Update UI links, remove some TS / PR 2

Updated UI links, removed some TS

Author: gabor-openai

README.md

@@ -1,25 +1,17 @@
 # OpenAI Guardrails
 
-> **Choose your language:**
-> - [Python](#python)
-> - [TypeScript](#typescript)
-
----
-
-# Python
-
 ## Overview
 
 OpenAI Guardrails is a Python package for adding robust, configurable safety and compliance guardrails to LLM applications. It provides a drop-in wrapper for OpenAI's Python client, enabling automatic input/output validation and moderation using a wide range of guardrails.
 
 ## Documentation
 
-For full details, advanced usage, and API reference, see here: [OpenAI Guardrails Alpha Documentation](https://oaig-whisper-yonder-xnjpy2.vercel.app/docs/).
+For full details, advanced usage, and API reference, see here: [OpenAI Guardrails Documentation](https://openai.github.io/openai-guardrails-python/).
 
 ## Quick Start: Using OpenAI Guardrails (Python)
 
 1. **Generate your guardrail spec JSON**
-   - Use the [Guardrails web UI](https://oaig-whisper-yonder-xnjpy2.vercel.app/) (pw: guardrails) to create a JSON configuration file describing which guardrails to apply and how to configure them.
+   - Use the [Guardrails web UI](https://platform.openai.com/guardrails) to create a JSON configuration file describing which guardrails to apply and how to configure them.
    - The wizard outputs a file like `guardrail_specs.json`.
 
 2. **Install dependencies**
@@ -65,7 +57,7 @@ For full details, advanced usage, and API reference, see here: [OpenAI Guardrail
    - The client will automatically apply all configured guardrails to inputs and outputs.
    - If a guardrail is triggered, a `GuardrailTripwireTriggered` exception will be raised. You should handle this exception to gracefully manage blocked or flagged content.
 
-> **Note:** The Guardrails web UI (in `frontend/`) is hosted [here](https://oaig-whisper-yonder-xnjpy2.vercel.app/). You do not need to run the web UI yourself to use the Python package.
+> **Note:** The Guardrails web UI is hosted [here](https://platform.openai.com/guardrails). You do not need to run the web UI yourself to use the Python package.
 
 ---
 
@@ -79,107 +71,6 @@ For full details, advanced usage, and API reference, see here: [OpenAI Guardrail
 
