构建一个基于SQL数据的问答系统 #

1pip install --upgrade --quiet langchain langchain-community langchain-openai faiss-cpu

1pip install python-dotenv

1from dotenv import load_dotenv
2assert load_dotenv()
3
4import os
5MODEL_NAME = os.environ.get("MODEL_NAME")
6EMBEDDING_MODEL_NAME = os.environ.get("EMBEDDING_MODEL_NAME")

1from langchain_community.utilities import SQLDatabase
2
3db = SQLDatabase.from_uri("sqlite:///Chinook.db")
4print(db.dialect)
5print(db.get_usable_table_names())
6db.run("SELECT * FROM Artist LIMIT 10;")

1['Album', 'Artist', 'Customer', 'Employee', 'Genre', 'Invoice', 'InvoiceLine', 'MediaType', 'Playlist', 'PlaylistTrack', 'Track']

1"[(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')]"

1from langchain_openai import ChatOpenAI
2
3llm = ChatOpenAI(model=MODEL_NAME)

1from langchain.chains import create_sql_query_chain
2
3chain = create_sql_query_chain(llm, db)
4response = chain.invoke({"question": "How many employees are there"})
5print(response)

1SELECT COUNT("EmployeeId") AS "TotalEmployees" FROM "Employee"\nLIMIT 1;

1db.run(response)

1'[(8,)]'

1chain.get_prompts()[0].pretty_print()

 1You are a SQLite expert. Given an input question, first create a syntactically correct SQLite query to run, then look at the results of the query and return the answer to the input question.
 2Unless the user specifies in the question a specific number of examples to obtain, query for at most 5 results using the LIMIT clause as per SQLite. You can order the results to return the most informative data in the database.
 3Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in double quotes (") to denote them as delimited identifiers.
 4Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
 5Pay attention to use date('now') function to get the current date, if the question involves "today".
 6
 7Use the following format:
 8
 9Question: Question here
10SQLQuery: SQL Query to run
11SQLResult: Result of the SQLQuery
12Answer: Final answer here
13
14Only use the following tables:
15{table_info}
16
17Question: {input}

1'[(8,)]'

 1from operator import itemgetter
 2
 3from langchain_core.output_parsers import StrOutputParser
 4from langchain_core.prompts import PromptTemplate
 5from langchain_core.runnables import RunnablePassthrough
 6
 7answer_prompt = PromptTemplate.from_template(
 8    """Given the following user question, corresponding SQL query, and SQL result, answer the user question.
 9
10Question: {question}
11SQL Query: {query}
12SQL Result: {result}
13Answer: """
14)
15
16chain = (
17    RunnablePassthrough.assign(query=write_query).assign(
18        result=itemgetter("query") | execute_query
19    )
20    | answer_prompt
21    | llm
22    | StrOutputParser()
23)
24
25chain.invoke({"question": "How many employees are there"})

1'There are a total of 8 employees.'

1from langchain_community.agent_toolkits import SQLDatabaseToolkit
2
3toolkit = SQLDatabaseToolkit(db=db, llm=llm)
4
5tools = toolkit.get_tools()
6
7tools

1[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 0x7c6f42ed4d90>),
2 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 0x7c6f42ed4d90>),
3 ListSQLDatabaseTool(db=<langchain_community.utilities.sql_database.SQLDatabase object at 0x7c6f42ed4d90>),
4 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 0x7c6f42ed4d90>, llm=ChatOpenAI(client=<openai.resources.chat.completions.Completions object at 0x7c6f4216dbd0>, async_client=<openai.resources.chat.completions.AsyncCompletions object at 0x7c6f42627810>, root_client=<openai.OpenAI object at 0x7c6f42625010>, root_async_client=<openai.AsyncOpenAI object at 0x7c6f421aaf10>, model_name='gpt-4o', 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 0x7c6f4216dbd0>, async_client=<openai.resources.chat.completions.AsyncCompletions object at 0x7c6f42627810>, root_client=<openai.OpenAI object at 0x7c6f42625010>, root_async_client=<openai.AsyncOpenAI object at 0x7c6f421aaf10>, model_name='gpt-4o', model_kwargs={}, openai_api_key=SecretStr('**********')), output_parser=StrOutputParser(), llm_kwargs={}))]

