langchain/docs/extras/modules/chains/additional/graph_kuzu_qa.ipynb
os1ma 2667ddc686
Fix make docs_build and related scripts (#7276)
**Description: a description of the change**

Fixed `make docs_build` and related scripts which caused errors. There
are several changes.

First, I made the build of the documentation and the API Reference into
two separate commands. This is because it takes less time to build. The
commands for documents are `make docs_build`, `make docs_clean`, and
`make docs_linkcheck`. The commands for API Reference are `make
api_docs_build`, `api_docs_clean`, and `api_docs_linkcheck`.

It looked like `docs/.local_build.sh` could be used to build the
documentation, so I used that. Since `.local_build.sh` was also building
API Rerefence internally, I removed that process. `.local_build.sh` also
added some Bash options to stop in error or so. Futher more added `cd
"${SCRIPT_DIR}"` at the beginning so that the script will work no matter
which directory it is executed in.

`docs/api_reference/api_reference.rst` is removed, because which is
generated by `docs/api_reference/create_api_rst.py`, and added it to
.gitignore.

Finally, the description of CONTRIBUTING.md was modified.

**Issue: the issue # it fixes (if applicable)**

https://github.com/hwchase17/langchain/issues/6413

**Dependencies: any dependencies required for this change**

`nbdoc` was missing in group docs so it was added. I installed it with
the `poetry add --group docs nbdoc` command. I am concerned if any
modifications are needed to poetry.lock. I would greatly appreciate it
if you could pay close attention to this file during the review.

**Tag maintainer**
- General / Misc / if you don't know who to tag: @baskaryan

If this PR needs any additional changes, I'll be happy to make them!

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-11 22:05:14 -04:00

375 lines
9.3 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",
"\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(\n",
" \"CREATE NODE TABLE Person (name STRING, birthDate STRING, PRIMARY KEY(name))\"\n",
")\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(\n",
" \"CREATE (:Movie {name: 'The Godfather Coda: The Death of Michael Corleone'})\"\n",
")\n",
"conn.execute(\n",
" \"MATCH (p:Person), (m:Movie) WHERE p.name = 'Al Pacino' AND m.name = 'The Godfather' CREATE (p)-[:ActedIn]->(m)\"\n",
")\n",
"conn.execute(\n",
" \"MATCH (p:Person), (m:Movie) WHERE p.name = 'Al Pacino' AND m.name = 'The Godfather: Part II' CREATE (p)-[:ActedIn]->(m)\"\n",
")\n",
"conn.execute(\n",
" \"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",
")\n",
"conn.execute(\n",
" \"MATCH (p:Person), (m:Movie) WHERE p.name = 'Robert De Niro' AND m.name = 'The Godfather: Part II' CREATE (p)-[:ActedIn]->(m)\"\n",
")"
]
},
{
"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(ChatOpenAI(temperature=0), graph=graph, verbose=True)"
]
},
{
"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
}