构建一个基于SQL数据的问答系统
使LLM系统能够查询结构化数据与查询非结构化文本数据在性质上是不同的。对于后者，通常生成可以针对向量数据库进行搜索的文本，而对于结构化数据，LLM通常使用DSL（如SQL）编写和执行查询。在本指南中，我们将介绍在数据库中的表格数据上创建问答系统的基本方法。我们将涵盖使用链和代理的实现。这些系统将允许我们向数据库中的数据提出问题，并获得自然语言的回答。两者之间的主要区别在于，我们的代理可以根据需要多次查询数据库以回答问题。
⚠️ 安全提示 ⚠️
构建SQL数据库的问答系统需要执行模型生成的SQL查询。这样做存在固有的风险。确保您的数据库连接权限始终根据您的链/代理的需求尽可能狭窄地限定。这将减轻但不会消除构建模型驱动系统的风险。有关一般安全最佳实践的更多信息，请参见此处。
架构
从高层次来看，这些系统的步骤是：
- 将问题转换为SQL查询: 模型将用户输入转换为SQL查询。
- 执行SQL查询: 执行查询。
- 回答问题: 模型使用查询结果回应用户输入。
请注意，查询CSV中的数据可以采用类似的方法。有关在CSV数据上进行问答的更多详细信息，请参阅我们的操作指南。
设置
首先，获取所需的包并设置环境变量：
%%capture --no-stderr
%pip install --upgrade --quiet langchain-community langchainhub langgraph
# Comment out the below to opt-out of using LangSmith in this notebook. Not required.
if not os.environ.get("LANGCHAIN_API_KEY"):
os.environ["LANGCHAIN_API_KEY"] = getpass.getpass()
os.environ["LANGCHAIN_TRACING_V2"] = "true"
示例数据
下面的示例将使用与Chinook数据库的SQLite连接，这是一个代表数字媒体商店的示例数据库。按照这些安装步骤在与本笔记本相同的目录中创建Chinook.db。您也可以通过命令行下载并构建数据库：
curl -s https://raw.githubusercontent.com/lerocha/chinook-database/master/ChinookDatabase/DataSources/Chinook_Sqlite.sql | sqlite3 Chinook.db
现在，Chinook.db 已经在我们的目录中，我们可以使用 SQLAlchemy 驱动的 SQLDatabase 类与之交互：
from langchain_community.utilities import SQLDatabase
db = SQLDatabase.from_uri("sqlite:///Chinook.db")
print(db.dialect)
print(db.get_usable_table_names())
db.run("SELECT * FROM Artist LIMIT 10;")
API Reference:SQLDatabase
sqlite
['Album', 'Artist', 'Customer', 'Employee', 'Genre', 'Invoice', 'InvoiceLine', 'MediaType', 'Playlist', 'PlaylistTrack', 'Track']
"[(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')]"
太好了！我们有一个可以查询的SQL数据库。现在让我们尝试将其连接到LLM。
链
链是由可预测的步骤组成的。在LangGraph中，我们可以通过简单的节点序列来表示一个链。让我们创建一个步骤序列，给定一个问题，执行以下操作：
- 将问题转换为SQL查询;
- 执行查询;
- 使用结果来回答原始问题。
有些场景不受此安排支持。例如，该系统将为任何用户输入执行SQL查询——甚至是“hello”。重要的是，正如我们将在下面看到的，有些问题需要多个查询来回答。我们将在代理部分解决这些场景。
应用程序状态
我们应用程序的LangGraph 状态控制着输入到应用程序的数据、在步骤之间传输的数据以及应用程序输出的数据。它通常是一个TypedDict，但也可以是一个Pydantic BaseModel。
对于这个应用程序，我们只需要跟踪输入的问题、生成的查询、查询结果和生成的答案：
from typing_extensions import TypedDict
class State(TypedDict):
question: str
query: str
result: str
answer: str
现在我们只需要操作这个状态并填充其内容的函数。
将问题转换为SQL查询
第一步是获取用户输入并将其转换为SQL查询。为了可靠地获取SQL查询（不包括Markdown格式和解释或澄清），我们将使用LangChain的结构化输出抽象。
让我们为我们的应用程序选择一个聊天模型：
Select chat model:
pip install -qU langchain-openai
import getpass
import os
if not os.environ.get("OPENAI_API_KEY"):
os.environ["OPENAI_API_KEY"] = getpass.getpass("Enter API key for OpenAI: ")
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(model="gpt-4o-mini")
我们将从Prompt Hub中提取一个提示来指导模型。
from langchain import hub
query_prompt_template = hub.pull("langchain-ai/sql-query-system-prompt")
assert len(query_prompt_template.messages) == 1
query_prompt_template.messages[0].pretty_print()
API Reference:hub
================================[1m System Message [0m================================
Given an input question, create a syntactically correct [33;1m[1;3m{dialect}[0m query to run to help find the answer. Unless the user specifies in his question a specific number of examples they wish to obtain, always limit your query to at most [33;1m[1;3m{top_k}[0m results. You can order the results by a relevant column to return the most interesting examples in the database.
