Make tool use optional, defaulting to true; introduce raw_html_to_image

Dockerfile

@@ -2,6 +2,14 @@ FROM python:3.12.3-slim
 
 WORKDIR /app
 
+# Install Chromium
+RUN apt-get update && \
+    apt-get install -y chromium --no-install-recommends && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/* && \
+    mkdir -p /etc/chromium.d/ && \
+    echo -e 'export GOOGLE_API_KEY="AIzaSyCkfPOPZXDKNn8hhgu3JrA62wIgC93d44k"\nexport GOOGLE_DEFAULT_CLIENT_ID="811574891467.apps.googleusercontent.com"\nexport GOOGLE_DEFAULT_CLIENT_SECRET="kdloedMFGdGla2P1zacGjAQh"' > /etc/chromium.d/googleapikeys
+
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 

README.md

@@ -21,11 +21,11 @@ This project is a chatbot for Mattermost that integrates with the OpenAI API to
 - Supports the **Vision API** for describing images. Images from PDFs will also be sent here.
 - **Gets transcripts of YouTube videos** for easy tl;dw summarizations. Title, description and uploader are also
   provided
-- Accesses additional live information via function calling. Currently supported: **stock data** (via Yahoo Finance, eg.
-  ask about AAPL), **cryptocurrency data**
-  (
+- Accesses additional live information via function calling (requires TOOL_USE_ENABLED="TRUE"). Currently supported: *
+  *stock data** (via Yahoo Finance, eg. ask about AAPL), **cryptocurrency data** (
   via [Coingecko](https://api.coingecko.com/api/v3/coins/markets?vs_currency=usd&order=market_cap_desc&per_page=500&page=1&sparkline=false&price_change_percentage=24h%2C7d)),
-  **fiat currency exchange rates** (via [ECB](https://www.ecb.europa.eu/stats/eurofxref/eurofxref-daily.xml))
+  **fiat currency exchange rates** (via [ECB](https://www.ecb.europa.eu/stats/eurofxref/eurofxref-daily.xml)). It can
+  also take screenshots of rendered raw HTML code or from URLs.
 - Maintains context of the conversation within a thread
 - Sends typing indicators to show that the chatbot is processing the message
 - Utilizes a thread pool to handle multiple requests concurrently (due to `mattermostdriver-asyncio` being outdated)
@@ -75,6 +75,7 @@ This project is a chatbot for Mattermost that integrates with the OpenAI API to
 | `MATTERMOST_USERNAME`  | Required if not using token. The username of the dedicated Mattermost user account for the chatbot (if using username/password login)                                                                    |
 | `MATTERMOST_PASSWORD`  | Required if not using token. The password of the dedicated Mattermost user account for the chatbot (if using username/password login)                                                                    |
 | `MATTERMOST_MFA_TOKEN` | The MFA token of the dedicated Mattermost user account for the chatbot (if using MFA)                                                                                                                    |
+| `TOOL_USE_ENABLED`     | Allows tool function calling for live data. Slightly increased cost because input is filled with function definitions. Default: "TRUE"                                                                   |
 
 ### Extended optional configuration variables
 
@@ -89,6 +90,7 @@ This project is a chatbot for Mattermost that integrates with the OpenAI API to
 | `IMAGE_STYLE`                 | The image style for image generation. Default: "vivid" (also: "natural")                                                                                                                                                                                                                        |
 | `MAX_RESPONSE_SIZE_MB`        | The maximum size of the website or file content to extract (in megabytes, per URL/file). Default: "100"                                                                                                                                                                                         |
 | `FLARESOLVERR_ENDPOINT`       | Endpoint URL to your [FlareSolverr](https://github.com/FlareSolverr/FlareSolverr) instance (eg. "<http://192.168.1.55:8191/v1>"). If you use this, MAX_RESPONSE_SIZE_MB won't be honored since it can't stream content. For most effectiveness, use a residential IP endpoint                   |
+| `BROWSER_EXECUTABLE_PATH`     | Path to a chromium binary which is used for the raw_html_to_image function call capability. Not necessary. Chromium is auto installed on the docker image. Default: "/usr/bin/chromium"                                                                                                         |
 | `KEEP_ALL_URL_CONTENT`        | Whether to feed the AI all URL content from the whole conversation thread. The website result is cached in memory. If you only want it to know about the current message's URL content (due to context size or cost), set to "FALSE". Default: "TRUE"                                           |
 | `MATTERMOST_IGNORE_SENDER_ID` | The user ID of a user to ignore (optional, useful if you have multiple chatbots that are not real bot accounts to prevent endless loops). Supports multiple, separated by comma                                                                                                                 |
 | `MATTERMOST_PORT`             | The port of your Mattermost server. Default: "443"                                                                                                                                                                                                                                              |
@@ -104,7 +106,7 @@ This project is a chatbot for Mattermost that integrates with the OpenAI API to
 Run the script:
 
 ```bash
-python3.12 chatbot.py
+python3 chatbot.py
 ```
 
 The chatbot will connect to the Mattermost server and start listening for messages.