documentation for gremlin graph

docs/docs/use_cases/graph/graph_gremlin_cosmosdb_qa.ipynb

@@ -0,0 +1,209 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "c94240f5",
+   "metadata": {},
+   "source": [
+    "# Gremlin (with CosmosDB) QA chain\n",
+    "\n",
+    "This notebook shows how to use LLMs to provide a natural language interface to a graph database you can query with the Gremlin query language."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dbc0ee68",
+   "metadata": {},
+   "source": [
+    "You will need to have a Azure CosmosDB Graph database instance. One option is to create a [free CosmosDB Graph database instance in Azure](https://learn.microsoft.com/en-us/azure/cosmos-db/free-tier). \n",
+    "\n",
+    "When you create your Cosmos DB account and Graph, use /type as partition key."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "62812aad",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.graphs import GremlinGraph\n",
+    "from langchain.chains.graph_qa import GremlinQAChain\n",
+    "from langchain_openai import AzureChatOpenAI\n",
+    "from langchain.schema import Document\n",
+    "from langchain_community.graphs.graph_document import GraphDocument, Node, Relationship\n",
+    "import nest_asyncio"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0928915d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cosmosdb_name = \"mycosmosdb\"\n",
+    "cosmosdb_db_id = \"graphtesting\"\n",
+    "cosmosdb_db_graph_id = \"mygraph\"\n",
+    "cosmosdb_access_Key = \"longstring==\"\n",
+    "\n",
+    "graph = GremlinGraph(\n",
+    "    url=f\"=wss://{cosmosdb_name}.gremlin.cosmos.azure.com:443/\", \n",
+    "    username=f\"/dbs/{cosmosdb_db_id}/colls/{cosmosdb_db_graph_id}\", \n",
+    "    password=cosmosdb_access_Key\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "995ea9b9",
+   "metadata": {},
+   "source": [
+    "## Seeding the database\n",
+    "\n",
+    "Assuming your database is empty, you can populate it using the GraphDocuments\n",
+    "\n",
+    "For Gremlin, always add property called 'label' for each Node.\n",
+    "If no label is set, Node.type is used as a label.\n",
+    "For cosmos using natural id's make sense, as they are visible in the graph explorer."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fedd26b9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "source_doc = Document(page_content=\"Matrix is a movie where Keanu Reeves, Laurence Fishburne and Carrie-Anne Moss acted.\")\n",
+    "movie = Node(id=\"The Matrix\", properties={\"label\":\"movie\", \"title\": \"The Matrix\"})\n",
+    "actor1 = Node(id=\"Keanu Reeves\", properties={\"label\":\"actor\", \"name\": \"Keanu Reeves\"})\n",
+    "actor2 = Node(id=\"Laurence Fishburne\", properties={\"label\":\"actor\", \"name\": \"Laurence Fishburne\"})\n",
+    "actor3 = Node(id=\"Carrie-Anne Moss\", properties={\"label\":\"actor\", \"name\": \"Carrie-Anne Moss\"})\n",
+    "rel1 = Relationship(id=5, type=\"ActedIn\",  source=actor1, target=movie, properties={\"label\":\"ActedIn\"})\n",
+    "rel2 = Relationship(id=6, type=\"ActedIn\", source=actor2, target=movie, properties={\"label\":\"ActedIn\"})\n",
+    "rel3 = Relationship(id=7, type=\"ActedIn\", source=actor3, target=movie, properties={\"label\":\"ActedIn\"})\n",
+    "rel4 = Relationship(id=8, type=\"Starring\",  source=movie, target=actor1, properties={\"label\":\"Strarring\"})\n",
+    "rel5 = Relationship(id=9, type=\"Starring\", source=movie, target=actor2, properties={\"label\":\"Strarring\"})\n",
+    "rel6 = Relationship(id=10, type=\"Straring\", source=movie, target=actor3, properties={\"label\":\"Strarring\"})\n",
+    "graph_doc = GraphDocument(\n",
+    "    nodes=[movie, actor1, actor2, actor3],\n",
+    "    relationships=[rel1, rel2, rel3, rel4, rel5, rel6],\n",
+    "    source=source_doc\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d18f77a3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# The underlying python-gremlin has a problem when running in notebook\n",
+    "# The following line is a workaround to fix the problem\n",
+    "nest_asyncio.apply()\n",
+    "\n",
+    "# Add the document to the CosmosDB graph.\n",
+    "graph.add_graph_documents([graph_doc])   "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "58c1a8ea",
+   "metadata": {},
+   "source": [
+    "## Refresh graph schema information\n",
+    "If the schema of database changes (after updates), you can refresh the schema information.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4e3de44f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "graph.refresh_schema()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1fe76ccd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(graph.schema)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "68a3c677",
+   "metadata": {},
+   "source": [
+    "## Querying the graph\n",
+    "\n",
+    "We can now use the gremlin QA chain to ask question of the graph"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7476ce98",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "chain = GremlinQAChain.from_llm(\n",
+    "    AzureChatOpenAI(temperature=0,\n",
+    "                    azure_deployment=\"gpt-4-turbo\",\n",
+    "                    ), \n",
+    "    graph=graph, \n",
+    "    verbose=True\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ef8ee27b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain.invoke(\"Who played in The Matrix?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "47c64027-cf42-493a-9c76-2d10ba753728",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain.run(\"How many people played in The Matrix?\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.9.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}