mirror of
https://github.com/hwchase17/langchain
synced 2024-10-29 17:07:25 +00:00
1269 lines
45 KiB
Plaintext
1269 lines
45 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "raw",
|
||
"metadata": {},
|
||
"source": [
|
||
"---\n",
|
||
"sidebar_position: 1\n",
|
||
"title: SQL\n",
|
||
"---"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"[](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/use_cases/sql.ipynb)\n",
|
||
"\n",
|
||
"## Use case\n",
|
||
"\n",
|
||
"Enterprise data is often stored in SQL databases.\n",
|
||
"\n",
|
||
"LLMs make it possible to interact with SQL databases using natural langugae.\n",
|
||
"\n",
|
||
"LangChain offers SQL Chains and Agents to build and run SQL queries based on natural language prompts. \n",
|
||
"\n",
|
||
"These are compatible with any SQL dialect supported by SQLAlchemy (e.g., MySQL, PostgreSQL, Oracle SQL, Databricks, SQLite).\n",
|
||
"\n",
|
||
"They enable use cases such as:\n",
|
||
"\n",
|
||
"- Generating queries that will be run based on natural language questions\n",
|
||
"- Creating chatbots that can answer questions based on database data\n",
|
||
"- Building custom dashboards based on insights a user wants to analyze\n",
|
||
"\n",
|
||
"## Overview\n",
|
||
"\n",
|
||
"LangChain provides tools to interact with SQL Databases:\n",
|
||
"\n",
|
||
"1. `Build SQL queries` based on natural language user questions\n",
|
||
"2. `Query a SQL database` using chains for query creation and execution\n",
|
||
"3. `Interact with a SQL database` using agents for robust and flexible querying \n",
|
||
"\n",
|
||
"\n",
|
||
"\n",
|
||
"## Quickstart\n",
|
||
"\n",
|
||
"First, get required packages and set environment variables:"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 2,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"! pip install langchain langchain-experimental openai\n",
|
||
"\n",
|
||
"# Set env var OPENAI_API_KEY or load from a .env file\n",
|
||
"# import dotenv\n",
|
||
"\n",
|
||
"# dotenv.load_dotenv()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"The below example will use a SQLite connection with Chinook database. \n",
|
||
" \n",
|
||
"Follow [installation steps](https://database.guide/2-sample-databases-sqlite/) to create `Chinook.db` in the same directory as this notebook:\n",
|
||
"\n",
|
||
"* Save [this file](https://raw.githubusercontent.com/lerocha/chinook-database/master/ChinookDatabase/DataSources/Chinook_Sqlite.sql) to the directory as `Chinook_Sqlite.sql`\n",
|
||
"* Run `sqlite3 Chinook.db`\n",
|
||
"* Run `.read Chinook_Sqlite.sql`\n",
|
||
"* Test `SELECT * FROM Artist LIMIT 10;`\n",
|
||
"\n",
|
||
"Now, `Chinhook.db` is in our directory.\n",
|
||
"\n",
|
||
"Let's create a `SQLDatabaseChain` to create and execute SQL queries."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 6,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"from langchain.utilities import SQLDatabase\n",
|
||
"from langchain.llms import OpenAI\n",
|
||
"from langchain_experimental.sql import SQLDatabaseChain\n",
|
||
"\n",
|
||
"db = SQLDatabase.from_uri(\"sqlite:///Chinook.db\")\n",
|
||
"llm = OpenAI(temperature=0, verbose=True)\n",
|
||
"db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 7,
|
||
"metadata": {
|
||
"scrolled": true
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"\n",
|
||
"\n",
|
||
"\u001b[1m> Entering new SQLDatabaseChain chain...\u001b[0m\n",
|
||
"How many employees are there?\n",
|
||
"SQLQuery:\u001b[32;1m\u001b[1;3mSELECT COUNT(*) FROM \"Employee\";\u001b[0m\n",
|
||
"SQLResult: \u001b[33;1m\u001b[1;3m[(8,)]\u001b[0m\n",
|
||
"Answer:\u001b[32;1m\u001b[1;3mThere are 8 employees.\u001b[0m\n",
|
||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||
]
|
||
},
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"'There are 8 employees.'"
