docs: add integration guide for PlainID SDK #32129
Open
+1
−0
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
CodSpeed WallTime Performance ReportMerging #32129 will not alter performanceComparing
|
CodSpeed Instrumentation Performance ReportMerging #32129 will not alter performanceComparing Summary
|
mdrxy
changed the title
There was a problem hiding this comment.
Pull Request Overview
This PR adds comprehensive documentation for integrating PlainID SDK with LangChain, providing developers with practical guidance on implementing authorization-aware agents. The documentation covers the complete workflow from installation to building chains that handle data categorization, anonymization, and secure retrieval.
Key changes:
- Complete integration guide with PlainID setup instructions
- Examples for category filtering, data anonymization, and retrieval with policy enforcement
- Code examples demonstrating chain composition and vector store integration
Comments suppressed due to low confidence (3)
docs/docs/integrations/tools/plainid.ipynb:1
- The placeholder '' is invalid Python syntax and will cause a syntax error. This should be replaced with a proper classifier instance.
{"cells": [{"cell_type": "markdown", "id": "f77a88b0", "metadata": {}, "source": ["# LangChain PlainID Integration Guide"]}, {"cell_type": "markdown", "id": "d3a825b0", "metadata": {}, "source": ["## Installation"]}, {"cell_type": "markdown", "id": "91f1382a", "metadata": {}, "source": ["Based on your environment, you can install the library using pip:"]}, {"cell_type": "code", "execution_count": null, "id": "b3aefa28", "metadata": {}, "outputs": [], "source": ["!pip install langchain_plainid"]}, {"cell_type": "markdown", "id": "d05905bd", "metadata": {}, "source": ["## Setup with PlainID"]}, {"cell_type": "markdown", "id": "63146826", "metadata": {}, "source": ["1. Retrieve your PlainID credentials to access the platform - client ID and client secret.\n", "2. Find your PlainID base URL. For production use: `https://platform-product.us1.plainid.io` (note: starts with `platform-product.`)\n", "\n", "**Security Note:** Do not store credentials in code. Use environment variables or secret managers."]}, {"cell_type": "markdown", "id": "7fbc84dc", "metadata": {}, "source": ["## Category Filtering Setup in PlainID"]}, {"cell_type": "markdown", "id": "977d6d86", "metadata": {}, "source": ["You need to configure the relevant Ruleset in PlainID. For example, for template `categories`:\n", "```rego\n", "# METADATA\n", "# custom:\n", "# plainid:\n", "# kind: Ruleset\n", "# name: All\n", "ruleset(asset, identity, requestParams, action) if {\n", " asset.template == \"categories\"\n", "}\n", "```\n", "Also configure asset types like `contract`, `HR` in PlainID."]}, {"cell_type": "code", "execution_count": null, "id": "993b425f", "metadata": {}, "outputs": [], "source": ["from langchain_plainid import PlainIDCategorizer, PlainIDPermissionsProvider\n", "\n", "permissions_provider = PlainIDPermissionsProvider(\n", " client_id=\"your_client_id\",\n", " client_secret=\"your_client_secret\",\n", " base_url=\"https://platform-product.us1.plainid.io\",\n", " plainid_categories_resource_type=\"categories\"\n", ")\n", "\n", "plainid_categorizer = PlainIDCategorizer(\n", " classifier_provider=<classifier>,\n", " permissions_provider=permissions_provider\n", ")\n", "\n", "query = \"I'd like to know the weather forecast for today\"\n", "result = plainid_categorizer.invoke(query)"]}, {"cell_type": "markdown", "id": "f45ed4fd", "metadata": {}, "source": ["## Category Classifiers"]}, {"cell_type": "markdown", "id": "f9536725", "metadata": {}, "source": ["### 1. LLMCategoryClassifierProvider"]}, {"cell_type": "code", "execution_count": null, "id": "a3d8a816", "metadata": {}, "outputs": [], "source": ["from langchain_plainid import LLMCategoryClassifierProvider\n", "llm_classifier = LLMCategoryClassifierProvider(llm=OllamaLLM(model=\"llama2\"))"]}, {"cell_type": "markdown", "id": "c24e92b1", "metadata": {}, "source": ["### 2. ZeroShotCategoryClassifierProvider"]}, {"cell_type": "code", "execution_count": null, "id": "601563bd", "metadata": {}, "outputs": [], "source": ["from langchain_plainid import ZeroShotCategoryClassifierProvider\n", "zeroshot_classifier = ZeroShotCategoryClassifierProvider()"]}, {"cell_type": "markdown", "id": "ed0b6a48", "metadata": {}, "source": ["## Anonymizer Setup in PlainID"]}, {"cell_type": "markdown", "id": "4c215a0f", "metadata": {}, "source": ["Example Ruleset for `entities` template:\n", "```rego\n", "# METADATA\n", "# custom:\n", "# plainid:\n", "# kind: Ruleset\n", "# name: PERSON\n", "ruleset(asset, identity, requestParams, action) if {\n", " asset.template == \"entities\"\n", " asset[\"path\"] == \"PERSON\"\n", " action.id in [\"MASK\"]\n", "}\n", "```"]}, {"cell_type": "code", "execution_count": null, "id": "40de20d5", "metadata": {}, "outputs": [], "source": ["from langchain_plainid import PlainIDPermissionsProvider, PlainIDAnonymizer\n", "\n", "permissions_provider = PlainIDPermissionsProvider(\n", " client_id=\"your_client_id\",\n", " client_secret=\"your_client_secret\",\n", " base_url=\"https://platform-product.us1.plainid.io\",\n", " plainid_entities_resource_type=\"entities\"\n", ")\n", "\n", "plainid_anonymizer = PlainIDAnonymizer(\n", " permissions_provider=permissions_provider,\n", " encrypt_key=\"your_encryption_key\"\n", ")\n", "\n", "query = \"What's the name of the person who is responsible for the contract?