Merge branch 'develop' of https://github.com/Gurubase/gurubase into t…

…ask/discord-slack-bots

.github/workflows/link-checker.yml

@@ -0,0 +1,25 @@
+name: Documentation
+
+on:
+  push:
+    branches:
+      - master
+      - develop
+  pull_request:
+    branches:
+      - master
+      - develop
+
+jobs:
+  link-checker:
+    name: Check links
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout the repository
+        uses: actions/checkout@v4
+
+      - name: Check the links
+        uses: lycheeverse/lychee-action@v1
+        with:
+          args: --max-concurrency 1 -v *.md **/*.md
+          fail: true

.lycheeignore

@@ -0,0 +1,3 @@
+http://localhost:8029/
+https://platform.openai.com/api-keys
+https://mastodon.social/@gurubaseio

README.md

@@ -15,7 +15,7 @@
 [![Twitter](https://img.shields.io/badge/Twitter-%231DA1F2.svg?logo=x&logoColor=white)](https://twitter.com/gurubaseio)
 [![Mastodon](https://img.shields.io/badge/Mastodon-%236364FF.svg?logo=mastodon&logoColor=white)](https://mastodon.social/@gurubaseio)
 [![Bluesky](https://img.shields.io/badge/Bluesky-%230285FF.svg?logo=bluesky&logoColor=white)](https://bsky.app/profile/gurubase.bsky.social)
-[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://github.com/Gurubase/gurubase/blob/main/LICENSE)
+[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://github.com/Gurubase/gurubase/blob/master/LICENSE)
 </div>
 
 - [What is Gurubase](#what-is-gurubase)

src/gurubase-backend/ARCHITECTURE.md

@@ -6,7 +6,7 @@ Gurubase is a scalable RAG (Retrieval Augmented Generation) system built to prov
 
 ## System Components
 
-![Gurubase Architecture](architecture.png)
+![Gurubase Architecture](imgs/architecture.png)
 
 ### Frontend (Next.js)
 - Built with Next.js
@@ -195,7 +195,7 @@ The task is run in three stages:
 
 An example of the summarization process looks like this:
 
-![Data Source Summarization](ds-summarization.png)
+![Data Source Summarization](imgs/ds-summarization.png)
 
 In this example, the red summarizations are the initial summarizations, and the blue summarizations are the recursive summarizations. And summarization 11 is the final summarization of the whole guru type. While the first stage creates summarizations 1-6, the second stage creates summarizations 7 and 8, and the third stage creates summarizations 9-11.
 
@@ -295,7 +295,7 @@ For any questions related to date, remember today's date is {date}.
 
 #### 2. Context Retrieval
 
-![Context Retrieval](context-retrieval.png)
+![Context Retrieval](imgs/context-retrieval.png)
 
 The `vector_db_fetch` function in `backend/core/utils.py` is responsible for context retrieval. It happens in multiple stages:
 

src/gurubase-backend/INTEGRATION_README.md

@@ -77,7 +77,7 @@
     - `${backend_url}/slack/events`
 8. Go to Intergrations and add this as Redirect URL:
     - `${frontend_url}/OAuth`
-9. Add these as Bot and User Token scopes:
+9. Go to OAuth & Permissions and add these as Bot and User Token scopes:
     - Bot
         - `channels:history`
         - `channels.join`
@@ -87,7 +87,7 @@
         - `groups:read`
         - `im:history`
         - `im:read`
-        - `npim:read`
+        - `mpim:read`
     - User
         - `channels:history`
         - `channels:read`
@@ -99,7 +99,7 @@
 11. Enable it
 12. Set this as request url:
     - `${backend_url}/slack/events`
-13. Add these as Subscribe to bot events:
+13. Go to Event Subscriptions and add these as Subscribe to bot events:
     - message.channels
 14. Go to Manage Distribution
 15. Click and confirm "Remove Hard Coded Information"

src/gurubase-backend/backend/backend/settings.py

@@ -28,11 +28,13 @@
 ROOT_PASSWORD = config('ROOT_PASSWORD', default='ChangeMe')
 
