Remove old tsconfig, update readme

README.md

@@ -9,21 +9,22 @@
 
 <div align="center">
 
-  ## Rebuff.ai
-  
+## Rebuff.ai
+
   <img width="250" src="https://imgur.com/ishzqSK.png" alt="Rebuff Logo">
 
-  ### **Self-hardening prompt injection detector**
-  Rebuff is designed to protect AI applications from prompt injection (PI) attacks through a [multi-layered defense](#features).
+### **Self-hardening prompt injection detector**
+
+Rebuff is designed to protect AI applications from prompt injection (PI) attacks through a [multi-layered defense](#features).
 
-  [Playground](https://playground.rebuff.ai/) • 
-  [Discord](https://discord.gg/R3U2XVNKeE) •
-  [Features](#features) •
-  [Installation](#installation) •
-  [Getting started](#getting-started) •
-  [Self-hosting](#self-hosting) •
-  [Contributing](#contributing) •
-  [Docs](https://docs.rebuff.ai)
+[Playground](https://playground.rebuff.ai/) •
+[Discord](https://discord.gg/R3U2XVNKeE) •
+[Features](#features) •
+[Installation](#installation) •
+[Getting started](#getting-started) •
+[Self-hosting](#self-hosting) •
+[Contributing](#contributing) •
+[Docs](https://docs.rebuff.ai)
 
 </div>
 <div align="center">
@@ -32,15 +33,14 @@
 
 </div>
 
-
 ## Disclaimer
 
 Rebuff is still a prototype and **cannot provide 100% protection** against prompt injection attacks!
 
 ## Features
 
-
 Rebuff offers 4 layers of defense:
+
 - Heuristics: Filter out potentially malicious input before it reaches the LLM.
 - LLM-based detection: Use a dedicated LLM to analyze incoming prompts and identify potential attacks.
 - VectorDB: Store embeddings of previous attacks in a vector database to recognize and prevent similar attacks in the future.
@@ -66,6 +66,7 @@ pip install rebuff
 ## Getting started
 
 ### Detect prompt injection on user input
+
 ```python
 from rebuff import Rebuff
 
@@ -109,65 +110,66 @@ if is_leak_detected:
 
 ## Self-hosting
 
-To self-host Rebuff, you need to set up the necessary providers like Pinecone, 
+To self-host Rebuff, you need to set up the necessary providers like Pinecone,
 Supabase, and OpenAI. Follow the links below to set up each provider:
 
 - [Pinecone](https://www.pinecone.io/)
 - [Supabase](https://supabase.io/)
 - [OpenAI](https://beta.openai.com/signup/)
 
-Once you have set up the providers, you'll need to stand up the relevant SQL and 
-vector databases on Supabase and Pinecone respectively. See the 
+Once you have set up the providers, you'll need to stand up the relevant SQL and
+vector databases on Supabase and Pinecone respectively. See the
 [server README](server/README.md) for more information.
 
-Now you can start the Rebuff server using Docker. First, build the Docker image:
+Now you can start the Rebuff server using npm.
 
 ```bash
-docker build -t rebuff .
+cd server
+```
+
+In the server directory create an `.env.local` file and add the following environment variables:
+
+```
+OPENAI_API_KEY=<your_openai_api_key>
+MASTER_API_KEY=12345
+BILLING_RATE_INT_10K=<your_billing_rate_int_10k>
+MASTER_CREDIT_AMOUNT=<your_master_credit_amount>
+NEXT_PUBLIC_SUPABASE_ANON_KEY=<your_next_public_supabase_anon_key>
+NEXT_PUBLIC_SUPABASE_URL=<your_next_public_supabase_url>
+PINECONE_API_KEY=<your_pinecone_api_key>
+PINECONE_ENVIRONMENT=<your_pinecone_environment>
+PINECONE_INDEX_NAME=<your_pinecone_index_name>
+SUPABASE_SERVICE_KEY=<your_supabase_service_key>
+REBUFF_API=http://localhost:3000
 ```
 
-Then, start the Docker container with the below command, 
-replacing the placeholders with your actual API keys, environment variables, and 
-desired server configurations.
+Install packages and run the server with the following:
 
 ```bash
-docker run -d -p 3000:3000 \
-  -e OPENAI_API_KEY=<your_openai_api_key> \
-  -e MASTER_API_KEY=12345 \
-  -e BILLING_RATE_INT_10K=<your_billing_rate_int_10k> \
-  -e MASTER_CREDIT_AMOUNT=<your_master_credit_amount> \
-  -e NEXT_PUBLIC_SUPABASE_ANON_KEY=<your_next_public_supabase_anon_key> \
-  -e NEXT_PUBLIC_SUPABASE_URL=<your_next_public_supabase_url> \
-  -e PINECONE_API_KEY=<your_pinecone_api_key> \
-  -e PINECONE_ENVIRONMENT=<your_pinecone_environment> \
-  -e PINECONE_INDEX_NAME=<your_pinecone_index_name> \
-  -e SUPABASE_SERVICE_KEY=<your_supabase_service_key> \
-  -e REBUFF_API=http://localhost:3000 \
-  --name rebuff rebuff
+npm install
+npm run dev
 ```
 
 Now, the Rebuff server should be running at `http://localhost:3000`.
 
-
 ### Server Configurations
 
-* `BILLING_RATE_INT_10K`: The amount of credits that should be deducted for
-every request. The value is an integer, and 10k refers to a single dollar amount.
-So if you set the value to 10000 then it will deduct 1 dollar per request. If you set
-it to 1 then it will deduct 0.1 cents per request.
-
+- `BILLING_RATE_INT_10K`: The amount of credits that should be deducted for
+  every request. The value is an integer, and 10k refers to a single dollar amount.
+  So if you set the value to 10000 then it will deduct 1 dollar per request. If you set
+  it to 1 then it will deduct 0.1 cents per request.
 
 ## How it works
-![Sequence Diagram](https://github.com/woop/rebuff/assets/6728866/3d90ebb3-d149-42e8-b991-a46c46d5a9e7)
 
+![Sequence Diagram](https://github.com/woop/rebuff/assets/6728866/3d90ebb3-d149-42e8-b991-a46c46d5a9e7)
 
 ## Contributing
 
 We'd love for you to join our community and help improve Rebuff! Here's how you can get involved:
 
 1. Star the project to show your support!
 2. Contribute to the open source project by submitting issues, improvements, or adding new features.
-3. Join our [Discord server](https://discord.gg/R3U2XVNKeE). 
+3. Join our [Discord server](https://discord.gg/R3U2XVNKeE).
 
 ## Development