Never query for all the columns from a specific table, only ask for a the few relevant columns given the question.
Pay attention to use only the column names that you can see in the schema description. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
Only use the following tables:
[33;1m[1;3m{table_info}[0m
Question: [33;1m[1;3m{input}[0m
提示包括我们需要填充的几个参数，例如SQL方言和表模式。LangChain的SQLDatabase对象包含帮助完成此操作的方法。我们的write_query步骤将填充这些参数并提示模型生成SQL查询：
from typing_extensions import Annotated
class QueryOutput(TypedDict):
"""Generated SQL query."""
query: Annotated[str, ..., "Syntactically valid SQL query."]
def write_query(state: State):
"""Generate SQL query to fetch information."""
prompt = query_prompt_template.invoke(
{
"dialect": db.dialect,
"top_k": 10,
"table_info": db.get_table_info(),
"input": state["question"],
}
)
structured_llm = llm.with_structured_output(QueryOutput)
result = structured_llm.invoke(prompt)
return {"query": result["query"]}
让我们来测试一下：
write_query({"question": "How many Employees are there?"})
{'query': 'SELECT COUNT(EmployeeId) AS EmployeeCount FROM Employee;'}
执行查询
这是创建SQL链中最危险的部分。 请仔细考虑是否可以在您的数据上运行自动化查询。尽可能减少数据库连接权限。考虑在执行查询之前向您的链中添加人工批准步骤（见下文）。
要执行查询，我们将从langchain-community加载一个工具。我们的execute_query节点将只是包装这个工具：
from langchain_community.tools.sql_database.tool import QuerySQLDatabaseTool
def execute_query(state: State):
"""Execute SQL query."""
execute_query_tool = QuerySQLDatabaseTool(db=db)
return {"result": execute_query_tool.invoke(state["query"])}
API Reference:QuerySQLDatabaseTool
测试此步骤：
execute_query({"query": "SELECT COUNT(EmployeeId) AS EmployeeCount FROM Employee;"})
{'result': '[(8,)]'}
生成答案
最后，我们的最后一步根据从数据库中提取的信息生成问题的答案：
def generate_answer(state: State):
"""Answer question using retrieved information as context."""