|
||
]
|
||
},
|
||
"execution_count": 7,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"db_chain.run(\"How many employees are there?\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"Note that this both creates and executes the query. \n",
|
||
"\n",
|
||
"In the following sections, we will cover the 3 different use cases mentioned in the overview.\n",
|
||
"\n",
|
||
"### Go deeper\n",
|
||
"\n",
|
||
"You can load tabular data from other sources other than SQL Databases.\n",
|
||
"For example:\n",
|
||
"- [Loading a CSV file](/docs/integrations/document_loaders/csv)\n",
|
||
"- [Loading a Pandas DataFrame](/docs/integrations/document_loaders/pandas_dataframe)\n",
|
||
"Here you can [check full list of Document Loaders](/docs/integrations/document_loaders/)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Case 1: Text-to-SQL query\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 8,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"from langchain.chat_models import ChatOpenAI\n",
|
||
"from langchain.chains import create_sql_query_chain"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"Let's create the chain that will build the SQL Query:\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 9,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"SELECT COUNT(*) FROM Employee\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"chain = create_sql_query_chain(ChatOpenAI(temperature=0), db)\n",
|
||
"response = chain.invoke({\"question\":\"How many employees are there\"})\n",
|
||
"print(response)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"After building the SQL query based on a user question, we can execute the query:"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 10,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"'[(8,)]'"
|
||
]
|
||
},
|
||
"execution_count": 10,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"db.run(response)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"As we can see, the SQL Query Builder chain **only created** the query, and we handled the **query execution separately**."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Go deeper\n",
|
||
"\n",
|
||
"**Looking under the hood**\n",
|
||
"\n",
|
||
"We can look at the [LangSmith trace](https://smith.langchain.com/public/c8fa52ea-be46-4829-bde2-52894970b830/r) to unpack this:\n",
|
||
"\n",
|
||
"[Some papers](https://arxiv.org/pdf/2204.00498.pdf) have reported good performance when prompting with:\n",
|
||
" \n",
|
||
"* A `CREATE TABLE` description for each table, which include column names, their types, etc\n",
|
||
"* Followed by three example rows in a `SELECT` statement\n",
|
||
"\n",
|
||
"`create_sql_query_chain` adopts this the best practice (see more in this [blog](https://blog.langchain.dev/llms-and-sql/)). \n",
|
||
"\n",
|
||
"\n",
|
||
"**Improvements**\n",
|
||
"\n",
|
||
"The query builder can be improved in several ways, such as (but not limited to):\n",
|
||
"\n",
|
||
"- Customizing database description to your specific use case\n",
|
||
"- Hardcoding a few examples of questions and their corresponding SQL query in the prompt\n",
|
||
"- Using a vector database to include dynamic examples that are relevant to the specific user question\n",
|
||
"\n",
|
||
"All these examples involve customizing the chain's prompt. \n",
|
||
"\n",
|
||
"For example, we can include a few examples in our prompt like so:"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 1,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"from langchain.prompts import PromptTemplate\n",
|
||
"\n",
|
||
"TEMPLATE = \"\"\"Given an input question, first create a syntactically correct {dialect} query to run, then look at the results of the query and return the answer.\n",
|
||
"Use the following format:\n",
|
||
"\n",
|
||
"Question: \"Question here\"\n",
|
||
"SQLQuery: \"SQL Query to run\"\n",
|
||
"SQLResult: \"Result of the SQLQuery\"\n",
|
||
"Answer: \"Final answer here\"\n",
|
||
"\n",
|
||
"Only use the following tables:\n",
|
||
"\n",
|
||
"{table_info}.\n",
|
||
"\n",
|
||
"Some examples of SQL queries that corrsespond to questions are:\n",
|
||
"\n",
|
||
"{few_shot_examples}\n",
|
||
"\n",
|
||
"Question: {input}\"\"\"\n",
|
||
"\n",
|
||
"CUSTOM_PROMPT = PromptTemplate(\n",
|
||
" input_variables=[\"input\", \"few_shot_examples\", \"table_info\", \"dialect\"], template=TEMPLATE\n",
|
||
")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"We can also access this [prompt](https://smith.langchain.com/hub/rlm/text-to-sql) in the LangChain prompt hub.\n",
|
||
"\n",
|
||
"This will work with your [LangSmith API key](https://docs.smith.langchain.com/)."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"from langchain import hub\n",
|
||
"CUSTOM_PROMPT = hub.pull(\"rlm/text-to-sql\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Case 2: Text-to-SQL query and execution\n",
|
||
"\n",
|
||
"We can use `SQLDatabaseChain` from `langchain_experimental` to create and run SQL queries."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 12,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"from langchain.llms import OpenAI\n",
|
||
"from langchain_experimental.sql import SQLDatabaseChain\n",
|
||
"\n",
|
||
"llm = OpenAI(temperature=0, verbose=True)\n",
|
||
"db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 13,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"\n",
|
||
"\n",
|
||
"\u001b[1m> Entering new SQLDatabaseChain chain...\u001b[0m\n",
|
||
"How many employees are there?\n",
|
||
"SQLQuery:\u001b[32;1m\u001b[1;3mSELECT COUNT(*) FROM \"Employee\";\u001b[0m\n",
|
||
"SQLResult: \u001b[33;1m\u001b[1;3m[(8,)]\u001b[0m\n",
|
||
"Answer:\u001b[32;1m\u001b[1;3mThere are 8 employees.\u001b[0m\n",
|
||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||
]
|
||
},
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"'There are 8 employees.'"
