Skip to content

The agent engineering platform.

docs: add Tilores provider and tools (#29244)

Stefan Berkner8977451c76bf
diff --git a/docs/docs/integrations/providers/tilores.ipynb b/docs/docs/integrations/providers/tilores.ipynb
new file mode 100644
index 0000000000..b51384ca4c
--- /dev/null
+++ b/docs/docs/integrations/providers/tilores.ipynb
@@ -0,0 +1,105 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Tilores\n",
+ "\n",
+ "[Tilores](https://tilores.io) is a platform that provides advanced entity resolution solutions for data integration and management. Using cutting-edge algorithms, machine learning, and a user-friendly interfaces, Tilores helps organizations match, resolve, and consolidate data from disparate sources, ensuring high-quality, consistent information."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Installation and Setup"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "y8ku6X96sebl"
+ },
+ "outputs": [],
+ "source": [
+ "%pip install --upgrade tilores-langchain"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "To access Tilores, you need to [create and configure an instance](https://app.tilores.io). If you prefer to test out Tilores first, you can use the [read-only demo credentials](https://github.com/tilotech/identity-rag-customer-insights-chatbot?tab=readme-ov-file#1-configure-customer-data-access)."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import os\n",
+ "\n",
+ "from tilores import TiloresAPI\n",
+ "\n",
+ "os.environ[\"TILORES_API_URL\"] = \"<api-url>\"\n",
+ "os.environ[\"TILORES_TOKEN_URL\"] = \"<token-url>\"\n",
+ "os.environ[\"TILORES_CLIENT_ID\"] = \"<client-id>\"\n",
+ "os.environ[\"TILORES_CLIENT_SECRET\"] = \"<client-secret>\"\n",
+ "\n",
+ "tilores = TiloresAPI.from_environ()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Please refer to the [Tilores documentation](https://docs.tilotech.io/tilores/publicsaaswalkthrough/) on how to create your own instance."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Toolkits\n",
+ "\n",
+ "You can use the [`TiloresTools`](/docs/integrations/tools/tilores) to query data from Tilores:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from tilores_langchain import TiloresTools"
+ ]
+ }
+ ],
+ "metadata": {
+ "colab": {
+ "provenance": []
+ },
+ "kernelspec": {
+ "display_name": "langchain",
+ "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": "3.12.8"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}
diff --git a/docs/docs/integrations/tools/tilores.ipynb b/docs/docs/integrations/tools/tilores.ipynb
new file mode 100644
index 0000000000..e2bb19fca4
--- /dev/null
+++ b/docs/docs/integrations/tools/tilores.ipynb
@@ -0,0 +1,350 @@
+{
+ "cells": [
+ {
+ "cell_type": "raw",
+ "id": "10238e62-3465-4973-9279-606cbb7ccf16",
+ "metadata": {},
+ "source": [
+ "---\n",
+ "sidebar_label: Tilores\n",
+ "---"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "a6f91f20",
+ "metadata": {},
+ "source": [
+ "# Tilores\n",
+ "\n",
+ "This notebook covers how to get started with the [Tilores](/docs/integrations/providers/tilores) tools.\n",
+ "For a more complex example you can checkout our [customer insights chatbot example](https://github.com/tilotech/identity-rag-customer-insights-chatbot).\n",
+ "\n",
+ "## Overview\n",
+ "\n",
+ "### Integration details\n",
+ "\n",
+ "| Class | Package | Serializable | JS support | Package latest |\n",
+ "| :--- | :--- | :---: | :---: | :---: |\n",
+ "| TiloresTools | [tilores-langchain](https://pypi.org/project/tilores-langchain/) | ❌ | ❌ | ![PyPI - Version](https://img.shields.io/pypi/v/tilores-langchain?style=flat-square&label=%20) |\n",
