c3-8726-d68cedf635f4",
"metadata": {},
"source": [
"We can now instantiate the toolkit:"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "42bd5a41-672a-4a53-b70a-2f0c0555758c",
"metadata": {},
"outputs": [],
"source": [
"from langchain_community.agent_toolkits.sql.toolkit import SQLDatabaseToolkit\n",
"\n",
"toolkit = SQLDatabaseToolkit(db=db, llm=llm)"
]
},
{
"cell_type": "markdown",
"id": "b2f882cf-4156-4a9f-a714-db97ec8ccc37",
"metadata": {},
"source": [
"## Tools\n",
"\n",
"View available tools:"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "a18c3e69-bee0-4f5d-813e-eeb540f41b98",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[QuerySQLDataBaseTool(description=\"Input to this tool is a detailed and correct SQL query, output is a result from the database. If the query is not correct, an error message will be returned. If an error is returned, rewrite the query, check the query, and try again. If you encounter an issue with Unknown column 'xxxx' in 'field list', use sql_db_schema to query the correct table fields.\", db=<langchain_community.utilities.sql_database.SQLDatabase object at 0x105e02860>),\n",
" InfoSQLDatabaseTool(description='Input to this tool is a comma-separated list of tables, output is the schema and sample rows for those tables. Be sure that the tables actually exist by calling sql_db_list_tables first! Example Input: table1, table2, table3', db=<langchain_community.utilities.sql_database.SQLDatabase object at 0x105e02860>),\n",
" ListSQLDatabaseTool(db=<langchain_community.utilities.sql_database.SQLDatabase object at 0x105e02860>),\n",
" QuerySQLCheckerTool(description='Use this tool to double check if your query is correct before executing it. Always use this tool before executing a query with sql_db_query!', db=<langchain_community.utilities.sql_database.SQLDatabase object at 0x105e02860>, llm=ChatOpenAI(client=<openai.resources.chat.completions.Completions object at 0x1148a97b0>, async_client=<openai.resources.chat.completions.AsyncCompletions object at 0x1148aaec0>, temperature=0.0, openai_api_key=SecretStr('**********'), openai_proxy=''), llm_chain=LLMChain(prompt=PromptTemplate(input_variables=['dialect', 'query'], template='\\n{query}\\nDouble check the {dialect} query above for common mistakes, including:\\n- Using NOT IN with NULL values\\n- Using UNION when UNION ALL should have been used\\n- Using BETWEEN for exclusive ranges\\n- Data type mismatch in predicates\\n- Properly quoting identifiers\\n- Using the correct number of arguments for functions\\n- Casting to the correct data type\\n- Using the proper columns for joins\\n\\nIf there are any of the above mistakes, rewrite the query. If there are no mistakes, just reproduce the original query.\\n\\nOutput the final SQL query only.\\n\\nSQL Query: '), llm=ChatOpenAI(client=<openai.resources.chat.completions.Completions object at 0x1148a97b0>, async_client=<openai.resources.chat.completions.AsyncCompletions object at 0x1148aaec0>, temperature=0.0, openai_api_key=SecretStr('**********'), openai_proxy='')))]"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"toolkit.get_tools()"
]
},
{
"cell_type": "markdown",
"id": "5f5751e3-2e98-485f-8164-db8094039c25",
"metadata": {},
"source": [
"API references:\n",
"\n",
"- [QuerySQLDataBaseTool](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.sql_database.tool.QuerySQLDataBaseTool.html)\n",
"- [InfoSQLDatabaseTool](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.sql_database.tool.InfoSQLDatabaseTool.html)\n",
"- [ListSQLDatabaseTool](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.sql_database.tool.ListSQLDatabaseTool.html)\n",
"- [QuerySQLCheckerTool](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.sql_database.tool.QuerySQLCheckerTool.html)"
]
},
{
"cell_type": "markdown",
"id": "c067e0ed-dcca-4dcc-81b2-a0eeb4fc2a9f",
"metadata": {},
"source": [
"## Use within an agent\n",
"\n",
"Following the [SQL Q&A Tutorial](/docs/tutorials/sql_qa/#agents), below we equip a simple question-answering agent with the tools in our toolkit. First we pull a relevant prompt and populate it with its required parameters:"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "eda12f8b-be90-4697-ac84-2ece9e2d1708",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['dialect', 'top_k']\n"
]
}
],
"source": [
"from langchain import hub\n",
"\n",
"prompt_template = hub.pull(\"langchain-ai/sql-agent-system-prompt\")\n",
"\n",
"assert len(prompt_template.messages) == 1\n",
"print(prompt_template.input_variables)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "3470ae96-e5e5-4717-a6d6-d7d28c7b7347",
"metadata": {},
"outputs": [],
"source": [
"system_message = prompt_template.format(dialect=\"SQLite\", top_k=5)"
]
},
{
"cell_type": "markdown",
"id": "97930c07-36d1-4137-94ae-fe5ac83ecc44",
"metadata": {},
"source": [
"We then instantiate the agent:"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "48bca92c-9b4b-4d5c-bcce-1b239c9e901c",
"metadata": {},
"outputs": [],
"source": [
"from langgraph.prebuilt import create_react_agent\n",
"\n",
"agent_executor = create_react_agent(\n",
" llm, toolkit.get_tools(), state_modifier=system_message\n",
")"
]
},
{
"cell_type": "markdown",
"id": "09fb1845-1105-4f41-98b4-24756452a3e3",
"metadata": {},
"source": [
"And issue it a query:"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "39e6d2bf-3194-4aba-854b-63faf919157b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"================================\u001b[1m Human Message \u001b[0m=================================\n",
"\n",
"Which country's customers spent the most?\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
"Tool Calls:\n",
" sql_db_list_tables (call_eiheSxiL0s90KE50XyBnBtJY)\n",
" Call ID: call_eiheSxiL0s90KE50XyBnBtJY\n",
" Args:\n",
"=================================\u001b[1m Tool Message \u001b[0m=================================\n",
"Name: sql_db_list_tables\n",
"\n",
"Album, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
"Tool Calls:\n",
" sql_db_schema (call_YKwGWt4UUVmxxY7vjjBDzFLJ)\n",
" Call ID: call_YKwGWt4UUVmxxY7vjjBDzFLJ\n",
" Args:\n",
" table_names: Customer, Invoice, InvoiceLine\n",
"=================================\u001b[1m Tool Message \u001b[0m=================================\n",
"Name: sql_db_schema\n",
"\n",
"\n",
"CREATE TABLE \"Customer\" (\n",
"\t\"CustomerId\" INTEGER NOT NULL, \n",
"\t\"FirstName\" NVARCHAR(40) NOT NULL, \n",
"\t\"LastName\" NVARCHAR(20) NOT NULL, \n",
"\t\"Company\" NVARCHAR(80), \n",
"\t\"Address\" NVARCHAR(70), \n",
"\t\"City\" NVARCHAR(40), \n",
"\t\"State\" NVARCHAR(40), \n",
"\t\"Country\" NVARCHAR(40), \n",
"\t\"PostalCode\" NVARCHAR(10), \n",
"\t\"Phone\" NVARCHAR(24), \n",
"\t\"Fax\" NVARCHAR(24), \n",
"\t\"Email\" NVARCHAR(60) NOT NULL, \n",
"\t\"SupportRepId\" INTEGER, \n",
"\tPRIMARY KEY (\"CustomerId\"), \n",
"\tFOREIGN KEY(\"SupportRepId\") REFERENCES \"Employee\" (\"EmployeeId\")\n",
")\n",
"\n",
"/*\n",
"3 rows from Customer table:\n",
"CustomerId\tFirstName\tLastName\tCompany\tAddress\tCity\tState\tCountry\tPostalCode\tPhone\tFax\tEmail\tSupportRepId\n",
"1\tLuís\tGonçalves\tEmbraer - Empresa Brasileira de Aeronáutica S.A.\tAv. Brigadeiro Faria Lima, 2170\tSão José dos Campos\tSP\tBrazil\t12227-000\t+55 (12) 3923-5555\t+55 (12) 3923-5566\tluisg@embraer.com.br\t3\n",
"2\tLeonie\tKöhler\tNone\tTheodor-Heuss-Straße 34\tStuttgart\tNone\tGermany\t70174\t+49 0711 2842222\tNone\tleonekohler@surfeu.de\t5\n",
"3\tFrançois\tTremblay\tNone\t1498 rue Bélanger\tMontréal\tQC\tCanada\tH2G 1A7\t+1 (514) 721-4711\tNone\tftremblay@gmail.com\t3\n",
"*/\n",
"\n",
"\n",
"CREATE TABLE \"Invoice\" (\n",
"\t\"InvoiceId\" INTEGER NOT NULL, \n",
"\t\"CustomerId\" INTEGER NOT NULL, \n",
"\t\"InvoiceDate\" DATETIME NOT NULL, \n",
"\t\"BillingAddress\" NVARCHAR(70), \n",
"\t\"BillingCity\" NVARCHAR(40), \n",
"\t\"BillingState\" NVARCHAR(40), \n",
"\t\"BillingCountry\" NVARCHAR(40), \n",
"\t\"BillingPostalCode\" NVARCHAR(10), \n",
"\t\"Total\" NUMERIC(10, 2) NOT NULL, \n",
"\tPRIMARY KEY (\"InvoiceId\"), \n",
"\tFOREIGN KEY(\"CustomerId\") REFERENCES \"Customer\" (\"CustomerId\")\n",
")\n",
"\n",
"/*\n",
"3 rows from Invoice table:\n",
"InvoiceId\tCustomerId\tInvoiceDate\tBillingAddress\tBillingCity\tBillingState\tBillingCountry\tBillingPostalCode\tTotal\n",
"1\t2\t2021-01-01 00:00:00\tTheodor-Heuss-Straße 34\tStuttgart\tNone\tGermany\t70174\t1.98\n",
"2\t4\t2021-01-02 00:00:00\tUllevålsveien 14\tOslo\tNone\tNorway\t0171\t3.96\n",
"3\t8\t2021-01-03 00:00:00\tGrétrystraat 63\tBrussels\tNone\tBelgium\t1000\t5.94\n",
"*/\n",
"\n",
"\n",
"CREATE TABLE \"InvoiceLine\" (\n",
"\t\"InvoiceLineId\" INTEGER NOT NULL, \n",
"\t\"InvoiceId\" INTEGER NOT NULL, \n",
"\t\"TrackId\" INTEGER NOT NULL, \n",
"\t\"UnitPrice\" NUMERIC(10, 2) NOT NULL, \n",
"\t\"Quantity\" INTEGER NOT NULL, \n",
"\tPRIMARY KEY (\"InvoiceLineId\"), \n",
"\tFOREIGN KEY(\"TrackId\") REFERENCES \"Track\" (\"TrackId\"), \n",
"\tFOREIGN KEY(\"InvoiceId\") REFERENCES \"Invoice\" (\"InvoiceId\")\n",
")\n",
"\n",
"/*\n",
"3 rows from InvoiceLine table:\n",
"InvoiceLineId\tInvoiceId\tTrackId\tUnitPrice\tQuantity\n",
"1\t1\t2\t0.99\t1\n",
"2\t1\t4\t0.99\t1\n",
"3\t2\t6\t0.99\t1\n",
"*/\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
"Tool Calls:\n",
" sql_db_query (call_7WBDcMxl1h7MnI05njx1q8V9)\n",
" Call ID: call_7WBDcMxl1h7MnI05njx1q8V9\n",
" Args:\n",
" query: SELECT c.Country, SUM(i.Total) AS TotalSpent FROM Customer c JOIN Invoice i ON c.CustomerId = i.CustomerId GROUP BY c.Country ORDER BY TotalSpent DESC LIMIT 1\n",
"=================================\u001b[1m Tool Message \u001b[0m=================================\n",
"Name: sql_db_query\n",
"\n",
"[('USA', 523.0600000000003)]\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
"\n",
"Customers from the USA spent the most, with a total amount spent of $523.06.\n"
]
}
],
"source": [
"example_query = \"Which country's customers spent the most?\"\n",
"\n",
"events = agent_executor.stream(\n",
" {\"messages\": [(\"user\", example_query)]},\n",
" stream_mode=\"values\",\n",
")\n",
"for event in events:\n",
" event[\"messages\"][-1].pretty_print()"
]
},
{
"cell_type": "markdown",
"id": "adbf3d8d-7570-45a5-950f-ce84db5145ab",
"metadata": {},
"source": [
"We can also observe the agent recover from an error:"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "23c1235c-6d18-43e4-98ab-85b426b53d94",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"================================\u001b[1m Human Message \u001b[0m=================================\n",
"\n",
"Who are the top 3 best selling artists?\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
"Tool Calls:\n",
" sql_db_query (call_9F6Bp2vwsDkeLW6FsJFqLiet)\n",
" Call ID: call_9F6Bp2vwsDkeLW6FsJFqLiet\n",
" Args:\n",
" query: SELECT artist_name, SUM(quantity) AS total_sold FROM sales GROUP BY artist_name ORDER BY total_sold DESC LIMIT 3\n",
"=================================\u001b[1m Tool Message \u001b[0m=================================\n",
"Name: sql_db_query\n",
"\n",
"Error: (sqlite3.OperationalError) no such table: sales\n",
"[SQL: SELECT artist_name, SUM(quantity) AS total_sold FROM sales GROUP BY artist_name ORDER BY total_sold DESC LIMIT 3]\n",
"(Background on this error at: https://sqlalche.me/e/20/e3q8)\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
"Tool Calls:\n",
" sql_db_list_tables (call_Gx5adzWnrBDIIxzUDzsn83zO)\n",
" Call ID: call_Gx5adzWnrBDIIxzUDzsn83zO\n",
" Args:\n",
"=================================\u001b[1m Tool Message \u001b[0m=================================\n",
"Name: sql_db_list_tables\n",
"\n",
"Album, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
"Tool Calls:\n",
" sql_db_schema (call_ftywrZgEgGWLrnk9dYC0xtZv)\n",
" Call ID: call_ftywrZgEgGWLrnk9dYC0xtZv\n",
" Args:\n",
" table_names: Artist, Album, InvoiceLine\n",
"=================================\u001b[1m Tool Message \u001b[0m=================================\n",
"Name: sql_db_schema\n",
"\n",
"\n",
"CREATE TABLE \"Album\" (\n",
"\t\"AlbumId\" INTEGER NOT NULL, \n",
"\t\"Title\" NVARCHAR(160) NOT NULL, \n",
"\t\"ArtistId\" INTEGER NOT NULL, \n",
"\tPRIMARY KEY (\"AlbumId\"), \n",
"\tFOREIGN KEY(\"ArtistId\") REFERENCES \"Artist\" (\"ArtistId\")\n",
")\n",
"\n",
"/*\n",
"3 rows from Album table:\n",
"AlbumId\tTitle\tArtistId\n",
"1\tFor Those About To Rock We Salute You\t1\n",
"2\tBalls to the Wall\t2\n",
"3\tRestless and Wild\t2\n",
"*/\n",
"\n",
"\n",
"CREATE TABLE \"Artist\" (\n",
"\t\"ArtistId\" INTEGER NOT NULL, \n",
"\t\"Name\" NVARCHAR(120), \n",
"\tPRIMARY KEY (\"ArtistId\")\n",
")\n",
"\n",
"/*\n",
"3 rows from Artist table:\n",
"ArtistId\tName\n",
"1\tAC/DC\n",
"2\tAccept\n",
"3\tAerosmith\n",
"*/\n",
"\n",
"\n",
"CREATE TABLE \"InvoiceLine\" (\n",
"\t\"InvoiceLineId\" INTEGER NOT NULL, \n",
"\t\"InvoiceId\" INTEGER NOT NULL, \n",
"\t\"TrackId\" INTEGER NOT NULL, \n",
"\t\"UnitPrice\" NUMERIC(10, 2) NOT NULL, \n",
"\t\"Quantity\" INTEGER NOT NULL, \n",
"\tPRIMARY KEY (\"InvoiceLineId\"), \n",
"\tFOREIGN KEY(\"TrackId\") REFERENCES \"Track\" (\"TrackId\"), \n",
"\tFOREIGN KEY(\"InvoiceId\") REFERENCES \"Invoice\" (\"InvoiceId\")\n",
")\n",
"\n",
"/*\n",
"3 rows from InvoiceLine table:\n",
"InvoiceLineId\tInvoiceId\tTrackId\tUnitPrice\tQuantity\n",
"1\t1\t2\t0.99\t1\n",
"2\t1\t4\t0.99\t1\n",
"3\t2\t6\t0.99\t1\n",
"*/\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
"Tool Calls:\n",
" sql_db_query (call_i6n3lmS7E2ZivN758VOayTiy)\n",
" Call ID: call_i6n3lmS7E2ZivN758VOayTiy\n",
" Args:\n",
" query: SELECT Artist.Name AS artist_name, SUM(InvoiceLine.Quantity) AS total_sold FROM Artist JOIN Album ON Artist.ArtistId = Album.ArtistId JOIN Track ON Album.AlbumId = Track.AlbumId JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER BY total_sold DESC LIMIT 3\n",
"=================================\u001b[1m Tool Message \u001b[0m=================================\n",
"Name: sql_db_query\n",
"\n",
"[('Iron Maiden', 140), ('U2', 107), ('Metallica', 91)]\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
"\n",
"The top 3 best selling artists are:\n",
"1. Iron Maiden - 140 units sold\n",
"2. U2 - 107 units sold\n",
"3. Metallica - 91 units sold\n"
]
}
],
"source": [
"example_query = \"Who are the top 3 best selling artists?\"\n",
"\n",
"events = agent_executor.stream(\n",
" {\"messages\": [(\"user\", example_query)]},\n",
" stream_mode=\"values\",\n",
")\n",
"for event in events:\n",
" event[\"messages\"][-1].pretty_print()"
]
},
{
"cell_type": "markdown",
"id": "73521f1b-be03-44e6-8b27-a9a46ae8e962",
"metadata": {},
"source": [
"## Specific functionality\n",
"\n",
"`SQLDatabaseToolkit` implements a [.get_context](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.sql.toolkit.SQLDatabaseToolkit.html#langchain_community.agent_toolkits.sql.toolkit.SQLDatabaseToolkit.get_context) method as a convenience for use in prompts or other contexts.\n",
"\n",
"**⚠️ Disclaimer ⚠️** : The agent may generate insert/update/delete queries. When this is not expected, use a custom prompt or create a SQL users without write permissions.\n",
"\n",
"The final user might overload your SQL database by asking a simple question such as \"run the biggest query possible\". The generated query might look like:\n",
"\n",
"```sql\n",
"SELECT * FROM \"public\".\"users\"\n",
" JOIN \"public\".\"user_permissions\" ON \"public\".\"users\".id = \"public\".\"user_permissions\".user_id\n",
" JOIN \"public\".\"projects\" ON \"public\".\"users\".id = \"public\".\"projects\".user_id\n",
" JOIN \"public\".\"events\" ON \"public\".\"projects\".id = \"public\".\"events\".project_id;\n",
"```\n",
"\n",
"For a transactional SQL database, if one of the table above contains millions of rows, the query might cause trouble to other applications using the same database.\n",
"\n",
"Most datawarehouse oriented databases support user-level quota, for limiting resource usage."
]
},
{
"cell_type": "markdown",
"id": "1aa8a7e3-87ca-4963-a224-0cbdc9d88714",
"metadata": {},
"source": [
"## API reference\n",
"\n",
"For detailed documentation of all SQLDatabaseToolkit features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.sql.toolkit.SQLDatabaseToolkit.html)."
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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",
"version": "3.10.4"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