\"\n", "result = plainid_anonymizer.invoke(query)"]}, {"cell_type": "markdown", "id": "cfa9b772", "metadata": {}, "source": ["## Full Chain Example"]}, {"cell_type": "code", "execution_count": null, "id": "7cb60e73", "metadata": {}, "outputs": [], "source": ["chain = plainid_categorizer | llm | vector_store | plainid_anonymizer | output_parser"]}, {"cell_type": "markdown", "id": "d43010fa", "metadata": {}, "source": ["## Retriever Setup"]}, {"cell_type": "markdown", "id": "ea6f43ce", "metadata": {}, "source": ["Rulesets for customer template:\n", "```rego\n", "ruleset(asset, identity, requestParams, action) if {\n", " asset.template == \"customer\"\n", " asset[\"country\"] == \"Sweden\"\n", " asset[\"country\"] != \"Russia\"\n", " contains(asset[\"country\"], \"we\")\n", " startswith(asset[\"country\"], \"Sw\")\n", "}\n", "ruleset(asset, identity, requestParams, action) if {\n", " asset.template == \"customer\"\n", " asset[\"country\"] in [\"aaa\", \"bbb\"]\n", " asset[\"age\"] <= 11111\n", " endswith(asset[\"country\"], \"wwww\")\n", "}\n", "```"]}, {"cell_type": "code", "execution_count": null, "id": "8b3a41af", "metadata": {}, "outputs": [], "source": ["from langchain_community.vectorstores import Chroma\n", "from langchain_core.documents import Document\n", "from langchain_plainid import PlainIDRetriever\n", "\n", "documents = [\n", " Document(\"Stockholm is the capital of Sweden.\", metadata={\"country\": \"Sweden\", \"age\": 5}),\n", " Document(\"Oslo is the capital of Norway.\", metadata={\"country\": \"Norway\", \"age\": 5}),\n", " Document(\"Copenhagen is the capital of Denmark.\", metadata={\"country\": \"Denmark\", \"age\": 5}),\n", " Document(\"Helsinki is the capital of Finland.\", metadata={\"country\": \"Finland\", \"age\": 5}),\n", " Document(\"Malm\u00f6 is a city in Sweden.\", metadata={\"country\": \"Sweden\", \"age\": 5}),\n", "]\n", "\n", "vector_store = Chroma.from_documents(documents, embeddings)\n", "plainid_retriever = PlainIDRetriever(vectorstore=vector_store, filter_provider=filter_provider)\n", "docs = plainid_retriever.invoke(\"What is the capital of Sweden?\")"]}, {"cell_type": "markdown", "id": "b0b3ceb8", "metadata": {}, "source": ["## Supported Vector Stores and Limitations"]}, {"cell_type": "markdown", "id": "11f1ec03", "metadata": {}, "source": ["| Vector Store | Not Supported Operators |\n", "|--------------|-----------------------------------------------|\n", "| FAISS | STARTSWITH, ENDSWITH, CONTAINS |\n", "| Chroma | IN, NOT_IN, STARTSWITH, ENDSWITH, CONTAINS |"]}], "metadata": {"title": "LangChain PlainID Integration"}, "nbformat": 4, "nbformat_minor": 5}
docs/docs/integrations/tools/plainid.ipynb:1
- OllamaLLM is used without importing it. This will result in a NameError at runtime.
{"cells": [{"cell_type": "markdown", "id": "f77a88b0", "metadata": {}, "source": ["# LangChain PlainID Integration Guide"]}, {"cell_type": "markdown", "id": "d3a825b0", "metadata": {}, "source": ["## Installation"]}, {"cell_type": "markdown", "id": "91f1382a", "metadata": {}, "source": ["Based on your environment, you can install the library using pip:"]}, {"cell_type": "code", "execution_count": null, "id": "b3aefa28", "metadata": {}, "outputs": [], "source": ["!pip install langchain_plainid"]}, {"cell_type": "markdown", "id": "d05905bd", "metadata": {}, "source": ["## Setup with PlainID"]}, {"cell_type": "markdown", "id": "63146826", "metadata": {}, "source": ["1. Retrieve your PlainID credentials to access the platform - client ID and client secret.\n", "2. Find your PlainID base URL. For production use: `https://platform-product.us1.plainid.io` (note: starts with `platform-product.`)\n", "\n", "**Security Note:** Do not store credentials in code. Use environment variables or secret managers."]}, {"cell_type": "markdown", "id": "7fbc84dc", "metadata": {}, "source": ["## Category Filtering Setup in PlainID"]}, {"cell_type": "markdown", "id": "977d6d86", "metadata": {}, "source": ["You need to configure the relevant Ruleset in PlainID. For example, for template `categories`:\n", "```rego\n", "# METADATA\n", "# custom:\n", "# plainid:\n", "# kind: Ruleset\n", "# name: All\n", "ruleset(asset, identity, requestParams, action) if {\n", " asset.template == \"categories\"\n", "}\n", "```\n", "Also configure asset types like `contract`, `HR` in PlainID."]