+ "\n",
+ "## Setup\n",
+ "\n",
+ "The integration requires the following packages:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 72,
+ "id": "f85b4089",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Note: you may need to restart the kernel to use updated packages.\n"
+ ]
+ }
+ ],
+ "source": [
+ "%pip install --quiet -U tilores-langchain langchain"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "b15e9266",
+ "metadata": {},
+ "source": [
+ "### Credentials\n",
+ "\n",
+ "To access Tilores, you need to [create and configure an instance](https://app.tilores.io). If you prefer to test out Tilores first, you can use the [read-only demo credentials](https://github.com/tilotech/identity-rag-customer-insights-chatbot?tab=readme-ov-file#1-configure-customer-data-access)."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 73,
+ "id": "e0b178a2-8816-40ca-b57c-ccdd86dde9c9",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import os\n",
+ "\n",
+ "os.environ[\"TILORES_API_URL\"] = \"<api-url>\"\n",
+ "os.environ[\"TILORES_TOKEN_URL\"] = \"<token-url>\"\n",
+ "os.environ[\"TILORES_CLIENT_ID\"] = \"<client-id>\"\n",
+ "os.environ[\"TILORES_CLIENT_SECRET\"] = \"<client-secret>\""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "1c97218f-f366-479d-8bf7-fe9f2f6df73f",
+ "metadata": {},
+ "source": [
+ "## Instantiation\n",
+ "\n",
+ "Here we show how to instantiate an instance of the Tilores tools:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 74,
+ "id": "8b3ddfe9-ca79-494c-a7ab-1f56d9407a64",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from tilores import TiloresAPI\n",
+ "from tilores_langchain import TiloresTools\n",
+ "\n",
+ "tilores = TiloresAPI.from_environ()\n",
+ "tilores_tools = TiloresTools(tilores)\n",
+ "search_tool = tilores_tools.search_tool()\n",
+ "edge_tool = tilores_tools.edge_tool()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "74147a1a",
+ "metadata": {},
+ "source": [
+ "## Invocation\n",
+ "\n",
+ "The parameters for the `tilores_search` tool are dependent on the [configured schema](https://docs.tilotech.io/tilores/schema/) within Tilores. The following examples will use the schema for the demo instance with generated data.\n",
+ "\n",
+ "### [Invoke directly with args](/docs/concepts/tools)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "010aea95",
+ "metadata": {},
+ "source": [
+ "The following example searches for a person called Sophie Müller in Berlin. The Tilores data contains multiple such persons and returns their known email addresses and phone numbers."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 75,
+ "id": "65310a8b-eb0c-4d9e-a618-4f4abe2414fc",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Number of entities: 3\n",
+ "Number of records: 3\n",
+ "Email Addresses: ['[email protected]', '[email protected]']\n",
+ "Phone Numbers: ['30987654', '30987654', '30987654']\n",
+ "Number of records: 5\n",
+ "Email Addresses: ['[email protected]', '[email protected]', '[email protected]']\n",
+ "Phone Numbers: ['30135792', '30135792']\n",
+ "Number of records: 2\n",
+ "Email Addresses: ['[email protected]']\n",
+ "Phone Numbers: ['30123456', '30123456']\n"
+ ]
+ }
+ ],
+ "source": [
+ "result = search_tool.invoke(\n",
+ " {\n",
+ " \"searchParams\": {\n",
+ " \"name\": \"Sophie Müller\",\n",
+ " \"city\": \"Berlin\",\n",
+ " },\n",
+ " \"recordFieldsToQuery\": {\n",
+ " \"email\": True,\n",
+ " \"phone\": True,\n",
+ " },\n",
+ " }\n",
+ ")\n",