|
||
]
|
||
},
|
||
"execution_count": 13,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"db_chain.run(\"How many employees are there?\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"As we can see, we get the same result as the previous case.\n",
|
||
"\n",
|
||
"Here, the chain **also handles the query execution** and provides a final answer based on the user question and the query result.\n",
|
||
"\n",
|
||
"**Be careful** while using this approach as it is susceptible to `SQL Injection`:\n",
|
||
"\n",
|
||
"* The chain is executing queries that are created by an LLM, and weren't validated\n",
|
||
"* e.g. records may be created, modified or deleted unintentionally_\n",
|
||
"\n",
|
||
"This is why we see the `SQLDatabaseChain` is inside `langchain_experimental`."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Go deeper\n",
|
||
"\n",
|
||
"**Looking under the hood**\n",
|
||
"\n",
|
||
"We can use the [LangSmith trace](https://smith.langchain.com/public/7f202a0c-1e35-42d6-a84a-6c2a58f697ef/r) to see what is happening under the hood:\n",
|
||
"\n",
|
||
"* As discussed above, first we create the query:\n",
|
||
"\n",
|
||
"```\n",
|
||
"text: ' SELECT COUNT(*) FROM \"Employee\";'\n",
|
||
"```\n",
|
||
"\n",
|
||
"* Then, it executes the query and passes the results to an LLM for synthesis.\n",
|
||
"\n",
|
||
"\n",
|
||
"\n",
|
||
"**Improvements**\n",
|
||
"\n",
|
||
"The performance of the `SQLDatabaseChain` can be enhanced in several ways:\n",
|
||
"\n",
|
||
"- [Adding sample rows](#adding-sample-rows)\n",
|
||
"- [Specifying custom table information](/docs/integrations/tools/sqlite#custom-table-info)\n",
|
||
"- [Using Query Checker](/docs/integrations/tools/sqlite#use-query-checker) self-correct invalid SQL using parameter `use_query_checker=True`\n",
|
||
"- [Customizing the LLM Prompt](/docs/integrations/tools/sqlite#customize-prompt) include specific instructions or relevant information, using parameter `prompt=CUSTOM_PROMPT`\n",
|
||
"- [Get intermediate steps](/docs/integrations/tools/sqlite#return-intermediate-steps) access the SQL statement as well as the final result using parameter `return_intermediate_steps=True`\n",
|
||
"- [Limit the number of rows](/docs/integrations/tools/sqlite#choosing-how-to-limit-the-number-of-rows-returned) a query will return using parameter `top_k=5`\n",
|
||
"\n",
|
||
"You might find [SQLDatabaseSequentialChain](/docs/integrations/tools/sqlite#sqldatabasesequentialchain)\n",
|
||
"useful for cases in which the number of tables in the database is large.\n",
|
||
"\n",
|
||
"This `Sequential Chain` handles the process of:\n",
|
||
"\n",
|
||
"1. Determining which tables to use based on the user question\n",
|
||
"2. Calling the normal SQL database chain using only relevant tables\n",
|
||
"\n",
|
||
"**Adding Sample Rows**\n",
|
||
"\n",
|
||
"Providing sample data can help the LLM construct correct queries when the data format is not obvious. \n",
|
||
"\n",
|
||
"For example, we can tell LLM that artists are saved with their full names by providing two rows from the Track table.\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 9,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"db = SQLDatabase.from_uri(\n",
|
||
" \"sqlite:///Chinook.db\",\n",
|
||
" include_tables=['Track'], # we include only one table to save tokens in the prompt :)\n",
|
||
" sample_rows_in_table_info=2)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"The sample rows are added to the prompt after each corresponding table's column information.\n",
|
||
"\n",
|
||
"We can use `db.table_info` and check which sample rows are included:"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 10,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"\n",
|
||
"CREATE TABLE \"Track\" (\n",
|
||
"\t\"TrackId\" INTEGER NOT NULL, \n",
|
||
"\t\"Name\" NVARCHAR(200) NOT NULL, \n",
|
||
"\t\"AlbumId\" INTEGER, \n",
|
||
"\t\"MediaTypeId\" INTEGER NOT NULL, \n",
|
||
"\t\"GenreId\" INTEGER, \n",
|
||
"\t\"Composer\" NVARCHAR(220), \n",
|
||
"\t\"Milliseconds\" INTEGER NOT NULL, \n",
|
||
"\t\"Bytes\" INTEGER, \n",
|
||
"\t\"UnitPrice\" NUMERIC(10, 2) NOT NULL, \n",
|
||
"\tPRIMARY KEY (\"TrackId\"), \n",
|
||
"\tFOREIGN KEY(\"MediaTypeId\") REFERENCES \"MediaType\" (\"MediaTypeId\"), \n",
|
||