}, {"cell_type": "code", "execution_count": null, "id": "993b425f", "metadata": {}, "outputs": [], "source": ["from langchain_plainid import PlainIDCategorizer, PlainIDPermissionsProvider\n", "\n", "permissions_provider = PlainIDPermissionsProvider(\n", " client_id=\"your_client_id\",\n", " client_secret=\"your_client_secret\",\n", " base_url=\"https://platform-product.us1.plainid.io\",\n", " plainid_categories_resource_type=\"categories\"\n", ")\n", "\n", "plainid_categorizer = PlainIDCategorizer(\n", " classifier_provider=<classifier>,\n", " permissions_provider=permissions_provider\n", ")\n", "\n", "query = \"I'd like to know the weather forecast for today\"\n", "result = plainid_categorizer.invoke(query)"]}, {"cell_type": "markdown", "id": "f45ed4fd", "metadata": {}, "source": ["## Category Classifiers"]}, {"cell_type": "markdown", "id": "f9536725", "metadata": {}, "source": ["### 1. LLMCategoryClassifierProvider"]}, {"cell_type": "code", "execution_count": null, "id": "a3d8a816", "metadata": {}, "outputs": [], "source": ["from langchain_plainid import LLMCategoryClassifierProvider\n", "llm_classifier = LLMCategoryClassifierProvider(llm=OllamaLLM(model=\"llama2\"))"]}, {"cell_type": "markdown", "id": "c24e92b1", "metadata": {}, "source": ["### 2. ZeroShotCategoryClassifierProvider"]}, {"cell_type": "code", "execution_count": null, "id": "601563bd", "metadata": {}, "outputs": [], "source": ["from langchain_plainid import ZeroShotCategoryClassifierProvider\n", "zeroshot_classifier = ZeroShotCategoryClassifierProvider()"]}, {"cell_type": "markdown", "id": "ed0b6a48", "metadata": {}, "source": ["## Anonymizer Setup in PlainID"]}, {"cell_type": "markdown", "id": "4c215a0f", "metadata": {}, "source": ["Example Ruleset for `entities` template:\n", "```rego\n", "# METADATA\n", "# custom:\n", "# plainid:\n", "# kind: Ruleset\n", "# name: PERSON\n", "ruleset(asset, identity, requestParams, action) if {\n", " asset.template == \"entities\"\n", " asset[\"path\"] == \"PERSON\"\n", " action.id in [\"MASK\"]\n", "}\n", "```"]}, {"cell_type": "code", "execution_count": null, "id": "40de20d5", "metadata": {}, "outputs": [], "source": ["from langchain_plainid import PlainIDPermissionsProvider, PlainIDAnonymizer\n", "\n", "permissions_provider = PlainIDPermissionsProvider(\n", " client_id=\"your_client_id\",\n", " client_secret=\"your_client_secret\",\n", " base_url=\"https://platform-product.us1.plainid.io\",\n", " plainid_entities_resource_type=\"entities\"\n", ")\n", "\n", "plainid_anonymizer = PlainIDAnonymizer(\n", " permissions_provider=permissions_provider,\n", " encrypt_key=\"your_encryption_key\"\n", ")\n", "\n", "query = \"What's the name of the person who is responsible for the contract?\"\n", "result = plainid_anonymizer.invoke(query)"]}, {"cell_type": "markdown", "id": "cfa9b772", "metadata": {}, "source": ["## Full Chain Example"]}, {"cell_type": "code", "execution_count": null, "id": "7cb60e73", "metadata": {}, "outputs": [], "source": ["chain = plainid_categorizer | llm | vector_store | plainid_anonymizer | output_parser"]}, {"cell_type": "markdown", "id": "d43010fa", "metadata": {}, "source": ["## Retriever Setup"]}, {"cell_type": "markdown", "id": "ea6f43ce", "metadata": {}, "source": ["Rulesets for customer template:\n", "```rego\n", "ruleset(asset, identity, requestParams, action) if {\n", " asset.template == \"customer\"\n", " asset[\"country\"] == \"Sweden\"\n", " asset[\"country\"] != \"Russia\"\n", " contains(asset[\"country\"], \"we\")\n", " startswith(asset[\"country\"], \"Sw\")\n", "}\n", "ruleset(asset, identity, requestParams, action) if {\n", " asset.template == \"customer\"\n", " asset[\"country\"] in [\"aaa\", \"bbb\"]\n", " asset[\"age\"] <= 11111\n", " endswith(asset[\"country\"], \"wwww\")\n", "}\n", "```"]}, {"cell_type": "code", "execution_count": null, "id": "8b3a41af", "metadata": {}, "outputs": [], "source": ["from langchain_community.vectorstores import Chroma\n", "from langchain_core.documents import Document\n", "from langchain_plainid import PlainIDRetriever\n", "\n", "documents = [\n", " Document(\"Stockholm is the capital of Sweden.\", metadata={\"country\": \"Sweden\", \"age\": 5}),\n", " Document(\"Oslo is the capital of Norway.\", metadata={\"country\": \"Norway\", \"age\": 5}),\n", " Document(\"Copenhagen is the capital of Denmark.\", metadata={\"country\": \"Denmark\", \"age\": 5}),\n", " Document(\"Helsinki is the capital of Finland.\", metadata={\"country\": \"Finland\", \"age\": 5}),\n", " Document(\"Malm\u00f6 is a city in Sweden.\", metadata={\"country\": \"Sweden\", \"age\": 5}),\n", "]\n", "\n", "vector_store = Chroma.from_documents(documents, embeddings)\n", "plainid_retriever = PlainIDRetriever(vectorstore=vector_store, filter_provider=filter_provider)\n", "docs = plainid_retriever.invoke(\"What is the capital of Sweden?\")"]}, {"cell_type": "markdown", "id": "b0b3ceb8", "metadata": {}, "source": ["## Supported Vector Stores and Limitations"]}, {"cell_type": "markdown", "id": "11f1ec03", "metadata": {}, "source": ["| Vector Store | Not Supported Operators |\n", "|--------------|-----------------------------------------------|\n", "| FAISS | STARTSWITH, ENDSWITH, CONTAINS |\n", "| Chroma | IN, NOT_IN, STARTSWITH, ENDSWITH, CONTAINS |"]}], "metadata": {"title": "LangChain PlainID Integration"}, "nbformat": 4, "nbformat_minor": 5}
docs/docs/integrations/tools/plainid.ipynb:1
- [nitpick] While the security note mentions not storing credentials in code, the examples still use placeholder strings that could be mistakenly used as-is. Consider using environment variable examples like
os.getenv('PLAINID_CLIENT_ID')to demonstrate best practices.