+ "print(\"Number of entities:\", len(result[\"data\"][\"search\"][\"entities\"]))\n",
+ "for entity in result[\"data\"][\"search\"][\"entities\"]:\n",
+ " print(\"Number of records:\", len(entity[\"records\"]))\n",
+ " print(\n",
+ " \"Email Addresses:\",\n",
+ " [record[\"email\"] for record in entity[\"records\"] if record.get(\"email\")],\n",
+ " )\n",
+ " print(\n",
+ " \"Phone Numbers:\",\n",
+ " [record[\"phone\"] for record in entity[\"records\"] if record.get(\"phone\")],\n",
+ " )"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "ab5c77ef",
+ "metadata": {},
+ "source": [
+ "If we're interested how the records from the first entity are related, we can use the edge_tool. Note that the Tilores entity resolution engine figured out the relation between those records automatically. Please refer to the [edge documentation](https://docs.tilotech.io/tilores/rules/#edges) for more details."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 76,
+ "id": "430e425c",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Number of edges: 7\n",
+ "Edges: ['e1f2g3h4-i5j6-k7l8-m9n0-o1p2q3r4s5t6:f2g3h4i5-j6k7-l8m9-n0o1-p2q3r4s5t6u7:L1', 'e1f2g3h4-i5j6-k7l8-m9n0-o1p2q3r4s5t6:g3h4i5j6-k7l8-m9n0-o1p2-q3r4s5t6u7v8:L4', 'e1f2g3h4-i5j6-k7l8-m9n0-o1p2q3r4s5t6:f2g3h4i5-j6k7-l8m9-n0o1-p2q3r4s5t6u7:L2', 'f2g3h4i5-j6k7-l8m9-n0o1-p2q3r4s5t6u7:g3h4i5j6-k7l8-m9n0-o1p2-q3r4s5t6u7v8:L1', 'f2g3h4i5-j6k7-l8m9-n0o1-p2q3r4s5t6u7:g3h4i5j6-k7l8-m9n0-o1p2-q3r4s5t6u7v8:L4', 'e1f2g3h4-i5j6-k7l8-m9n0-o1p2q3r4s5t6:g3h4i5j6-k7l8-m9n0-o1p2-q3r4s5t6u7v8:L1', 'e1f2g3h4-i5j6-k7l8-m9n0-o1p2q3r4s5t6:f2g3h4i5-j6k7-l8m9-n0o1-p2q3r4s5t6u7:L4']\n"
+ ]
+ }
+ ],
+ "source": [
+ "edge_result = edge_tool.invoke(\n",
+ " {\"entityID\": result[\"data\"][\"search\"][\"entities\"][0][\"id\"]}\n",
+ ")\n",
+ "edges = edge_result[\"data\"][\"entity\"][\"entity\"][\"edges\"]\n",
+ "print(\"Number of edges:\", len(edges))\n",
+ "print(\"Edges:\", edges)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "d6e73897",
+ "metadata": {},
+ "source": [
+ "### [Invoke with ToolCall](/docs/concepts/tools)\n",
+ "\n",
+ "We can also invoke the tool with a model-generated ToolCall, in which case a ToolMessage will be returned:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 77,
+ "id": "f90e33a7",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "ToolMessage(content='{\"data\": {\"search\": {\"entities\": [{\"id\": \"9601cf3b-e85f-46ab-aaa8-ffb8b46f1c5b\", \"hits\": {\"c3d4e5f6-g7h8-i9j0-k1l2-m3n4o5p6q7r8\": [\"L1\"]}, \"records\": [{\"email\": \"\", \"phone\": \"30123456\"}, {\"email\": \"[email protected]\", \"phone\": \"30123456\"}]}, {\"id\": \"03da2e11-0aa2-4d17-8aaa-7b32c52decd9\", \"hits\": {\"e1f2g3h4-i5j6-k7l8-m9n0-o1p2q3r4s5t6\": [\"L1\"], \"g3h4i5j6-k7l8-m9n0-o1p2-q3r4s5t6u7v8\": [\"L1\"]}, \"records\": [{\"email\": \"[email protected]\", \"phone\": \"30987654\"}, {\"email\": \"\", \"phone\": \"30987654\"}, {\"email\": \"[email protected]\", \"phone\": \"30987654\"}]}, {\"id\": \"4d896fb5-0d08-4212-a043-b5deb0347106\", \"hits\": {\"j6k7l8m9-n0o1-p2q3-r4s5-t6u7v8w9x0y1\": [\"L1\"], \"l8m9n0o1-p2q3-r4s5-t6u7-v8w9x0y1z2a3\": [\"L1\"], \"m9n0o1p2-q3r4-s5t6-u7v8-w9x0y1z2a3b4\": [\"L1\"], \"n0o1p2q3-r4s5-t6u7-v8w9-x0y1z2a3b4c5\": [\"L1\"]}, \"records\": [{\"email\": \"[email protected]\", \"phone\": \"\"}, {\"email\": \"[email protected]\", \"phone\": \"\"}, {\"email\": \"\", \"phone\": \"30135792\"}, {\"email\": \"\", \"phone\": \"\"}, {\"email\": \"[email protected]\", \"phone\": \"30135792\"}]}]}}}', name='tilores_search', tool_call_id='1')"
+ ]
+ },