752
docs/docs/integrations/toolkits/xorbits.ipynb
View File

@ -1,752 +0,0 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Xorbits"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This notebook shows how to use agents to interact with [Xorbits Pandas](https://doc.xorbits.io/en/latest/reference/pandas/index.html) dataframe and [Xorbits Numpy](https://doc.xorbits.io/en/latest/reference/numpy/index.html) ndarray. It is mostly optimized for question answering.\n",
"\n",
"**NOTE: this agent calls the `Python` agent under the hood, which executes LLM generated Python code - this can be bad if the LLM generated Python code is harmful. Use cautiously.**"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Pandas examples"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"ExecuteTime": {
"end_time": "2023-07-13T08:06:33.955439Z",
"start_time": "2023-07-13T08:06:33.767539500Z"
}
},
"outputs": [],
"source": [
"import xorbits.pandas as pd\n",
"from langchain_experimental.agents.agent_toolkits import create_xorbits_agent\n",
"from langchain_openai import OpenAI"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"ExecuteTime": {
"end_time": "2023-07-13T08:06:33.955439Z",
"start_time": "2023-07-13T08:06:33.767539500Z"
}
},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "05b7c067b1114ce9a8aef4a58a5d5fef",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0.00/100 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"data = pd.read_csv(\"titanic.csv\")\n",
"agent = create_xorbits_agent(OpenAI(temperature=0), data, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"ExecuteTime": {
"end_time": "2023-07-13T08:11:06.622471100Z",
"start_time": "2023-07-13T08:11:03.183042Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to count the number of rows and columns\n",
"Action: python_repl_ast\n",
"Action Input: data.shape\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m(891, 12)\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: There are 891 rows and 12 columns.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'There are 891 rows and 12 columns.'"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"How many rows and columns are there?\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"ExecuteTime": {
"end_time": "2023-07-13T08:11:23.189275300Z",
"start_time": "2023-07-13T08:11:11.029030900Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "8c63d745a7eb41a484043a5dba357997",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0.00/100 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[32;1m\u001b[1;3mThought: I need to count the number of people in pclass 1\n",
"Action: python_repl_ast\n",
"Action Input: data[data['Pclass'] == 1].shape[0]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m216\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: There are 216 people in pclass 1.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'There are 216 people in pclass 1.'"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"How many people are in pclass 1?\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to calculate the mean age\n",
"Action: python_repl_ast\n",
"Action Input: data['Age'].mean()\u001b[0m"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "29af2e29f2d64a3397c212812adf0e9b",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0.00/100 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Observation: \u001b[36;1m\u001b[1;3m29.69911764705882\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The mean age is 29.69911764705882.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The mean age is 29.69911764705882.'"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"whats the mean age?\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to group the data by sex and then find the average age for each group\n",
"Action: python_repl_ast\n",
"Action Input: data.groupby('Sex')['Age'].mean()\u001b[0m"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "c3d28625c35946fd91ebc2a47f8d8c5b",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0.00/100 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Observation: \u001b[36;1m\u001b[1;3mSex\n",
"female 27.915709\n",
"male 30.726645\n",
"Name: Age, dtype: float64\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the average age for each group\n",
"Final Answer: The average age for female passengers is 27.92 and the average age for male passengers is 30.73.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The average age for female passengers is 27.92 and the average age for male passengers is 30.73.'"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"Group the data by sex and find the average age for each group\")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "c72aab63b20d47599f4f9806f6887a69",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0.00/100 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[32;1m\u001b[1;3mThought: I need to filter the dataframe to get the desired result\n",
"Action: python_repl_ast\n",
"Action Input: data[(data['Age'] > 30) & (data['Fare'] > 30) & (data['Fare'] < 50) & ((data['Pclass'] == 1) | (data['Pclass'] == 2))].shape[0]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m20\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: 20\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'20'"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\n",
" \"Show the number of people whose age is greater than 30 and fare is between 30 and 50 , and pclass is either 1 or 2\"\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Numpy examples"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "fa8baf315a0c41c89392edc4a24b76f5",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0.00/100 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import xorbits.numpy as np\n",
"from langchain_experimental.agents.agent_toolkits import create_xorbits_agent\n",
"from langchain_openai import OpenAI\n",
"\n",
"arr = np.array([1, 2, 3, 4, 5, 6])\n",
"agent = create_xorbits_agent(OpenAI(temperature=0), arr, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to find out the shape of the array\n",
"Action: python_repl_ast\n",
"Action Input: data.shape\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m(6,)\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The shape of the array is (6,).\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The shape of the array is (6,).'"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"Give the shape of the array \")"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to access the 2nd element of the array\n",
"Action: python_repl_ast\n",
"Action Input: data[1]\u001b[0m"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "64efcc74f81f404eb0a7d3f0326cd8b3",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0.00/100 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Observation: \u001b[36;1m\u001b[1;3m2\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: 2\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'2'"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"Give the 2nd element of the array \")"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to reshape the array and then transpose it\n",
"Action: python_repl_ast\n",
"Action Input: np.reshape(data, (2,3)).T\u001b[0m"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "fce51acf6fb347c0b400da67c6750534",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0.00/100 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Observation: \u001b[36;1m\u001b[1;3m[[1 4]\n",
" [2 5]\n",
" [3 6]]\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The reshaped and transposed array is [[1 4], [2 5], [3 6]].\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The reshaped and transposed array is [[1 4], [2 5], [3 6]].'"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\n",
" \"Reshape the array into a 2-dimensional array with 2 rows and 3 columns, and then transpose it\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to reshape the array and then sum it\n",
"Action: python_repl_ast\n",
"Action Input: np.sum(np.reshape(data, (3,2)), axis=0)\u001b[0m"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "27fd4a0bbf694936bc41a6991064dec2",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0.00/100 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Observation: \u001b[36;1m\u001b[1;3m[ 9 12]\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The sum of the array along the first axis is [9, 12].\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The sum of the array along the first axis is [9, 12].'"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\n",
" \"Reshape the array into a 2-dimensional array with 3 rows and 2 columns and sum the array along the first axis\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "a591b6d7913f45cba98d2f3b71a5120a",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0.00/100 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"arr = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]])\n",
"agent = create_xorbits_agent(OpenAI(temperature=0), arr, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to use the numpy covariance function\n",
"Action: python_repl_ast\n",
"Action Input: np.cov(data)\u001b[0m"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "5fe40f83cfae48d0919c147627b5839f",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0.00/100 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Observation: \u001b[36;1m\u001b[1;3m[[1. 1. 1.]\n",
" [1. 1. 1.]\n",
" [1. 1. 1.]]\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The covariance matrix is [[1. 1. 1.], [1. 1. 1.], [1. 1. 1.]].\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The covariance matrix is [[1. 1. 1.], [1. 1. 1.], [1. 1. 1.]].'"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"calculate the covariance matrix\")"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to use the SVD function\n",
"Action: python_repl_ast\n",
"Action Input: U, S, V = np.linalg.svd(data)\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now have the U matrix\n",
"Final Answer: U = [[-0.70710678 -0.70710678]\n",
" [-0.70710678 0.70710678]]\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'U = [[-0.70710678 -0.70710678]\\n [-0.70710678 0.70710678]]'"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"compute the U of Singular Value Decomposition of the matrix\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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",
"version": "3.10.1"
}
},
"nbformat": 4,
"nbformat_minor": 4
}

2
docs/docs/integrations/toolkits/ainetwork.ipynb → docs/docs/integrations/tools/ainetwork.ipynb
View File