{"cells": [{"cell_type": "markdown", "id": "f77a88b0", "metadata": {}, "source": ["# LangChain PlainID Integration Guide"]}, {"cell_type": "markdown", "id": "d3a825b0", "metadata": {}, "source": ["## Installation"]}, {"cell_type": "markdown", "id": "91f1382a", "metadata": {}, "source": ["Based on your environment, you can install the library using pip:"]}, {"cell_type": "code", "execution_count": null, "id": "b3aefa28", "metadata": {}, "outputs": [], "source": ["!pip install langchain_plainid"]}, {"cell_type": "markdown", "id": "d05905bd", "metadata": {}, "source": ["## Setup with PlainID"]}, {"cell_type": "markdown", "id": "63146826", "metadata": {}, "source": ["1. Retrieve your PlainID credentials to access the platform - client ID and client secret.\n", "2. Find your PlainID base URL. For production use: `https://platform-product.us1.plainid.io` (note: starts with `platform-product.`)\n", "\n", "**Security Note:** Do not store credentials in code. Use environment variables or secret managers."]}, {"cell_type": "markdown", "id": "7fbc84dc", "metadata": {}, "source": ["## Category Filtering Setup in PlainID"]}, {"cell_type": "markdown", "id": "977d6d86", "metadata": {}, "source": ["You need to configure the relevant Ruleset in PlainID. For example, for template `categories`:\n", "```rego\n", "# METADATA\n", "# custom:\n", "# plainid:\n", "# kind: Ruleset\n", "# name: All\n", "ruleset(asset, identity, requestParams, action) if {\n", " asset.template == \"categories\"\n", "}\n", "```\n", "Also configure asset types like `contract`, `HR` in PlainID."]}, {"cell_type": "code", "execution_count": null, "id": "993b425f", "metadata": {}, "outputs": [], "source": ["from langchain_plainid import PlainIDCategorizer, PlainIDPermissionsProvider\n", "\n", "permissions_provider = PlainIDPermissionsProvider(\n", " client_id=\"your_client_id\",\n", " client_secret=\"your_client_secret\",\n", " base_url=\"https://platform-product.us1.plainid.io\",\n", " plainid_categories_resource_type=\"categories\"\n", ")\n", "\n", "plainid_categorizer = PlainIDCategorizer(\n", " classifier_provider=<classifier>,\n", " permissions_provider=permissions_provider\n", ")\n", "\n", "query = \"I'd like to know the weather forecast for today\"\n", "result = plainid_categorizer.invoke(query)"]}, {"cell_type": "markdown", "id": "f45ed4fd", "metadata": {}, "source": ["## Category Classifiers"]}, {"cell_type": "markdown", "id": "f9536725", "metadata": {}, "source": ["### 1. LLMCategoryClassifierProvider"]}, {"cell_type": "code", "execution_count": null, "id": "a3d8a816", "metadata": {}, "outputs": [], "source": ["from langchain_plainid import LLMCategoryClassifierProvider\n", "llm_classifier = LLMCategoryClassifierProvider(llm=OllamaLLM(model=\"llama2\"))"]}, {"cell_type": "markdown", "id": "c24e92b1", "metadata": {}, "source": ["### 2. ZeroShotCategoryClassifierProvider"]}, {"cell_type": "code", "execution_count": null, "id": "601563bd", "metadata": {}, "outputs": [], "source": ["from langchain_plainid import ZeroShotCategoryClassifierProvider\n", "zeroshot_classifier = ZeroShotCategoryClassifierProvider()"]}, {"cell_type": "markdown", "id": "ed0b6a48", "metadata": {}, "source": ["## Anonymizer Setup in PlainID"]}, {"cell_type": "markdown", "id": "4c215a0f", "metadata": {}, "source": ["Example Ruleset for `entities` template:\n", "```rego\n", "# METADATA\n", "# custom:\n", "# plainid:\n", "# kind: Ruleset\n", "# name: PERSON\n", "ruleset(asset, identity, requestParams, action) if {\n", " asset.template == \"entities\"\n", " asset[\"path\"] == \"PERSON\"\n", " action.id in [\"MASK\"]\n", "}\n", "```"]}, {"cell_type": "code", "execution_count": null, "id": "40de20d5", "metadata": {}, "outputs": [], "source": ["from langchain_plainid import PlainIDPermissionsProvider, PlainIDAnonymizer\n", "\n", "permissions_provider = PlainIDPermissionsProvider(\n", " client_id=\"your_client_id\",\n", " client_secret=\"your_client_secret\",\n", " base_url=\"https://platform-product.us1.plainid.io\",\n", " plainid_entities_resource_type=\"entities\"\n", ")\n", "\n", "plainid_anonymizer = PlainIDAnonymizer(\n", " permissions_provider=permissions_provider,\n", " encrypt_key=\"your_encryption_key\"\n", ")\n", "\n", "query = \"What's the name of the person who is responsible for the contract?\"\n", "result = plainid_anonymizer.invoke(query)"]}, {"cell_type": "markdown", "id": "cfa9b772", "metadata": {}, "source": ["## Full Chain Example"]}, {"cell_type": "code", "execution_count": null, "id": "7cb60e73", "metadata": {}, "outputs": [], "source": ["chain = plainid_categorizer | llm | vector_store | plainid_anonymizer | output_parser"]}, {"cell_type": "markdown", "id": "d43010fa", "metadata": {}, "source": ["## Retriever Setup"]}, {"cell_type": "markdown", "id": "ea6f43ce", "metadata": {}, "source": ["Rulesets for customer template:\n", "```rego\n", "ruleset(asset, identity, requestParams, action) if {\n", " asset.template == \"customer\"\n", " asset[\"country\"] == \"Sweden\"\n", " asset[\"country\"] != \"Russia\"\n", " contains(asset[\"country\"], \"we\")\n", " startswith(asset[\"country\"], \"Sw\")\n", "}\n", "ruleset(asset, identity, requestParams, action) if {\n", " asset.template == \"customer\"\n", " asset[\"country\"] in [\"aaa\", \"bbb\"]\n", " asset[\"age\"] <= 11111\n", " endswith(asset[\"country\"], \"wwww\")\n", "}\n", "```"]}, {"cell_type": "code", "execution_count": null, "id": "8b3a41af", "metadata": {}, "outputs": [], "source": ["from langchain_community.vectorstores import Chroma\n", "from langchain_core.documents import Document\n", "from langchain_plainid import PlainIDRetriever\n", "\n", "documents = [\n", " Document(\"Stockholm is the capital of Sweden.\", metadata={\"country\": \"Sweden\", \"age\": 5}),\n", " Document(\"Oslo is the capital of Norway.