mirror of
https://github.com/kennethreitz/langchain.git
synced 2026-06-05 23:00:18 +00:00
Harrison/use functions agent (#6185)
Co-authored-by: Francisco Ingham <24279597+fpingham@users.noreply.github.com>
This commit is contained in:
Harrison Chase
@@ -37,7 +37,30 @@
|
||||
"from langchain.agents.agent_toolkits import SQLDatabaseToolkit\n",
|
||||
"from langchain.sql_database import SQLDatabase\n",
|
||||
"from langchain.llms.openai import OpenAI\n",
|
||||
"from langchain.agents import AgentExecutor"
|
||||
"from langchain.agents import AgentExecutor\n",
|
||||
"from langchain.agents.agent_types import AgentType\n",
|
||||
"from langchain.chat_models import ChatOpenAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "65ec5bb3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"db = SQLDatabase.from_uri(\"sqlite:///../../../../../notebooks/Chinook.db\")\n",
|
||||
"toolkit = SQLDatabaseToolkit(db=db, llm=OpenAI(temperature=0))\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f74d1792",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Using ZERO_SHOT_REACT_DESCRIPTION\n",
|
||||
"\n",
|
||||
"This shows how to initialize the agent using the ZERO_SHOT_REACT_DESCRIPTION agent type. Note that this is an alternative to the above."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -49,16 +72,39 @@
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"db = SQLDatabase.from_uri(\"sqlite:///../../../../notebooks/Chinook.db\")\n",
|
||||
"toolkit = SQLDatabaseToolkit(db=db)\n",
|
||||
"\n",
|
||||
"agent_executor = create_sql_agent(\n",
|
||||
" llm=OpenAI(temperature=0),\n",
|
||||
" toolkit=toolkit,\n",
|
||||
" verbose=True\n",
|
||||
" verbose=True,\n",
|
||||
" agent_type=AgentType.ZERO_SHOT_REACT_DESCRIPTION\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "971cc455",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Using OpenAI Functions\n",
|
||||
"\n",
|
||||
"This shows how to initialize the agent using the OPENAI_FUNCTIONS agent type. Note that this is an alternative to the above."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "6426a27d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# agent_executor = create_sql_agent(\n",
|
||||
"# llm=ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-0613\"),\n",
|
||||
"# toolkit=toolkit,\n",
|
||||
"# verbose=True,\n",
|
||||
"# agent_type=AgentType.OPENAI_FUNCTIONS\n",
|
||||
"# )"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "36ae48c7-cb08-4fef-977e-c7d4b96a464b",
|
||||
@@ -69,7 +115,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": 4,
|
||||
"id": "ff70e83d-5ad0-4fc7-bb96-27d82ac166d7",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
@@ -81,14 +127,16 @@
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mAction: list_tables_sql_db\n",
|
||||
"Action Input: \"\"\u001b[0m\n",
|
||||
"Observation: \u001b[38;5;200m\u001b[1;3mArtist, Invoice, Playlist, Genre, Album, PlaylistTrack, Track, InvoiceLine, MediaType, Employee, Customer\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema of the playlisttrack table\n",
|
||||
"Action: schema_sql_db\n",
|
||||
"Action Input: \"PlaylistTrack\"\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3m\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m\n",
|
||||
"Invoking: `list_tables_sql_db` with `{}`\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[0m\u001b[38;5;200m\u001b[1;3mAlbum, Artist, Track, PlaylistTrack, InvoiceLine, sales_table, Playlist, Genre, Employee, Customer, Invoice, MediaType\u001b[0m\u001b[32;1m\u001b[1;3m\n",
|
||||
"Invoking: `schema_sql_db` with `PlaylistTrack`\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[0m\u001b[33;1m\u001b[1;3m\n",
|
||||
"CREATE TABLE \"PlaylistTrack\" (\n",
|
||||
"\t\"PlaylistId\" INTEGER NOT NULL, \n",
|
||||
"\t\"TrackId\" INTEGER NOT NULL, \n",
|
||||
@@ -97,13 +145,36 @@
|
||||
"\tFOREIGN KEY(\"PlaylistId\") REFERENCES \"Playlist\" (\"PlaylistId\")\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"SELECT * FROM 'PlaylistTrack' LIMIT 3;\n",
|
||||
"PlaylistId TrackId\n",
|
||||
"1 3402\n",
|
||||
"1 3389\n",
|
||||
"1 3390\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: The PlaylistTrack table has two columns, PlaylistId and TrackId, and is linked to the Playlist and Track tables.\u001b[0m\n",
|
||||
"/*\n",
|
||||
"3 rows from PlaylistTrack table:\n",
|
||||
"PlaylistId\tTrackId\n",
|
||||
"1\t3402\n",
|
||||
"1\t3389\n",
|
||||
"1\t3390\n",
|
||||
"*/\u001b[0m\u001b[32;1m\u001b[1;3mThe `PlaylistTrack` table has two columns: `PlaylistId` and `TrackId`. It is a junction table that represents the relationship between playlists and tracks. \n",
|
||||
"\n",
|
||||
"Here is the schema of the `PlaylistTrack` table:\n",
|
||||
"\n",
|
||||
"```\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",
|
||||
"Here are three sample rows from the `PlaylistTrack` table:\n",
|
||||
"\n",
|
||||
"```\n",
|
||||
"PlaylistId TrackId\n",
|
||||
"1 3402\n",
|
||||
"1 3389\n",
|
||||
"1 3390\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"Please let me know if there is anything else I can help you with.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
@@ -111,10 +182,10 @@
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'The PlaylistTrack table has two columns, PlaylistId and TrackId, and is linked to the Playlist and Track tables.'"
|
||||
"'The `PlaylistTrack` table has two columns: `PlaylistId` and `TrackId`. It is a junction table that represents the relationship between playlists and tracks. \\n\\nHere is the schema of the `PlaylistTrack` table:\\n\\n```\\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\\nHere are three sample rows from the `PlaylistTrack` table:\\n\\n```\\nPlaylistId TrackId\\n1 3402\\n1 3389\\n1 3390\\n```\\n\\nPlease let me know if there is anything else I can help you with.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -519,7 +590,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.9"
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
Reference in New Issue
Block a user