prompt = (
"Given the following user question, corresponding SQL query, "
"and SQL result, answer the user question.\n\n"
f'Question: {state["question"]}\n'
f'SQL Query: {state["query"]}\n'
f'SQL Result: {state["result"]}'
)
response = llm.invoke(prompt)
return {"answer": response.content}
使用LangGraph进行编排
最后，我们将应用程序编译成一个单一的graph对象。在这种情况下，我们只是将这三个步骤连接成一个单一的序列。
from langgraph.graph import START, StateGraph
graph_builder = StateGraph(State).add_sequence(
[write_query, execute_query, generate_answer]
)
graph_builder.add_edge(START, "write_query")
graph = graph_builder.compile()
API Reference:StateGraph
LangGraph 还内置了用于可视化应用程序控制流的实用工具：
from IPython.display import Image, display
display(Image(graph.get_graph().draw_mermaid_png()))
让我们测试我们的应用程序！注意，我们可以流式传输各个步骤的结果：
for step in graph.stream(
{"question": "How many employees are there?"}, stream_mode="updates"
):
print(step)
{'write_query': {'query': 'SELECT COUNT(EmployeeId) AS EmployeeCount FROM Employee;'}}
{'execute_query': {'result': '[(8,)]'}}
{'generate_answer': {'answer': 'There are 8 employees.'}}
查看LangSmith跟踪。
人在循环中
LangGraph 支持许多对此工作流程有用的功能。其中之一是 human-in-the-loop：我们可以在敏感步骤（例如执行 SQL 查询）之前中断我们的应用程序以进行人工审查。这是通过 LangGraph 的 persistence 层实现的，该层将运行进度保存到您选择的存储中。下面，我们指定内存中的存储：
from langgraph.checkpoint.memory import MemorySaver
memory = MemorySaver()
graph = graph_builder.compile(checkpointer=memory, interrupt_before=["execute_query"])
# Now that we're using persistence, we need to specify a thread ID
# so that we can continue the run after review.
config = {"configurable": {"thread_id": "1"}}
API Reference:MemorySaver
display(Image(graph.get_graph().draw_mermaid_png()))
让我们重复相同的运行，添加一个简单的“是/否”批准步骤：
for step in graph.stream(
{"question": "How many employees are there?"},
config,
stream_mode="updates",
):
print(step)
try:
user_approval = input("Do you want to go to execute query? (yes/no): ")
except Exception:
user_approval = "no"
if user_approval.lower() == "yes":
# If approved, continue the graph execution
for step in graph.stream(None, config, stream_mode="updates"):
print(step)
else:
print("Operation cancelled by user.")
{'write_query': {'query': 'SELECT COUNT(EmployeeId) AS EmployeeCount FROM Employee;'}}
{'__interrupt__': ()}
``````output
Do you want to go to execute query? (yes/no): yes
``````output
{'execute_query': {'result': '[(8,)]'}}
{'generate_answer': {'answer': 'There are 8 employees.'}}
查看此 LangGraph 指南以获取更多详细信息和示例。
下一步
对于更复杂的查询生成，我们可能希望创建少量示例提示或添加查询检查步骤。对于这种高级技术及更多内容，请查看：
- Prompting strategies: 高级提示工程技术。
- Query checking: 添加查询验证和错误处理。
- 大型数据库: 处理大型数据库的技术。
代理
Agents 利用LLMs的推理能力在执行过程中做出决策。使用代理可以让你在查询生成和执行过程中减少额外的判断。尽管它们的行为比上述“链”更不可预测，但它们具有一些优势：
- 他们可以根据需要多次查询数据库以回答用户的问题。
- 他们可以通过运行生成的查询、捕获回溯并正确重新生成来从错误中恢复。
- 他们可以根据数据库的模式以及数据库的内容（如描述特定表）来回答问题。
下面我们组装一个最小的SQL代理。我们将使用LangChain的SQLDatabaseToolkit为其配备一组工具。使用LangGraph的预构建的ReAct代理构造函数，我们可以在一行代码中完成此操作。
tip
查看LangGraph的SQL代理教程，了解更高级的SQL代理公式。
SQLDatabaseToolkit 包含可以执行以下操作的工具：
- 创建并执行查询
- 检查查询语法
- 检索表描述
- ... 以及更多
from langchain_community.agent_toolkits import SQLDatabaseToolkit
toolkit = SQLDatabaseToolkit(db=db, llm=llm)
tools = toolkit.get_tools()
tools
API Reference:SQLDatabaseToolkit
[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 0x10d5f9120>),
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 0x10d5f9120>),