\", metadata={\"country\": \"Norway\", \"age\": 5}),\n", " Document(\"Copenhagen is the capital of Denmark.\", metadata={\"country\": \"Denmark\", \"age\": 5}),\n", " Document(\"Helsinki is the capital of Finland.\", metadata={\"country\": \"Finland\", \"age\": 5}),\n", " Document(\"Malm\u00f6 is a city in Sweden.\", metadata={\"country\": \"Sweden\", \"age\": 5}),\n", "]\n", "\n", "vector_store = Chroma.from_documents(documents, embeddings)\n", "plainid_retriever = PlainIDRetriever(vectorstore=vector_store, filter_provider=filter_provider)\n", "docs = plainid_retriever.invoke(\"What is the capital of Sweden?\")"]}, {"cell_type": "markdown", "id": "b0b3ceb8", "metadata": {}, "source": ["## Supported Vector Stores and Limitations"]}, {"cell_type": "markdown", "id": "11f1ec03", "metadata": {}, "source": ["| Vector Store | Not Supported Operators |\n", "|--------------|-----------------------------------------------|\n", "| FAISS | STARTSWITH, ENDSWITH, CONTAINS |\n", "| Chroma | IN, NOT_IN, STARTSWITH, ENDSWITH, CONTAINS |"]}], "metadata": {"title": "LangChain PlainID Integration"}, "nbformat": 4, "nbformat_minor": 5}
| @@ -0,0 +1 @@ | |||
| {"cells": [{"cell_type": "markdown", "id": "f77a88b0", "metadata": {}, "source": ["# LangChain PlainID Integration Guide"]}, {"cell_type": "markdown", "id": "d3a825b0", "metadata": {}, "source": ["## Installation"]}, {"cell_type": "markdown", "id": "91f1382a", "metadata": {}, "source": ["Based on your environment, you can install the library using pip:"]}, {"cell_type": "code", "execution_count": null, "id": "b3aefa28", "metadata": {}, "outputs": [], "source": ["!pip install langchain_plainid"]}, {"cell_type": "markdown", "id": "d05905bd", "metadata": {}, "source": ["## Setup with PlainID"]}, {"cell_type": "markdown", "id": "63146826", "metadata": {}, "source": ["1. Retrieve your PlainID credentials to access the platform - client ID and client secret.\n", "2. Find your PlainID base URL. For production use: `https://platform-product.us1.plainid.io` (note: starts with `platform-product.`)\n", "\n", "**Security Note:** Do not store credentials in code. Use environment variables or secret managers."]}, {"cell_type": "markdown", "id": "7fbc84dc", "metadata": {}, "source": ["## Category Filtering Setup in PlainID"]}, {"cell_type": "markdown", "id": "977d6d86", "metadata": {}, "source": ["You need to configure the relevant Ruleset in PlainID. For example, for template `categories`:\n", "```rego\n", "# METADATA\n", "# custom:\n", "# plainid:\n", "# kind: Ruleset\n", "# name: All\n", "ruleset(asset, identity, requestParams, action) if {\n", " asset.template == \"categories\"\n", "}\n", "```\n", "Also configure asset types like `contract`, `HR` in PlainID."]}, {"cell_type": "code", "execution_count": null, "id": "993b425f", "metadata": {}, "outputs": [], "source": ["from langchain_plainid import PlainIDCategorizer, PlainIDPermissionsProvider\n", "\n", "permissions_provider = PlainIDPermissionsProvider(\n", " client_id=\"your_client_id\",\n", " client_secret=\"your_client_secret\",\n", " base_url=\"https://platform-product.us1.plainid.io\",\n", " plainid_categories_resource_type=\"categories\"\n", ")\n", "\n", "plainid_categorizer = PlainIDCategorizer(\n", " classifier_provider=<classifier>,\n", " permissions_provider=permissions_provider\n", ")\n", "\n", "query = \"I'd like to know the weather forecast for today\"\n", "result = plainid_categorizer.invoke(query)"]}, {"cell_type": "markdown", "id": "f45ed4fd", "metadata": {}, "source": ["## Category Classifiers"]}, {"cell_type": "markdown", "id": "f9536725", "metadata": {}, "source": ["### 1. LLMCategoryClassifierProvider"]}, {"cell_type": "code", "execution_count": null, "id": "a3d8a816", "metadata": {}, "outputs": [], "source": ["from langchain_plainid import LLMCategoryClassifierProvider\n", "llm_classifier = LLMCategoryClassifierProvider(llm=OllamaLLM(model=\"llama2\"))"]}, {"cell_type": "markdown", "id": "c24e92b1", "metadata": {}, "source": ["### 2. ZeroShotCategoryClassifierProvider"]}, {"cell_type": "code", "execution_count": null, "id": "601563bd", "metadata": {}, "outputs": [], "source": ["from langchain_plainid import ZeroShotCategoryClassifierProvider\n", "zeroshot_classifier = ZeroShotCategoryClassifierProvider()"]}, {"cell_type": "markdown", "id": "ed0b6a48", "metadata": {}, "source": ["## Anonymizer Setup in PlainID"]}, {"cell_type": "markdown", "id": "4c215a0f", "metadata": {}, "source": ["Example Ruleset for `entities` template:\n", "```rego\n", "# METADATA\n", "# custom:\n", "# plainid:\n", "# kind: Ruleset\n", "# name: PERSON\n", "ruleset(asset, identity, requestParams, action) if {\n", " asset.template == \"entities\"\n", " asset[\"path\"] == \"PERSON\"\n", " action.id in [\"MASK\"]\n", "}\n", "```"]}, {"cell_type": "code", "execution_count": null, "id": "40de20d5", "metadata": {}, "outputs": [], "source": ["from langchain_plainid import PlainIDPermissionsProvider, PlainIDAnonymizer\n", "\n", "permissions_provider = PlainIDPermissionsProvider(\n", " client_id=\"your_client_id\",\n", " client_secret=\"your_client_secret\",\n", " base_url=\"https://platform-product.us1.plainid.io\",\n", " plainid_entities_resource_type=\"entities\"\n", ")\n", "\n", "plainid_anonymizer = PlainIDAnonymizer(\n", " permissions_provider=permissions_provider,\n", " encrypt_key=\"your_encryption_key\"\n", ")\n", "\n", "query = \"What's the name of the person who is responsible for the contract?