"\tFOREIGN KEY(\"GenreId\") REFERENCES \"Genre\" (\"GenreId\"), \n",
|
||
"\tFOREIGN KEY(\"AlbumId\") REFERENCES \"Album\" (\"AlbumId\")\n",
|
||
")\n",
|
||
"\n",
|
||
"/*\n",
|
||
"2 rows from Track table:\n",
|
||
"TrackId\tName\tAlbumId\tMediaTypeId\tGenreId\tComposer\tMilliseconds\tBytes\tUnitPrice\n",
|
||
"1\tFor Those About To Rock (We Salute You)\t1\t1\t1\tAngus Young, Malcolm Young, Brian Johnson\t343719\t11170334\t0.99\n",
|
||
"2\tBalls to the Wall\t2\t2\t1\tNone\t342562\t5510424\t0.99\n",
|
||
"*/\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"print(db.table_info)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Case 3: SQL agents\n",
|
||
"\n",
|
||
"LangChain has an SQL Agent which provides a more flexible way of interacting with SQL Databases than the `SQLDatabaseChain`.\n",
|
||
"\n",
|
||
"The main advantages of using the SQL Agent are:\n",
|
||
"\n",
|
||
"- It can answer questions based on the databases' schema as well as on the databases' content (like describing a specific table)\n",
|
||
"- It can recover from errors by running a generated query, catching the traceback and regenerating it correctly\n",
|
||
"\n",
|
||
"To initialize the agent, we use `create_sql_agent` function. \n",
|
||
"\n",
|
||
"This agent contains the `SQLDatabaseToolkit` which contains tools to: \n",
|
||
"\n",
|
||
"* Create and execute queries\n",
|
||
"* Check query syntax\n",
|
||
"* Retrieve table descriptions\n",
|
||
"* ... and more"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 14,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"from langchain.agents import create_sql_agent\n",
|
||
"from langchain.agents.agent_toolkits import SQLDatabaseToolkit\n",
|
||
"# from langchain.agents import AgentExecutor\n",
|
||
"from langchain.agents.agent_types import AgentType\n",
|
||
"\n",
|
||
"db = SQLDatabase.from_uri(\"sqlite:///Chinook.db\")\n",
|
||
"llm = OpenAI(temperature=0, verbose=True)\n",
|
||
"\n",
|
||
"agent_executor = create_sql_agent(\n",
|
||
" llm=OpenAI(temperature=0),\n",
|
||
" toolkit=SQLDatabaseToolkit(db=db, llm=OpenAI(temperature=0)),\n",
|
||
" verbose=True,\n",
|
||
" agent_type=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n",
|
||
")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Agent task example #1 - Running queries\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 15,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"\n",
|
||
"\n",
|
||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||
"\u001b[32;1m\u001b[1;3mAction: sql_db_list_tables\n",
|
||
"Action Input: \u001b[0m\n",
|
||
"Observation: \u001b[38;5;200m\u001b[1;3mAlbum, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track\u001b[0m\n",
|
||
"Thought:\u001b[32;1m\u001b[1;3m I should query the schema of the Invoice and Customer tables.\n",
|
||
"Action: sql_db_schema\n",
|
||
"Action Input: Invoice, Customer\u001b[0m\n",
|
||
"Observation: \u001b[33;1m\u001b[1;3m\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\t2009-01-01 00:00:00\tTheodor-Heuss-Straße 34\tStuttgart\tNone\tGermany\t70174\t1.98\n",
|
||
"2\t4\t2009-01-02 00:00:00\tUllevålsveien 14\tOslo\tNone\tNorway\t0171\t3.96\n",
|
||
"3\t8\t2009-01-03 00:00:00\tGrétrystraat 63\tBrussels\tNone\tBelgium\t1000\t5.94\n",
|
||
"*/\u001b[0m\n",
|
||
"Thought:\u001b[32;1m\u001b[1;3m I should query the total sales per country.\n",
|
||
"Action: sql_db_query\n",
|
||
"Action Input: SELECT Country, SUM(Total) AS TotalSales FROM Invoice INNER JOIN Customer ON Invoice.CustomerId = Customer.CustomerId GROUP BY Country ORDER BY TotalSales DESC LIMIT 10\u001b[0m\n",
|
||
"Observation: \u001b[36;1m\u001b[1;3m[('USA', 523.0600000000003), ('Canada', 303.9599999999999), ('France', 195.09999999999994), ('Brazil', 190.09999999999997), ('Germany', 156.48), ('United Kingdom', 112.85999999999999), ('Czech Republic', 90.24000000000001), ('Portugal', 77.23999999999998), ('India', 75.25999999999999), ('Chile', 46.62)]\u001b[0m\n",
|
||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||
"Final Answer: The country with the highest total sales is the USA, with a total of $523.06.\u001b[0m\n",
|
||
"\n",
|
||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||
]
|
||
},
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"'The country with the highest total sales is the USA, with a total of $523.06.'"