 1from langchain_core.messages import SystemMessage
 2
 3SQL_PREFIX = """You are an agent designed to interact with a SQL database.
 4Given an input question, create a syntactically correct SQLite query to run, then look at the results of the query and return the answer.
 5Unless the user specifies a specific number of examples they wish to obtain, always limit your query to at most 5 results.
 6You can order the results by a relevant column to return the most interesting examples in the database.
 7Never query for all the columns from a specific table, only ask for the relevant columns given the question.
 8You have access to tools for interacting with the database.
 9Only use the below tools. Only use the information returned by the below tools to construct your final answer.
10You MUST double check your query before executing it. If you get an error while executing a query, rewrite the query and try again.
11
12DO NOT make any DML statements (INSERT, UPDATE, DELETE, DROP etc.) to the database.
13
14To start you should ALWAYS look at the tables in the database to see what you can query.
15Do NOT skip this step.
16Then you should query the schema of the most relevant tables."""
17
18system_message = SystemMessage(content=SQL_PREFIX)

1pip install -Uq langgraph

1from langchain_core.messages import HumanMessage
2from langgraph.prebuilt import create_react_agent
3agent_executor = create_react_agent(llm, tools, state_modifier=system_message)

1for s in agent_executor.stream(
2    {"messages": [HumanMessage(content="Which country's customers spent the most?")]}
3):
4    print(s)
5    print("----")

 1{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_vnHKe3oul1xbpX0Vrb2vsamZ', 'function': {'arguments': '{"query":"SELECT c.Country, SUM(i.Total) AS Total_Spent FROM customers c JOIN invoices i ON c.CustomerId = i.CustomerId GROUP BY c.Country ORDER BY Total_Spent DESC LIMIT 1"}', 'name': 'sql_db_query'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 53, 'prompt_tokens': 557, 'total_tokens': 610}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_3b956da36b', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-da250593-06b5-414c-a9d9-3fc77036dd9c-0', tool_calls=[{'name': 'sql_db_query', 'args': {'query': 'SELECT c.Country, SUM(i.Total) AS Total_Spent FROM customers c JOIN invoices i ON c.CustomerId = i.CustomerId GROUP BY c.Country ORDER BY Total_Spent DESC LIMIT 1'}, 'id': 'call_vnHKe3oul1xbpX0Vrb2vsamZ'}])]}}
 2----
 3{'action': {'messages': [ToolMessage(content='Error: (sqlite3.OperationalError) no such table: customers\n[SQL: SELECT c.Country, SUM(i.Total) AS Total_Spent FROM customers c JOIN invoices i ON c.CustomerId = i.CustomerId GROUP BY c.Country ORDER BY Total_Spent DESC LIMIT 1]\n(Background on this error at: https://sqlalche.me/e/20/e3q8)', name='sql_db_query', id='1a5c85d4-1b30-4af3-ab9b-325cbce3b2b4', tool_call_id='call_vnHKe3oul1xbpX0Vrb2vsamZ')]}}
 4----
 5{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_pp3BBD1hwpdwskUj63G3tgaQ', 'function': {'arguments': '{}', 'name': 'sql_db_list_tables'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 12, 'prompt_tokens': 699, 'total_tokens': 711}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_3b956da36b', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-04cf0e05-61d0-4673-b5dc-1a9b5fd71fff-0', tool_calls=[{'name': 'sql_db_list_tables', 'args': {}, 'id': 'call_pp3BBD1hwpdwskUj63G3tgaQ'}])]}}
 6----
 7{'action': {'messages': [ToolMessage(content='Album, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track', name='sql_db_list_tables', id='c2668450-4d73-4d32-8d75-8aac8fa153fd', tool_call_id='call_pp3BBD1hwpdwskUj63G3tgaQ')]}}
 8----
 9{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_22Asbqgdx26YyEvJxBuANVdY', 'function': {'arguments': '{"query":"SELECT c.Country, SUM(i.Total) AS Total_Spent FROM Customer c JOIN Invoice i ON c.CustomerId = i.CustomerId GROUP BY c.Country ORDER BY Total_Spent DESC LIMIT 1"}', 'name': 'sql_db_query'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 53, 'prompt_tokens': 744, 'total_tokens': 797}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_3b956da36b', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-bdd94241-ca49-4f15-b31a-b7c728a34ea8-0', tool_calls=[{'name': 'sql_db_query', 'args': {'query': 'SELECT c.Country, SUM(i.Total) AS Total_Spent FROM Customer c JOIN Invoice i ON c.CustomerId = i.CustomerId GROUP BY c.Country ORDER BY Total_Spent DESC LIMIT 1'}, 'id': 'call_22Asbqgdx26YyEvJxBuANVdY'}])]}}
10----
11{'action': {'messages': [ToolMessage(content="[('USA', 523.0600000000003)]", name='sql_db_query', id='f647e606-8362-40ab-8d34-612ff166dbe1', tool_call_id='call_22Asbqgdx26YyEvJxBuANVdY')]}}
12----
13{'agent': {'messages': [AIMessage(content='Customers from the USA spent the most, with a total amount spent of $523.06.', response_metadata={'token_usage': {'completion_tokens': 20, 'prompt_tokens': 819, 'total_tokens': 839}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_3b956da36b', 'finish_reason': 'stop', 'logprobs': None}, id='run-92e88de0-ff62-41da-8181-053fb5632af4-0')]}}
14----