 ---
 
-# TypeScript
-
-## Overview
-
-Guardrails TypeScript is a Node.js/TypeScript framework for secure AI calls with OpenAI Guardrails. It provides a port of the Python Guardrails framework with enhanced type safety, Node.js integration, and a high-level client API mirroring the Python version.
-
-> **Note:** The TypeScript package is currently in development and not yet published to npm. Use the local installation methods below.
-
-## Quick Start: Using OpenAI Guardrails (TypeScript)
-
-### 1. Install Locally
-
-Clone the repository and install dependencies:
-```bash
-# From the root of the repo
-cd guardrails-ts
-npm install
-npm run build
-```
-
-You can also install it into your own project from the local path:
-```bash
-npm install /absolute/path/to/guardrails/guardrails-ts
-```
-
-### 2. Using the Guardrails Client in TypeScript
-
-The TypeScript client now provides a high-level API similar to Python:
-
-```typescript
-import { GuardrailsOpenAI } from '@guardrails/guardrails-ts';
-import * as path from 'path';
-// Create a GuardrailsOpenAI client with your config
-const client = await GuardrailsOpenAI.create(path.resolve('guardrails_config.json'), {
-  apiKey: process.env.OPENAI_API_KEY,
-});
-try {
-  const response = await client.chat.completions.create({
-    model: 'gpt-5',
-    messages: [{ role: 'user', content: '...' }],
-  });
-  console.log(response.llm_response.choices[0].message.content);
-} catch (e) {
-  // Handle blocked or flagged content
-  console.error('Guardrail triggered:', e);
-}
-// Example: Using the new OpenAI Responses API with Guardrails
-try {
-  const resp = await client.responses.create({
-    model: 'gpt-5',
-    input: '...',
-    // Optionally, add file_search or other tool arguments as needed
-  });
-  console.log(resp.llm_response.output_text);
-} catch (e) {
-  console.error('Guardrail triggered (responses API):', e);
-}
-```
-
-### 3. CLI Usage
-
-You can also use the CLI for validation and evaluation:
-
-```bash
-# Run directly with npm (from guardrails-ts directory)
-npm run cli -- --help
-npm run cli -- validate config.json
-npm run cli -- eval --config-path config.json --dataset-path dataset.jsonl
-
-# Or install globally for CLI access
-npm install -g .
-guardrails-ts --help
-guardrails-ts validate config.json
-guardrails-ts eval --config-path config.json --dataset-path dataset.jsonl
-```
-
-### 4. Running Examples
-
-```bash
-# Build the package first
-npm run build
-
-# Run example scripts (from guardrails-ts/examples)
-cd examples
-npx tsx simple-runtime-usage.ts
-npx tsx guardrails-demo.ts
-```
-
----
-
-## What Does the TypeScript Package Provide?
-
-- **GuardrailsOpenAI** and **GuardrailsAzureOpenAI**: Drop-in replacements for OpenAI's `OpenAI` and `AzureOpenAI` clients, with automatic guardrail enforcement (mirrors Python API).
-- **Automatic input/output validation**: Guardrails are applied to all relevant API calls (e.g., `chat.completions.create`, `responses.create`, etc.).
-- **Configurable guardrails**: Choose which checks to enable, and customize their parameters via the JSON spec.
-- **Tripwire support**: Optionally block or mask unsafe content, or just log/flag it for review.
-- **CLI tool**: Validate configs, run evaluations, and more from the command line.
-- **Evaluation framework**: Test guardrail performance on datasets and measure metrics like precision, recall, and F1 scores.
-
----
-
 ## Available Guardrails
 
 Below is a list of all built-in guardrails you can configure. Each can be enabled/disabled and customized in your JSON spec.
@@ -202,9 +93,9 @@ Below is a list of all built-in guardrails you can configure. Each can be enable
 
 ## License
 
-For the duration of this early access alpha, `guardrails` (including both the Python and TypeScript packages) is distributed under the Alpha Evaluation Agreement that your organization signed with OpenAI.
+For the duration of this early access alpha, `guardrails` is distributed under the Alpha Evaluation Agreement that your organization signed with OpenAI.
 
-Both the Python and TypeScript packages are intended to be MIT-licensed in the future, subject to change.
+The Python package is intended to be MIT-licensed in the future, subject to change.
 
 ## Disclaimers
 

docs/agents_sdk_integration.md

@@ -83,7 +83,7 @@ agent = GuardrailAgent(config=JsonString('{"version": 1, ...}'), ...)
 
 ## Next Steps
 
-- Use the [Guardrails Wizard](https://guardrails-vercel-git-main-openai.vercel.app/guardrails) to generate your configuration
+- Use the [Guardrails Wizard](https://platform.openai.com/guardrails) to generate your configuration
 - Explore available guardrails for your use case  
 - Learn about pipeline configuration in our [quickstart](./quickstart.md)
 - For more details on the OpenAI Agents SDK, refer to the [Agent SDK documentation](https://openai.github.io/openai-agents-python/).

docs/evals.md

@@ -20,17 +20,25 @@ python guardrail_evals.py \
   --models gpt-5 gpt-5-mini gpt-5-nano
 ```
 
-Test with included demo files in our [github repository](https://github.com/OpenAI-Early-Access/guardrails/tree/main/src/guardrails/evals/eval_demo)
+Test with included demo files in our [github repository](https://github.com/openai/openai-guardrails-python/tree/main/src/guardrails/evals/eval_demo)
 
 ## Dependencies
 
-The evals tool requires a few extra packages that are not installed with the core `guardrails` package. Please install the following before running evaluations or benchmarks:
+### Benchmark Mode
+When running benchmark mode (ROC curves, precision at recall thresholds, visualizations), you need additional packages:
 
