v2.2.0

Introducing the API_URL variable! 🚀

• Now route chatbot requests to custom API endpoints.
• Just set the API_URL environment variable and you're good to go.

Upgrade today and enjoy the added flexibility!

Changes

• API_URL variable added by @justinh-rahb in #41

Full Changelog: v2.1.2...v2.2.0

v2.1.2

What's Changed

• Update main.py by @justinh-rahb

Full Changelog: v2.1.1...v2.1.2

v2.1.1

What's Changed

• Update main.py by @justinh-rahb in #40

Full Changelog: v2.1.0...v2.1.1

v2.1.0

🚀 Welcome to Version 2.1! 🚀

We're ecstatic to present version 2.1. With this update, we're ushering in a series of important enhancements that will elevate your chatbot experience!

What's New

• Content Moderation: Keeping our platform safe and user-friendly is a top priority. With the new content moderation feature, inappropriate messages will be flagged, ensuring a wholesome experience for all.
• Max Token Limit: We're optimizing interactions by introducing a max token output limit, making sure responses are concise and relevant.

Changes

• Added Moderation & Enhanced Output Limitations by @justinh-rahb in #39

Full Changelog: v2.0.0...v2.1.0

v2.0.0

🚀 Welcome to Version 2.0! 🚀

We are thrilled to introduce version 2.0, a significant update that brings the long-awaited integration with DALL-E for image generation!

What's New

🎨 DALL-E Integration: Users can now generate images directly in the chat! Use the /image command followed by your creative prompt to bring your ideas to life.

Changes

• GitHub Page by @justinh-rahb in #34
• Add DALL-E image generation by @justinh-rahb in #38

Full Changelog: v1.7.1...v2.0.0

v1.7.1

LLMs are lossy compression algorithms, never forget.

What's Changed

• Fix /reset regression by @justinh-rahb in #30

Full Changelog: v1.7.0...v1.7.1

v1.7.0

We've implemented token counting for each message the bot processes. This new feature prevents the bot from sending messages that are too large, which could potentially overload the system. If a message exceeds the token limit, the bot will respond with an error message asking the user to try a shorter message.

What's Changed

• Implement token count limit by @justinh-rahb in #24
• Fix tokenizer encoding by @justinh-rahb in #25
• Fix tokenizer function by @justinh-rahb in #26
• Count system and user prompt by @justinh-rahb in #27
• Fix tokenizer (again) by @justinh-rahb in #28
• Fix argument count by @justinh-rahb in #29

Full Changelog: v1.6.1...v1.7.0

v1.6.1

Send canned response after /reset instead of generating reply.

What's Changed

• Update main.py by @justinh-rahb in #20

Full Changelog: v1.6.0...v1.6.1

v1.6.0

What's Changed

• Add /reset command by @justinh-rahb in #19

Full Changelog: v1.5.0...v1.6.0

v1.5.0

What's Changed

• Repo infrastructure by @justinh-rahb in #12
• Update README.md by @justinh-rahb in #13
• Update gcp-deploy.yml by @justinh-rahb in #14
• Update gcp-deploy.yml by @justinh-rahb in #15
• Update repo meta by @justinh-rahb in #16
• Integrate simpleaichat for session-based chat functionality by @justinh-rahb in #17
• Enhance User Session Management with TTL Functionality by @justinh-rahb in #18

Full Changelog: v1.0.0...v1.2.0