1for s in agent_executor.stream(
2    {"messages": [HumanMessage(content="Describe the playlisttrack table")]}
3):
4    print(s)
5    print("----")

 1{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_WN0N3mm8WFvPXYlK9P7KvIEr', 'function': {'arguments': '{"table_names":"playlisttrack"}', 'name': 'sql_db_schema'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 17, 'prompt_tokens': 554, 'total_tokens': 571}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_3b956da36b', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-be278326-4115-4c67-91a0-6dc97e7bffa4-0', tool_calls=[{'name': 'sql_db_schema', 'args': {'table_names': 'playlisttrack'}, 'id': 'call_WN0N3mm8WFvPXYlK9P7KvIEr'}])]}}
 2----
 3{'action': {'messages': [ToolMessage(content="Error: table_names {'playlisttrack'} not found in database", name='sql_db_schema', id='fe32b3d3-a40f-4802-a6b8-87a2453af8c2', tool_call_id='call_WN0N3mm8WFvPXYlK9P7KvIEr')]}}
 4----
 5{'agent': {'messages': [AIMessage(content='I apologize for the error. Let me first check the available tables in the database.', additional_kwargs={'tool_calls': [{'id': 'call_CzHt30847ql2MmnGxgYeVSL2', 'function': {'arguments': '{}', 'name': 'sql_db_list_tables'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 30, 'prompt_tokens': 592, 'total_tokens': 622}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_3b956da36b', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-f6c107bb-e945-4848-a83c-f57daec1144e-0', tool_calls=[{'name': 'sql_db_list_tables', 'args': {}, 'id': 'call_CzHt30847ql2MmnGxgYeVSL2'}])]}}
 6----
 7{'action': {'messages': [ToolMessage(content='Album, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track', name='sql_db_list_tables', id='a4950f74-a0ad-4558-ba54-7bcf99539a02', tool_call_id='call_CzHt30847ql2MmnGxgYeVSL2')]}}
 8----
 9{'agent': {'messages': [AIMessage(content='The database contains a table named "PlaylistTrack". Let me retrieve the schema and sample rows from the "PlaylistTrack" table.', additional_kwargs={'tool_calls': [{'id': 'call_wX9IjHLgRBUmxlfCthprABRO', 'function': {'arguments': '{"table_names":"PlaylistTrack"}', 'name': 'sql_db_schema'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 44, 'prompt_tokens': 658, 'total_tokens': 702}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_3b956da36b', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-e8d34372-1159-4654-a185-1e7d0cb70269-0', tool_calls=[{'name': 'sql_db_schema', 'args': {'table_names': 'PlaylistTrack'}, 'id': 'call_wX9IjHLgRBUmxlfCthprABRO'}])]}}
10----
11{'action': {'messages': [ToolMessage(content='\nCREATE 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/*\n3 rows from PlaylistTrack table:\nPlaylistId\tTrackId\n1\t3402\n1\t3389\n1\t3390\n*/', name='sql_db_schema', id='f6ffc37a-188a-4690-b84e-c9f2c78b1e49', tool_call_id='call_wX9IjHLgRBUmxlfCthprABRO')]}}
12----
13{'agent': {'messages': [AIMessage(content='The "PlaylistTrack" table has the following schema:\n- PlaylistId: INTEGER (NOT NULL)\n- TrackId: INTEGER (NOT NULL)\n- Primary Key: (PlaylistId, TrackId)\n- Foreign Key: TrackId references Track(TrackId)\n- Foreign Key: PlaylistId references Playlist(PlaylistId)\n\nHere are 3 sample rows from the "PlaylistTrack" table:\n1. PlaylistId: 1, TrackId: 3402\n2. PlaylistId: 1, TrackId: 3389\n3. PlaylistId: 1, TrackId: 3390\n\nIf you have any specific questions or queries regarding the "PlaylistTrack" table, feel free to ask!', response_metadata={'token_usage': {'completion_tokens': 145, 'prompt_tokens': 818, 'total_tokens': 963}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_3b956da36b', 'finish_reason': 'stop', 'logprobs': None}, id='run-961a4552-3cbd-4d28-b338-4d2f1ac40ea0-0')]}}
14----