@ -4,7 +4,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# AINetwork\n", "# AINetwork Toolkit\n",
"\n", "\n",
">[AI Network](https://www.ainetwork.ai/build-on-ain) is a layer 1 blockchain designed to accommodate large-scale AI models, utilizing a decentralized GPU network powered by the [$AIN token](https://www.ainetwork.ai/token), enriching AI-driven `NFTs` (`AINFTs`).\n", ">[AI Network](https://www.ainetwork.ai/build-on-ain) is a layer 1 blockchain designed to accommodate large-scale AI models, utilizing a decentralized GPU network powered by the [$AIN token](https://www.ainetwork.ai/token), enriching AI-driven `NFTs` (`AINFTs`).\n",
">\n", ">\n",

2
docs/docs/integrations/toolkits/amadeus.ipynb → docs/docs/integrations/tools/amadeus.ipynb
View File

@ -4,7 +4,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Amadeus\n", "# Amadeus Toolkit\n",
"\n", "\n",
"This notebook walks you through connecting LangChain to the `Amadeus` travel APIs.\n", "This notebook walks you through connecting LangChain to the `Amadeus` travel APIs.\n",
"\n", "\n",

170
docs/docs/integrations/tools/apify.ipynb
View File

@ -1,170 +0,0 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Apify\n",
"\n",
"This notebook shows how to use the [Apify integration](/docs/integrations/providers/apify) for LangChain.\n",
"\n",
"[Apify](https://apify.com) is a cloud platform for web scraping and data extraction,\n",
"which provides an [ecosystem](https://apify.com/store) of more than a thousand\n",
"ready-made apps called *Actors* for various web scraping, crawling, and data extraction use cases.\n",
"For example, you can use it to extract Google Search results, Instagram and Facebook profiles, products from Amazon or Shopify, Google Maps reviews, etc. etc.\n",
"\n",
"In this example, we'll use the [Website Content Crawler](https://apify.com/apify/website-content-crawler) Actor,\n",
"which can deeply crawl websites such as documentation, knowledge bases, help centers, or blogs,\n",
"and extract text content from the web pages. Then we feed the documents into a vector index and answer questions from it.\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%pip install --upgrade --quiet apify-client langchain-community langchain-openai langchain"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"First, import `ApifyWrapper` into your source code:"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from langchain.indexes import VectorstoreIndexCreator\n",
"from langchain_community.utilities import ApifyWrapper\n",
"from langchain_core.documents import Document\n",
"from langchain_openai import OpenAI\n",
"from langchain_openai.embeddings import OpenAIEmbeddings"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Initialize it using your [Apify API token](https://docs.apify.com/platform/integrations/api#api-token) and for the purpose of this example, also with your OpenAI API key:"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"os.environ[\"OPENAI_API_KEY\"] = \"Your OpenAI API key\"\n",
"os.environ[\"APIFY_API_TOKEN\"] = \"Your Apify API token\"\n",
"\n",
"apify = ApifyWrapper()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Then run the Actor, wait for it to finish, and fetch its results from the Apify dataset into a LangChain document loader.\n",
"\n",
"Note that if you already have some results in an Apify dataset, you can load them directly using `ApifyDatasetLoader`, as shown in [this notebook](/docs/integrations/document_loaders/apify_dataset). In that notebook, you'll also find the explanation of the `dataset_mapping_function`, which is used to map fields from the Apify dataset records to LangChain `Document` fields."
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"loader = apify.call_actor(\n",
" actor_id=\"apify/website-content-crawler\",\n",
" run_input={\"startUrls\": [{\"url\": \"https://python.langchain.com\"}]},\n",
" dataset_mapping_function=lambda item: Document(\n",
" page_content=item[\"text\"] or \"\", metadata={\"source\": item[\"url\"]}\n",
" ),\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Initialize the vector index from the crawled documents:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"index = VectorstoreIndexCreator(embedding=OpenAIEmbeddings()).from_loaders([loader])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"And finally, query the vector index:"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"query = \"What is LangChain?\"\n",
"result = index.query_with_sources(query, llm=OpenAI())"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" LangChain is a standard interface through which you can interact with a variety of large language models (LLMs). It provides modules that can be used to build language model applications, and it also provides chains and agents with memory capabilities.\n",
"\n",
"https://python.langchain.com/en/latest/modules/models/llms.html, https://python.langchain.com/en/latest/getting_started/getting_started.html\n"
]
}
],
"source": [
"print(result[\"answer\"])\n",
"print(result[\"sources\"])"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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",
"version": "3.11.3"
}
},
"nbformat": 4,
"nbformat_minor": 4
}

2
docs/docs/integrations/toolkits/azure_ai_services.ipynb → docs/docs/integrations/tools/azure_ai_services.ipynb
View File

@ -4,7 +4,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Azure AI Services\n", "# Azure AI Services Toolkit\n",
"\n", "\n",
"This toolkit is used to interact with the `Azure AI Services API` to achieve some multimodal capabilities.\n", "This toolkit is used to interact with the `Azure AI Services API` to achieve some multimodal capabilities.\n",
"\n", "\n",

2
docs/docs/integrations/toolkits/azure_cognitive_services.ipynb → docs/docs/integrations/tools/azure_cognitive_services.ipynb
View File

@ -4,7 +4,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Azure Cognitive Services\n", "# Azure Cognitive Services Toolkit\n",
"\n", "\n",
"This toolkit is used to interact with the `Azure Cognitive Services API` to achieve some multimodal capabilities.\n", "This toolkit is used to interact with the `Azure Cognitive Services API` to achieve some multimodal capabilities.\n",
"\n", "\n",

14
docs/docs/integrations/toolkits/cassandra_database.ipynb → docs/docs/integrations/tools/cassandra_database.ipynb
View File

@ -4,7 +4,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Cassandra Database\n", "# Cassandra Database Toolkit\n",
"\n", "\n",
">`Apache Cassandra®` is a widely used database for storing transactional application data. The introduction of functions and >tooling in Large Language Models has opened up some exciting use cases for existing data in Generative AI applications. \n", ">`Apache Cassandra®` is a widely used database for storing transactional application data. The introduction of functions and >tooling in Large Language Models has opened up some exciting use cases for existing data in Generative AI applications. \n",
"\n", "\n",
@ -148,11 +148,6 @@
" CassandraDatabaseToolkit,\n", " CassandraDatabaseToolkit,\n",
")\n", ")\n",
"from langchain_community.tools.cassandra_database.prompt import QUERY_PATH_PROMPT\n", "from langchain_community.tools.cassandra_database.prompt import QUERY_PATH_PROMPT\n",
"from langchain_community.tools.cassandra_database.tool import (\n",
" GetSchemaCassandraDatabaseTool,\n",
" GetTableDataCassandraDatabaseTool,\n",
" QueryCassandraDatabaseTool,\n",
")\n",
"from langchain_community.utilities.cassandra_database import CassandraDatabase\n", "from langchain_community.utilities.cassandra_database import CassandraDatabase\n",
"from langchain_openai import ChatOpenAI" "from langchain_openai import ChatOpenAI"
] ]
@ -263,12 +258,7 @@
"source": [ "source": [
"# Create a CassandraDatabase instance\n", "# Create a CassandraDatabase instance\n",
"# Uses the cassio session to connect to the database\n", "# Uses the cassio session to connect to the database\n",
"db = CassandraDatabase()\n", "db = CassandraDatabase()"
"\n",
"# Create the Cassandra Database tools\n",
"query_tool = QueryCassandraDatabaseTool(db=db)\n",
"schema_tool = GetSchemaCassandraDatabaseTool(db=db)\n",
"select_data_tool = GetTableDataCassandraDatabaseTool(db=db)"
] ]
}, },
{ {

2
docs/docs/integrations/toolkits/clickup.ipynb → docs/docs/integrations/tools/clickup.ipynb
View File

@ -4,7 +4,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# ClickUp\n", "# ClickUp Toolkit\n",
"\n", "\n",
">[ClickUp](https://clickup.com/) is an all-in-one productivity platform that provides small and large teams across industries with flexible and customizable work management solutions, tools, and functions. \n", ">[ClickUp](https://clickup.com/) is an all-in-one productivity platform that provides small and large teams across industries with flexible and customizable work management solutions, tools, and functions. \n",
"\n", "\n",

49
docs/docs/integrations/toolkits/cogniswitch.ipynb → docs/docs/integrations/tools/cogniswitch.ipynb
View File

@ -5,44 +5,17 @@
"id": "19062701", "id": "19062701",
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Cogniswitch Tools\n", "# Cogniswitch Toolkit\n",
"\n", "\n",
"**Use CogniSwitch to build production ready applications that can consume, organize and retrieve knowledge flawlessly. Using the framework of your choice, in this case Langchain CogniSwitch helps alleviate the stress of decision making when it comes to, choosing the right storage and retrieval formats. It also eradicates reliability issues and hallucinations when it comes to responses that are generated. Get started by interacting with your knowledge in just two simple steps.**\n", "CogniSwitch is used to build production ready applications that can consume, organize and retrieve knowledge flawlessly. Using the framework of your choice, in this case Langchain, CogniSwitch helps alleviate the stress of decision making when it comes to, choosing the right storage and retrieval formats. It also eradicates reliability issues and hallucinations when it comes to responses that are generated. \n",
"\n", "\n",
"visit [https://www.cogniswitch.ai/developer to register](https://www.cogniswitch.ai/developer?utm_source=langchain&utm_medium=langchainbuild&utm_id=dev).\n", "## Setup\n",
"\n", "\n",
"**Registration:** \n", "Visit [this page](https://www.cogniswitch.ai/developer?utm_source=langchain&utm_medium=langchainbuild&utm_id=dev) to register a Cogniswitch account.\n",
"\n", "\n",
"- Signup with your email and verify your registration \n", "- Signup with your email and verify your registration \n",
"\n", "\n",
"- You will get a mail with a platform token and oauth token for using the services.\n", "- You will get a mail with a platform token and oauth token for using the services.\n"
"\n",
"\n",
"\n",
"**step 1: Instantiate the toolkit and get the tools:**\n",
"\n",
"- Instantiate the cogniswitch toolkit with the cogniswitch token, openAI API key and OAuth token and get the tools. \n",
"\n",
"**step 2: Instantiate the agent with the tools and llm:**\n",
"- Instantiate the agent with the list of cogniswitch tools and the llm, into the agent executor.\n",
"\n",
"**step 3: CogniSwitch Store Tool:** \n",
"\n",
"***CogniSwitch knowledge source file tool***\n",
"- Use the agent to upload a file by giving the file path.(formats that are currently supported are .pdf, .docx, .doc, .txt, .html) \n",
"- The content from the file will be processed by the cogniswitch and stored in your knowledge store. \n",
"\n",
"***CogniSwitch knowledge source url tool***\n",
"- Use the agent to upload a URL. \n",
"- The content from the url will be processed by the cogniswitch and stored in your knowledge store. \n",
"\n",
"**step 4: CogniSwitch Status Tool:**\n",
"- Use the agent to know the status of the document uploaded with a document name.\n",
"- You can also check the status of document processing in cogniswitch console. \n",
"\n",
"**step 5: CogniSwitch Answer Tool:**\n",
"- Use the agent to ask your question.\n",
"- You will get the answer from your knowledge as the response. \n"
] ]
}, },
{ {
@ -60,7 +33,7 @@
"id": "1435b193", "id": "1435b193",
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Import necessary libraries" "## Import necessary libraries"
] ]
}, },
{ {
@ -86,7 +59,7 @@
"id": "6e6acf0e", "id": "6e6acf0e",
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Cogniswitch platform token, OAuth token and OpenAI API key" "## Cogniswitch platform token, OAuth token and OpenAI API key"
] ]
}, },
{ {
@ -108,7 +81,7 @@
"id": "320e02fc", "id": "320e02fc",
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Instantiate the cogniswitch toolkit with the credentials" "## Instantiate the cogniswitch toolkit with the credentials"
] ]
}, },
{ {
@ -146,7 +119,7 @@
"id": "4aae43a3", "id": "4aae43a3",
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Instantiate the llm" "## Instantiate the LLM"
] ]
}, },
{ {
@ -169,7 +142,9 @@
"id": "04179282", "id": "04179282",
"metadata": {}, "metadata": {},
"source": [ "source": [
"### Create a agent executor" "## Use the LLM with the Toolkit\n",
"\n",
"### Create an agent with the LLM and Toolkit"
] ]
}, },
{ {

2
docs/docs/integrations/tools/connery.ipynb
View File

@ -9,7 +9,7 @@
"Using this tool, you can integrate individual Connery Action into your LangChain agent.\n", "Using this tool, you can integrate individual Connery Action into your LangChain agent.\n",
"\n", "\n",
"If you want to use more than one Connery Action in your agent,\n", "If you want to use more than one Connery Action in your agent,\n",
"check out the [Connery Toolkit](/docs/integrations/toolkits/connery) documentation.\n", "check out the [Connery Toolkit](/docs/integrations/tools/connery_toolkit) documentation.\n",
"\n", "\n",
"## What is Connery?\n", "## What is Connery?\n",
"\n", "\n",

0
docs/docs/integrations/toolkits/connery.ipynb → docs/docs/integrations/tools/connery_toolkit.ipynb
View File

120
docs/docs/integrations/toolkits/financial_datasets.ipynb → docs/docs/integrations/tools/financial_datasets.ipynb
View File

