langchainrb

langchainrb copied to clipboard

**Describe the solution you'd like** We could suport latest pinecone major release 1.0 to support new V2 API. For the moment it seems to work with 1.0 `client = Langchain::Vectorsearch::Pinecone.new(environment:...

night91

# Description This PR is the first prototype based on discussion #629. The purpose is to make it possible to use ChatMessage instead of raw Hash for chat messages, and...

kokuyouwind

WIP: Improve LLM model tool annotation

1

WIP: Overload the `Module` class Evaluate using https://github.com/kieranklaassen/tool_tailor

andreibondarev

Support Ruby 3.0 again

3

Support using the gem with ruby 3.0, preventing users to stick with outdated gem versions due to their current Ruby version. Also, I've removed dependency to active support 7, as...

alvaromat

andreibondarev

Feat/groq

3

Hi @andreibondarev, Here you could find a PoC of using Groq Cloud: https://console.groq.com/login for inference. Also because Groq does not support (yet?) embbedding. i give it the ability to pass...

bricesanchez

Remove check support assistant message

1

Because when we use other message type, but check support LLM, so someone can not implement other llm. If someboy use not exist message, will raise error default. ``` Langchain::Messages::XXMessage...

tianlu1677

Hi. First of all thanks for all your work. I've seen [ruby 3 is not supported because it's reached EOL](https://github.com/patterns-ai-core/langchainrb/commit/4a4d98e9ead56611714fa3fdc083accefe11842d). We are still using ruby 3.0. I acknowledge we need...

alvaromat

khaile

Preparation for opening the Assistant to accept custom LLM

2

* Removed references to the private method in the Assistant’s specs * Use the LLM adapter in the Assistant instance whenever possible, instead of calling LLM directly

qarol