|
||
]
|
||
},
|
||
"execution_count": 15,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"agent_executor.run(\n",
|
||
" \"List the total sales per country. Which country's customers spent the most?\"\n",
|
||
")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"Looking at the [LangSmith trace](https://smith.langchain.com/public/a86dbe17-5782-4020-bce6-2de85343168a/r), we can see:\n",
|
||
"\n",
|
||
"* The agent is using a ReAct style prompt\n",
|
||
"* First, it will look at the tables: `Action: sql_db_list_tables` using tool `sql_db_list_tables`\n",
|
||
"* Given the tables as an observation, it `thinks` and then determinates the next `action`:\n",
|
||
"\n",
|
||
"```\n",
|
||
"Observation: Album, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track\n",
|
||
"Thought: I should query the schema of the Invoice and Customer tables.\n",
|
||
"Action: sql_db_schema\n",
|
||
"Action Input: Invoice, Customer\n",
|
||
"```\n",
|
||
"\n",
|
||
"* It then formulates the query using the schema from tool `sql_db_schema`\n",
|
||
"\n",
|
||
"```\n",
|
||
"Thought: I should query the total sales per country.\n",
|
||
"Action: sql_db_query\n",
|
||
"Action Input: SELECT Country, SUM(Total) AS TotalSales FROM Invoice INNER JOIN Customer ON Invoice.CustomerId = Customer.CustomerId GROUP BY Country ORDER BY TotalSales DESC LIMIT 10\n",
|
||
"```\n",
|
||
"\n",
|
||
"* It finally executes the generated query using tool `sql_db_query`\n",
|
||
"\n",
|
||
""
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Agent task example #2 - Describing a Table"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 14,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"\n",
|
||
"\n",
|
||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||
"\u001b[32;1m\u001b[1;3mAction: sql_db_list_tables\n",
|
||
"Action Input: \u001b[0m\n",
|
||
"Observation: \u001b[38;5;200m\u001b[1;3mAlbum, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track\u001b[0m\n",
|
||
"Thought:\u001b[32;1m\u001b[1;3m The PlaylistTrack table is the most relevant to the question.\n",
|
||
"Action: sql_db_schema\n",
|
||
"Action Input: PlaylistTrack\u001b[0m\n",
|
||
"Observation: \u001b[33;1m\u001b[1;3m\n",
|
||
"CREATE TABLE \"PlaylistTrack\" (\n",
|
||
"\t\"PlaylistId\" INTEGER NOT NULL, \n",
|
||
"\t\"TrackId\" INTEGER NOT NULL, \n",
|
||
"\tPRIMARY KEY (\"PlaylistId\", \"TrackId\"), \n",
|
||
"\tFOREIGN KEY(\"TrackId\") REFERENCES \"Track\" (\"TrackId\"), \n",
|
||
"\tFOREIGN KEY(\"PlaylistId\") REFERENCES \"Playlist\" (\"PlaylistId\")\n",
|
||
")\n",
|
||
"\n",
|
||
"/*\n",
|
||
"3 rows from PlaylistTrack table:\n",
|
||
"PlaylistId\tTrackId\n",
|
||
"1\t3402\n",
|
||
"1\t3389\n",
|
||
"1\t3390\n",
|
||
"*/\u001b[0m\n",
|
||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||
"Final Answer: The PlaylistTrack table contains two columns, PlaylistId and TrackId, which are both integers and form a primary key. It also has two foreign keys, one to the Track table and one to the Playlist table.\u001b[0m\n",
|
||
"\n",
|
||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||
]
|
||
},
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"'The PlaylistTrack table contains two columns, PlaylistId and TrackId, which are both integers and form a primary key. It also has two foreign keys, one to the Track table and one to the Playlist table.'"
|
||
]
|
||
},
|
||
"execution_count": 14,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"agent_executor.run(\"Describe the playlisttrack table\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Extending the SQL Toolkit\n",
|
||
"\n",
|
||
"Although the out-of-the-box SQL Toolkit contains the necessary tools to start working on a database, it is often the case that some extra tools may be useful for extending the agent's capabilities. This is particularly useful when trying to use **domain specific knowledge** in the solution, in order to improve its overall performance.\n",
|
||
"\n",
|
||
"Some examples include:\n",
|
||
"\n",
|
||
"- Including dynamic few shot examples\n",
|
||
"- Finding misspellings in proper nouns to use as column filters\n",
|
||
"\n",
|
||
"We can create separate tools which tackle these specific use cases and include them as a complement to the standard SQL Toolkit. Let's see how to include these two custom tools.\n",
|
||
"\n",
|
||
"#### Including dynamic few-shot examples\n",
|
||
"\n",
|
||
"In order to include dynamic few-shot examples, we need a custom **Retriever Tool** that handles the vector database in order to retrieve the examples that are semantically similar to the user’s question.\n",
|
||
"\n",
|
||
"Let's start by creating a dictionary with some examples: "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 1,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# few_shots = {'List all artists.': 'SELECT * FROM artists;',\n",
|
||
"# \"Find all albums for the artist 'AC/DC'.\": \"SELECT * FROM albums WHERE ArtistId = (SELECT ArtistId FROM artists WHERE Name = 'AC/DC');\",\n",
|
||
"# \"List all tracks in the 'Rock' genre.\": \"SELECT * FROM tracks WHERE GenreId = (SELECT GenreId FROM genres WHERE Name = 'Rock');\",\n",