@ -1,19 +1,12 @@
{ {
"cells": [ "cells": [
{
"cell_type": "raw",
"id": "afaf8039",
"metadata": {},
"source": [
"---\n",
"sidebar_label: financial datasets\n",
"---"
]
},
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {
"collapsed": false
},
"source": [ "source": [
"# FinancialDatasetsToolkit\n", "# FinancialDatasets Toolkit\n",
"\n", "\n",
"The [financial datasets](https://financialdatasets.ai/) stock market API provides REST endpoints that let you get financial data for 16,000+ tickers spanning 30+ years.\n", "The [financial datasets](https://financialdatasets.ai/) stock market API provides REST endpoints that let you get financial data for 16,000+ tickers spanning 30+ years.\n",
"\n", "\n",
@ -23,46 +16,43 @@
"\n", "\n",
"`FINANCIAL_DATASETS_API_KEY`: Get it from [financialdatasets.ai](https://financialdatasets.ai/).\n", "`FINANCIAL_DATASETS_API_KEY`: Get it from [financialdatasets.ai](https://financialdatasets.ai/).\n",
"`OPENAI_API_KEY`: Get it from [OpenAI](https://platform.openai.com/)." "`OPENAI_API_KEY`: Get it from [OpenAI](https://platform.openai.com/)."
], ]
"metadata": {
"collapsed": false
}
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [], "outputs": [],
"source": [ "source": [
"import getpass\n", "import getpass\n",
"import os\n", "import os\n",
"\n", "\n",
"os.environ[\"FINANCIAL_DATASETS_API_KEY\"] = getpass.getpass()" "os.environ[\"FINANCIAL_DATASETS_API_KEY\"] = getpass.getpass()"
], ]
"metadata": {
"collapsed": false
}
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [], "outputs": [],
"source": [ "source": [
"os.environ[\"OPENAI_API_KEY\"] = getpass.getpass()" "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass()"
], ]
"metadata": {
"collapsed": false
}
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {
"collapsed": false
},
"source": [ "source": [
"### Installation\n", "### Installation\n",
"\n", "\n",
"This toolkit lives in the `langchain-community` package." "This toolkit lives in the `langchain-community` package."
], ]
"metadata": {
"collapsed": false
}
}, },
{ {
"cell_type": "code", "cell_type": "code",
@ -124,18 +114,21 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {
"collapsed": false
},
"source": [ "source": [
"## Use within an agent\n", "## Use within an agent\n",
"\n", "\n",
"Let's equip our agent with the FinancialDatasetsToolkit and ask financial questions." "Let's equip our agent with the FinancialDatasetsToolkit and ask financial questions."
], ]
"metadata": {
"collapsed": false
}
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [], "outputs": [],
"source": [ "source": [
"system_prompt = \"\"\"\n", "system_prompt = \"\"\"\n",
@ -170,19 +163,16 @@
"Remember, your goal is to provide accurate, insightful financial analysis to\n", "Remember, your goal is to provide accurate, insightful financial analysis to\n",
"help users make informed decisions. Always maintain a professional and objective tone in your responses.\n", "help users make informed decisions. Always maintain a professional and objective tone in your responses.\n",
"\"\"\"" "\"\"\""
], ]
"metadata": {
"collapsed": false
}
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"source": [
"Instantiate the LLM."
],
"metadata": { "metadata": {
"collapsed": false "collapsed": false
} },
"source": [
"Instantiate the LLM."
]
}, },
{ {
"cell_type": "code", "cell_type": "code",
@ -199,12 +189,12 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"source": [
"Define a user query."
],
"metadata": { "metadata": {
"collapsed": false "collapsed": false
} },
"source": [
"Define a user query."
]
}, },
{ {
"cell_type": "code", "cell_type": "code",
@ -218,16 +208,19 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"source": [
"Create the agent."
],
"metadata": { "metadata": {
"collapsed": false "collapsed": false
} },
"source": [
"Create the agent."
]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [], "outputs": [],
"source": [ "source": [
"from langchain.agents import AgentExecutor, create_tool_calling_agent\n", "from langchain.agents import AgentExecutor, create_tool_calling_agent\n",
@ -245,48 +238,45 @@
"\n", "\n",
"agent = create_tool_calling_agent(model, tools, prompt)\n", "agent = create_tool_calling_agent(model, tools, prompt)\n",
"agent_executor = AgentExecutor(agent=agent, tools=tools)" "agent_executor = AgentExecutor(agent=agent, tools=tools)"
], ]
"metadata": {
"collapsed": false
}
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"source": [
"Query the agent."
],
"metadata": { "metadata": {
"collapsed": false "collapsed": false
} },
"source": [
"Query the agent."
]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [], "outputs": [],
"source": [ "source": [
"agent_executor.invoke({\"input\": query})" "agent_executor.invoke({\"input\": query})"
], ]
"metadata": {
"collapsed": false
}
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {
"collapsed": false
},
"source": [ "source": [
"## API reference\n", "## API reference\n",
"\n", "\n",
"For detailed documentation of all `FinancialDatasetsToolkit` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.financial_datasets.toolkit.FinancialDatasetsToolkit.html)." "For detailed documentation of all `FinancialDatasetsToolkit` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.financial_datasets.toolkit.FinancialDatasetsToolkit.html)."
], ]
"metadata": {
"collapsed": false
}
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"source": [],
"metadata": { "metadata": {
"collapsed": false "collapsed": false
} },
"source": []
} }
], ],
"metadata": { "metadata": {

11
docs/docs/integrations/toolkits/github.ipynb → docs/docs/integrations/tools/github.ipynb
View File

@ -4,16 +4,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"---\n", "# Github Toolkit\n",
"sidebar_label: Github\n",
"---"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# GithubToolkit\n",
"\n", "\n",
"The `Github` toolkit contains tools that enable an LLM agent to interact with a github repository. \n", "The `Github` toolkit contains tools that enable an LLM agent to interact with a github repository. \n",
"The tool is a wrapper for the [PyGitHub](https://github.com/PyGithub/PyGithub) library. \n", "The tool is a wrapper for the [PyGitHub](https://github.com/PyGithub/PyGithub) library. \n",

2
docs/docs/integrations/toolkits/gitlab.ipynb → docs/docs/integrations/tools/gitlab.ipynb
View File

@ -4,7 +4,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Gitlab\n", "# Gitlab Toolkit\n",
"\n", "\n",
"The `Gitlab` toolkit contains tools that enable an LLM agent to interact with a gitlab repository. \n", "The `Gitlab` toolkit contains tools that enable an LLM agent to interact with a gitlab repository. \n",
"The tool is a wrapper for the [python-gitlab](https://github.com/python-gitlab/python-gitlab) library. \n", "The tool is a wrapper for the [python-gitlab](https://github.com/python-gitlab/python-gitlab) library. \n",

11
docs/docs/integrations/toolkits/gmail.ipynb → docs/docs/integrations/tools/gmail.ipynb
View File

@ -4,16 +4,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"---\n", "# Gmail Toolkit\n",
"sidebar_label: GMail\n",
"---"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# GmailToolkit\n",
"\n", "\n",
"This will help you getting started with the GMail [toolkit](/docs/concepts/#toolkits). This toolkit interacts with the GMail API to read messages, draft and send messages, and more. For detailed documentation of all GmailToolkit features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/gmail/langchain_google_community.gmail.toolkit.GmailToolkit.html).\n", "This will help you getting started with the GMail [toolkit](/docs/concepts/#toolkits). This toolkit interacts with the GMail API to read messages, draft and send messages, and more. For detailed documentation of all GmailToolkit features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/gmail/langchain_google_community.gmail.toolkit.GmailToolkit.html).\n",
"\n", "\n",

2
docs/docs/integrations/toolkits/jira.ipynb → docs/docs/integrations/tools/jira.ipynb
View File

@ -5,7 +5,7 @@
"id": "245a954a", "id": "245a954a",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Jira\n", "# Jira Toolkit\n",
"\n", "\n",
"This notebook goes over how to use the `Jira` toolkit.\n", "This notebook goes over how to use the `Jira` toolkit.\n",
"\n", "\n",

2
docs/docs/integrations/toolkits/json.ipynb → docs/docs/integrations/tools/json.ipynb
View File

@ -5,7 +5,7 @@
"id": "85fb2c03-ab88-4c8c-97e3-a7f2954555ab", "id": "85fb2c03-ab88-4c8c-97e3-a7f2954555ab",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# JSON\n", "# JSON Toolkit\n",
"\n", "\n",
"This notebook showcases an agent interacting with large `JSON/dict` objects. \n", "This notebook showcases an agent interacting with large `JSON/dict` objects. \n",
"This is useful when you want to answer questions about a JSON blob that's too large to fit in the context window of an LLM. The agent is able to iteratively explore the blob to find what it needs to answer the user's question.\n", "This is useful when you want to answer questions about a JSON blob that's too large to fit in the context window of an LLM. The agent is able to iteratively explore the blob to find what it needs to answer the user's question.\n",

2
docs/docs/integrations/toolkits/multion.ipynb → docs/docs/integrations/tools/multion.ipynb
View File

@ -4,7 +4,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# MultiOn\n", "# MultiOn Toolkit\n",
" \n", " \n",
"[MultiON](https://www.multion.ai/blog/multion-building-a-brighter-future-for-humanity-with-ai-agents) has built an AI Agent that can interact with a broad array of web services and applications. \n", "[MultiON](https://www.multion.ai/blog/multion-building-a-brighter-future-for-humanity-with-ai-agents) has built an AI Agent that can interact with a broad array of web services and applications. \n",
"\n", "\n",

2
docs/docs/integrations/toolkits/nasa.ipynb → docs/docs/integrations/tools/nasa.ipynb
View File

@ -5,7 +5,7 @@
"id": "e6fd05db-21c2-4227-9900-0840bc62cb31", "id": "e6fd05db-21c2-4227-9900-0840bc62cb31",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# NASA\n", "# NASA Toolkit\n",
"\n", "\n",
"This notebook shows how to use agents to interact with the NASA toolkit. The toolkit provides access to the NASA Image and Video Library API, with potential to expand and include other accessible NASA APIs in future iterations.\n", "This notebook shows how to use agents to interact with the NASA toolkit. The toolkit provides access to the NASA Image and Video Library API, with potential to expand and include other accessible NASA APIs in future iterations.\n",
"\n", "\n",

2
docs/docs/integrations/toolkits/office365.ipynb → docs/docs/integrations/tools/office365.ipynb
View File

@ -4,7 +4,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Office365\n", "# Office365 Toolkit\n",
"\n", "\n",
">[Microsoft 365](https://www.office.com/) is a product family of productivity software, collaboration and cloud-based services owned by `Microsoft`.\n", ">[Microsoft 365](https://www.office.com/) is a product family of productivity software, collaboration and cloud-based services owned by `Microsoft`.\n",
">\n", ">\n",

2
docs/docs/integrations/toolkits/openapi.ipynb → docs/docs/integrations/tools/openapi.ipynb
View File

@ -5,7 +5,7 @@
"id": "85fb2c03-ab88-4c8c-97e3-a7f2954555ab", "id": "85fb2c03-ab88-4c8c-97e3-a7f2954555ab",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# OpenAPI\n", "# OpenAPI Toolkit\n",
"\n", "\n",
"We can construct agents to consume arbitrary APIs, here APIs conformant to the `OpenAPI`/`Swagger` specification." "We can construct agents to consume arbitrary APIs, here APIs conformant to the `OpenAPI`/`Swagger` specification."
] ]

2
docs/docs/integrations/toolkits/openapi_nla.ipynb → docs/docs/integrations/tools/openapi_nla.ipynb
View File

@ -5,7 +5,7 @@
"id": "c7ad998d", "id": "c7ad998d",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Natural Language APIs\n", "# Natural Language API Toolkits\n",
"\n", "\n",
"`Natural Language API` Toolkits (`NLAToolkits`) permit LangChain Agents to efficiently plan and combine calls across endpoints. \n", "`Natural Language API` Toolkits (`NLAToolkits`) permit LangChain Agents to efficiently plan and combine calls across endpoints. \n",
"\n", "\n",

0
docs/docs/integrations/toolkits/pandas.ipynb → docs/docs/integrations/tools/pandas.ipynb
View File

2
docs/docs/integrations/toolkits/playwright.ipynb → docs/docs/integrations/tools/playwright.ipynb
View File

@ -4,7 +4,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# PlayWright Browser\n", "# PlayWright Browser Toolkit\n",
"\n", "\n",
"This toolkit is used to interact with the browser. While other tools (like the `Requests` tools) are fine for static sites, `PlayWright Browser` toolkits let your agent navigate the web and interact with dynamically rendered sites. \n", "This toolkit is used to interact with the browser. While other tools (like the `Requests` tools) are fine for static sites, `PlayWright Browser` toolkits let your agent navigate the web and interact with dynamically rendered sites. \n",
"\n", "\n",

4
docs/docs/integrations/tools/polygon.ipynb
View File

@ -7,7 +7,7 @@
"id": "245a954a" "id": "245a954a"
}, },
"source": [ "source": [
"# Polygon Stock Market API Tools\n", "# Polygon IO\n",
"\n", "\n",
">[Polygon](https://polygon.io/) The Polygon.io Stocks API provides REST endpoints that let you query the latest market data from all US stock exchanges.\n", ">[Polygon](https://polygon.io/) The Polygon.io Stocks API provides REST endpoints that let you query the latest market data from all US stock exchanges.\n",
"\n", "\n",
@ -25,7 +25,7 @@
}, },
"outputs": [ "outputs": [
{ {
"name": "stdin", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
" ········\n" " ········\n"

0
docs/docs/integrations/toolkits/polygon.ipynb → docs/docs/integrations/tools/polygon_toolkit.ipynb
View File

2
docs/docs/integrations/toolkits/powerbi.ipynb → docs/docs/integrations/tools/powerbi.ipynb
View File

