Harrison/cypher

docs/modules/chains/examples/graph_cypher_qa.ipynb

@@ -0,0 +1,230 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "c94240f5",
+   "metadata": {},
+   "source": [
+    "# GraphCypherQAChain\n",
+    "\n",
+    "This notebook shows how to use LLMs to provide a natural language interface to a graph database you can query with the Cypher query language."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dbc0ee68",
+   "metadata": {},
+   "source": [
+    "You will need to have a running Neo4j instance. One option is to create a [free Neo4j database instance in their Aura cloud service](https://neo4j.com/cloud/platform/aura-graph-database/). You can also run the database locally using the [Neo4j Desktop application](https://neo4j.com/download/), or running a docker container.\n",
+    "You can run a local docker container by running the executing the following script:\n",
+    "\n",
+    "```\n",
+    "docker run \\\n",
+    "    --name neo4j \\\n",
+    "    -p 7474:7474 -p 7687:7687 \\\n",
+    "    -d \\\n",
+    "    -e NEO4J_AUTH=neo4j/pleaseletmein \\\n",
+    "    -e NEO4J_PLUGINS=\\[\\\"apoc\\\"\\]  \\\n",
+    "    neo4j:latest\n",
+    "```\n",
+    "\n",
+    "If you are using the docker container, you need to wait a couple of second for the database to start."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "62812aad",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.chains import GraphCypherQAChain\n",
+    "from langchain.graphs import Neo4jGraph"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "0928915d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "graph = Neo4jGraph(\n",
+    "    url=\"bolt://localhost:7687\", username=\"neo4j\", password=\"pleaseletmein\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "995ea9b9",
+   "metadata": {},
+   "source": [
+    "## Seeding the database\n",
+    "\n",
+    "Assuming your database is empty, you can populate it using Cypher query language. The following Cypher statement is idempotent, which means the database information will be the same if you run it one or multiple times."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "fedd26b9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "graph.query(\n",
+    "    \"\"\"\n",
+    "MERGE (m:Movie {name:\"Top Gun\"})\n",
+    "WITH m\n",
+    "UNWIND [\"Tom Cruise\", \"Val Kilmer\", \"Anthony Edwards\", \"Meg Ryan\"] AS actor\n",
+    "MERGE (a:Actor {name:actor})\n",
+    "MERGE (a)-[:ACTED_IN]->(m)\n",
+    "\"\"\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "58c1a8ea",
+   "metadata": {},
+   "source": [
+    "## Refresh graph schema information\n",
+    "If the schema of database changes, you can refresh the schema information needed to generate Cypher statements."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "4e3de44f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "graph.refresh_schema()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "1fe76ccd",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "        Node properties are the following:\n",
+      "        [{'properties': [{'property': 'name', 'type': 'STRING'}], 'labels': 'Movie'}, {'properties': [{'property': 'name', 'type': 'STRING'}], 'labels': 'Actor'}]\n",
+      "        Relationship properties are the following:\n",
+      "        []\n",
+      "        The relationships are the following:\n",
+      "        ['(:Actor)-[:ACTED_IN]->(:Movie)']\n",
+      "        \n"
+     ]
+    }
+   ],
+   "source": [
+    "print(graph.get_schema)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "68a3c677",
+   "metadata": {},
+   "source": [
+    "## Querying the graph\n",
+    "\n",
+    "We can now use the graph cypher QA chain to ask question of the graph"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "7476ce98",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = GraphCypherQAChain.from_llm(\n",
+    "    ChatOpenAI(temperature=0), graph=graph, verbose=True\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "ef8ee27b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new GraphCypherQAChain chain...\u001b[0m\n",
+      "Generated Cypher:\n",
+      "\u001b[32;1m\u001b[1;3mMATCH (a:Actor)-[:ACTED_IN]->(m:Movie {name: 'Top Gun'})\n",
+      "RETURN a.name\u001b[0m\n",
+      "Full Context:\n",
+      "\u001b[32;1m\u001b[1;3m[{'a.name': 'Tom Cruise'}, {'a.name': 'Val Kilmer'}, {'a.name': 'Anthony Edwards'}, {'a.name': 'Meg Ryan'}]\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'Tom Cruise, Val Kilmer, Anthony Edwards, and Meg Ryan played in Top Gun.'"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.run(\"Who played in Top Gun?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b4825316",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

langchain/chains/__init__.py

@@ -10,6 +10,7 @@
 )
 from langchain.chains.flare.base import FlareChain
 from langchain.chains.graph_qa.base import GraphQAChain
+from langchain.chains.graph_qa.cypher import GraphCypherQAChain
 from langchain.chains.hyde.base import HypotheticalDocumentEmbedder
 from langchain.chains.llm import LLMChain
 from langchain.chains.llm_bash.base import LLMBashChain
@@ -58,6 +59,7 @@
     "HypotheticalDocumentEmbedder",
     "ChatVectorDBChain",
     "GraphQAChain",
+    "GraphCypherQAChain",
     "ConstitutionalChain",
     "QAGenerationChain",
     "RetrievalQA",