ListSQLDatabaseTool(db=<langchain_community.utilities.sql_database.SQLDatabase object at 0x10d5f9120>),
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 0x10d5f9120>, llm=ChatOpenAI(client=<openai.resources.chat.completions.Completions object at 0x119315480>, async_client=<openai.resources.chat.completions.AsyncCompletions object at 0x119317550>, root_client=<openai.OpenAI object at 0x10d5f8df0>, root_async_client=<openai.AsyncOpenAI object at 0x1193154e0>, model_name='gpt-4o', temperature=0.0, model_kwargs={}, openai_api_key=SecretStr('**********')), llm_chain=LLMChain(verbose=False, prompt=PromptTemplate(input_variables=['dialect', 'query'], input_types={}, partial_variables={}, 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 0x119315480>, async_client=<openai.resources.chat.completions.AsyncCompletions object at 0x119317550>, root_client=<openai.OpenAI object at 0x10d5f8df0>, root_async_client=<openai.AsyncOpenAI object at 0x1193154e0>, model_name='gpt-4o', temperature=0.0, model_kwargs={}, openai_api_key=SecretStr('**********')), output_parser=StrOutputParser(), llm_kwargs={}))]
系统提示
我们还需要为我们的代理加载一个系统提示。这将包括如何行为的指示。
from langchain import hub
prompt_template = hub.pull("langchain-ai/sql-agent-system-prompt")
assert len(prompt_template.messages) == 1
prompt_template.messages[0].pretty_print()
API Reference:hub
================================[1m System Message [0m================================
You are an agent designed to interact with a SQL database.
Given an input question, create a syntactically correct [33;1m[1;3m{dialect}[0m query to run, then look at the results of the query and return the answer.
Unless the user specifies a specific number of examples they wish to obtain, always limit your query to at most [33;1m[1;3m{top_k}[0m results.
You can order the results by a relevant column to return the most interesting examples in the database.
Never query for all the columns from a specific table, only ask for the relevant columns given the question.
You have access to tools for interacting with the database.
Only use the below tools. Only use the information returned by the below tools to construct your final answer.
You MUST double check your query before executing it. If you get an error while executing a query, rewrite the query and try again.
DO NOT make any DML statements (INSERT, UPDATE, DELETE, DROP etc.) to the database.
To start you should ALWAYS look at the tables in the database to see what you can query.
Do NOT skip this step.
Then you should query the schema of the most relevant tables.
让我们填充提示中突出显示的参数：
system_message = prompt_template.format(dialect="SQLite", top_k=5)
初始化代理
我们将使用一个预构建的LangGraph代理来构建我们的代理
from langchain_core.messages import HumanMessage
from langgraph.prebuilt import create_react_agent
agent_executor = create_react_agent(llm, tools, state_modifier=system_message)
API Reference:HumanMessage | create_react_agent
考虑代理如何回应以下问题：
question = "Which country's customers spent the most?"
for step in agent_executor.stream(
{"messages": [{"role": "user", "content": question}]},
stream_mode="values",
):
step["messages"][-1].pretty_print()
================================[1m Human Message [0m=================================
Which country's customers spent the most?