@ -5,7 +5,7 @@
"id": "9363398d", "id": "9363398d",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# PowerBI Dataset\n", "# PowerBI Toolkit\n",
"\n", "\n",
"This notebook showcases an agent interacting with a `Power BI Dataset`. The agent is answering more general questions about a dataset, as well as recover from errors.\n", "This notebook showcases an agent interacting with a `Power BI Dataset`. The agent is answering more general questions about a dataset, as well as recover from errors.\n",
"\n", "\n",

338
docs/docs/integrations/tools/requests.ipynb
View File

File diff suppressed because one or more lines are too long

2
docs/docs/integrations/toolkits/robocorp.ipynb → docs/docs/integrations/tools/robocorp.ipynb
View File

@ -5,7 +5,7 @@
"id": "e49f1e0d", "id": "e49f1e0d",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Robocorp\n", "# Robocorp Toolkit\n",
"\n", "\n",
"This notebook covers how to get started with [Robocorp Action Server](https://github.com/robocorp/robocorp) action toolkit and LangChain.\n", "This notebook covers how to get started with [Robocorp Action Server](https://github.com/robocorp/robocorp) action toolkit and LangChain.\n",
"\n", "\n",

441
docs/docs/integrations/tools/search_tools.ipynb
View File

@ -1,441 +0,0 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "6510f51c",
"metadata": {},
"source": [
"# Search Tools\n",
"\n",
"This notebook shows off usage of various search tools."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "e6860c2d",
"metadata": {
"pycharm": {
"is_executing": true
}
},
"outputs": [],
"source": [
"from langchain.agents import AgentType, initialize_agent, load_tools\n",
"from langchain_openai import OpenAI"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "dadbcfcd",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)"
]
},
{
"cell_type": "markdown",
"id": "ee251155",
"metadata": {},
"source": [
"## Google Serper API Wrapper\n",
"\n",
"First, let's try to use the Google Serper API tool."
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "0cdaa487",
"metadata": {},
"outputs": [],
"source": [
"tools = load_tools([\"google-serper\"], llm=llm)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "01b1ab4a",
"metadata": {},
"outputs": [],
"source": [
"agent = initialize_agent(\n",
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "5cf44ec0",
"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 conditions.\n",
"Action: Search\n",
"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"
]
},
{
"data": {
"text/plain": [
"'The current temperature in Pomfret is 37°F.'"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"What is the weather in Pomfret?\")"
]
},
{
"cell_type": "markdown",
"id": "8786bdc8",
"metadata": {},
"source": [
"## SearchApi\n",
"\n",
"Second, let's try SearchApi tool."
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "5fd5ca32",
"metadata": {},
"outputs": [],
"source": [
"tools = load_tools([\"searchapi\"], llm=llm)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "547c9cf5-aa4d-48ed-b7a5-29ecc1491adf",
"metadata": {},
"outputs": [],
"source": [
"agent = initialize_agent(\n",
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "a7564c40-83ec-490b-ad36-385be5c20e58",
"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 need to find out the current weather in Pomfret.\n",
"Action: searchapi\n",
"Action Input: \"weather in Pomfret\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mThu 14 | Day ... Some clouds this morning will give way to generally sunny skies for the afternoon. High 73F. Winds NW at 5 to 10 mph.\n",
"Hourly Weather-Pomfret, CT · 1 pm. 71°. 0%. Sunny. Feels Like71°. WindNW 9 mph · 2 pm. 72°. 0%. Sunny. Feels Like72°. WindNW 9 mph · 3 pm. 72°. 0%. Sunny. Feels ...\n",
"10 Day Weather-Pomfret, VT. As of 4:28 am EDT. Today. 68°/48°. 4%. Thu 14 | Day. 68°. 4%. WNW 10 mph. Some clouds this morning will give way to generally ...\n",
"Be prepared with the most accurate 10-day forecast for Pomfret, MD with highs, lows, chance of precipitation from The Weather Channel and Weather.com.\n",
"Current Weather. 10:00 PM. 65°F. RealFeel® 67°. Mostly cloudy. LOCAL HURRICANE TRACKER. Category2. Lee. Late Friday Night - Saturday Afternoon.\n",
"10 Day Weather-Pomfret, NY. As of 5:09 pm EDT. Tonight. --/55°. 10%. Wed 13 | Night. 55°. 10%. NW 11 mph. Some clouds. Low near 55F.\n",
"Pomfret CT. Overnight. Overnight: Patchy fog before 3am, then patchy fog after 4am. Otherwise, mostly. Patchy Fog. Low: 58 °F. Thursday.\n",
"Isolated showers. Mostly cloudy, with a high near 76. Calm wind. Chance of precipitation is 20%. Tonight. Mostly Cloudy. Mostly cloudy, with a ...\n",
"Partly sunny, with a high near 67. Breezy, with a north wind 18 to 22 mph, with gusts as high as 34 mph. Chance of precipitation is 30%. ... A chance of showers ...\n",
"Today's Weather - Pomfret, CT ... Patchy fog. Showers. Lows in the upper 50s. Northwest winds around 5 mph. Chance of rain near 100 percent. ... Sunny. Patchy fog ...\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 mostly cloudy with a high near 67 and a chance of showers. Winds are from the north at 18 to 22 mph with gusts up to 34 mph.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The current weather in Pomfret is mostly cloudy with a high near 67 and a chance of showers. Winds are from the north at 18 to 22 mph with gusts up to 34 mph.'"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"What is the weather in Pomfret?\")"
]
},
{
"cell_type": "markdown",
"id": "0e39fc46",
"metadata": {},
"source": [
"## SerpAPI\n",
"\n",
"Now, let's use the SerpAPI tool."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "e1c39a0f",
"metadata": {},
"outputs": [],
"source": [
"tools = load_tools([\"serpapi\"], llm=llm)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "900dd6cb",
"metadata": {},
"outputs": [],
"source": [
"agent = initialize_agent(\n",
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "342ee8ec",
"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 need to find out what the current weather is in Pomfret.\n",
"Action: Search\n",
"Action Input: \"weather in Pomfret\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m{'type': 'weather_result', 'temperature': '69', 'unit': 'Fahrenheit', 'precipitation': '2%', 'humidity': '90%', 'wind': '1 mph', 'location': 'Pomfret, CT', 'date': 'Sunday 9:00 PM', 'weather': 'Clear'}\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the current weather in Pomfret.\n",
"Final Answer: The current weather in Pomfret is 69 degrees Fahrenheit, 2% precipitation, 90% humidity, and 1 mph wind. It is currently clear.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The current weather in Pomfret is 69 degrees Fahrenheit, 2% precipitation, 90% humidity, and 1 mph wind. It is currently clear.'"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"What is the weather in Pomfret?\")"
]
},
{
"cell_type": "markdown",
"id": "adc8bb68",
"metadata": {},
"source": [
"## GoogleSearchAPIWrapper\n",
"\n",
"Now, let's use the official Google Search API Wrapper."
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "ef24f92d",
"metadata": {},
"outputs": [],
"source": [
"tools = load_tools([\"google-search\"], llm=llm)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "909cd28b",
"metadata": {},
"outputs": [],
"source": [
"agent = initialize_agent(\n",
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "46515d2a",
"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 conditions.\n",
"Action: Google Search\n",
"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"
]
},
{
"data": {
"text/plain": [
"'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%.'"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"What is the weather in Pomfret?\")"
]
},
{
"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": [
"agent = initialize_agent(\n",
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
")"
]
},
{
"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\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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",
"version": "3.11.3"
},
"vscode": {
"interpreter": {
"hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}

11
docs/docs/integrations/toolkits/slack.ipynb → docs/docs/integrations/tools/slack.ipynb
View File

@ -4,16 +4,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"---\n", "# Slack Toolkit\n",
"sidebar_label: Slack\n",
"---"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# SlackToolkit\n",
"\n", "\n",
"This will help you getting started with the Slack [toolkit](/docs/concepts/#toolkits). For detailed documentation of all SlackToolkit features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.slack.toolkit.SlackToolkit.html).\n", "This will help you getting started with the Slack [toolkit](/docs/concepts/#toolkits). For detailed documentation of all SlackToolkit features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.slack.toolkit.SlackToolkit.html).\n",
"\n", "\n",

4
docs/docs/integrations/toolkits/spark_sql.ipynb → docs/docs/integrations/tools/spark_sql.ipynb
View File

@ -4,9 +4,9 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Spark SQL\n", "# Spark SQL Toolkit\n",
"\n", "\n",
"This notebook shows how to use agents to interact with `Spark SQL`. Similar to [SQL Database Agent](/docs/integrations/toolkits/sql_database), it is designed to address general inquiries about `Spark SQL` and facilitate error recovery.\n", "This notebook shows how to use agents to interact with `Spark SQL`. Similar to [SQL Database Agent](/docs/integrations/tools/sql_database), it is designed to address general inquiries about `Spark SQL` and facilitate error recovery.\n",
"\n", "\n",
"**NOTE: Note that, as this agent is in active development, all answers might not be correct. Additionally, it is not guaranteed that the agent won't perform DML statements on your Spark cluster given certain questions. Be careful running it on sensitive data!**" "**NOTE: Note that, as this agent is in active development, all answers might not be correct. Additionally, it is not guaranteed that the agent won't perform DML statements on your Spark cluster given certain questions. Be careful running it on sensitive data!**"
] ]