 ```bash
-pip install numpy pandas matplotlib seaborn scikit-learn
+pip install "guardrails[benchmark]"
 ```
 
-These dependencies are only needed for the evals and benchmarking workflows (metrics and visualization), not for using `guardrails` at runtime.
+This installs:
+- `numpy>=1.24.0` - Core scientific computing
+- `scikit-learn>=1.3.0` - Machine learning metrics
+- `matplotlib>=3.7.0` - Visualization
+- `seaborn>=0.12.0` - Statistical plots
+- `pandas>=2.0.0` - Data processing
+
+**Note**: These dependencies are only needed for benchmarking workflows (metrics calculation and visualization), not for basic evaluation mode.
 
 ## Arguments
 
@@ -53,7 +61,7 @@ These dependencies are only needed for the evals and benchmarking workflows (met
 
 Export a configuration from the Guardrails Wizard UI and pass its path via `--config-path`.
 
-- Open the [Wizard UI](https://oaig-whisper-yonder-xnjpy2.vercel.app/guardrails)
+- Open the [Wizard UI](https://platform.openai.com/guardrails)
 - Configure the guardrails you want to evaluate
 - Use Export to download the config file (JSON)
 - Run the evaluator with `--config-path /path/to/exported_config.json`
@@ -190,4 +198,4 @@ python guardrail_evals.py \
 ## Next Steps
 
 - See the [API Reference](./ref/eval/guardrail_evals.md) for detailed documentation
-- Use [Wizard UI](https://oaig-whisper-yonder-xnjpy2.vercel.app/guardrails) for configuring guardrails without code
+- Use [Wizard UI](https://platform.openai.com/guardrails) for configuring guardrails without code

docs/examples.md

@@ -1,25 +1,25 @@
 # Examples
 
-Ready-to-run examples demonstrating Guardrails in various scenarios. See the [`guardrails/examples/`](https://github.com/OpenAI-Early-Access/guardrails/tree/main/guardrails/examples/) folder for complete implementations.
+Ready-to-run examples demonstrating Guardrails in various scenarios. See the [`guardrails/examples/`](https://github.com/openai/openai-guardrails-python/tree/main/examples/) folder for complete implementations.
 
 ## Example Implementations
 
-- [hello_world.py](https://github.com/OpenAI-Early-Access/guardrails/tree/main/guardrails/examples/basic/hello_world.py) — Basic pipeline configuration with input/output guardrails
-- [agents_sdk.py](https://github.com/OpenAI-Early-Access/guardrails/tree/main/guardrails/examples/basic/agents_sdk.py) — Integration with OpenAI Agents SDK
-- [pii_mask_example.py](https://github.com/OpenAI-Early-Access/guardrails/tree/main/guardrails/examples/basic/pii_mask_example.py) — PII detection and scrubbing
-- [structured_outputs_example.py](https://github.com/OpenAI-Early-Access/guardrails/tree/main/guardrails/examples/basic/structured_outputs_example.py) — Using responses.parse with guardrails
-- [Streaming (fast)](https://github.com/OpenAI-Early-Access/guardrails/tree/main/guardrails/examples/implementation_code/fast) — Stream output while guardrails run
-- [Blocking (slow)](https://github.com/OpenAI-Early-Access/guardrails/tree/main/guardrails/examples/implementation_code/slow) — Validate fully before showing output
+- [hello_world.py](https://github.com/openai/openai-guardrails-python/tree/main/examples/basic/hello_world.py) — Basic pipeline configuration with input/output guardrails
+- [agents_sdk.py](https://github.com/openai/openai-guardrails-python/tree/main/examples/basic/agents_sdk.py) — Integration with OpenAI Agents SDK
+- [pii_mask_example.py](https://github.com/openai/openai-guardrails-python/tree/main/examples/basic/pii_mask_example.py) — PII detection and scrubbing
+- [structured_outputs_example.py](https://github.com/openai/openai-guardrails-python/tree/main/examples/basic/structured_outputs_example.py) — Using responses.parse with guardrails
+- [Streaming](https://github.com/openai/openai-guardrails-python/tree/main/examples/implementation_code/streaming) — Stream output while guardrails run
+- [Blocking](https://github.com/openai/openai-guardrails-python/tree/main/examples/implementation_code/blocking) — Validate fully before showing output
 