\"\n", "result = plainid_anonymizer.invoke(query)"]}, {"cell_type": "markdown", "id": "cfa9b772", "metadata": {}, "source": ["## Full Chain Example"]}, {"cell_type": "code", "execution_count": null, "id": "7cb60e73", "metadata": {}, "outputs": [], "source": ["chain = plainid_categorizer | llm | vector_store | plainid_anonymizer | output_parser"]}, {"cell_type": "markdown", "id": "d43010fa", "metadata": {}, "source": ["## Retriever Setup"]}, {"cell_type": "markdown", "id": "ea6f43ce", "metadata": {}, "source": ["Rulesets for customer template:\n", "```rego\n", "ruleset(asset, identity, requestParams, action) if {\n", " asset.template == \"customer\"\n", " asset[\"country\"] == \"Sweden\"\n", " asset[\"country\"] != \"Russia\"\n", " contains(asset[\"country\"], \"we\")\n", " startswith(asset[\"country\"], \"Sw\")\n", "}\n", "ruleset(asset, identity, requestParams, action) if {\n", " asset.template == \"customer\"\n", " asset[\"country\"] in [\"aaa\", \"bbb\"]\n", " asset[\"age\"] <= 11111\n", " endswith(asset[\"country\"], \"wwww\")\n", "}\n", "```"]}, {"cell_type": "code", "execution_count": null, "id": "8b3a41af", "metadata": {}, "outputs": [], "source": ["from langchain_community.vectorstores import Chroma\n", "from langchain_core.documents import Document\n", "from langchain_plainid import PlainIDRetriever\n", "\n", "documents = [\n", " Document(\"Stockholm is the capital of Sweden.\", metadata={\"country\": \"Sweden\", \"age\": 5}),\n", " Document(\"Oslo is the capital of Norway.\", metadata={\"country\": \"Norway\", \"age\": 5}),\n", " Document(\"Copenhagen is the capital of Denmark.\", metadata={\"country\": \"Denmark\", \"age\": 5}),\n", " Document(\"Helsinki is the capital of Finland.\", metadata={\"country\": \"Finland\", \"age\": 5}),\n", " Document(\"Malm\u00f6 is a city in Sweden.\", metadata={\"country\": \"Sweden\", \"age\": 5}),\n", "]\n", "\n", "vector_store = Chroma.from_documents(documents, embeddings)\n", "plainid_retriever = PlainIDRetriever(vectorstore=vector_store, filter_provider=filter_provider)\n", "docs = plainid_retriever.invoke(\"What is the capital of Sweden?\")"]}, {"cell_type": "markdown", "id": "b0b3ceb8", "metadata": {}, "source": ["## Supported Vector Stores and Limitations"]}, {"cell_type": "markdown", "id": "11f1ec03", "metadata": {}, "source": ["| Vector Store | Not Supported Operators |\n", "|--------------|-----------------------------------------------|\n", "| FAISS | STARTSWITH, ENDSWITH, CONTAINS |\n", "| Chroma | IN, NOT_IN, STARTSWITH, ENDSWITH, CONTAINS |"]}], "metadata": {"title": "LangChain PlainID Integration"}, "nbformat": 4, "nbformat_minor": 5} | |||
There was a problem hiding this comment.
Multiple undefined variables are used in this chain: 'llm', 'vector_store', and 'output_parser'. These need to be defined or imported before use.
Copilot uses AI. Check for mistakes.
| @@ -0,0 +1 @@ | |||
| {"cells": [{"cell_type": "markdown", "id": "f77a88b0", "metadata": {}, "source": ["# LangChain PlainID Integration Guide"]}, {"cell_type": "markdown", "id": "d3a825b0", "metadata": {}, "source": ["## Installation"]}, {"cell_type": "markdown", "id": "91f1382a", "metadata": {}, "source": ["Based on your environment, you can install the library using pip:"]}, {"cell_type": "code", "execution_count": null, "id": "b3aefa28", "metadata": {}, "outputs": [], "source": ["!pip install langchain_plainid"]}, {"cell_type": "markdown", "id": "d05905bd", "metadata": {}, "source": ["## Setup with PlainID"]}, {"cell_type": "markdown", "id": "63146826", "metadata": {}, "source": ["1. Retrieve your PlainID credentials to access the platform - client ID and client secret.\n", "2. Find your PlainID base URL. For production use: `https://platform-product.us1.plainid.io` (note: starts with `platform-product.`)\n", "\n", "**Security Note:** Do not store credentials in code. Use environment variables or secret managers."]}, {"cell_type": "markdown", "id": "7fbc84dc", "metadata": {}, "source": ["## Category Filtering Setup in PlainID"]}, {"cell_type": "markdown", "id": "977d6d86", "metadata": {}, "source": ["You need to configure the relevant Ruleset in PlainID. For example, for template `categories`:\n", "```rego\n", "# METADATA\n", "# custom:\n", "# plainid:\n", "# kind: Ruleset\n", "# name: All\n", "ruleset(asset, identity, requestParams, action) if {\n", " asset.template == \"categories\"\n", "}\n", "```\n", "Also configure asset types like `contract`, `HR` in PlainID."]}, {"cell_type": "code", "execution_count": null, "id": "993b425f", "metadata": {}, "outputs": [], "source": ["from langchain_plainid import PlainIDCategorizer, PlainIDPermissionsProvider\n", "\n", "permissions_provider = PlainIDPermissionsProvider(\n", " client_id=\"your_client_id\",\n", " client_secret=\"your_client_secret\",\n", " base_url=\"https://platform-product.us1.plainid.io\",\n", " plainid_categories_resource_type=\"categories\"\n", ")\n", "\n", "plainid_categorizer = PlainIDCategorizer(\n", " classifier_provider=<classifier>,\n", " permissions_provider=permissions_provider\n", ")\n", "\n", "query = \"I'd like to know the weather forecast for today\"\n", "result = plainid_categorizer.invoke(query)"]}, {"cell_type": "markdown", "id": "f45ed4fd", "metadata": {}, "source": ["## Category Classifiers"]}, {"cell_type": "markdown", "id": "f9536725", "metadata": {}, "source": ["### 1. LLMCategoryClassifierProvider"]}, {"cell_type": "code", "execution_count": null, "id": "a3d8a816", "metadata": {}, "outputs": [], "source": ["from langchain_plainid import LLMCategoryClassifierProvider\n", "llm_classifier = LLMCategoryClassifierProvider(llm=OllamaLLM(model=\"llama2\"))"]}, {"cell_type": "markdown", "id": "c24e92b1", "metadata": {}, "source": ["### 2. ZeroShotCategoryClassifierProvider"]}, {"cell_type": "code", "execution_count": null, "id": "601563bd", "metadata": {}, "outputs": [], "source": ["from langchain_plainid import ZeroShotCategoryClassifierProvider\n", "zeroshot_classifier = ZeroShotCategoryClassifierProvider()"]}, {"cell_type": "markdown", "id": "ed0b6a48", "metadata": {}, "source": ["## Anonymizer