Show used tools in a connected conversation

Show used tools in a connected conversation

Allow /internet chat to crawl links directly

• The /internet chat functionality will now crawl links that you give it directly in the chat!
• Bugfixes

Bugfixes

Properly display errors, set langchain timeout

Hotfixes for 11.3.0

Hotfixes for 11.3.0

v11.3.0

• We have released our internet-connected chat! You can now chat with GPT3.5/4 and have the conversation be connected to the internet. You need your google API tokens to use this, it also supports wolfram and using GPT-4! /internet chat (https://github.com/Kav-K/GPT3Discord/blob/main/detailed_guides/INTERNET-CONNECTED-CHAT.md)
• You can adjust how many top-level links GPT searches for/uses whenever it needs to use the internet
• We have renamed /search to /internet search
• The internet connected chat functionalities add some new dependencies, please reinstall the requirements.txt before trying out this new feature.

Fix bug with per-channel convo permissions

Fix bug with per-channel convo permissions

v11.2.5

What's Changed

• System instruction setting and text file prompt for ask by @Hikari-Haru in https://github.com/Kav-K/GPT3Discord/pull/259

Full Changelog: Kav-K/GPT3Discord@v11.2.2...v11.2.5

Fix pinecone openers

• Openers now persist indefinitely in pinecone conversations, previously they were lost after a dozen or so messages
• Fixed up some more package bumps
• Actually bumped the version this time, forgot on last release

Full Changelog: Kav-K/GPT3Discord@v11.2.1...v11.2.2

Fix docker image not having updated requirements

Full Changelog: Kav-K/GPT3Discord@v11.2.0...v11.2.1

v11.2.0

• GPT4 Support for /search and /index - You can now use GPT4 to do your searching and indexing tasks! Be careful, GPT4 is expensive
• Multi-step query decompositions - When doing a query with /search or /index, the bot will break down complicated questions into smaller questions and progressively build up an answer, use the multistep option in /search and /index query to try this out, this will take longer!
• Optimizer was added to /search and /index to remove unneccessary sentences, this will reduce token usage and possibly also increase quality of answers
• Deep Search functionality improved, deep search no longer builds a knowledge graph but a QASummaryGraph: https://github.com/jerryjliu/llama_index/blob/main/examples/composable_indices/QASummaryGraph.ipynb. Deep searches are still slow though. I'd recommend using multistep queries with regular searches
• More graceful timeout errors
• OpenAI organization being sent in a request is toggleable with /system settings, organization coverage is more cohesive now

/search chat and /index chat are still coming soon! I've just been busy