mirror of
https://github.com/hwchase17/langchain
synced 2024-10-29 17:07:25 +00:00
0fce8ef178
This PR adds `KuzuGraph` and `KuzuQAChain` for interacting with [Kùzu database](https://github.com/kuzudb/kuzu). Kùzu is an in-process property graph database management system (GDBMS) built for query speed and scalability. The `KuzuGraph` and `KuzuQAChain` provide the same functionality as the existing integration with NebulaGraph and Neo4j and enables query generation and question answering over Kùzu database. A notebook example and a simple test case have also been added. --------- Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
364 lines
9.2 KiB
Plaintext
364 lines
9.2 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# KuzuQAChain\n",
|
|
"\n",
|
|
"This notebook shows how to use LLMs to provide a natural language interface to [Kùzu](https://kuzudb.com) database."
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"[Kùzu](https://kuzudb.com) is an in-process property graph database management system. You can simply install it with `pip`:\n",
|
|
"\n",
|
|
"```bash\n",
|
|
"pip install kuzu\n",
|
|
"```\n",
|
|
"\n",
|
|
"Once installed, you can simply import it and start creating a database on the local machine and connect to it:\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import kuzu\n",
|
|
"db = kuzu.Database(\"test_db\")\n",
|
|
"conn = kuzu.Connection(db)"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"First, we create the schema for a simple movie database:"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"<kuzu.query_result.QueryResult at 0x1066ff410>"
|
|
]
|
|
},
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"conn.execute(\"CREATE NODE TABLE Movie (name STRING, PRIMARY KEY(name))\")\n",
|
|
"conn.execute(\"CREATE NODE TABLE Person (name STRING, birthDate STRING, PRIMARY KEY(name))\")\n",
|
|
"conn.execute(\"CREATE REL TABLE ActedIn (FROM Person TO Movie)\")"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"Then we can insert some data."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"<kuzu.query_result.QueryResult at 0x107016210>"
|
|
]
|
|
},
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"conn.execute(\"CREATE (:Person {name: 'Al Pacino', birthDate: '1940-04-25'})\")\n",
|
|
"conn.execute(\"CREATE (:Person {name: 'Robert De Niro', birthDate: '1943-08-17'})\")\n",
|
|
"conn.execute(\"CREATE (:Movie {name: 'The Godfather'})\")\n",
|
|
"conn.execute(\"CREATE (:Movie {name: 'The Godfather: Part II'})\")\n",
|
|
"conn.execute(\"CREATE (:Movie {name: 'The Godfather Coda: The Death of Michael Corleone'})\")\n",
|
|
"conn.execute(\"MATCH (p:Person), (m:Movie) WHERE p.name = 'Al Pacino' AND m.name = 'The Godfather' CREATE (p)-[:ActedIn]->(m)\")\n",
|
|
"conn.execute(\"MATCH (p:Person), (m:Movie) WHERE p.name = 'Al Pacino' AND m.name = 'The Godfather: Part II' CREATE (p)-[:ActedIn]->(m)\")\n",
|
|
"conn.execute(\"MATCH (p:Person), (m:Movie) WHERE p.name = 'Al Pacino' AND m.name = 'The Godfather Coda: The Death of Michael Corleone' CREATE (p)-[:ActedIn]->(m)\")\n",
|
|
"conn.execute(\"MATCH (p:Person), (m:Movie) WHERE p.name = 'Robert De Niro' AND m.name = 'The Godfather: Part II' CREATE (p)-[:ActedIn]->(m)\")"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Creating `KuzuQAChain`\n",
|
|
"\n",
|
|
"We can now create the `KuzuGraph` and `KuzuQAChain`. To create the `KuzuGraph` we simply need to pass the database object to the `KuzuGraph` constructor."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.chat_models import ChatOpenAI\n",
|
|
"from langchain.graphs import KuzuGraph\n",
|
|
"from langchain.chains import KuzuQAChain"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"graph = KuzuGraph(db)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"chain = KuzuQAChain.from_llm(\n",
|
|
" ChatOpenAI(temperature=0), graph=graph, verbose=True\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Refresh graph schema information\n",
