Add Slack PDF Summarizer Bot

slack-pdf-summarizer/.env.example

@@ -0,0 +1,13 @@
+# Slack Bot credentials (from https://api.slack.com/apps)
+SLACK_BOT_TOKEN=xoxb-your-bot-token
+SLACK_SIGNING_SECRET=your-signing-secret
+SLACK_APP_TOKEN=xapp-your-app-level-token
+
+# OpenAI API key (from https://platform.openai.com/api-keys)
+OPENAI_API_KEY=sk-your-openai-api-key
+
+# Optional: OpenAI model to use (defaults to gpt-4o)
+OPENAI_MODEL=gpt-4o
+
+# Optional: port for the Slack app (defaults to 3000)
+PORT=3000

slack-pdf-summarizer/.gitignore

@@ -0,0 +1,2 @@
+node_modules/
+.env

slack-pdf-summarizer/README.md

@@ -0,0 +1,89 @@
+# Slack PDF Summarizer
+
+A Slack bot that automatically detects when a PDF is shared in a channel and replies in a thread with a concise bullet-point summary of the document's key insights.
+
+## How it works
+
+1. A user drops a PDF into any channel the bot is a member of.
+2. The bot detects the PDF attachment, downloads it, and extracts the text.
+3. The extracted text is sent to OpenAI (GPT-4o by default) with a prompt that produces 3–7 bullet points of key insights.
+4. The summary is posted as a threaded reply on the original message.
+
+## Prerequisites
+
+- **Node.js** 18+ (uses native `fetch`)
+- A **Slack App** with Socket Mode enabled
+- An **OpenAI API key**
+
+## Slack App Setup
+
+1. Go to [api.slack.com/apps](https://api.slack.com/apps) and click **Create New App → From scratch**.
+2. Under **Socket Mode**, enable it and generate an **App-Level Token** with the `connections:write` scope. Save this as `SLACK_APP_TOKEN`.
+3. Under **OAuth & Permissions**, add these **Bot Token Scopes**:
+   - `channels:history` — read messages in public channels
+   - `groups:history` — read messages in private channels
+   - `im:history` — read direct messages
+   - `chat:write` — post summary replies
+   - `files:read` — download shared PDF files
+4. Under **Event Subscriptions**, enable events and subscribe to these **bot events**:
+   - `message.channels`
+   - `message.groups`
+   - `message.im`
+5. Install the app to your workspace. Copy the **Bot User OAuth Token** (`xoxb-…`) as `SLACK_BOT_TOKEN`.
+6. Copy the **Signing Secret** from **Basic Information** as `SLACK_SIGNING_SECRET`.
+7. Invite the bot to any channels where you want automatic PDF summarization (`/invite @YourBotName`).
+
+## Installation
+
+```bash
+cd slack-pdf-summarizer
+npm install
+```
+
+## Configuration
+
+Copy the example env file and fill in your credentials:
+
+```bash
+cp .env.example .env
+```
+
+| Variable | Required | Description |
+|---|---|---|
+| `SLACK_BOT_TOKEN` | Yes | Bot User OAuth Token (`xoxb-…`) |
+| `SLACK_SIGNING_SECRET` | Yes | Signing secret from app Basic Information |
+| `SLACK_APP_TOKEN` | Yes | App-Level Token (`xapp-…`) for Socket Mode |
+| `OPENAI_API_KEY` | Yes | OpenAI API key |
+| `OPENAI_MODEL` | No | Model to use (default: `gpt-4o`) |
+| `PORT` | No | Server port (default: `3000`) |
+
+## Running
+
+```bash
+# Load env vars and start the bot
+node -r dotenv/config src/app.js
+
+# Or if you set env vars another way:
+npm start
+```
+
+For development with auto-reload:
+
+```bash
+npm run dev
+```
+
+## Architecture
+
+```
+src/
+├── app.js              # Slack Bolt app — listens for messages with PDFs
+├── pdf-extractor.js    # Extracts text from PDF buffers via pdf-parse
+└── summarizer.js       # Sends extracted text to OpenAI for summarization
+```
+
+## Notes
+
+- **Image-based PDFs** (scanned documents without OCR) will not produce usable text. The bot will report that it could not extract meaningful content.
+- Very large PDFs are truncated to ~100 000 characters before summarization to stay within model context limits.
+- The bot processes multiple PDFs in a single message concurrently.