Setup in PlainID"]}, {"cell_type": "markdown", "id": "4c215a0f", "metadata": {}, "source": ["Example Ruleset for `entities` template:\n", "```rego\n", "# METADATA\n", "# custom:\n", "# plainid:\n", "# kind: Ruleset\n", "# name: PERSON\n", "ruleset(asset, identity, requestParams, action) if {\n", " asset.template == \"entities\"\n", " asset[\"path\"] == \"PERSON\"\n", " action.id in [\"MASK\"]\n", "}\n", "```"]}, {"cell_type": "code", "execution_count": null, "id": "40de20d5", "metadata": {}, "outputs": [], "source": ["from langchain_plainid import PlainIDPermissionsProvider, PlainIDAnonymizer\n", "\n", "permissions_provider = PlainIDPermissionsProvider(\n", " client_id=\"your_client_id\",\n", " client_secret=\"your_client_secret\",\n", " base_url=\"https://platform-product.us1.plainid.io\",\n", " plainid_entities_resource_type=\"entities\"\n", ")\n", "\n", "plainid_anonymizer = PlainIDAnonymizer(\n", " permissions_provider=permissions_provider,\n", " encrypt_key=\"your_encryption_key\"\n", ")\n", "\n", "query = \"What's the name of the person who is responsible for the contract?\"\n", "result = plainid_anonymizer.invoke(query)"]}, {"cell_type": "markdown", "id": "cfa9b772", "metadata": {}, "source": ["## Full Chain Example"]}, {"cell_type": "code", "execution_count": null, "id": "7cb60e73", "metadata": {}, "outputs": [], "source": ["chain = plainid_categorizer | llm | vector_store | plainid_anonymizer | output_parser"]}, {"cell_type": "markdown", "id": "d43010fa", "metadata": {}, "source": ["## Retriever Setup"]}, {"cell_type": "markdown", "id": "ea6f43ce", "metadata": {}, "source": ["Rulesets for customer template:\n", "```rego\n", "ruleset(asset, identity, requestParams, action) if {\n", " asset.template == \"customer\"\n", " asset[\"country\"] == \"Sweden\"\n", " asset[\"country\"] != \"Russia\"\n", " contains(asset[\"country\"], \"we\")\n", " startswith(asset[\"country\"], \"Sw\")\n", "}\n", "ruleset(asset, identity, requestParams, action) if {\n", " asset.template == \"customer\"\n", " asset[\"country\"] in [\"aaa\", \"bbb\"]\n", " asset[\"age\"] <= 11111\n", " endswith(asset[\"country\"], \"wwww\")\n", "}\n", "```"]}, {"cell_type": "code", "execution_count": null, "id": "8b3a41af", "metadata": {}, "outputs": [], "source": ["from langchain_community.vectorstores import Chroma\n", "from langchain_core.documents import Document\n", "from langchain_plainid import PlainIDRetriever\n", "\n", "documents = [\n", " Document(\"Stockholm is the capital of Sweden.\", metadata={\"country\": \"Sweden\", \"age\": 5}),\n", " Document(\"Oslo is the capital of Norway.\", metadata={\"country\": \"Norway\", \"age\": 5}),\n", " Document(\"Copenhagen is the capital of Denmark.\", metadata={\"country\": \"Denmark\", \"age\": 5}),\n", " Document(\"Helsinki is the capital of Finland.\", metadata={\"country\": \"Finland\", \"age\": 5}),\n", " Document(\"Malm\u00f6 is a city in Sweden.\", metadata={\"country\": \"Sweden\", \"age\": 5}),\n", "]\n", "\n", "vector_store = Chroma.from_documents(documents, embeddings)\n", "plainid_retriever = PlainIDRetriever(vectorstore=vector_store, filter_provider=filter_provider)\n", "docs = plainid_retriever.invoke(\"What is the capital of Sweden?\")"]}, {"cell_type": "markdown", "id": "b0b3ceb8", "metadata": {}, "source": ["## Supported Vector Stores and Limitations"]}, {"cell_type": "markdown", "id": "11f1ec03", "metadata": {}, "source": ["| Vector Store | Not Supported Operators |\n", "|--------------|-----------------------------------------------|\n", "| FAISS | STARTSWITH, ENDSWITH, CONTAINS |\n", "| Chroma | IN, NOT_IN, STARTSWITH, ENDSWITH, CONTAINS |"]}], "metadata": {"title": "LangChain PlainID Integration"}, "nbformat": 4, "nbformat_minor": 5} | |||
There was a problem hiding this comment.
The variable 'filter_provider' is used without being defined. This should be defined or replaced with the correct permissions_provider instance.
Copilot uses AI. Check for mistakes.
| @@ -0,0 +1 @@ | |||
| {"cells": [{"cell_type": "markdown", "id": "f77a88b0", "metadata": {}, "source": ["# LangChain PlainID Integration Guide"]}, {"cell_type": "markdown", "id": "d3a825b0", "metadata": {}, "source": ["## Installation"]}, {"cell_type": "markdown", "id": "91f1382a", "metadata": {}, "source": ["Based on your environment, you can install the library using pip:"]}, {"cell_type": "code", "execution_count": null, "id": "b3aefa28", "metadata": {}, "outputs": [], "source": ["!pip install langchain_plainid"]}, {"cell_type": "markdown", "id": "d05905bd", "metadata": {}, "source": ["## Setup with PlainID"]}, {"cell_type": "markdown", "id": "63146826", "metadata": {}, "source": ["1. Retrieve your PlainID credentials to access the platform - client ID and client secret.\n", "2. Find your PlainID base URL. For production use: `https://platform-product.us1.plainid.io` (note: starts with `platform-product.`)\n", "\n", "**Security Note:** Do not store credentials in code. Use environment variables or secret managers."]}, {"cell_type": "markdown", "id": "7fbc84dc", "metadata": {}, "source": ["## Category Filtering Setup in PlainID"]}, {"cell_type": "markdown", "id": "977d6d86", "metadata": {}, "source": ["You need to configure the relevant Ruleset in PlainID. For example, for template `categories`:\n", "```rego\n", "# METADATA\n", "# custom:\n", "# plainid:\n", "# kind: Ruleset\n", "# name: All\n", "ruleset(asset, identity, requestParams, action) if {\n", " asset.template == \"categories\"\n", "}\n", "```\n", "Also configure asset types like `contract`, `HR` in PlainID."]