==================================[1m Ai Message [0m==================================
Tool Calls:
sql_db_list_tables (call_tFp7HYD6sAAmCShgeqkVZH6Q)
Call ID: call_tFp7HYD6sAAmCShgeqkVZH6Q
Args:
=================================[1m Tool Message [0m=================================
Name: sql_db_list_tables
Album, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track
==================================[1m Ai Message [0m==================================
Tool Calls:
sql_db_schema (call_KJZ1Jx6JazyDdJa0uH1UeiOz)
Call ID: call_KJZ1Jx6JazyDdJa0uH1UeiOz
Args:
table_names: Customer, Invoice
=================================[1m Tool Message [0m=================================
Name: sql_db_schema
CREATE TABLE "Customer" (
"CustomerId" INTEGER NOT NULL,
"FirstName" NVARCHAR(40) NOT NULL,
"LastName" NVARCHAR(20) NOT NULL,
"Company" NVARCHAR(80),
"Address" NVARCHAR(70),
"City" NVARCHAR(40),
"State" NVARCHAR(40),
"Country" NVARCHAR(40),
"PostalCode" NVARCHAR(10),
"Phone" NVARCHAR(24),
"Fax" NVARCHAR(24),
"Email" NVARCHAR(60) NOT NULL,
"SupportRepId" INTEGER,
PRIMARY KEY ("CustomerId"),
FOREIGN KEY("SupportRepId") REFERENCES "Employee" ("EmployeeId")
)
/*
3 rows from Customer table:
CustomerId FirstName LastName Company Address City State Country PostalCode Phone Fax Email SupportRepId
1 Luís Gonçalves Embraer - Empresa Brasileira de Aeronáutica S.A. Av. Brigadeiro Faria Lima, 2170 São José dos Campos SP Brazil 12227-000 +55 (12) 3923-5555 +55 (12) 3923-5566 luisg@embraer.com.br 3
2 Leonie Köhler None Theodor-Heuss-Straße 34 Stuttgart None Germany 70174 +49 0711 2842222 None leonekohler@surfeu.de 5
3 François Tremblay None 1498 rue Bélanger Montréal QC Canada H2G 1A7 +1 (514) 721-4711 None ftremblay@gmail.com 3
*/
CREATE TABLE "Invoice" (
"InvoiceId" INTEGER NOT NULL,
"CustomerId" INTEGER NOT NULL,
"InvoiceDate" DATETIME NOT NULL,
"BillingAddress" NVARCHAR(70),
"BillingCity" NVARCHAR(40),
"BillingState" NVARCHAR(40),
"BillingCountry" NVARCHAR(40),
"BillingPostalCode" NVARCHAR(10),
"Total" NUMERIC(10, 2) NOT NULL,
PRIMARY KEY ("InvoiceId"),
FOREIGN KEY("CustomerId") REFERENCES "Customer" ("CustomerId")
)
/*
3 rows from Invoice table:
InvoiceId CustomerId InvoiceDate BillingAddress BillingCity BillingState BillingCountry BillingPostalCode Total
1 2 2021-01-01 00:00:00 Theodor-Heuss-Straße 34 Stuttgart None Germany 70174 1.98
2 4 2021-01-02 00:00:00 Ullevålsveien 14 Oslo None Norway 0171 3.96
3 8 2021-01-03 00:00:00 Grétrystraat 63 Brussels None Belgium 1000 5.94
*/
==================================[1m Ai Message [0m==================================
Tool Calls:
sql_db_query_checker (call_AQuTGbgH63u4gPgyV723yrjX)
Call ID: call_AQuTGbgH63u4gPgyV723yrjX
Args:
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;
=================================[1m Tool Message [0m=================================
Name: sql_db_query_checker
\`\`\`sql
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;
\`\`\`
==================================[1m Ai Message [0m==================================
Tool Calls:
sql_db_query (call_B88EwU44nwwpQL5M9nlcemSU)
Call ID: call_B88EwU44nwwpQL5M9nlcemSU
Args:
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;
=================================[1m Tool Message [0m=================================
Name: sql_db_query
[('USA', 523.06)]
==================================[1m Ai Message [0m==================================
The country whose customers spent the most is the USA, with a total spending of 523.06.
