Skip to content

Activity

Showing most recent first

Keep max tokens for local models but remove it for the hosted models.

patwpushed 1 commit to main • c064db0…2f77a9a • 
3 days ago

Removed the older gemini models and added the new family.

patwpushed 1 commit to main • 21db5ad…c064db0 • 
3 days ago

Added Sonnet 3.7

patwpushed 1 commit to main • 4bc0bd7…21db5ad • 
on Feb 24

Using fixed max_token limits. Removed ability to config output tokens…

patwpushed 1 commit to main • bad305b…4bc0bd7 • 
on Feb 8

Added deepseek-reasoner

patwpushed 1 commit to main • 68593c5…bad305b • 
on Jan 20

Added option for raw output, which is useful for cut/pasting markdown…

patwpushed 1 commit to main • 7f3dc22…68593c5 • 
on Dec 31, 2024

Fixed issue with chatpt model name and errors show up in history now.

patwpushed 1 commit to main • b129958…7f3dc22 • 
on Dec 26, 2024

Updated 4o to latest, removed old gpt4

patwpushed 1 commit to main • 1eb374d…b129958 • 
on Dec 26, 2024

Fixed haiku model version

patwpushed 1 commit to main • 2b3ac01…1eb374d • 
on Dec 26, 2024

Added Deepseek support, removed mistral-medium and added ministral se…

patwpushed 1 commit to main • 7e21af8…2b3ac01 • 
on Dec 26, 2024

Removed llama 3.1-70b for cerebras and replaced it with 3.3

patwpushed 1 commit to main • 3aaae92…7e21af8 • 
on Dec 12, 2024

Added Gemini Flash 2.0

patwpushed 1 commit to main • 7184b13…3aaae92 • 
on Dec 11, 2024

Added a session key to remove a bug with older installs

patwpushed 1 commit to main • a4e30ad…7184b13 • 
on Nov 29, 2024

Bottybot now uses the OAI endpoint for llama.cpp. Updated the default…

patwpushed 1 commit to main • f49f7b1…a4e30ad • 
on Nov 29, 2024

Updated code for o1 models to fix issue with system messages and temp…

patwpushed 1 commit to main • 7493a75…f49f7b1 • 
on Nov 20, 2024

Added Google Gemini models (finally)

patwpushed 1 commit to main • 88129cd…7493a75 • 
on Nov 10, 2024

Added Haiku 3.5

patwpushed 1 commit to main • 1702404…88129cd • 
on Nov 4, 2024

Updated sonnet to latest version

patwpushed 1 commit to main • 615ed2f…1702404 • 
on Oct 22, 2024

Added GPT o1 models. They don't work for me, but the name looks right.

patwpushed 1 commit to main • 34057dd…615ed2f • 
on Sep 13, 2024

Added cerebras and removed some obsolete models.

patwpushed 1 commit to main • ab99e9c…34057dd • 
on Aug 28, 2024

Pin the mistral API library version

patwpushed 1 commit to main • 5494a5b…ab99e9c • 
on Aug 12, 2024

Added GPT 4o-mini

patwpushed 1 commit to main • 5567389…5494a5b • 
on Jul 18, 2024

Added Sonnet 3.5

patwpushed 1 commit to main • a571b20…5567389 • 
on Jun 20, 2024

Updated all the mistral models

patwpushed 1 commit to main • b8cb9f9…a571b20 • 
on Jun 12, 2024

Issue with history order that was messing up the API

patwpushed 1 commit to main • 3a88f4e…b8cb9f9 • 
on Jun 11, 2024

LLM hallucinated a method

patwpushed 1 commit to main • b8c5dea…3a88f4e • 
on Jun 3, 2024

Changed to a POST instead of a GET. Prompts could get very long.

patwpushed 1 commit to main • 9716eec…b8c5dea • 
on Jun 3, 2024

Added API endpoint for calling any model through GET request. Fixed s…

patwpushed 1 commit to main • 983d550…9716eec • 
on Jun 3, 2024

Added gpt-4o and changed gpt4-turbo to regular version, not preview.

patwpushed 1 commit to main • 2117bde…983d550 • 
on May 17, 2024

Added sample templates for a few of the newer models. Plz god why can…

patwpushed 1 commit to main • fd65850…2117bde • 
on Apr 23, 2024