837
docs/docs/integrations/tools/sql_database.ipynb
View File

@ -2,390 +2,591 @@
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "id": "0e499e90-7a6d-4fab-8aab-31a4df417601",
"collapsed": false, "metadata": {},
"jupyter": {
"outputs_hidden": false
}
},
"source": [ "source": [
"# SQL Database\n", "# SQLDatabase Toolkit\n",
"\n", "\n",
":::note\n", "This will help you getting started with the SQL Database [toolkit](/docs/concepts/#toolkits). For detailed documentation of all `SQLDatabaseToolkit` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.sql.toolkit.SQLDatabaseToolkit.html).\n",
"The `SQLDatabase` adapter utility is a wrapper around a database connection.\n",
"\n", "\n",
"For talking to SQL databases, it uses the [SQLAlchemy] Core API .\n", "Tools within the `SQLDatabaseToolkit` are designed to interact with a `SQL` database. \n",
":::\n",
"\n", "\n",
"A common application is to enable agents to answer questions using data in a relational database, potentially in an iterative fashion (e.g., recovering from errors).\n",
"\n", "\n",
"This notebook shows how to use the utility to access an SQLite database.\n", "**⚠️ Security note ⚠️**\n",
"It uses the example [Chinook Database], and demonstrates those features:\n",
"\n", "\n",
"- Query using SQL\n", "Building Q&A systems of SQL databases requires executing model-generated SQL queries. There are inherent risks in doing this. Make sure that your database connection permissions are always scoped as narrowly as possible for your chain/agent's needs. This will mitigate though not eliminate the risks of building a model-driven system. For more on general security best practices, [see here](/docs/security).\n",
"- Query using SQLAlchemy selectable\n",
"- Fetch modes `cursor`, `all`, and `one`\n",
"- Bind query parameters\n",
"\n", "\n",
"[Chinook Database]: https://github.com/lerocha/chinook-database\n", "## Setup\n",
"[SQLAlchemy]: https://www.sqlalchemy.org/\n",
"\n", "\n",
"\n", "If you want to get automated tracing from runs of individual tools, you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
"You can use the `Tool` or `@tool` decorator to create a tool from this utility.\n",
"\n",
"\n",
"::: {.callout-caution}\n",
"If creating a tool from the SQLDatbase utility and combining it with an LLM or exposing it to an end user\n",
"remember to follow good security practices.\n",
"\n",
"See security information: https://python.langchain.com/docs/security\n",
":::"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"metadata": { "id": "3de6e3be-1fd9-42a3-8564-8ca7dca11e1c",
"collapsed": true, "metadata": {},
"jupyter": {
"outputs_hidden": true
}
},
"outputs": [], "outputs": [],
"source": [ "source": [
"!wget 'https://github.com/lerocha/chinook-database/releases/download/v1.4.2/Chinook_Sqlite.sql'" "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
] "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {
"collapsed": false,
"jupyter": {
"outputs_hidden": false
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"1|AC/DC\r\n",
"2|Accept\r\n",
"3|Aerosmith\r\n",
"4|Alanis Morissette\r\n",
"5|Alice In Chains\r\n",
"6|Antônio Carlos Jobim\r\n",
"7|Apocalyptica\r\n",
"8|Audioslave\r\n",
"9|BackBeat\r\n",
"10|Billy Cobham\r\n",
"11|Black Label Society\r\n",
"12|Black Sabbath\r\n"
]
}
],
"source": [
"!sqlite3 -bail -cmd '.read Chinook_Sqlite.sql' -cmd 'SELECT * FROM Artist LIMIT 12;' -cmd '.quit'"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"collapsed": false,
"jupyter": {
"outputs_hidden": false
}
},
"outputs": [],
"source": [
"!sqlite3 -bail -cmd '.read Chinook_Sqlite.sql' -cmd '.save Chinook.db' -cmd '.quit'"
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "id": "31896b61-68d2-4b4d-be9d-b829eda327d1",
"collapsed": false, "metadata": {},
"jupyter": {
"outputs_hidden": false
}
},
"source": [ "source": [
"## Initialize Database" "### Installation\n",
"\n",
"This toolkit lives in the `langchain-community` package:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c4933e04-9120-4ccc-9ef7-369987823b0e",
"metadata": {},
"outputs": [],
"source": [
"%pip install --upgrade --quiet langchain-community"
]
},
{
"cell_type": "markdown",
"id": "6ad08dbe-1642-448c-b58d-153810024375",
"metadata": {},
"source": [
"For demonstration purposes, we will access a prompt in the LangChain [Hub](https://smith.langchain.com/hub). We will also require `langgraph` to demonstrate the use of the toolkit with an agent. This is not required to use the toolkit."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f3dead45-9908-497d-a5a3-bce30642e88f",
"metadata": {},
"outputs": [],
"source": [
"%pip install --upgrade --quiet langchainhub langgraph"
]
},
{
"cell_type": "markdown",
"id": "804533b1-2f16-497b-821b-c82d67fcf7b6",
"metadata": {},
"source": [
"## Instantiation\n",
"\n",
"The `SQLDatabaseToolkit` toolkit requires:\n",
"\n",
"- a [SQLDatabase](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.sql_database.SQLDatabase.html) object;\n",
"- a LLM or chat model (for instantiating the [QuerySQLCheckerTool](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.sql_database.tool.QuerySQLCheckerTool.html) tool).\n",
"\n",
"Below, we instantiate the toolkit with these objects. Let's first create a database object.\n",
"\n",
"This guide uses the example `Chinook` database based on [these instructions](https://database.guide/2-sample-databases-sqlite/).\n",
"\n",
"Below we will use the `requests` library to pull the `.sql` file and create an in-memory SQLite database. Note that this approach is lightweight, but ephemeral and not thread-safe. If you'd prefer, you can follow the instructions to save the file locally as `Chinook.db` and instantiate the database via `db = SQLDatabase.from_uri(\"sqlite:///Chinook.db\")`."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "40d05f9b-5a8f-4307-8f8b-4153db0fdfa9",
"metadata": {},
"outputs": [],
"source": [
"import sqlite3\n",
"\n",
"import requests\n",
"from langchain_community.utilities.sql_database import SQLDatabase\n",
"from sqlalchemy import create_engine\n",
"from sqlalchemy.pool import StaticPool\n",
"\n",
"\n",
"def get_engine_for_chinook_db():\n",
" \"\"\"Pull sql file, populate in-memory database, and create engine.\"\"\"\n",
" url = \"https://raw.githubusercontent.com/lerocha/chinook-database/master/ChinookDatabase/DataSources/Chinook_Sqlite.sql\"\n",
" response = requests.get(url)\n",
" sql_script = response.text\n",
"\n",
" connection = sqlite3.connect(\":memory:\", check_same_thread=False)\n",
" connection.executescript(sql_script)\n",
" return create_engine(\n",
" \"sqlite://\",\n",
" creator=lambda: connection,\n",
" poolclass=StaticPool,\n",
" connect_args={\"check_same_thread\": False},\n",
" )\n",
"\n",
"\n",
"engine = get_engine_for_chinook_db()\n",
"\n",
"db = SQLDatabase(engine)"
]
},
{
"cell_type": "markdown",
"id": "2b9a6326-78fd-4c42-a1cb-4316619ac449",
"metadata": {},
"source": [
"We will also need a LLM or chat model:\n",
"\n",
"```{=mdx}\n",
"import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
"\n",
"<ChatModelTabs customVarName=\"llm\" />\n",
"```"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": 2,
"metadata": { "id": "cc6e6108-83d9-404f-8f31-474c2fbf5f6c",
"collapsed": false, "metadata": {},
"jupyter": {
"outputs_hidden": false
}
},
"outputs": [], "outputs": [],
"source": [ "source": [
"from pprint import pprint\n", "# | output: false\n",
"# | echo: false\n",
"\n", "\n",
"import sqlalchemy as sa\n", "from langchain_openai import ChatOpenAI\n",
"from langchain_community.utilities import SQLDatabase\n",
"\n", "\n",
"db = SQLDatabase.from_uri(\"sqlite:///Chinook.db\")" "llm = ChatOpenAI(temperature=0)"
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "id": "77925e72-4730-43c3-8726-d68cedf635f4",
"collapsed": false, "metadata": {},
"jupyter": {
"outputs_hidden": false
}
},
"source": [ "source": [
"## Query as cursor\n", "We can now instantiate the toolkit:"
"\n",
"The fetch mode `cursor` returns results as SQLAlchemy's\n",
"`CursorResult` instance."
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 30, "execution_count": 3,
"metadata": { "id": "42bd5a41-672a-4a53-b70a-2f0c0555758c",
"collapsed": false, "metadata": {},
"jupyter": { "outputs": [],
"outputs_hidden": false
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'sqlalchemy.engine.cursor.CursorResult'>\n",
"[{'ArtistId': 1, 'Name': 'AC/DC'},\n",
" {'ArtistId': 2, 'Name': 'Accept'},\n",
" {'ArtistId': 3, 'Name': 'Aerosmith'},\n",
" {'ArtistId': 4, 'Name': 'Alanis Morissette'},\n",
" {'ArtistId': 5, 'Name': 'Alice In Chains'},\n",
" {'ArtistId': 6, 'Name': 'Antônio Carlos Jobim'},\n",
" {'ArtistId': 7, 'Name': 'Apocalyptica'},\n",
" {'ArtistId': 8, 'Name': 'Audioslave'},\n",
" {'ArtistId': 9, 'Name': 'BackBeat'},\n",
" {'ArtistId': 10, 'Name': 'Billy Cobham'},\n",
" {'ArtistId': 11, 'Name': 'Black Label Society'},\n",
" {'ArtistId': 12, 'Name': 'Black Sabbath'}]\n"
]
}
],
"source": [ "source": [
"result = db.run(\"SELECT * FROM Artist LIMIT 12;\", fetch=\"cursor\")\n", "from langchain_community.agent_toolkits.sql.toolkit import SQLDatabaseToolkit\n",
"print(type(result))\n", "\n",
"pprint(list(result.mappings()))" "toolkit = SQLDatabaseToolkit(db=db, llm=llm)"
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "id": "b2f882cf-4156-4a9f-a714-db97ec8ccc37",
"collapsed": false, "metadata": {},
"jupyter": {
"outputs_hidden": false
}
},
"source": [ "source": [
"## Query as string payload\n", "## Tools\n",
"\n", "\n",
"The fetch modes `all` and `one` return results in string format." "View available tools:"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {
"collapsed": false,
"jupyter": {
"outputs_hidden": false
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'str'>\n",
"[(1, 'AC/DC'), (2, 'Accept'), (3, 'Aerosmith'), (4, 'Alanis Morissette'), (5, 'Alice In Chains'), (6, 'Antônio Carlos Jobim'), (7, 'Apocalyptica'), (8, 'Audioslave'), (9, 'BackBeat'), (10, 'Billy Cobham'), (11, 'Black Label Society'), (12, 'Black Sabbath')]\n"
]
}
],
"source": [
"result = db.run(\"SELECT * FROM Artist LIMIT 12;\", fetch=\"all\")\n",
"print(type(result))\n",
"print(result)"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {
"collapsed": false,
"jupyter": {
"outputs_hidden": false
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'str'>\n",
"[(1, 'AC/DC')]\n"
]
}
],
"source": [
"result = db.run(\"SELECT * FROM Artist LIMIT 12;\", fetch=\"one\")\n",
"print(type(result))\n",
"print(result)"
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": false,
"jupyter": {
"outputs_hidden": false
}
},
"source": [
"## Query with parameters\n",
"\n",
"In order to bind query parameters, use the optional `parameters` argument."
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {
"collapsed": false,
"jupyter": {
"outputs_hidden": false
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[{'ArtistId': 35, 'Name': 'Pedro Luís & A Parede'},\n",
" {'ArtistId': 115, 'Name': 'Page & Plant'},\n",
" {'ArtistId': 116, 'Name': 'Passengers'},\n",
" {'ArtistId': 117, 'Name': \"Paul D'Ianno\"},\n",
" {'ArtistId': 118, 'Name': 'Pearl Jam'},\n",
" {'ArtistId': 119, 'Name': 'Peter Tosh'},\n",
" {'ArtistId': 120, 'Name': 'Pink Floyd'},\n",
" {'ArtistId': 121, 'Name': 'Planet Hemp'},\n",
" {'ArtistId': 186, 'Name': 'Pedro Luís E A Parede'},\n",
" {'ArtistId': 256, 'Name': 'Philharmonia Orchestra & Sir Neville Marriner'},\n",
" {'ArtistId': 275, 'Name': 'Philip Glass Ensemble'}]\n"
]
}
],
"source": [
"result = db.run(\n",
" \"SELECT * FROM Artist WHERE Name LIKE :search;\",\n",
" parameters={\"search\": \"p%\"},\n",
" fetch=\"cursor\",\n",
")\n",
"pprint(list(result.mappings()))"
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": false,
"jupyter": {
"outputs_hidden": false
}
},
"source": [
"## Query with SQLAlchemy selectable\n",
"\n",
"Other than plain-text SQL statements, the adapter also accepts SQLAlchemy selectables."
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 4,
"metadata": { "id": "a18c3e69-bee0-4f5d-813e-eeb540f41b98",
"collapsed": false, "metadata": {},
"jupyter": { "outputs": [
"outputs_hidden": false {
"data": {
"text/plain": [
"[QuerySQLDataBaseTool(description=\"Input to this tool is a detailed and correct SQL query, output is a result from the database. If the query is not correct, an error message will be returned. If an error is returned, rewrite the query, check the query, and try again. If you encounter an issue with Unknown column 'xxxx' in 'field list', use sql_db_schema to query the correct table fields.\", db=<langchain_community.utilities.sql_database.SQLDatabase object at 0x105e02860>),\n",
" InfoSQLDatabaseTool(description='Input to this tool is a comma-separated list of tables, output is the schema and sample rows for those tables. Be sure that the tables actually exist by calling sql_db_list_tables first! Example Input: table1, table2, table3', db=<langchain_community.utilities.sql_database.SQLDatabase object at 0x105e02860>),\n",
" ListSQLDatabaseTool(db=<langchain_community.utilities.sql_database.SQLDatabase object at 0x105e02860>),\n",
" QuerySQLCheckerTool(description='Use this tool to double check if your query is correct before executing it. Always use this tool before executing a query with sql_db_query!', db=<langchain_community.utilities.sql_database.SQLDatabase object at 0x105e02860>, llm=ChatOpenAI(client=<openai.resources.chat.completions.Completions object at 0x1148a97b0>, async_client=<openai.resources.chat.completions.AsyncCompletions object at 0x1148aaec0>, temperature=0.0, openai_api_key=SecretStr('**********'), openai_proxy=''), llm_chain=LLMChain(prompt=PromptTemplate(input_variables=['dialect', 'query'], template='\\n{query}\\nDouble check the {dialect} query above for common mistakes, including:\\n- Using NOT IN with NULL values\\n- Using UNION when UNION ALL should have been used\\n- Using BETWEEN for exclusive ranges\\n- Data type mismatch in predicates\\n- Properly quoting identifiers\\n- Using the correct number of arguments for functions\\n- Casting to the correct data type\\n- Using the proper columns for joins\\n\\nIf there are any of the above mistakes, rewrite the query. If there are no mistakes, just reproduce the original query.\\n\\nOutput the final SQL query only.\\n\\nSQL Query: '), llm=ChatOpenAI(client=<openai.resources.chat.completions.Completions object at 0x1148a97b0>, async_client=<openai.resources.chat.completions.AsyncCompletions object at 0x1148aaec0>, temperature=0.0, openai_api_key=SecretStr('**********'), openai_proxy='')))]"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
} }
}, ],
"source": [
"toolkit.get_tools()"
]
},
{
"cell_type": "markdown",
"id": "5f5751e3-2e98-485f-8164-db8094039c25",
"metadata": {},
"source": [
"API references:\n",
"\n",