+ "execution_count": 77,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# This is usually generated by a model, but we'll create a tool call directly for demo purposes.\n",
+ "model_generated_tool_call = {\n",
+ " \"args\": {\n",
+ " \"searchParams\": {\n",
+ " \"name\": \"Sophie Müller\",\n",
+ " \"city\": \"Berlin\",\n",
+ " },\n",
+ " \"recordFieldsToQuery\": {\n",
+ " \"email\": True,\n",
+ " \"phone\": True,\n",
+ " },\n",
+ " },\n",
+ " \"id\": \"1\",\n",
+ " \"name\": search_tool.name,\n",
+ " \"type\": \"tool_call\",\n",
+ "}\n",
+ "search_tool.invoke(model_generated_tool_call)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "659f9fbd-6fcf-445f-aa8c-72d8e60154bd",
+ "metadata": {},
+ "source": [
+ "## Chaining\n",
+ "\n",
+ "We can use our tool in a chain by first binding it to a [tool-calling model](/docs/how_to/tool_calling/) and then calling it:\n",
+ "\n",
+ "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
+ "\n",
+ "<ChatModelTabs customVarName=\"llm\" />\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "af3123ad-7a02-40e5-b58e-7d56e23e5830",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# | output: false\n",
+ "# | echo: false\n",
+ "\n",
+ "# !pip install -qU langchain langchain-openai\n",
+ "from langchain.chat_models import init_chat_model\n",
+ "\n",
+ "llm = init_chat_model(model=\"gpt-4o\", model_provider=\"openai\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "fdbf35b5-3aaf-4947-9ec6-48c21533fb95",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from langchain_core.prompts import ChatPromptTemplate\n",
+ "from langchain_core.runnables import RunnableConfig, chain\n",
+ "\n",
+ "prompt = ChatPromptTemplate(\n",
+ " [\n",
+ " (\"system\", \"You are a helpful assistant.\"),\n",
+ " (\"human\", \"{user_input}\"),\n",
+ " (\"placeholder\", \"{messages}\"),\n",
+ " ]\n",
+ ")\n",
+ "\n",
+ "# specifying tool_choice will force the model to call this tool.\n",
+ "llm_with_tools = llm.bind_tools([search_tool], tool_choice=search_tool.name)\n",
+ "\n",
+ "llm_chain = prompt | llm_with_tools\n",
+ "\n",
+ "\n",
+ "@chain\n",
+ "def tool_chain(user_input: str, config: RunnableConfig):\n",
+ " input_ = {\"user_input\": user_input}\n",
+ " ai_msg = llm_chain.invoke(input_, config=config)\n",
+ " tool_msgs = search_tool.batch(ai_msg.tool_calls, config=config)\n",
+ " return llm_chain.invoke({**input_, \"messages\": [ai_msg, *tool_msgs]}, config=config)\n",
+ "\n",
+ "\n",
+ "tool_chain.invoke(\"Tell me the email addresses from Sophie Müller from Berlin.\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "4ac8146c",
+ "metadata": {},
+ "source": [
+ "## API reference\n",
+ "\n",
+ "For detailed documentation of all Tilores features and configurations head to the official documentation: https://docs.tilotech.io/tilores/"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "langchain",
+ "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": "3.12.8"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/libs/packages.yml b/libs/packages.yml
index 1cb609c308..4bdf49680f 100644
--- a/libs/packages.yml
+++ b/libs/packages.yml
@@ -346,6 +346,11 @@ packages:
path: .
repo: MehdiZare/langchain-fmp-data
downloads: 0
+- name: tilores-langchain
+ path: .
+ repo: tilotech/tilores-langchain
+ provider_page: tilores
+ downloads: 0
- name: langchain-pipeshift
path: .
repo: pipeshift-org/langchain-pipeshift
@@ -354,4 +359,4 @@ packages:
path: .
repo: paymanai/langchain-payman-tool
downloads: 0
- downloads_updated_at: "2025-01-22T00:00:00+00:00"
\ No newline at end of file
+ downloads_updated_at: "2025-01-22T00:00:00+00:00"