"initial commit"

docs/docs/integrations/memory/falkordb_chat_message_history.ipynb

@@ -0,0 +1,73 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# FalkorDB\n",
+    "\n",
+    "<a href='https://docs.falkordb.com/' target='_blank'>FalkorDB</a> is an open-source graph database management system, renowned for its efficient management of highly connected data. Unlike traditional databases that store data in tables, FalkorDB uses a graph structure with nodes, edges, and properties to represent and store data. This design allows for high-performance queries on complex data relationships.\n",
+    "\n",
+    "This notebook goes over how to use `FalkorDB` to store chat message history\n",
+    "\n",
+    "**NOTE**: You can use FalkorDB locally or use FalkorDB Cloud. <a href='https://docs.falkordb.com/' target='blank'>See installation instructions</a>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# For this example notebook we will be using FalkorDB locally\n",
+    "host = \"localhost\"\n",
+    "port = 6379"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_falkordb.message_history import (\n",
+    "    FalkorDBChatMessageHistory,\n",
+    ")\n",
+    "\n",
+    "history = FalkorDBChatMessageHistory(host=host, port=port, session_id=\"session_id_1\")\n",
+    "\n",
+    "history.add_user_message(\"hi!\")\n",
+    "\n",
+    "history.add_ai_message(\"whats up?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[HumanMessage(content='hi!', additional_kwargs={}, response_metadata={}),\n",
+       " AIMessage(content='whats up?', additional_kwargs={}, response_metadata={})]"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "history.messages"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/integrations/providers/falkordb.ipynb

@@ -0,0 +1,72 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# FalkorDB\n",
+    "\n",
+    ">What is `FalkorDB`?\n",
+    "\n",
+    ">- FalkorDB is an `open-source database management system` that specializes in graph database technology.\n",
+    ">- FalkorDB allows you to represent and store data in nodes and edges, making it ideal for handling connected data and relationships.\n",
+    ">- FalkorDB Supports OpenCypher query language with proprietary extensions, making it easy to interact with and query your graph data.\n",
+    ">- With FalkorDB, you can achieve high-performance `graph traversals and queries`, suitable for production-level systems.\n",
+    "\n",
+    ">Get started with FalkorDB by visiting [their website](https://docs.falkordb.com/)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Installation and Setup\n",
+    "\n",
+    "- Install the Python SDK with `pip install falkordb langchain-falkordb`"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## VectorStore\n",
+    "\n",
+    "The FalkorDB vector index is used as a vectorstore,\n",
+    "whether for semantic search or example selection.\n",
+    "\n",
+    "```python\n",
+    "from langchain_community.vectorstores.falkordb_vector import FalkorDBVector\n",
+    "```\n",
+    "or \n",
+    "\n",
+    "```python\n",
+    "from langchain_falkordb.vectorstore import FalkorDBVector\n",
+    "```\n",
+    "\n",
+    "See a [usage example](/docs/integrations/vectorstores/falkordbvector.ipynb)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Memory\n",
+    "\n",
+    "See a [usage example](/docs/integrations/memory/falkordb_chat_message_history.ipynb).\n",
+    "\n",
+    "```python\n",
+    "from langchain_falkordb.message_history import (\n",
+    "    FalkorDBChatMessageHistory,\n",
+    ")\n",
+    "```"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

libs/packages.yml

@@ -166,4 +166,7 @@ packages:
     path: .
   - name: langchain-predictionguard
     repo: predictionguard/langchain-predictionguard
+    path: .
+  - name: langchain-falkordb
+    repo: kingtroga/langchain-falkordb
     path: .