"- [QuerySQLDataBaseTool](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.sql_database.tool.QuerySQLDataBaseTool.html)\n",
"- [InfoSQLDatabaseTool](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.sql_database.tool.InfoSQLDatabaseTool.html)\n",
"- [ListSQLDatabaseTool](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.sql_database.tool.ListSQLDatabaseTool.html)\n",
"- [QuerySQLCheckerTool](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.sql_database.tool.QuerySQLCheckerTool.html)"
]
},
{
"cell_type": "markdown",
"id": "c067e0ed-dcca-4dcc-81b2-a0eeb4fc2a9f",
"metadata": {},
"source": [
"## Use within an agent\n",
"\n",
"Following the [SQL Q&A Tutorial](/docs/tutorials/sql_qa/#agents), below we equip a simple question-answering agent with the tools in our toolkit. First we pull a relevant prompt and populate it with its required parameters:"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "eda12f8b-be90-4697-ac84-2ece9e2d1708",
"metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"[{'ArtistId': 35, 'Name': 'Pedro Luís & A Parede'},\n", "['dialect', 'top_k']\n"
" {'ArtistId': 115, 'Name': 'Page & Plant'},\n",
" {'ArtistId': 116, 'Name': 'Passengers'},\n",
" {'ArtistId': 117, 'Name': \"Paul D'Ianno\"},\n",
" {'ArtistId': 118, 'Name': 'Pearl Jam'},\n",
" {'ArtistId': 119, 'Name': 'Peter Tosh'},\n",
" {'ArtistId': 120, 'Name': 'Pink Floyd'},\n",
" {'ArtistId': 121, 'Name': 'Planet Hemp'},\n",
" {'ArtistId': 186, 'Name': 'Pedro Luís E A Parede'},\n",
" {'ArtistId': 256, 'Name': 'Philharmonia Orchestra & Sir Neville Marriner'},\n",
" {'ArtistId': 275, 'Name': 'Philip Glass Ensemble'}]\n"
] ]
} }
], ],
"source": [ "source": [
"# In order to build a selectable on SA's Core API, you need a table definition.\n", "from langchain import hub\n",
"metadata = sa.MetaData()\n",
"artist = sa.Table(\n",
" \"Artist\",\n",
" metadata,\n",
" sa.Column(\"ArtistId\", sa.INTEGER, primary_key=True),\n",
" sa.Column(\"Name\", sa.TEXT),\n",
")\n",
"\n", "\n",
"# Build a selectable with the same semantics of the recent query.\n", "prompt_template = hub.pull(\"langchain-ai/sql-agent-system-prompt\")\n",
"query = sa.select(artist).where(artist.c.Name.like(\"p%\"))\n",
"result = db.run(query, fetch=\"cursor\")\n",
"pprint(list(result.mappings()))"
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": false,
"jupyter": {
"outputs_hidden": false
}
},
"source": [
"## Query with execution options\n",
"\n", "\n",
"It is possible to augment the statement invocation with custom execution options.\n", "assert len(prompt_template.messages) == 1\n",
"For example, when applying a schema name translation, subsequent statements will\n", "print(prompt_template.input_variables)"
"fail, because they try to hit a non-existing table."
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 6,
"metadata": { "id": "3470ae96-e5e5-4717-a6d6-d7d28c7b7347",
"collapsed": false, "metadata": {},
"jupyter": {
"outputs_hidden": false
}
},
"outputs": [], "outputs": [],
"source": [ "source": [
"query = sa.select(artist).where(artist.c.Name.like(\"p%\"))\n", "system_message = prompt_template.format(dialect=\"SQLite\", top_k=5)"
"db.run(query, fetch=\"cursor\", execution_options={\"schema_translate_map\": {None: \"bar\"}})" ]
},
{
"cell_type": "markdown",
"id": "97930c07-36d1-4137-94ae-fe5ac83ecc44",
"metadata": {},
"source": [
"We then instantiate the agent:"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "48bca92c-9b4b-4d5c-bcce-1b239c9e901c",
"metadata": {},
"outputs": [],
"source": [
"from langgraph.prebuilt import create_react_agent\n",
"\n",
"agent_executor = create_react_agent(\n",
" llm, toolkit.get_tools(), state_modifier=system_message\n",
")"
]
},
{
"cell_type": "markdown",
"id": "09fb1845-1105-4f41-98b4-24756452a3e3",
"metadata": {},
"source": [
"And issue it a query:"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "39e6d2bf-3194-4aba-854b-63faf919157b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"================================\u001b[1m Human Message \u001b[0m=================================\n",
"\n",
"Which country's customers spent the most?\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
"Tool Calls:\n",
" sql_db_list_tables (call_eiheSxiL0s90KE50XyBnBtJY)\n",
" Call ID: call_eiheSxiL0s90KE50XyBnBtJY\n",
" Args:\n",
"=================================\u001b[1m Tool Message \u001b[0m=================================\n",
"Name: sql_db_list_tables\n",
"\n",
"Album, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
"Tool Calls:\n",
" sql_db_schema (call_YKwGWt4UUVmxxY7vjjBDzFLJ)\n",
" Call ID: call_YKwGWt4UUVmxxY7vjjBDzFLJ\n",
" Args:\n",
" table_names: Customer, Invoice, InvoiceLine\n",
"=================================\u001b[1m Tool Message \u001b[0m=================================\n",
"Name: sql_db_schema\n",
"\n",
"\n",
"CREATE TABLE \"Customer\" (\n",
"\t\"CustomerId\" INTEGER NOT NULL, \n",
"\t\"FirstName\" NVARCHAR(40) NOT NULL, \n",
"\t\"LastName\" NVARCHAR(20) NOT NULL, \n",
"\t\"Company\" NVARCHAR(80), \n",
"\t\"Address\" NVARCHAR(70), \n",
"\t\"City\" NVARCHAR(40), \n",
"\t\"State\" NVARCHAR(40), \n",
"\t\"Country\" NVARCHAR(40), \n",
"\t\"PostalCode\" NVARCHAR(10), \n",
"\t\"Phone\" NVARCHAR(24), \n",
"\t\"Fax\" NVARCHAR(24), \n",
"\t\"Email\" NVARCHAR(60) NOT NULL, \n",
"\t\"SupportRepId\" INTEGER, \n",
"\tPRIMARY KEY (\"CustomerId\"), \n",
"\tFOREIGN KEY(\"SupportRepId\") REFERENCES \"Employee\" (\"EmployeeId\")\n",
")\n",
"\n",
"/*\n",
"3 rows from Customer table:\n",
"CustomerId\tFirstName\tLastName\tCompany\tAddress\tCity\tState\tCountry\tPostalCode\tPhone\tFax\tEmail\tSupportRepId\n",
"1\tLuís\tGonçalves\tEmbraer - Empresa Brasileira de Aeronáutica S.A.\tAv. Brigadeiro Faria Lima, 2170\tSão José dos Campos\tSP\tBrazil\t12227-000\t+55 (12) 3923-5555\t+55 (12) 3923-5566\tluisg@embraer.com.br\t3\n",
"2\tLeonie\tKöhler\tNone\tTheodor-Heuss-Straße 34\tStuttgart\tNone\tGermany\t70174\t+49 0711 2842222\tNone\tleonekohler@surfeu.de\t5\n",
"3\tFrançois\tTremblay\tNone\t1498 rue Bélanger\tMontréal\tQC\tCanada\tH2G 1A7\t+1 (514) 721-4711\tNone\tftremblay@gmail.com\t3\n",
"*/\n",
"\n",
"\n",
"CREATE TABLE \"Invoice\" (\n",
"\t\"InvoiceId\" INTEGER NOT NULL, \n",
"\t\"CustomerId\" INTEGER NOT NULL, \n",
"\t\"InvoiceDate\" DATETIME NOT NULL, \n",
"\t\"BillingAddress\" NVARCHAR(70), \n",
"\t\"BillingCity\" NVARCHAR(40), \n",
"\t\"BillingState\" NVARCHAR(40), \n",
"\t\"BillingCountry\" NVARCHAR(40), \n",
"\t\"BillingPostalCode\" NVARCHAR(10), \n",
"\t\"Total\" NUMERIC(10, 2) NOT NULL, \n",
"\tPRIMARY KEY (\"InvoiceId\"), \n",
"\tFOREIGN KEY(\"CustomerId\") REFERENCES \"Customer\" (\"CustomerId\")\n",
")\n",
"\n",
"/*\n",
"3 rows from Invoice table:\n",
"InvoiceId\tCustomerId\tInvoiceDate\tBillingAddress\tBillingCity\tBillingState\tBillingCountry\tBillingPostalCode\tTotal\n",
"1\t2\t2021-01-01 00:00:00\tTheodor-Heuss-Straße 34\tStuttgart\tNone\tGermany\t70174\t1.98\n",
"2\t4\t2021-01-02 00:00:00\tUllevålsveien 14\tOslo\tNone\tNorway\t0171\t3.96\n",
"3\t8\t2021-01-03 00:00:00\tGrétrystraat 63\tBrussels\tNone\tBelgium\t1000\t5.94\n",
"*/\n",
"\n",
"\n",
"CREATE TABLE \"InvoiceLine\" (\n",
"\t\"InvoiceLineId\" INTEGER NOT NULL, \n",
"\t\"InvoiceId\" INTEGER NOT NULL, \n",
"\t\"TrackId\" INTEGER NOT NULL, \n",
"\t\"UnitPrice\" NUMERIC(10, 2) NOT NULL, \n",
"\t\"Quantity\" INTEGER NOT NULL, \n",
"\tPRIMARY KEY (\"InvoiceLineId\"), \n",
"\tFOREIGN KEY(\"TrackId\") REFERENCES \"Track\" (\"TrackId\"), \n",
"\tFOREIGN KEY(\"InvoiceId\") REFERENCES \"Invoice\" (\"InvoiceId\")\n",
")\n",
"\n",
"/*\n",
"3 rows from InvoiceLine table:\n",
"InvoiceLineId\tInvoiceId\tTrackId\tUnitPrice\tQuantity\n",
"1\t1\t2\t0.99\t1\n",
"2\t1\t4\t0.99\t1\n",
"3\t2\t6\t0.99\t1\n",
"*/\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
"Tool Calls:\n",
" sql_db_query (call_7WBDcMxl1h7MnI05njx1q8V9)\n",
" Call ID: call_7WBDcMxl1h7MnI05njx1q8V9\n",
" Args:\n",
" query: SELECT c.Country, SUM(i.Total) AS TotalSpent FROM Customer c JOIN Invoice i ON c.CustomerId = i.CustomerId GROUP BY c.Country ORDER BY TotalSpent DESC LIMIT 1\n",
"=================================\u001b[1m Tool Message \u001b[0m=================================\n",
"Name: sql_db_query\n",
"\n",
"[('USA', 523.0600000000003)]\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
"\n",
"Customers from the USA spent the most, with a total amount spent of $523.06.\n"
]
}
],
"source": [
"example_query = \"Which country's customers spent the most?\"\n",
"\n",
"events = agent_executor.stream(\n",
" {\"messages\": [(\"user\", example_query)]},\n",
" stream_mode=\"values\",\n",
")\n",
"for event in events:\n",
" event[\"messages\"][-1].pretty_print()"
]
},
{
"cell_type": "markdown",
"id": "adbf3d8d-7570-45a5-950f-ce84db5145ab",
"metadata": {},
"source": [
"We can also observe the agent recover from an error:"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "23c1235c-6d18-43e4-98ab-85b426b53d94",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"================================\u001b[1m Human Message \u001b[0m=================================\n",
"\n",
"Who are the top 3 best selling artists?\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
"Tool Calls:\n",
" sql_db_query (call_9F6Bp2vwsDkeLW6FsJFqLiet)\n",
" Call ID: call_9F6Bp2vwsDkeLW6FsJFqLiet\n",
" Args:\n",
" query: SELECT artist_name, SUM(quantity) AS total_sold FROM sales GROUP BY artist_name ORDER BY total_sold DESC LIMIT 3\n",
"=================================\u001b[1m Tool Message \u001b[0m=================================\n",
"Name: sql_db_query\n",
"\n",
"Error: (sqlite3.OperationalError) no such table: sales\n",
"[SQL: SELECT artist_name, SUM(quantity) AS total_sold FROM sales GROUP BY artist_name ORDER BY total_sold DESC LIMIT 3]\n",
"(Background on this error at: https://sqlalche.me/e/20/e3q8)\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
"Tool Calls:\n",
" sql_db_list_tables (call_Gx5adzWnrBDIIxzUDzsn83zO)\n",
" Call ID: call_Gx5adzWnrBDIIxzUDzsn83zO\n",
" Args:\n",
"=================================\u001b[1m Tool Message \u001b[0m=================================\n",
"Name: sql_db_list_tables\n",
"\n",
"Album, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
"Tool Calls:\n",
" sql_db_schema (call_ftywrZgEgGWLrnk9dYC0xtZv)\n",
" Call ID: call_ftywrZgEgGWLrnk9dYC0xtZv\n",
" Args:\n",
" table_names: Artist, Album, InvoiceLine\n",
"=================================\u001b[1m Tool Message \u001b[0m=================================\n",
"Name: sql_db_schema\n",
"\n",
"\n",
"CREATE TABLE \"Album\" (\n",
"\t\"AlbumId\" INTEGER NOT NULL, \n",
"\t\"Title\" NVARCHAR(160) NOT NULL, \n",
"\t\"ArtistId\" INTEGER NOT NULL, \n",
"\tPRIMARY KEY (\"AlbumId\"), \n",
"\tFOREIGN KEY(\"ArtistId\") REFERENCES \"Artist\" (\"ArtistId\")\n",
")\n",
"\n",
"/*\n",
"3 rows from Album table:\n",
"AlbumId\tTitle\tArtistId\n",
"1\tFor Those About To Rock We Salute You\t1\n",
"2\tBalls to the Wall\t2\n",
"3\tRestless and Wild\t2\n",
"*/\n",
"\n",
"\n",
"CREATE TABLE \"Artist\" (\n",
"\t\"ArtistId\" INTEGER NOT NULL, \n",
"\t\"Name\" NVARCHAR(120), \n",
"\tPRIMARY KEY (\"ArtistId\")\n",
")\n",
"\n",
"/*\n",
"3 rows from Artist table:\n",
"ArtistId\tName\n",
"1\tAC/DC\n",
"2\tAccept\n",
"3\tAerosmith\n",
"*/\n",
"\n",
"\n",
"CREATE TABLE \"InvoiceLine\" (\n",
"\t\"InvoiceLineId\" INTEGER NOT NULL, \n",
"\t\"InvoiceId\" INTEGER NOT NULL, \n",
"\t\"TrackId\" INTEGER NOT NULL, \n",
"\t\"UnitPrice\" NUMERIC(10, 2) NOT NULL, \n",
"\t\"Quantity\" INTEGER NOT NULL, \n",
"\tPRIMARY KEY (\"InvoiceLineId\"), \n",
"\tFOREIGN KEY(\"TrackId\") REFERENCES \"Track\" (\"TrackId\"), \n",
"\tFOREIGN KEY(\"InvoiceId\") REFERENCES \"Invoice\" (\"InvoiceId\")\n",
")\n",
"\n",
"/*\n",
"3 rows from InvoiceLine table:\n",
"InvoiceLineId\tInvoiceId\tTrackId\tUnitPrice\tQuantity\n",
"1\t1\t2\t0.99\t1\n",
"2\t1\t4\t0.99\t1\n",
"3\t2\t6\t0.99\t1\n",
"*/\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
"Tool Calls:\n",
" sql_db_query (call_i6n3lmS7E2ZivN758VOayTiy)\n",
" Call ID: call_i6n3lmS7E2ZivN758VOayTiy\n",
" Args:\n",
" query: SELECT Artist.Name AS artist_name, SUM(InvoiceLine.Quantity) AS total_sold FROM Artist JOIN Album ON Artist.ArtistId = Album.ArtistId JOIN Track ON Album.AlbumId = Track.AlbumId JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER BY total_sold DESC LIMIT 3\n",
"=================================\u001b[1m Tool Message \u001b[0m=================================\n",
"Name: sql_db_query\n",
"\n",
"[('Iron Maiden', 140), ('U2', 107), ('Metallica', 91)]\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
"\n",
"The top 3 best selling artists are:\n",
"1. Iron Maiden - 140 units sold\n",
"2. U2 - 107 units sold\n",
"3. Metallica - 91 units sold\n"
]
}
],
"source": [
"example_query = \"Who are the top 3 best selling artists?\"\n",
"\n",
"events = agent_executor.stream(\n",
" {\"messages\": [(\"user\", example_query)]},\n",
" stream_mode=\"values\",\n",
")\n",
"for event in events:\n",
" event[\"messages\"][-1].pretty_print()"
]
},
{
"cell_type": "markdown",
"id": "73521f1b-be03-44e6-8b27-a9a46ae8e962",
"metadata": {},
"source": [
"## Specific functionality\n",
"\n",
"`SQLDatabaseToolkit` implements a [.get_context](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.sql.toolkit.SQLDatabaseToolkit.html#langchain_community.agent_toolkits.sql.toolkit.SQLDatabaseToolkit.get_context) method as a convenience for use in prompts or other contexts.\n",
"\n",
"**⚠️ Disclaimer ⚠️** : The agent may generate insert/update/delete queries. When this is not expected, use a custom prompt or create a SQL users without write permissions.\n",
"\n",
"The final user might overload your SQL database by asking a simple question such as \"run the biggest query possible\". The generated query might look like:\n",
"\n",
"```sql\n",
"SELECT * FROM \"public\".\"users\"\n",
" JOIN \"public\".\"user_permissions\" ON \"public\".\"users\".id = \"public\".\"user_permissions\".user_id\n",
" JOIN \"public\".\"projects\" ON \"public\".\"users\".id = \"public\".\"projects\".user_id\n",
" JOIN \"public\".\"events\" ON \"public\".\"projects\".id = \"public\".\"events\".project_id;\n",
"```\n",
"\n",
"For a transactional SQL database, if one of the table above contains millions of rows, the query might cause trouble to other applications using the same database.\n",
"\n",
"Most datawarehouse oriented databases support user-level quota, for limiting resource usage."
]
},
{
"cell_type": "markdown",
"id": "1aa8a7e3-87ca-4963-a224-0cbdc9d88714",
"metadata": {},
"source": [
"## API reference\n",
"\n",
"For detailed documentation of all SQLDatabaseToolkit features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.sql.toolkit.SQLDatabaseToolkit.html)."
] ]
} }
], ],
@ -405,9 +606,9 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.9" "version": "3.10.4"
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 4 "nbformat_minor": 5
} }