 1import ast
 2import re
 3
 4
 5def query_as_list(db, query):
 6    res = db.run(query)
 7    res = [el for sub in ast.literal_eval(res) for el in sub if el]
 8    res = [re.sub(r"\b\d+\b", "", string).strip() for string in res]
 9    return list(set(res))
10
11
12artists = query_as_list(db, "SELECT Name FROM Artist")
13albums = query_as_list(db, "SELECT Title FROM Album")
14albums[:5]

1['Big Ones',
2 'Cidade Negra - Hits',
3 'In Step',
4 'Use Your Illusion I',
5 'Voodoo Lounge']

 1from langchain.agents.agent_toolkits import create_retriever_tool
 2from langchain_community.vectorstores import FAISS
 3from langchain_openai import OpenAIEmbeddings
 4
 5vector_db = FAISS.from_texts(artists + albums, OpenAIEmbeddings(model=EMBEDDING_MODEL_NAME))
 6retriever = vector_db.as_retriever(search_kwargs={"k": 5})
 7description = """Use to look up values to filter on. Input is an approximate spelling of the proper noun, output is \
 8valid proper nouns. Use the noun most similar to the search."""
 9retriever_tool = create_retriever_tool(
10    retriever,
11    name="search_proper_nouns",
12    description=description,
13)

1print(retriever_tool.invoke("Alice Chains"))

1Alice In Chains
2
3Alanis Morissette
4
5Pearl Jam
6
7Pearl Jam
8
9Audioslave

 1system = """You are an agent designed to interact with a SQL database.
 2Given an input question, create a syntactically correct SQLite query to run, then look at the results of the query and return the answer.
 3Unless the user specifies a specific number of examples they wish to obtain, always limit your query to at most 5 results.
 4You can order the results by a relevant column to return the most interesting examples in the database.
 5Never query for all the columns from a specific table, only ask for the relevant columns given the question.
 6You have access to tools for interacting with the database.
 7Only use the given tools. Only use the information returned by the tools to construct your final answer.
 8You MUST double check your query before executing it. If you get an error while executing a query, rewrite the query and try again.
 9
10DO NOT make any DML statements (INSERT, UPDATE, DELETE, DROP etc.) to the database.
11
12You have access to the following tables: {table_names}
13
14If you need to filter on a proper noun, you must ALWAYS first look up the filter value using the "search_proper_nouns" tool!
15Do not try to guess at the proper name - use this function to find similar ones.""".format(
16    table_names=db.get_usable_table_names()
17)
18
19system_message = SystemMessage(content=system)
20
21tools.append(retriever_tool)
22
23agent = create_react_agent(llm, tools, state_modifier=system_message)

1for s in agent.stream(
2    {"messages": [HumanMessage(content="How many albums does alis in chain have?")]}
3):
4    print(s)
5    print("----")