|
|
"\n",
|
|
"If the schema of database changes, you can refresh the schema information needed to generate Cypher statements."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# graph.refresh_schema()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Node properties: [{'properties': [('name', 'STRING')], 'label': 'Movie'}, {'properties': [('name', 'STRING'), ('birthDate', 'STRING')], 'label': 'Person'}]\n",
|
|
"Relationships properties: [{'properties': [], 'label': 'ActedIn'}]\n",
|
|
"Relationships: ['(:Person)-[:ActedIn]->(:Movie)']\n",
|
|
"\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"print(graph.get_schema)"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Querying the graph\n",
|
|
"\n",
|
|
"We can now use the `KuzuQAChain` to ask question of the graph"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"\n",
|
|
"\n",
|
|
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
|
"Generated Cypher:\n",
|
|
"\u001b[32;1m\u001b[1;3mMATCH (p:Person)-[:ActedIn]->(m:Movie {name: 'The Godfather: Part II'}) RETURN p.name\u001b[0m\n",
|
|
"Full Context:\n",
|
|
"\u001b[32;1m\u001b[1;3m[{'p.name': 'Al Pacino'}, {'p.name': 'Robert De Niro'}]\u001b[0m\n",
|
|
"\n",
|
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'Al Pacino and Robert De Niro both played in The Godfather: Part II.'"
|
|
]
|
|
},
|
|
"execution_count": 9,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"chain.run(\"Who played in The Godfather: Part II?\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 10,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"\n",
|
|
"\n",
|
|
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
|
"Generated Cypher:\n",
|
|
"\u001b[32;1m\u001b[1;3mMATCH (p:Person {name: 'Robert De Niro'})-[:ActedIn]->(m:Movie)\n",
|
|
"RETURN m.name\u001b[0m\n",
|
|
"Full Context:\n",
|
|
"\u001b[32;1m\u001b[1;3m[{'m.name': 'The Godfather: Part II'}]\u001b[0m\n",
|
|
"\n",
|
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'Robert De Niro played in The Godfather: Part II.'"
|
|
]
|
|
},
|
|
"execution_count": 10,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"chain.run(\"Robert De Niro played in which movies?\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 11,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"\n",
|
|
"\n",
|
|
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
|
"Generated Cypher:\n",
|
|
"\u001b[32;1m\u001b[1;3mMATCH (p:Person {name: 'Robert De Niro'})-[:ActedIn]->(m:Movie)\n",
|
|
"RETURN p.birthDate\u001b[0m\n",
|
|
"Full Context:\n",
|
|
"\u001b[32;1m\u001b[1;3m[{'p.birthDate': '1943-08-17'}]\u001b[0m\n",
|
|
"\n",
|
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'Robert De Niro was born on August 17, 1943.'"
|
|
]
|
|
},
|
|
"execution_count": 11,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"chain.run(\"Robert De Niro is born in which year?\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 12,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"\n",
|
|
"\n",
|
|
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
|
"Generated Cypher:\n",
|
|
"\u001b[32;1m\u001b[1;3mMATCH (p:Person)-[:ActedIn]->(m:Movie{name:'The Godfather: Part II'})\n",
|
|
"WITH p, m, p.birthDate AS birthDate\n",
|
|
"ORDER BY birthDate ASC\n",
|
|
"LIMIT 1\n",
|
|
"RETURN p.name\u001b[0m\n",
|
|
"Full Context:\n",
|
|
"\u001b[32;1m\u001b[1;3m[{'p.name': 'Al Pacino'}]\u001b[0m\n",
|
|
"\n",
|
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'The oldest actor who played in The Godfather: Part II is Al Pacino.'"
|
|
]
|
|
},
|
|
"execution_count": 12,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"chain.run(\"Who is the oldest actor who played in The Godfather: Part II?\")"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.11.4"
|
|
},
|
|
"orig_nbformat": 4
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|