2
docs/docs/integrations/toolkits/steam.ipynb → docs/docs/integrations/tools/steam.ipynb
View File

@ -4,7 +4,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Steam Game Recommendation & Game Details\n", "# Steam Toolkit\n",
"\n", "\n",
">[Steam (Wikipedia)](https://en.wikipedia.org/wiki/Steam_(service)) is a video game digital distribution service and storefront developed by `Valve Corporation`. It provides game updates automatically for Valve's games, and expanded to distributing third-party titles. `Steam` offers various features, like game server matchmaking with Valve Anti-Cheat measures, social networking, and game streaming services.\n", ">[Steam (Wikipedia)](https://en.wikipedia.org/wiki/Steam_(service)) is a video game digital distribution service and storefront developed by `Valve Corporation`. It provides game updates automatically for Valve's games, and expanded to distributing third-party titles. `Steam` offers various features, like game server matchmaking with Valve Anti-Cheat measures, social networking, and game streaming services.\n",
"\n", "\n",

3
docs/package.json
View File

@ -76,5 +76,6 @@
}, },
"engines": { "engines": {
"node": ">=18" "node": ">=18"
} },
"packageManager": "yarn@1.22.22+sha512.a6b2f7906b721bba3d67d4aff083df04dad64c399707841b7acf00f6b133b7ac24255f2652fa22ae3534329dc6180534e98d17432037ff6fd140556e2bb3137e"
} }

165
docs/scripts/tool_feat_table.py
View File

@ -2,6 +2,11 @@ import sys
from pathlib import Path from pathlib import Path
SEARCH_TOOL_FEAT_TABLE = { SEARCH_TOOL_FEAT_TABLE = {
"Tavily Search": {
"pricing": "1000 free searches/month",
"available_data": "URL, Content, Title, Images, Answer",
"link": "/docs/integrations/tools/tavily_search",
},
"Exa Search": { "Exa Search": {
"pricing": "1000 free searches/month", "pricing": "1000 free searches/month",
"available_data": "URL, Author, Title, Published Date", "available_data": "URL, Author, Title, Published Date",
@ -90,6 +95,74 @@ CODE_INTERPRETER_TOOL_FEAT_TABLE = {
}, },
} }
PRODUCTIVITY_TOOL_FEAT_TABLE = {
"Gmail Toolkit": {
"link": "/docs/integrations/tools/gmail",
"pricing": "Free, with limit of 250 quota units per user per second",
},
"Github Toolkit": {
"link": "/docs/integrations/tools/github",
"pricing": "Free",
},
"Gitlab Toolkit": {
"link": "/docs/integrations/tools/gitlab",
"pricing": "Free for personal project",
},
"Slack Toolkit": {
"link": "/docs/integrations/tools/slack",
"pricing": "Free",
},
"Jira Toolkit": {
"link": "/docs/integrations/tools/jira",
"pricing": "Free, with [rate limits](https://developer.atlassian.com/cloud/jira/platform/rate-limiting/)",
},
"Office365 Toolkit": {
"link": "/docs/integrations/tools/office365",
"pricing": "Free with Office365, includes [rate limits](https://learn.microsoft.com/en-us/graph/throttling-limits)",
},
"Twilio Tool": {
"link": "/docs/integrations/tools/twilio",
"pricing": "Free trial, with [pay-as-you-go pricing](https://www.twilio.com/en-us/pricing) after",
},
"Infobip Tool": {
"link": "/docs/integrations/tools/infobip",
"pricing": "Free trial, with variable pricing after",
},
}
WEBBROWSING_TOOL_FEAT_TABLE = {
"Requests Toolkit": {
"link": "/docs/integrations/tools/requests",
"interactions": False,
"pricing": "Free",
},
"PlayWright Browser Toolkit": {
"link": "/docs/integrations/tools/playwright",
"interactions": True,
"pricing": "Free",
},
"MultiOn Toolkit": {
"link": "/docs/integrations/tools/multion",
"interactions": True,
"pricing": "40 free requests/day",
},
}
DATABASE_TOOL_FEAT_TABLE = {
"SQLDatabase Toolkit": {
"link": "/docs/integrations/tools/sql_database",
"operations": "Any SQL operation",
},
"Spark SQL Toolkit": {
"link": "/docs/integrations/tools/spark_sql",
"operations": "Any SQL operation",
},
"Cassandra Database Toolkit": {
"link": "/docs/integrations/tools/cassandra_database",
"operations": "SELECT and schema introspection",
},
}
TOOLS_TEMPLATE = """\ TOOLS_TEMPLATE = """\
--- ---
sidebar_position: 0 sidebar_position: 0
@ -107,25 +180,104 @@ If you'd like to contribute an integration, see [Contributing integrations](/doc
::: :::
## Search Tools ## Search
The following table shows tools that execute online searches in some shape or form: The following table shows tools that execute online searches in some shape or form:
{search_table} {search_table}
## Code Interpreter Tools ## Code Interpreter
The following table shows tools that can be used as code interpreters: The following table shows tools that can be used as code interpreters:
{code_interpreter_table} {code_interpreter_table}
""" ## Productivity
The following table shows tools that can be used to automate tasks in productivity tools:
{productivity_table}
## Web Browsing
The following table shows tools that can be used to automate tasks in web browsers:
{webbrowsing_table}
## Database
The following table shows tools that can be used to automate tasks in databases:
{database_table}
""" # noqa: E501
def get_productivity_table() -> str:
"""Get the table of productivity tools."""
header = [
"tool",
"pricing",
]
title = [
"Tool/Toolkit",
"Pricing",
]
rows = [title, [":-"] + [":-:"] * (len(title) - 1)]
for productivity_tool, feats in sorted(PRODUCTIVITY_TOOL_FEAT_TABLE.items()):
# Fields are in the order of the header
row = [
f"[{productivity_tool}]({feats['link']})",
]
for h in header[1:]:
row.append(feats.get(h))
rows.append(row)
return "\n".join(["|".join(row) for row in rows])
def get_webbrowsing_table() -> str:
"""Get the table of web browsing tools."""
header = ["tool", "pricing", "interactions"]
title = ["Tool/Toolkit", "Pricing", "Supports Interacting with the Browser"]
rows = [title, [":-"] + [":-:"] * (len(title) - 1)]
for web_browsing_tool, feats in sorted(WEBBROWSING_TOOL_FEAT_TABLE.items()):
# Fields are in the order of the header
row = [
f"[{web_browsing_tool}]({feats['link']})",
]
for h in header[1:]:
value = feats.get(h)
if h == "interactions":
if value is True:
row.append("✅")
else:
row.append("❌")
else:
row.append(value)
rows.append(row)
return "\n".join(["|".join(row) for row in rows])
def get_database_table() -> str:
"""Get the table of database tools."""
header = ["tool", "operations"]
title = ["Tool/Toolkit", "Allowed Operations"]
rows = [title, [":-"] + [":-:"] * (len(title) - 1)]
for database_tool, feats in sorted(DATABASE_TOOL_FEAT_TABLE.items()):
# Fields are in the order of the header
row = [
f"[{database_tool}]({feats['link']})",
]
for h in header[1:]:
row.append(feats.get(h))
rows.append(row)
return "\n".join(["|".join(row) for row in rows])
def get_search_tools_table() -> str: def get_search_tools_table() -> str:
"""Get the table of search tools.""" """Get the table of search tools."""
header = ["tool", "pricing", "available_data"] header = ["tool", "pricing", "available_data"]
title = ["Tool", "Free/Paid", "Return Data"] title = ["Tool/Toolkit", "Free/Paid", "Return Data"]
rows = [title, [":-"] + [":-:"] * (len(title) - 1)] rows = [title, [":-"] + [":-:"] * (len(title) - 1)]
for search_tool, feats in sorted(SEARCH_TOOL_FEAT_TABLE.items()): for search_tool, feats in sorted(SEARCH_TOOL_FEAT_TABLE.items()):
# Fields are in the order of the header # Fields are in the order of the header
@ -148,7 +300,7 @@ def get_code_interpreter_table() -> str:
"return_results", "return_results",
] ]
title = [ title = [
"Tool", "Tool/Toolkit",
"Supported Languages", "Supported Languages",
"Sandbox Lifetime", "Sandbox Lifetime",
"Supports File Uploads", "Supports File Uploads",
@ -182,6 +334,9 @@ if __name__ == "__main__":
tools_page = TOOLS_TEMPLATE.format( tools_page = TOOLS_TEMPLATE.format(
search_table=get_search_tools_table(), search_table=get_search_tools_table(),
code_interpreter_table=get_code_interpreter_table(), code_interpreter_table=get_code_interpreter_table(),
productivity_table=get_productivity_table(),
webbrowsing_table=get_webbrowsing_table(),
database_table=get_database_table(),
) )
with open(output_integrations_dir / "tools" / "index.mdx", "w") as f: with open(output_integrations_dir / "tools" / "index.mdx", "w") as f:
f.write(tools_page) f.write(tools_page)

17
docs/sidebars.js
View File

@ -250,7 +250,7 @@ module.exports = {
}, },
{ {
type: "category", type: "category",
label: "Tools", label: "Tools/Toolkits",
collapsed: true, collapsed: true,
items: [ items: [
{ {
@ -263,21 +263,6 @@ module.exports = {
id: "integrations/tools/index", id: "integrations/tools/index",
}, },
}, },
{
type: "category",
label: "Toolkits",
collapsed: true,
items: [
{
type: "autogenerated",
dirName: "integrations/toolkits",
},
],
link: {
type: "doc",
id: "integrations/toolkits/index",
},
},
{ {
type: "category", type: "category",
label: "Key-value stores", label: "Key-value stores",

8
docs/vercel.json
View File

@ -73,6 +73,14 @@
{ {
"source": "/v0.2/docs/how_to/migrate_chains(/?)", "source": "/v0.2/docs/how_to/migrate_chains(/?)",
"destination": "/v0.2/docs/versions/migrating_chains" "destination": "/v0.2/docs/versions/migrating_chains"
},
{
"source": "/v0.2/docs/integrations/tools/search_tools/",
"destination": "/v0.2/docs/integrations/tools#search"
},
{
"source": "/v0.2/docs/integrations/toolkits/airbyte_structured_qa/",
"destination": "/v0.2/docs/integrations/document_loaders/airbyte/"
} }
] ]
} }

2
libs/partners/robocorp/README.md
View File

@ -14,4 +14,4 @@ pip install -U langchain-robocorp
## Action Server Toolkit ## Action Server Toolkit
See [ActionServerToolkit](https://python.langchain.com/docs/integrations/toolkits/robocorp) for detailed documentation. See [ActionServerToolkit](https://python.langchain.com/docs/integrations/tools/robocorp) for detailed documentation.