support env var for anthropic keys

Author: Onurbon

README.md

@@ -15,6 +15,13 @@ export OPENAI_API_KEY=sk-something-something
 export OPENAI_API_KEY_PASSWORD=some-password
 ```
 
+Likewise for Claude:
+
+```
+export ANTHROPIC_API_KEY=sk-something-something
+export ANTHROPIC_API_KEY_PASSWORD=some-password
+```
+
 If a team member has already set up a Google Cloud Storage project, add the keys for that project to the same `.env` file. Otheriwse,
 see the "Setting up a Google Cloud instance" section for how to set up a project.
 
@@ -71,33 +78,33 @@ export type SourceRow = {
   timestamp?: string; // timestamp in the video
 };
 ```
+
 ## Provided client
 
 Open `localhost:8080/` to see the example of client provided.
 The client is written in plain html/css/js in the `public` folder.
 
-
 ## Setting up a Google Cloud instance
 
 ### Set up Google Cloud storage & services
 
 First create a new storage bucket:
+
 - Create a Google Cloud project and a Google Cloud Storage bucket
 - Add `GCLOUD_STORAGE_BUCKET=name-of-your-bucket` to your `.env`
 - Make sure this bucket has public access so that anyone can read from it (to
-make your reports accessible from your browser):
-    - Turn off the "Prevent public access" protect
-    - In the "Permissions" tab, click "Grant access." Add the principal `allUsers`
-      and assign the role `Storage Object User`.
+  make your reports accessible from your browser): - Turn off the "Prevent public access" protect - In the "Permissions" tab, click "Grant access." Add the principal `allUsers`
+  and assign the role `Storage Object User`.
 
 Then create a service account for this bucket:
+
 - In the "IAM & Admin" view, select "Service Accounts" from the left menu, and
   then click "Create service account"
 - Give this account the "Editor" role
 - Create keys for this account and download them as a json file:
-    - Save this file as `./google-credentials.json`
-    - Encode this using by running the command `base64 -i ./google-credentials.json`
-    - Put this in a variable `GOOGLE_CREDENTIALS_ENCODED` in your `.env`
+  - Save this file as `./google-credentials.json`
+  - Encode this using by running the command `base64 -i ./google-credentials.json`
+  - Put this in a variable `GOOGLE_CREDENTIALS_ENCODED` in your `.env`
 
 Your .env file should now look like this:
 
@@ -134,13 +141,13 @@ Note: the first deploy with fail if you haven't set the .env variables as descri
 Your cloud instance is now ready to use!
 
 To upload a new image (e.g. after a fresh git pull), deploy a new docker image to the same instance:
+
 - Run `./bin/docker-build-gcloud.sh`
 - Open the google console and search for gloud cloud run
 - Find your project and the `tttc-light-js` app
 - Click "EDIT AND DEPLOY NEW VERSION"
 - Find the new docker image that you just pushed from the list of available images
 
-
 ## Using docker locally (not recommended)
 
 There should be no need to use docker for local development, except when working on the Dockerfile or testing something docker-related, in which case you might want to use these scripts:

src/server.ts

@@ -33,12 +33,15 @@ app.post("/generate", async (req, res) => {
       throw new Error("Missing data");
     }
     config.data = formatData(config.data);
+    // allow users to use our keys if they provided the password
     if (config.apiKey === process.env.OPENAI_API_KEY_PASSWORD) {
-      // allow users to use our keys if they provided the password
       config.apiKey = process.env.OPENAI_API_KEY!;
+    } else if (config.apiKey === process.env.ANTHROPIC_API_KEY_PASSWORD) {
+      config.apiKey = process.env.ANTHROPIC_API_KEY!;
     }
+
     if (!config.apiKey) {
-      throw new Error("Missing OpenAI API key");
+      throw new Error("Missing API key");
     }
     config.filename = config.filename || uniqueSlug(config.title);
     const url = getUrl(config.filename);