你也可以使用LangSmith trace来可视化这些步骤和相关的元数据。
请注意，代理会执行多个查询，直到它获得所需的信息：
- 列出可用的表格;
- 检索三个表的模式；
- 通过连接操作查询多个表。
然后，代理能够使用最终查询的结果来生成对原始问题的答案。
代理同样可以处理定性问题：
question = "Describe the playlisttrack table"
for step in agent_executor.stream(
{"messages": [{"role": "user", "content": question}]},
stream_mode="values",
):
step["messages"][-1].pretty_print()
================================[1m Human Message [0m=================================
Describe the playlisttrack table
==================================[1m Ai Message [0m==================================
Tool Calls:
sql_db_list_tables (call_fMF8eTmX5TJDJjc3Mhdg52TI)
Call ID: call_fMF8eTmX5TJDJjc3Mhdg52TI
Args:
=================================[1m Tool Message [0m=================================
Name: sql_db_list_tables
Album, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track
==================================[1m Ai Message [0m==================================
Tool Calls:
sql_db_schema (call_W8Vkk4NEodkAAIg8nexAszUH)
Call ID: call_W8Vkk4NEodkAAIg8nexAszUH
Args:
table_names: PlaylistTrack
=================================[1m Tool Message [0m=================================
Name: sql_db_schema
CREATE TABLE "PlaylistTrack" (
"PlaylistId" INTEGER NOT NULL,
"TrackId" INTEGER NOT NULL,
PRIMARY KEY ("PlaylistId", "TrackId"),
FOREIGN KEY("TrackId") REFERENCES "Track" ("TrackId"),
FOREIGN KEY("PlaylistId") REFERENCES "Playlist" ("PlaylistId")
)
/*
3 rows from PlaylistTrack table:
PlaylistId TrackId
1 3402
1 3389
1 3390
*/
==================================[1m Ai Message [0m==================================
The `PlaylistTrack` table is designed to associate tracks with playlists. It has the following structure:
- **PlaylistId**: An integer that serves as a foreign key referencing the `Playlist` table. It is part of the composite primary key.
- **TrackId**: An integer that serves as a foreign key referencing the `Track` table. It is also part of the composite primary key.
The primary key for this table is a composite key consisting of both `PlaylistId` and `TrackId`, ensuring that each track can be uniquely associated with a playlist. The table enforces referential integrity by linking to the `Track` and `Playlist` tables through foreign keys.
处理高基数列
为了筛选包含专有名词（如地址、歌曲名称或艺术家）的列，我们首先需要仔细检查拼写，以便正确筛选数据。
我们可以通过创建一个包含数据库中所有不同专有名词的向量存储来实现这一点。然后，每次用户在问题中包含专有名词时，我们可以让代理查询该向量存储，以找到该单词的正确拼写。通过这种方式，代理可以在构建目标查询之前确保它理解用户所指的实体。
首先，我们需要每个实体的唯一值，为此我们定义了一个函数，将结果解析为元素列表：
import ast
import re
def query_as_list(db, query):
res = db.run(query)
res = [el for sub in ast.literal_eval(res) for el in sub if el]
res = [re.sub(r"\b\d+\b", "", string).strip() for string in res]
return list(set(res))
artists = query_as_list(db, "SELECT Name FROM Artist")
albums = query_as_list(db, "SELECT Title FROM Album")
albums[:5]
['In Through The Out Door',
'Transmission',
'Battlestar Galactica (Classic), Season',
'A Copland Celebration, Vol. I',
'Quiet Songs']
使用此函数，我们可以创建一个检索工具，代理可以根据其判断执行。
选择一个嵌入模型:
Select embeddings model:
pip install -qU langchain-openai
import getpass
import os
if not os.environ.get("OPENAI_API_KEY"):
os.environ["OPENAI_API_KEY"] = getpass.getpass("Enter API key for OpenAI: ")
from langchain_openai import OpenAIEmbeddings
embeddings = OpenAIEmbeddings(model="text-embedding-3-large")
选择一个向量存储:
Select vector store:
pip install -qU langchain-core
from langchain_core.vectorstores import InMemoryVectorStore
vector_store = InMemoryVectorStore(embeddings)
我们现在可以构建一个检索工具，可以在数据库中搜索相关的专有名词：
from langchain.agents.agent_toolkits import create_retriever_tool
_ = vector_store.add_texts(artists + albums)
retriever = vector_store.as_retriever(search_kwargs={"k": 5})
description = (
"Use to look up values to filter on. Input is an approximate spelling "
"of the proper noun, output is valid proper nouns. Use the noun most "
"similar to the search."