}, {"cell_type": "code", "execution_count": null, "id": "993b425f", "metadata": {}, "outputs": [], "source": ["from langchain_plainid import PlainIDCategorizer, PlainIDPermissionsProvider\n", "\n", "permissions_provider = PlainIDPermissionsProvider(\n", " client_id=\"your_client_id\",\n", " client_secret=\"your_client_secret\",\n", " base_url=\"https://platform-product.us1.plainid.io\",\n", " plainid_categories_resource_type=\"categories\"\n", ")\n", "\n", "plainid_categorizer = PlainIDCategorizer(\n", " classifier_provider=<classifier>,\n", " permissions_provider=permissions_provider\n", ")\n", "\n", "query = \"I'd like to know the weather forecast for today\"\n", "result = plainid_categorizer.invoke(query)"]}, {"cell_type": "markdown", "id": "f45ed4fd", "metadata": {}, "source": ["## Category Classifiers"]}, {"cell_type": "markdown", "id": "f9536725", "metadata": {}, "source": ["### 1. LLMCategoryClassifierProvider"]}, {"cell_type": "code", "execution_count": null, "id": "a3d8a816", "metadata": {}, "outputs": [], "source": ["from langchain_plainid import LLMCategoryClassifierProvider\n", "llm_classifier = LLMCategoryClassifierProvider(llm=OllamaLLM(model=\"llama2\"))"]}, {"cell_type": "markdown", "id": "c24e92b1", "metadata": {}, "source": ["### 2. ZeroShotCategoryClassifierProvider"]}, {"cell_type": "code", "execution_count": null, "id": "601563bd", "metadata": {}, "outputs": [], "source": ["from langchain_plainid import ZeroShotCategoryClassifierProvider\n", "zeroshot_classifier = ZeroShotCategoryClassifierProvider()"]}, {"cell_type": "markdown", "id": "ed0b6a48", "metadata": {}, "source": ["## Anonymizer Setup in PlainID"]}, {"cell_type": "markdown", "id": "4c215a0f", "metadata": {}, "source": ["Example Ruleset for `entities` template:\n", "```rego\n", "# METADATA\n", "# custom:\n", "# plainid:\n", "# kind: Ruleset\n", "# name: PERSON\n", "ruleset(asset, identity, requestParams, action) if {\n", " asset.template == \"entities\"\n", " asset[\"path\"] == \"PERSON\"\n", " action.id in [\"MASK\"]\n", "}\n", "```"]}, {"cell_type": "code", "execution_count": null, "id": "40de20d5", "metadata": {}, "outputs": [], "source": ["from langchain_plainid import PlainIDPermissionsProvider, PlainIDAnonymizer\n", "\n", "permissions_provider = PlainIDPermissionsProvider(\n", " client_id=\"your_client_id\",\n", " client_secret=\"your_client_secret\",\n", " base_url=\"https://platform-product.us1.plainid.io\",\n", " plainid_entities_resource_type=\"entities\"\n", ")\n", "\n", "plainid_anonymizer = PlainIDAnonymizer(\n", " permissions_provider=permissions_provider,\n", " encrypt_key=\"your_encryption_key\"\n", ")\n", "\n", "query = \"What's the name of the person who is responsible for the contract?\"\n", "result = plainid_anonymizer.invoke(query)"]}, {"cell_type": "markdown", "id": "cfa9b772", "metadata": {}, "source": ["## Full Chain Example"]}, {"cell_type": "code", "execution_count": null, "id": "7cb60e73", "metadata": {}, "outputs": [], "source": ["chain = plainid_categorizer | llm | vector_store | plainid_anonymizer | output_parser"]}, {"cell_type": "markdown", "id": "d43010fa", "metadata": {}, "source": ["## Retriever Setup"]}, {"cell_type": "markdown", "id": "ea6f43ce", "metadata": {}, "source": ["Rulesets for customer template:\n", "```rego\n", "ruleset(asset, identity, requestParams, action) if {\n", " asset.template == \"customer\"\n", " asset[\"country\"] == \"Sweden\"\n", " asset[\"country\"] != \"Russia\"\n", " contains(asset[\"country\"], \"we\")\n", " startswith(asset[\"country\"], \"Sw\")\n", "}\n", "ruleset(asset, identity, requestParams, action) if {\n", " asset.template == \"customer\"\n", " asset[\"country\"] in [\"aaa\", \"bbb\"]\n", " asset[\"age\"] <= 11111\n", " endswith(asset[\"country\"], \"wwww\")\n", "}\n", "```"]}, {"cell_type": "code", "execution_count": null, "id": "8b3a41af", "metadata": {}, "outputs": [], "source": ["from langchain_community.vectorstores import Chroma\n", "from langchain_core.documents import Document\n", "from langchain_plainid import PlainIDRetriever\n", "\n", "documents = [\n", " Document(\"Stockholm is the capital of Sweden.\", metadata={\"country\": \"Sweden\", \"age\": 5}),\n", " Document(\"Oslo is the capital of Norway.\", metadata={\"country\": \"Norway\", \"age\": 5}),\n", " Document(\"Copenhagen is the capital of Denmark.\", metadata={\"country\": \"Denmark\", \"age\": 5}),\n", " Document(\"Helsinki is the capital of Finland.\", metadata={\"country\": \"Finland\", \"age\": 5}),\n", " Document(\"Malm\u00f6 is a city in Sweden.\", metadata={\"country\": \"Sweden\", \"age\": 5}),\n", "]\n", "\n", "vector_store = Chroma.from_documents(documents, embeddings)\n", "plainid_retriever = PlainIDRetriever(vectorstore=vector_store, filter_provider=filter_provider)\n", "docs = plainid_retriever.invoke(\"What is the capital of Sweden?\")"]}, {"cell_type": "markdown", "id": "b0b3ceb8", "metadata": {}, "source": ["## Supported Vector Stores and Limitations"]}, {"cell_type": "markdown", "id": "11f1ec03", "metadata": {}, "source": ["| Vector Store | Not Supported Operators |\n", "|--------------|-----------------------------------------------|\n", "| FAISS | STARTSWITH, ENDSWITH, CONTAINS |\n", "| Chroma | IN, NOT_IN, STARTSWITH, ENDSWITH, CONTAINS |"]}], "metadata": {"title": "LangChain PlainID Integration"}, "nbformat": 4, "nbformat_minor": 5} | |||
There was a problem hiding this comment.
The variable 'embeddings' is used without being defined or imported. An embeddings instance needs to be created first.
Copilot uses AI. Check for mistakes.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description:
This PR adds a usage notebook for the PlainID integration with LangChain. It includes examples demonstrating how to build chains for data categorization, anonymization, and retrieval based on PlainID policy enforcement. This provides a practical guide for developers looking to embed authorization-aware agents using LangChain.
Issue:
None
Dependencies:
None