|
||
"# 'Find the total duration of all tracks.': 'SELECT SUM(Milliseconds) FROM tracks;',\n",
|
||
"# 'List all customers from Canada.': \"SELECT * FROM customers WHERE Country = 'Canada';\",\n",
|
||
"# 'How many tracks are there in the album with ID 5?': 'SELECT COUNT(*) FROM tracks WHERE AlbumId = 5;',\n",
|
||
"# 'Find the total number of invoices.': 'SELECT COUNT(*) FROM invoices;',\n",
|
||
"# 'List all tracks that are longer than 5 minutes.': 'SELECT * FROM tracks WHERE Milliseconds > 300000;',\n",
|
||
"# 'Who are the top 5 customers by total purchase?': 'SELECT CustomerId, SUM(Total) AS TotalPurchase FROM invoices GROUP BY CustomerId ORDER BY TotalPurchase DESC LIMIT 5;',\n",
|
||
"# 'Which albums are from the year 2000?': \"SELECT * FROM albums WHERE strftime('%Y', ReleaseDate) = '2000';\",\n",
|
||
"# 'How many employees are there': 'SELECT COUNT(*) FROM \"employee\"'\n",
|
||
"# }"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"We can then create a retriever using the list of questions, assigning the target SQL query as metadata:"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 24,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
|
||
"from langchain.vectorstores import FAISS\n",
|
||
"from langchain.schema import Document\n",
|
||
"\n",
|
||
"embeddings = OpenAIEmbeddings()\n",
|
||
"\n",
|
||
"few_shot_docs = [Document(page_content=question, metadata={'sql_query': few_shots[question]}) for question in few_shots.keys()]\n",
|
||
"vector_db = FAISS.from_documents(few_shot_docs, embeddings)\n",
|
||
"retriever = vector_db.as_retriever()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"Now we can create our own custom tool and append it as a new tool in the `create_sql_agent` function:"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 5,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"from langchain.agents.agent_toolkits import create_retriever_tool\n",
|
||
"\n",
|
||
"tool_description = \"\"\"\n",
|
||
"This tool will help you understand similar examples to adapt them to the user question.\n",
|
||
"Input to this tool should be the user question.\n",
|
||
"\"\"\"\n",
|
||
"\n",
|
||
"retriever_tool = create_retriever_tool(\n",
|
||
" retriever,\n",
|
||
" name='sql_get_similar_examples',\n",
|
||
" description=tool_description\n",
|
||
" )\n",
|
||
"custom_tool_list = [retriever_tool]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"Now we can create the agent, adjusting the standard SQL Agent suffix to consider our use case. Although the most straightforward way to handle this would be to include it just in the tool description, this is often not enough and we need to specify it in the agent prompt using the `suffix` argument in the constructor."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 22,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"from langchain.agents import create_sql_agent, AgentType\n",
|
||
"from langchain.agents.agent_toolkits import SQLDatabaseToolkit\n",
|
||
"from langchain.utilities import SQLDatabase\n",
|
||
"from langchain.chat_models import ChatOpenAI\n",
|
||
"\n",
|
||
"db = SQLDatabase.from_uri(\"sqlite:///Chinook.db\")\n",
|
||
"llm = ChatOpenAI(model_name='gpt-4',temperature=0)\n",
|
||
"\n",
|
||
"toolkit = SQLDatabaseToolkit(db=db, llm=llm)\n",
|
||
"\n",
|
||
"custom_suffix = \"\"\"\n",
|
||
"I should first get the similar examples I know.\n",
|
||
"If the examples are enough to construct the query, I can build it.\n",
|
||
"Otherwise, I can then look at the tables in the database to see what I can query.\n",
|
||
"Then I should query the schema of the most relevant tables\n",
|
||
"\"\"\"\n",
|
||
"\n",
|
||
"agent = create_sql_agent(llm=llm,\n",
|
||
" toolkit=toolkit,\n",
|
||
" verbose=True,\n",
|
||
" agent_type=AgentType.OPENAI_FUNCTIONS,\n",
|
||
" extra_tools=custom_tool_list,\n",
|
||
" suffix=custom_suffix\n",
|
||
" )"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"Let's try it out:"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 23,
|
||
"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",
|
||
"Invoking: `sql_get_similar_examples` with `How many employees do we have?`\n",
|
||
"\n",
|
||
"\n",
|
||
"\u001b[0m\u001b[33;1m\u001b[1;3m[Document(page_content='How many employees are there', metadata={'sql_query': 'SELECT COUNT(*) FROM \"employee\"'}), Document(page_content='Find the total number of invoices.', metadata={'sql_query': 'SELECT COUNT(*) FROM invoices;'})]\u001b[0m\u001b[32;1m\u001b[1;3m\n",
|
||
"Invoking: `sql_db_query_checker` with `SELECT COUNT(*) FROM employee`\n",
|
||
"responded: {content}\n",
|
||
"\n",
|
||
"\u001b[0m\u001b[36;1m\u001b[1;3mSELECT COUNT(*) FROM employee\u001b[0m\u001b[32;1m\u001b[1;3m\n",
|
||
"Invoking: `sql_db_query` with `SELECT COUNT(*) FROM employee`\n",
|
||
"\n",
|
||
"\n",
|
||
"\u001b[0m\u001b[36;1m\u001b[1;3m[(8,)]\u001b[0m\u001b[32;1m\u001b[1;3mWe have 8 employees.\u001b[0m\n",
|
||
"\n",
|
||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||
]
|
||
},
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"'We have 8 employees.'"