 1{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_86uzEat33FDtwwdd4wePPn8m', 'function': {'arguments': '{"query":"alis in chain"}', 'name': 'search_proper_nouns'}, 'type': 'function'}], 'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 19, 'prompt_tokens': 665, 'total_tokens': 684, 'completion_tokens_details': None}, 'model_name': 'gpt-4o-2024-08-06', 'system_fingerprint': 'fp_67802d9a6d', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-4f44bed3-cff5-4eb8-afe6-8a0c7c7197e9-0', tool_calls=[{'name': 'search_proper_nouns', 'args': {'query': 'alis in chain'}, 'id': 'call_86uzEat33FDtwwdd4wePPn8m', 'type': 'tool_call'}], usage_metadata={'input_tokens': 665, 'output_tokens': 19, 'total_tokens': 684, 'input_token_details': {}, 'output_token_details': {}})]}}
 2----
 3{'tools': {'messages': [ToolMessage(content='Alice In Chains\n\nIn Step\n\nIV\n\nTransmission\n\nCoda', name='search_proper_nouns', id='60ea710e-bb08-4918-bdd6-71fdc77379fd', tool_call_id='call_86uzEat33FDtwwdd4wePPn8m')]}}
 4----
 5{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_Wh6i6bH4K7kgvaICDLbV2mJY', 'function': {'arguments': '{"table_names": "Album, Artist"}', 'name': 'sql_db_schema'}, 'type': 'function'}, {'id': 'call_331fXVKjNDgIpkRbzqKyZoia', 'function': {'arguments': '{"query": "Alice In Chains"}', 'name': 'search_proper_nouns'}, 'type': 'function'}], 'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 53, 'prompt_tokens': 708, 'total_tokens': 761, 'completion_tokens_details': None}, 'model_name': 'gpt-4o-2024-08-06', 'system_fingerprint': 'fp_67802d9a6d', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-07a58711-5007-43ce-9460-7d1e0a922ab7-0', tool_calls=[{'name': 'sql_db_schema', 'args': {'table_names': 'Album, Artist'}, 'id': 'call_Wh6i6bH4K7kgvaICDLbV2mJY', 'type': 'tool_call'}, {'name': 'search_proper_nouns', 'args': {'query': 'Alice In Chains'}, 'id': 'call_331fXVKjNDgIpkRbzqKyZoia', 'type': 'tool_call'}], usage_metadata={'input_tokens': 708, 'output_tokens': 53, 'total_tokens': 761, 'input_token_details': {}, 'output_token_details': {}})]}}
 6----
 7{'tools': {'messages': [ToolMessage(content='\nCREATE 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/*\n3 rows from Album table:\nAlbumId\tTitle\tArtistId\n1\tFor Those About To Rock We Salute You\t1\n2\tBalls to the Wall\t2\n3\tRestless and Wild\t2\n*/\n\n\nCREATE TABLE "Artist" (\n\t"ArtistId" INTEGER NOT NULL, \n\t"Name" NVARCHAR(120), \n\tPRIMARY KEY ("ArtistId")\n)\n\n/*\n3 rows from Artist table:\nArtistId\tName\n1\tAC/DC\n2\tAccept\n3\tAerosmith\n*/', name='sql_db_schema', id='21a37a02-fd87-4600-a3fe-bc1e65395c43', tool_call_id='call_Wh6i6bH4K7kgvaICDLbV2mJY'), ToolMessage(content='Alice In Chains\n\nSoundgarden\n\nPearl Jam\n\nPearl Jam\n\nChris Cornell', name='search_proper_nouns', id='c287ed3a-00a4-4cd5-94ed-537e3cd56108', tool_call_id='call_331fXVKjNDgIpkRbzqKyZoia')]}}
 8----
 9{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_JePs9JuFrKvf7m1dsQfItMYU', 'function': {'arguments': '{"query":"SELECT COUNT(*) FROM Album INNER JOIN Artist ON Album.ArtistId = Artist.ArtistId WHERE Artist.Name = \'Alice In Chains\'"}', 'name': 'sql_db_query'}, 'type': 'function'}], 'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 41, 'prompt_tokens': 1002, 'total_tokens': 1043, 'completion_tokens_details': None}, 'model_name': 'gpt-4o-2024-08-06', 'system_fingerprint': 'fp_67802d9a6d', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-c321d9b5-c313-4945-b6ca-f2ff2f42c6b2-0', tool_calls=[{'name': 'sql_db_query', 'args': {'query': "SELECT COUNT(*) FROM Album INNER JOIN Artist ON Album.ArtistId = Artist.ArtistId WHERE Artist.Name = 'Alice In Chains'"}, 'id': 'call_JePs9JuFrKvf7m1dsQfItMYU', 'type': 'tool_call'}], usage_metadata={'input_tokens': 1002, 'output_tokens': 41, 'total_tokens': 1043, 'input_token_details': {}, 'output_token_details': {}})]}}
10----
11{'tools': {'messages': [ToolMessage(content='[(1,)]', name='sql_db_query', id='56ec1ae7-a0e5-4793-8d34-9879b0d3842a', tool_call_id='call_JePs9JuFrKvf7m1dsQfItMYU')]}}
12----
13{'agent': {'messages': [AIMessage(content='Alice In Chains has 1 album in the database.', additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 12, 'prompt_tokens': 1056, 'total_tokens': 1068, 'completion_tokens_details': None}, 'model_name': 'gpt-4o-2024-08-06', 'system_fingerprint': 'fp_d54531d9eb', 'finish_reason': 'stop', 'logprobs': None}, id='run-aa41d7ae-a1dc-4838-9dad-f6214a62e75f-0', usage_metadata={'input_tokens': 1056, 'output_tokens': 12, 'total_tokens': 1068, 'input_token_details': {}, 'output_token_details': {}})]}}
14----