feat: allowing frontend to use a separate server for backend

ucbepic · Dec 22, 2024 · e3ef30d · e3ef30d
1 parent 3dba91b
commit e3ef30d
Showing 1 changed file with 17 additions and 5 deletions.
diff --git a/docs/playground/index.md b/docs/playground/index.md
@@ -12,6 +12,14 @@ Building complex LLM pipelines for your data often requires experimentation and
 - ✨ Refine operations based on sample outputs  
 - 🔄 Build complex pipelines step-by-step
 
+## Public Playground
+
+You can access our hosted playground at [docetl.org/playground](https://docetl.org/playground). You'll need to provide your own LLM API keys to use the service. The chatbot and prompt engineering assistants are powered by OpenAI models, so you'll need to provide an OpenAI API key.
+
+!!! note "Data Storage Notice"
+
+    As this is a research project, we cache results and store data on our servers to improve the system. While we will never sell or release your data, if you have privacy concerns, we recommend running the playground locally using the installation instructions below.
+
 ## Installation
 
 There are two ways to run the playground:
@@ -24,7 +32,9 @@ The easiest way to get started is using Docker:
 
 Create `.env` in the root directory (for the FastAPI backend):
 ```bash
-OPENAI_API_KEY=your_api_key_here # Or your LLM provider's API key
+# Required: API key for your preferred LLM provider (OpenAI, Anthropic, etc)
+# The key format will depend on your chosen provider (sk-..., anthro-...)
+OPENAI_API_KEY=your_api_key_here 
 BACKEND_ALLOW_ORIGINS=
 BACKEND_HOST=localhost
 BACKEND_PORT=8000
@@ -35,9 +45,11 @@ FRONTEND_PORT=3000
 
 Create `.env.local` in the `website` directory (for the frontend) **note that this must be in the `website` directory**:
 ```bash
-OPENAI_API_KEY=sk-xxx # For the AI assistant in the interface
-OPENAI_API_BASE=https://api.openai.com/v1 # For the AI assistant in the interface
-MODEL_NAME=gpt-4o-mini # For the AI assistant in the interface
+# Optional: These are only needed if you want to use the AI assistant chatbot 
+# and prompt engineering tools. Must be OpenAI API keys specifically.
+OPENAI_API_KEY=sk-xxx
+OPENAI_API_BASE=https://api.openai.com/v1
+MODEL_NAME=gpt-4o-mini
 
 NEXT_PUBLIC_BACKEND_HOST=localhost
 NEXT_PUBLIC_BACKEND_PORT=8000
@@ -72,7 +84,7 @@ cd docetl
 
 2. Set up environment variables in `.env` in the root directory:
 ```bash
-OPENAI_API_KEY=your_api_key_here
+LLM_API_KEY=your_api_key_here
 BACKEND_ALLOW_ORIGINS=
 BACKEND_HOST=localhost
 BACKEND_PORT=8000