 SENTRY_ENABLED = config('SENTRY_ENABLED', default=False, cast=bool)
-if SENTRY_ENABLED:
+
+if SENTRY_ENABLED or ENV == "selfhosted":
     import sentry_sdk
     from sentry_sdk.integrations.celery import CeleryIntegration
-    from sentry_sdk.integrations.django import DjangoIntegration
-    SENTRY_DSN = config('SENTRY_DSN')
+    from sentry_sdk.integrations.django import DjangoIntegration    
+    # Use the configured DSN or fallback to selfhosted DSN - https://sentry.zendesk.com/hc/en-us/articles/26741783759899-My-DSN-key-is-publicly-visible-is-this-a-security-vulnerability
+    SENTRY_DSN = config('SENTRY_DSN', default="https://[email protected]/4508715634982912")
     sentry_sdk.init(
         dsn=SENTRY_DSN,
         integrations=[DjangoIntegration(), CeleryIntegration(monitor_beat_tasks=False)],
@@ -411,7 +413,7 @@
 
 SLACK_CLIENT_ID = config('SLACK_CLIENT_ID', default='')
 SLACK_CLIENT_SECRET = config('SLACK_CLIENT_SECRET', default='')
-PROD_BACKEND_URL = config('PROD_BACKEND_URL', default='https://kubernetesguru-backend-api.getanteon.com')
+PROD_BACKEND_URL = config('PROD_BACKEND_URL', default='https://api.gurubase.io')
 
 
 API_CONCURRENCY_THROTTLE_RATE = config('API_CONCURRENCY_THROTTLE_RATE', default='10/m')

src/gurubase-backend/backend/core/auth.py

@@ -190,7 +190,7 @@ def wrapper(request, *args, **kwargs):
         if widget_id_obj.domain_url:
             origin = request.headers.get('Origin')
             if not origin or not origin.rstrip('/').endswith(widget_id_obj.domain_url):
-                return Response({'msg': 'Invalid domain'}, status=status.HTTP_401_UNAUTHORIZED)
+                return Response({'msg': 'Invalid domain. Please check your domain URL in Gurubase platform'}, status=status.HTTP_401_UNAUTHORIZED)
 
         request.guru_type = widget_id_obj.guru_type
         return view_func(request, *args, **kwargs)

src/gurubase-backend/backend/core/migrations/0029_merge_20250126_1945.py

@@ -0,0 +1,14 @@
+# Generated by Django 4.2.18 on 2025-01-26 19:45
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('core', '0022_merge_0021_apikey_name_0021_merge_20250120_0950'),
+        ('core', '0028_alter_integration_unique_together'),
+    ]
+
+    operations = [
+    ]

src/gurubase-frontend/src/components/Integrations/IntegrationContent.jsx

@@ -62,7 +62,7 @@ const IntegrationContent = ({ type, customGuru, error }) => {
       description:
         "By connecting your account, you can easily share all your posts and invite your friends.",
       iconSize: "w-5 h-5",
-      url: `https://slack.com/oauth/v2/authorize?client_id=8327841447732.8318709976774&scope=app_mentions:read,channels:history,channels:join,channels:read,chat:write,groups:history,groups:read,groups:write,im:history,im:read,im:write,mpim:read,mpim:write,channels:manage&user_scope=channels:history,channels:read,chat:write,groups:history,groups:read,im:history,channels:write,groups:write,mpim:write,im:write`,
+      url: `https://slack.com/oauth/v2/authorize?client_id=1269209097589.8354424793156&scope=assistant:write,channels:history,channels:join,channels:read,chat:write,groups:history,groups:read,im:history,im:read,mpim:read&user_scope=channels:history,channels:read,chat:write,groups:history,groups:read,im:history`,
       icon: SlackIcon
     },
     discord: {