langchain/chains/graph_qa/cypher.py

@@ -0,0 +1,90 @@
+"""Question answering over a graph."""
+from __future__ import annotations
+
+from typing import Any, Dict, List, Optional
+
+from pydantic import Field
+
+from langchain.base_language import BaseLanguageModel
+from langchain.callbacks.manager import CallbackManagerForChainRun
+from langchain.chains.base import Chain
+from langchain.chains.graph_qa.prompts import CYPHER_GENERATION_PROMPT, PROMPT
+from langchain.chains.llm import LLMChain
+from langchain.graphs.neo4j_graph import Neo4jGraph
+from langchain.prompts.base import BasePromptTemplate
+
+
+class GraphCypherQAChain(Chain):
+    """Chain for question-answering against a graph by generating Cypher statements."""
+
+    graph: Neo4jGraph = Field(exclude=True)
+    cypher_generation_chain: LLMChain
+    qa_chain: LLMChain
+    input_key: str = "query"  #: :meta private:
+    output_key: str = "result"  #: :meta private:
+
+    @property
+    def input_keys(self) -> List[str]:
+        """Return the input keys.
+
+        :meta private:
+        """
+        return [self.input_key]
+
+    @property
+    def output_keys(self) -> List[str]:
+        """Return the output keys.
+
+        :meta private:
+        """
+        _output_keys = [self.output_key]
+        return _output_keys
+
+    @classmethod
+    def from_llm(
+        cls,
+        llm: BaseLanguageModel,
+        *,
+        qa_prompt: BasePromptTemplate = PROMPT,
+        cypher_prompt: BasePromptTemplate = CYPHER_GENERATION_PROMPT,
+        **kwargs: Any,
+    ) -> GraphCypherQAChain:
+        """Initialize from LLM."""
+        qa_chain = LLMChain(llm=llm, prompt=qa_prompt)
+        cypher_generation_chain = LLMChain(llm=llm, prompt=cypher_prompt)
+
+        return cls(
+            qa_chain=qa_chain,
+            cypher_generation_chain=cypher_generation_chain,
+            **kwargs,
+        )
+
+    def _call(
+        self,
+        inputs: Dict[str, Any],
+        run_manager: Optional[CallbackManagerForChainRun] = None,
+    ) -> Dict[str, str]:
+        """Generate Cypher statement, use it to look up in db and answer question."""
+        _run_manager = run_manager or CallbackManagerForChainRun.get_noop_manager()
+        callbacks = _run_manager.get_child()
+        question = inputs[self.input_key]
+
+        generated_cypher = self.cypher_generation_chain.run(
+            {"question": question, "schema": self.graph.get_schema}, callbacks=callbacks
+        )
+
+        _run_manager.on_text("Generated Cypher:", end="\n", verbose=self.verbose)
+        _run_manager.on_text(
+            generated_cypher, color="green", end="\n", verbose=self.verbose
+        )
+        context = self.graph.query(generated_cypher)
+
+        _run_manager.on_text("Full Context:", end="\n", verbose=self.verbose)
+        _run_manager.on_text(
+            str(context), color="green", end="\n", verbose=self.verbose
+        )
+        result = self.qa_chain(
+            {"question": question, "context": context},
+            callbacks=callbacks,
+        )
+        return {self.output_key: result[self.qa_chain.output_key]}

langchain/chains/graph_qa/prompts.py

@@ -32,3 +32,19 @@
 PROMPT = PromptTemplate(
     template=prompt_template, input_variables=["context", "question"]
 )
+
+CYPHER_GENERATION_TEMPLATE = """Task:Generate Cypher statement to query a graph database.
+Instructions:
+Use only the provided relationship types and properties in the schema.
+Do not use any other relationship types or properties that are not provided.
+Schema:
+{schema}
+Note: Do not include any explanations or apologies in your responses.
+Do not respond to any questions that might ask anything else than for you to construct a Cypher statement.
+Do not include any text except the generated Cypher statement.
+
+The question is:
+{question}"""
+CYPHER_GENERATION_PROMPT = PromptTemplate(
+    input_variables=["schema", "question"], template=CYPHER_GENERATION_TEMPLATE
+)

langchain/graphs/__init__.py

@@ -1,4 +1,5 @@
 """Graph implementations."""
+from langchain.graphs.neo4j_graph import Neo4jGraph
 from langchain.graphs.networkx_graph import NetworkxEntityGraph
 
-__all__ = ["NetworkxEntityGraph"]
+__all__ = ["NetworkxEntityGraph", "Neo4jGraph"]