langchain/docs/extras/modules/chains/additional/graph_hugegraph_qa.ipynb

309 lines
8.0 KiB
Plaintext
Raw Normal View History

{
"cells": [
{
"cell_type": "markdown",
"id": "d2777010",
"metadata": {},
"source": [
"# HugeGraph QA Chain\n",
"\n",
"This notebook shows how to use LLMs to provide a natural language interface to [HugeGraph](https://hugegraph.apache.org/cn/) database."
]
},
{
"cell_type": "markdown",
"id": "f26dcbe4",
"metadata": {},
"source": [
"You will need to have a running HugeGraph instance.\n",
"You can run a local docker container by running the executing the following script:\n",
"\n",
"```\n",
"docker run \\\n",
" --name=graph \\\n",
" -itd \\\n",
" -p 8080:8080 \\\n",
" hugegraph/hugegraph\n",
"```\n",
"\n",
"If we want to connect HugeGraph in the application, we need to install python sdk:\n",
"\n",
"```\n",
"pip3 install hugegraph-python\n",
"```"
]
},
{
"cell_type": "markdown",
"id": "d64a29f1",
"metadata": {},
"source": [
"If you are using the docker container, you need to wait a couple of second for the database to start, and then we need create schema and write graph data for the database."
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "e53ab93e",
"metadata": {},
"outputs": [],
"source": [
"from hugegraph.connection import PyHugeGraph\n",
"\n",
"client = PyHugeGraph(\"localhost\", \"8080\", user=\"admin\", pwd=\"admin\", graph=\"hugegraph\")"
]
},
{
"cell_type": "markdown",
"id": "b7c3a50e",
"metadata": {},
"source": [
"First, we create the schema for a simple movie database:"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "ef5372a8",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'create EdgeLabel success, Detail: \"b\\'{\"id\":1,\"name\":\"ActedIn\",\"source_label\":\"Person\",\"target_label\":\"Movie\",\"frequency\":\"SINGLE\",\"sort_keys\":[],\"nullable_keys\":[],\"index_labels\":[],\"properties\":[],\"status\":\"CREATED\",\"ttl\":0,\"enable_label_index\":true,\"user_data\":{\"~create_time\":\"2023-07-04 10:48:47.908\"}}\\'\"'"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\"\"\"schema\"\"\"\n",
"schema = client.schema()\n",
"schema.propertyKey(\"name\").asText().ifNotExist().create()\n",
"schema.propertyKey(\"birthDate\").asText().ifNotExist().create()\n",
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>
2023-07-12 02:05:14 +00:00
"schema.vertexLabel(\"Person\").properties(\n",
" \"name\", \"birthDate\"\n",
").usePrimaryKeyId().primaryKeys(\"name\").ifNotExist().create()\n",
"schema.vertexLabel(\"Movie\").properties(\"name\").usePrimaryKeyId().primaryKeys(\n",
" \"name\"\n",
").ifNotExist().create()\n",
"schema.edgeLabel(\"ActedIn\").sourceLabel(\"Person\").targetLabel(\n",
" \"Movie\"\n",
").ifNotExist().create()"
]
},
{
"cell_type": "markdown",
"id": "016f7989",
"metadata": {},
"source": [
"Then we can insert some data."
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "b7f4c370",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"1:Robert De Niro--ActedIn-->2:The Godfather Part II"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\"\"\"graph\"\"\"\n",
"g = client.graph()\n",
"g.addVertex(\"Person\", {\"name\": \"Al Pacino\", \"birthDate\": \"1940-04-25\"})\n",
"g.addVertex(\"Person\", {\"name\": \"Robert De Niro\", \"birthDate\": \"1943-08-17\"})\n",
"g.addVertex(\"Movie\", {\"name\": \"The Godfather\"})\n",
"g.addVertex(\"Movie\", {\"name\": \"The Godfather Part II\"})\n",
"g.addVertex(\"Movie\", {\"name\": \"The Godfather Coda The Death of Michael Corleone\"})\n",
"\n",
"g.addEdge(\"ActedIn\", \"1:Al Pacino\", \"2:The Godfather\", {})\n",
"g.addEdge(\"ActedIn\", \"1:Al Pacino\", \"2:The Godfather Part II\", {})\n",
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>
2023-07-12 02:05:14 +00:00
"g.addEdge(\n",
" \"ActedIn\", \"1:Al Pacino\", \"2:The Godfather Coda The Death of Michael Corleone\", {}\n",
")\n",
"g.addEdge(\"ActedIn\", \"1:Robert De Niro\", \"2:The Godfather Part II\", {})"
]
},
{
"cell_type": "markdown",
"id": "5b8f7788",
"metadata": {},
"source": [
"## Creating `HugeGraphQAChain`\n",
"\n",
"We can now create the `HugeGraph` and `HugeGraphQAChain`. To create the `HugeGraph` we simply need to pass the database object to the `HugeGraph` constructor."
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "f1f68fcf",
"metadata": {
"is_executing": true
},
"outputs": [],
"source": [
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.chains import HugeGraphQAChain\n",
"from langchain.graphs import HugeGraph"
]
},
{
"cell_type": "code",
"execution_count": 28,
"id": "b86ebfa7",
"metadata": {},
"outputs": [],
"source": [
"graph = HugeGraph(\n",
" username=\"admin\",\n",
" password=\"admin\",\n",
" address=\"localhost\",\n",
" port=8080,\n",
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>
2023-07-12 02:05:14 +00:00
" graph=\"hugegraph\",\n",
")"
]
},
{
"cell_type": "markdown",
"id": "e262540b",
"metadata": {},
"source": [
"## Refresh graph schema information\n",
"\n",
"If the schema of database changes, you can refresh the schema information needed to generate Gremlin statements."
]
},
{
"cell_type": "code",
"execution_count": 29,
"id": "134dd8d6",
"metadata": {},
"outputs": [],
"source": [
"# graph.refresh_schema()"
]
},
{
"cell_type": "code",
"execution_count": 30,
"id": "e78b8e72",
"metadata": {
"ExecuteTime": {}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Node properties: [name: Person, primary_keys: ['name'], properties: ['name', 'birthDate'], name: Movie, primary_keys: ['name'], properties: ['name']]\n",
"Edge properties: [name: ActedIn, properties: []]\n",
"Relationships: ['Person--ActedIn-->Movie']\n",
"\n"
]
}
],
"source": [
"print(graph.get_schema)"
]
},
{
"cell_type": "markdown",
"id": "5c27e813",
"metadata": {},
"source": [
"## Querying the graph\n",
"\n",
"We can now use the graph Gremlin QA chain to ask question of the graph"
]
},
{
"cell_type": "code",
"execution_count": 31,
"id": "3b23dead",
"metadata": {},
"outputs": [],
"source": [
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>
2023-07-12 02:05:14 +00:00
"chain = HugeGraphQAChain.from_llm(ChatOpenAI(temperature=0), graph=graph, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 32,
"id": "76aecc93",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"Generated gremlin:\n",
"\u001b[32;1m\u001b[1;3mg.V().has('Movie', 'name', 'The Godfather').in('ActedIn').valueMap(true)\u001b[0m\n",
"Full Context:\n",
"\u001b[32;1m\u001b[1;3m[{'id': '1:Al Pacino', 'label': 'Person', 'name': ['Al Pacino'], 'birthDate': ['1940-04-25']}]\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'Al Pacino played in The Godfather.'"
]
},
"execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain.run(\"Who played in The Godfather?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "869f0258",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "venv",
"language": "python",
"name": "venv"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}