 ## Hallucination Detection Example
 
 Complete implementation using real documents as knowledge sources:
-[`examples/hallucination_detection/`](https://github.com/OpenAI-Early-Access/guardrails/tree/main/guardrails/examples/hallucination_detection)
+[`examples/hallucination_detection/`](https://github.com/openai/openai-guardrails-python/tree/main/examples/hallucination_detection)
 
 ## Getting Started
 
 1. Follow the Quickstart guide: [Python](./quickstart.md)
-2. Explore repositories: [Python examples](https://github.com/OpenAI-Early-Access/guardrails/tree/main/guardrails/examples/)
+2. Explore repositories: [Python examples](https://github.com/openai/openai-guardrails-python/tree/main/examples/)
 3. Run scripts to see Guardrails in action
 
 Each example is self-contained with clear configuration and usage patterns.

docs/index.md

@@ -1,6 +1,6 @@
 # Guardrails
 
-**Guardrails** is a safety framework for LLM applications that automatically validates inputs and outputs using configurable checks. Use the [Guardrails Wizard](https://guardrails-vercel-git-main-openai.vercel.app/guardrails) to create configurations, then drop in our client classes for automatic validation.
+**Guardrails** is a safety framework for LLM applications that automatically validates inputs and outputs using configurable checks. Use the [Guardrails Wizard](https://platform.openai.com/guardrails) to create configurations, then drop in our client classes for automatic validation.
 
 ![Guardrails Wizard](assets/images/guardrails_wizard_screenshot.png)
 
@@ -42,7 +42,7 @@ print(response.llm_response.output_text)
 
 - [Quickstart](./quickstart.md) - Full quickstart guide
 - [Examples](./examples.md) - See real implementations
-- [Guardrails Wizard](https://guardrails-vercel-git-main-openai.vercel.app/guardrails) - Create configurations visually
+- [Guardrails Wizard](https://platform.openai.com/guardrails) - Create configurations visually
 
 ## Disclaimers
 

docs/quickstart.md

@@ -21,7 +21,7 @@ export OPENAI_API_KEY=sk-...
 
 ## Create Pipeline Configuration
 
-The fastest way is using the [Guardrails Wizard](https://guardrails-vercel-git-main-openai.vercel.app/guardrails) - a no-code tool for creating configurations.
+The fastest way is using the [Guardrails Wizard](https://platform.openai.com/guardrails) - a no-code tool for creating configurations.
 
 Or define manually:
 

docs/ref/checks/hallucination_detection.md

@@ -79,7 +79,7 @@ print(response.llm_response.output_text)
 
 ### Complete Example
 
-See [`examples/hallucination_detection/`](https://github.com/OpenAI-Early-Access/guardrails/tree/main/guardrails/examples/hallucination_detection) for the full implementation.
+See [`examples/hallucination_detection/`](https://github.com/openai/openai-guardrails-python/tree/main/examples/hallucination_detection) for the full implementation.
 
 ### Notes
 

docs/streaming_output.md

@@ -47,5 +47,5 @@ response = await client.responses.create(
 
 See complete examples:
 
-- [Non-streaming (safe)](https://github.com/OpenAI-Early-Access/guardrails/tree/main/guardrails/examples/implementation_code/slow)
-- [Streaming (fast)](https://github.com/OpenAI-Early-Access/guardrails/tree/main/guardrails/examples/implementation_code/fast)
+- [Non-streaming (blocking)](https://github.com/openai/openai-guardrails-python/tree/main/examples/implementation_code/blocking)
+- [Streaming](https://github.com/openai/openai-guardrails-python/tree/main/examples/implementation_code/streaming)

examples/implementation_code/slow/slow_agents.py renamed to examples/implementation_code/blocking/blocking_agents.py

@@ -1,4 +1,4 @@
-"""Minimal non-streaming implementation with guardrails using the new GuardrailsClient."""
+"""Minimal non-streaming (blocking) implementation with guardrails using the new GuardrailsClient."""
 
 # Please integrate openai-guardrails into my LLM calls.