Go to file
Roman Rizzi 4f1a3effe0
REFACTOR: Migrate Vllm/TGI-served models to the OpenAI format. (#588)
Both endpoints provide OpenAI-compatible servers. The only difference is that Vllm doesn't support passing tools as a separate parameter. Even if the tool param is supported, it ultimately relies on the model's ability to handle native functions, which is not the case with the models we have today.

As a part of this change, we are dropping support for StableBeluga/Llama2 models. They don't have a chat_template, meaning the new API can translate them.

These changes let us remove some of our existing dialects and are a first step in our plan to support any LLM by defining them as data-driven concepts.

 I rewrote the "translate" method to use a template method and extracted the tool support strategies into its classes to simplify the code.

Finally, these changes bring support for Ollama when running in dev mode. It only works with Mistral for now, but it will change soon..
2024-05-07 10:02:16 -03:00
.github/workflows Initial commit 2023-02-17 11:33:47 -03:00
admin/assets/javascripts/discourse DEV: Moving around admin persona config routes again (#586) 2024-05-02 12:42:30 +10:00
app REFACTOR: Migrate Vllm/TGI-served models to the OpenAI format. (#588) 2024-05-07 10:02:16 -03:00
assets FIX: uploader not removing app event (#601) 2024-05-06 14:42:55 +10:00
config REFACTOR: Migrate Vllm/TGI-served models to the OpenAI format. (#588) 2024-05-07 10:02:16 -03:00
db FEATURE: support Chat with AI Persona via a DM (#488) 2024-05-06 09:49:02 +10:00
discourse_automation FEATURE: Mixtral/Mistral/Haiku Automation Support (#571) 2024-04-11 09:50:46 -03:00
lib REFACTOR: Migrate Vllm/TGI-served models to the OpenAI format. (#588) 2024-05-07 10:02:16 -03:00
public/ai-share UX: prevent social share content from overflowing container (#597) 2024-04-30 09:47:21 -04:00
spec REFACTOR: Migrate Vllm/TGI-served models to the OpenAI format. (#588) 2024-05-07 10:02:16 -03:00
test/javascripts FEATURE: support Chat with AI Persona via a DM (#488) 2024-05-06 09:49:02 +10:00
tokenizers FEATURE: Add BGE-M3 embeddings support (#569) 2024-04-10 17:24:01 -03:00
.discourse-compatibility DEV: Lower pinned version to fix unsupported API error on stable (#514) 2024-03-07 14:30:05 +00:00
.eslintrc.cjs DEV: Update linting configs (#280) 2023-11-03 11:30:09 +00:00
.gitignore Initial commit 2023-02-17 11:33:47 -03:00
.prettierignore FEATURE: UI to update ai personas on admin page (#290) 2023-11-21 16:56:43 +11:00
.prettierrc.cjs DEV: Update linting configs (#280) 2023-11-03 11:30:09 +00:00
.rubocop.yml DEV: Update linting configs (#280) 2023-11-03 11:30:09 +00:00
.streerc DEV: Update linting configs (#280) 2023-11-03 11:30:09 +00:00
.template-lintrc.cjs DEV: Update linting (#326) 2023-11-29 23:01:48 +01:00
Gemfile DEV: Update linting configs (#280) 2023-11-03 11:30:09 +00:00
Gemfile.lock DEV: Fix new Rubocop offenses 2024-03-06 15:23:29 +01:00
LICENSE Initial commit 2023-02-17 11:33:47 -03:00
README.md CHORE: Update Readme (#185) 2023-09-04 15:46:35 -03:00
package.json DEV: Update linting (#423) 2024-01-13 00:28:06 +01:00
plugin.rb REFACTOR: Simplify tool invocation by removing bot_user and llm parameters (#603) 2024-05-07 21:55:46 +10:00
translator.yml UX: Display the indexing progress for RAG uploads (#557) 2024-04-09 11:03:07 -03:00
yarn.lock DEV: Update linting (#423) 2024-01-13 00:28:06 +01:00

README.md

Discourse AI Plugin

Plugin Summary

For more information, please see: https://meta.discourse.org/t/discourse-ai/259214?u=falco