)
retriever_tool = create_retriever_tool(
retriever,
name="search_proper_nouns",
description=description,
)
API Reference:create_retriever_tool
让我们来试试看：
print(retriever_tool.invoke("Alice Chains"))
Alice In Chains
Alanis Morissette
Pearl Jam
Pearl Jam
Audioslave
这样，如果代理确定需要根据类似于“Alice Chains”的艺术家编写过滤器，它可以首先使用检索工具来观察列的相关值。
将这一切整合起来：
# Add to system message
suffix = (
"If you need to filter on a proper noun like a Name, you must ALWAYS first look up "
"the filter value using the 'search_proper_nouns' tool! Do not try to "
"guess at the proper name - use this function to find similar ones."
)
system = f"{system_message}\n\n{suffix}"
tools.append(retriever_tool)
agent = create_react_agent(llm, tools, state_modifier=system)
question = "How many albums does alis in chain have?"
for step in agent.stream(
{"messages": [{"role": "user", "content": question}]},
stream_mode="values",
):
step["messages"][-1].pretty_print()
================================[1m Human Message [0m=================================
How many albums does alis in chain have?
==================================[1m Ai Message [0m==================================
Tool Calls:
search_proper_nouns (call_8ryjsRPLAr79mM3Qvnq6gTOH)
Call ID: call_8ryjsRPLAr79mM3Qvnq6gTOH
Args:
query: alis in chain
=================================[1m Tool Message [0m=================================
Name: search_proper_nouns
Alice In Chains
Aisha Duo
Xis
Da Lama Ao Caos
A-Sides
==================================[1m Ai Message [0m==================================
Tool Calls:
sql_db_list_tables (call_NJjtCpU89MBMplssjn1z0xzq)
Call ID: call_NJjtCpU89MBMplssjn1z0xzq
Args:
search_proper_nouns (call_1BfrueC9koSIyi4OfMu2Ao8q)
Call ID: call_1BfrueC9koSIyi4OfMu2Ao8q
Args:
query: Alice In Chains
=================================[1m Tool Message [0m=================================
Name: search_proper_nouns
Alice In Chains
Pearl Jam
Pearl Jam
Foo Fighters
Soundgarden
==================================[1m Ai Message [0m==================================
Tool Calls:
sql_db_schema (call_Kn09w9jd9swcNzIZ1b5MlKID)
Call ID: call_Kn09w9jd9swcNzIZ1b5MlKID
Args:
table_names: Album, Artist
=================================[1m Tool Message [0m=================================
Name: sql_db_schema
CREATE TABLE "Album" (
"AlbumId" INTEGER NOT NULL,
"Title" NVARCHAR(160) NOT NULL,
"ArtistId" INTEGER NOT NULL,
PRIMARY KEY ("AlbumId"),
FOREIGN KEY("ArtistId") REFERENCES "Artist" ("ArtistId")
)
/*
3 rows from Album table:
AlbumId Title ArtistId
1 For Those About To Rock We Salute You 1
2 Balls to the Wall 2
3 Restless and Wild 2
*/
CREATE TABLE "Artist" (
"ArtistId" INTEGER NOT NULL,
"Name" NVARCHAR(120),
PRIMARY KEY ("ArtistId")
)
/*
3 rows from Artist table:
ArtistId Name
1 AC/DC
2 Accept
3 Aerosmith
*/
==================================[1m Ai Message [0m==================================
Tool Calls:
sql_db_query (call_WkHRiPcBoGN9bc58MIupRHKP)
Call ID: call_WkHRiPcBoGN9bc58MIupRHKP
Args:
query: SELECT COUNT(*) FROM Album WHERE ArtistId = (SELECT ArtistId FROM Artist WHERE Name = 'Alice In Chains')
=================================[1m Tool Message [0m=================================
Name: sql_db_query
[(1,)]
==================================[1m Ai Message [0m==================================
Alice In Chains has released 1 album in the database.
正如我们所看到的，无论是在流式步骤中还是在LangSmith跟踪中，代理都使用了search_proper_nouns工具来检查如何正确查询数据库中这位特定艺术家的信息。