|
||
]
|
||
},
|
||
"execution_count": 23,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"agent.run(\"How many employees do we have?\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"As we can see, the agent first used the `sql_get_similar_examples` tool in order to retrieve similar examples. As the question was very similar to other few shot examples, the agent **didn't need to use any other tool** from the standard Toolkit, thus **saving time and tokens**."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"#### Finding and correcting misspellings for proper nouns\n",
|
||
"\n",
|
||
"In order to filter columns that contain proper nouns such as addresses, song names or artists, we first need to double-check the spelling in order to filter the data correctly. \n",
|
||
"\n",
|
||
"We can achieve this by creating a vector store using all the distinct proper nouns that exist in the database. We can then have the agent query that vector store each time the user includes a proper noun in their question, to find the correct spelling for that word. In this way, the agent can make sure it understands which entity the user is referring to before building the target query.\n",
|
||
"\n",
|
||
"Let's follow a similar approach to the few shots, but without metadata: just embedding the proper nouns and then querying to get the most similar one to the misspelled user question.\n",
|
||
"\n",
|
||
"First we need the unique values for each entity we want, for which we define a function that parses the result into a list of elements:"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 37,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"import ast\n",
|
||
"import re\n",
|
||
"\n",
|
||
"def run_query_save_results(db, query):\n",
|
||
" res = db.run(query)\n",
|
||
" res = [el for sub in ast.literal_eval(res) for el in sub if el]\n",
|
||
" res = [re.sub(r'\\b\\d+\\b', '', string).strip() for string in res]\n",
|
||
" return res\n",
|
||
"\n",
|
||
"artists = run_query_save_results(db, \"SELECT Name FROM Artist\")\n",
|
||
"albums = run_query_save_results(db, \"SELECT Title FROM Album\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"Now we can proceed with creating the custom **retreiver tool** and the final agent:"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 51,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"from langchain.agents.agent_toolkits import create_retriever_tool\n",
|
||
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
|
||
"from langchain.vectorstores import FAISS\n",
|
||
"\n",
|
||
"\n",
|
||
"texts = (artists + albums)\n",
|
||
"\n",
|
||
"embeddings = OpenAIEmbeddings()\n",
|
||
"vector_db = FAISS.from_texts(texts, embeddings)\n",
|
||
"retriever = vector_db.as_retriever()\n",
|
||
"\n",
|
||
"retriever_tool = create_retriever_tool(\n",
|
||
" retriever,\n",
|
||
" name='name_search',\n",
|
||
" description='use to learn how a piece of data is actually written, can be from names, surnames addresses etc'\n",
|
||
" )\n",
|
||
"\n",
|
||
"custom_tool_list = [retriever_tool]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 54,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"from langchain.agents import create_sql_agent, AgentType\n",
|
||
"from langchain.agents.agent_toolkits import SQLDatabaseToolkit\n",
|
||
"from langchain.utilities import SQLDatabase\n",
|
||
"from langchain.chat_models import ChatOpenAI\n",
|
||
"\n",
|
||
"# db = SQLDatabase.from_uri(\"sqlite:///Chinook.db\")\n",
|
||
"llm = ChatOpenAI(model_name='gpt-4', temperature=0)\n",
|
||
"\n",
|
||
"toolkit = SQLDatabaseToolkit(db=db, llm=llm)\n",
|
||
"\n",
|
||
"custom_suffix = \"\"\"\n",
|
||
"If a user asks for me to filter based on proper nouns, I should first check the spelling using the name_search tool.\n",
|
||
"Otherwise, I can then look at the tables in the database to see what I can query.\n",
|
||
"Then I should query the schema of the most relevant tables\n",
|
||
"\"\"\"\n",
|
||
"\n",
|
||
"agent = create_sql_agent(llm=llm,\n",
|
||
" toolkit=toolkit,\n",
|
||
" verbose=True,\n",
|
||
" agent_type=AgentType.OPENAI_FUNCTIONS,\n",
|
||
" extra_tools=custom_tool_list,\n",
|
||
" suffix=custom_suffix\n",
|
||
" )"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"Let's try it out:"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 55,
|
||
"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",
|
||
"Invoking: `name_search` with `alis in pains`\n",
|
||
"\n",
|
||
"\n",
|
||
"\u001b[0m\u001b[33;1m\u001b[1;3m[Document(page_content='House of Pain', metadata={}), Document(page_content='Alice In Chains', metadata={}), Document(page_content='Aisha Duo', metadata={}), Document(page_content='House Of Pain', metadata={})]\u001b[0m\u001b[32;1m\u001b[1;3m\n",
|
||
"Invoking: `sql_db_list_tables` with ``\n",
|
||
"responded: {content}\n",
|
||
"\n",
|
||
"\u001b[0m\u001b[38;5;200m\u001b[1;3mAlbum, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track\u001b[0m\u001b[32;1m\u001b[1;3m\n",
|
||
"Invoking: `sql_db_schema` with `Album, Artist`\n",
|
||
"responded: {content}\n",
|
||
"\n",
|
||
"\u001b[0m\u001b[33;1m\u001b[1;3m\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",
|
||
"*/\u001b[0m\u001b[32;1m\u001b[1;3m\n",
|
||
"Invoking: `sql_db_query_checker` with `SELECT COUNT(*) FROM Album JOIN Artist ON Album.ArtistId = Artist.ArtistId WHERE Artist.Name = 'Alice In Chains'`\n",
|
||
"responded: {content}\n",
|
||
"\n",
|
||
"\u001b[0m\u001b[36;1m\u001b[1;3mSELECT COUNT(*) FROM Album JOIN Artist ON Album.ArtistId = Artist.ArtistId WHERE Artist.Name = 'Alice In Chains'\u001b[0m\u001b[32;1m\u001b[1;3m\n",
|
||
"Invoking: `sql_db_query` with `SELECT COUNT(*) FROM Album JOIN Artist ON Album.ArtistId = Artist.ArtistId WHERE Artist.Name = 'Alice In Chains'`\n",
|
||
"\n",
|
||
"\n",
|
||
"\u001b[0m\u001b[36;1m\u001b[1;3m[(1,)]\u001b[0m\u001b[32;1m\u001b[1;3mAlice In Chains has 1 album in the database.\u001b[0m\n",
|
||
"\n",
|
||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||
]
|
||
},
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"'Alice In Chains has 1 album in the database.'"
|
||
]
|
||
},
|
||
"execution_count": 55,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"agent.run(\"How many albums does alis in pains have?\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"As we can see, the agent used the `name_search` tool in order to check how to correctly query the database for this specific artist."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Go deeper\n",
|
||
"\n",
|
||
"To learn more about the SQL Agent and how it works we refer to the [SQL Agent Toolkit](/docs/integrations/toolkits/sql_database) documentation.\n",
|
||
"\n",
|
||
"You can also check Agents for other document types:\n",
|
||
"- [Pandas Agent](/docs/integrations/toolkits/pandas.html)\n",
|
||
"- [CSV Agent](/docs/integrations/toolkits/csv.html)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Elastic Search\n",
|
||
"\n",
|
||
"Going beyond the above use-case, there are integrations with other databases.\n",
|
||
"\n",
|
||
"For example, we can interact with Elasticsearch analytics database. \n",
|
||
"\n",
|
||
"This chain builds search queries via the Elasticsearch DSL API (filters and aggregations).\n",
|
||
"\n",
|
||
"The Elasticsearch client must have permissions for index listing, mapping description and search queries.\n",
|
||
"\n",
|
||
"See [here](https://www.elastic.co/guide/en/elasticsearch/reference/current/docker.html) for instructions on how to run Elasticsearch locally.\n",
|
||
"\n",
|
||
"Make sure to install the Elasticsearch Python client before:\n",
|
||
"\n",
|
||
"```sh\n",
|
||
"pip install elasticsearch\n",
|
||
"```"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 15,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"from elasticsearch import Elasticsearch\n",
|
||
"from langchain.chat_models import ChatOpenAI\n",
|
||
"from langchain.chains.elasticsearch_database import ElasticsearchDatabaseChain"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# Initialize Elasticsearch python client.\n",
|
||
"# See https://elasticsearch-py.readthedocs.io/en/v8.8.2/api.html#elasticsearch.Elasticsearch\n",
|
||
"ELASTIC_SEARCH_SERVER = \"https://elastic:pass@localhost:9200\"\n",
|
||
"db = Elasticsearch(ELASTIC_SEARCH_SERVER)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"Uncomment the next cell to initially populate your db."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# customers = [\n",
|
||
"# {\"firstname\": \"Jennifer\", \"lastname\": \"Walters\"},\n",
|
||
"# {\"firstname\": \"Monica\",\"lastname\":\"Rambeau\"},\n",
|
||
"# {\"firstname\": \"Carol\",\"lastname\":\"Danvers\"},\n",
|
||
"# {\"firstname\": \"Wanda\",\"lastname\":\"Maximoff\"},\n",
|
||
"# {\"firstname\": \"Jennifer\",\"lastname\":\"Takeda\"},\n",
|
||
"# ]\n",
|
||
"# for i, customer in enumerate(customers):\n",
|
||
"# db.create(index=\"customers\", document=customer, id=i)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"llm = ChatOpenAI(model_name=\"gpt-4\", temperature=0)\n",
|
||
"chain = ElasticsearchDatabaseChain.from_llm(llm=llm, database=db, verbose=True)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"question = \"What are the first names of all the customers?\"\n",
|
||
"chain.run(question)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"We can customize the prompt."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"from langchain.chains.elasticsearch_database.prompts import DEFAULT_DSL_TEMPLATE\n",
|
||
"from langchain.prompts.prompt import PromptTemplate\n",
|
||
"\n",
|
||
"PROMPT_TEMPLATE = \"\"\"Given an input question, create a syntactically correct Elasticsearch query to run. Unless the user specifies in their question a specific number of examples they wish to obtain, always limit your query to at most {top_k} results. You can order the results by a relevant column to return the most interesting examples in the database.\n",
|
||
"\n",
|
||
"Unless told to do not query for all the columns from a specific index, only ask for a the few relevant columns given the question.\n",
|
||
"\n",
|
||
"Pay attention to use only the column names that you can see in the mapping description. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which index. Return the query as valid json.\n",
|
||
"\n",
|
||
"Use the following format:\n",
|
||
"\n",
|
||
"Question: Question here\n",
|
||
"ESQuery: Elasticsearch Query formatted as json\n",
|
||
"\"\"\"\n",
|
||
"\n",
|
||
"PROMPT = PromptTemplate.from_template(\n",
|
||
" PROMPT_TEMPLATE,\n",
|
||
")\n",
|
||
"chain = ElasticsearchDatabaseChain.from_llm(llm=llm, database=db, query_prompt=PROMPT)"
|
||
]
|
||
}
|
||
],
|
||
"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": "3.9.1"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 4
|
||
}
|