Abraxas-365 / Abraxas-365/langchain-rust

Add Groq LLM integration (or ability to create custom LLM models)

Aberta
#239 2 comentários 0 reações 0 responsáveis Ver no GitHub
Linguagem predominante
Rust
Estrelas
1.3k
Forks
177
Métricas de merge de PRs
Nenhum PR com merge em 30d

Descrição

**Is your feature request related to a problem? Please describe.**
I have used the python Langchain library in a previous project for a Django backend. Now Im working on a new project that uses Tauri and its rust backend so naturally i was looking for implementation for Langchain in rust. In python I started using the [Groq chat model](https://python.langchain.com/api_reference/groq/chat_models/langchain_groq.chat_models.ChatGroq.html), I really liked its simple price model and fast inference so naturally i would want to use it in this project as well but currently there is no support for this.

**Describe the solution you'd like**
I would like an integration for the llm Groq model for langchain-rust like OpenAI,Claude and Ollama is supported. Currently there are some unnoffical sdk for Groq like [groq-api-rust](https://crates.io/crates/groq-api-rust) or [groq-rust](https://crates.io/crates/groq-rust)

**Describe alternatives you've considered**
The other alternative and more scalable solution for similar issues would be the ability to create a custom chat model similarly to how the python SDK works by wrapping the llm with the BaseChatModel.

https://python.langchain.com/docs/how_to/custom_chat_model/

Guia de contribuição

Abrir o guia de contribuição

Direção de pesquisa

Look at existing LLM integrations like OpenAI and Ollama in the langchain-rust codebase, likely in a directory like `langchain-rust/src/llm/`. Review the unofficial Groq Rust SDKs mentioned. Understand how to implement a new chat model struct that conforms to the library's traits. Check for any existing base model or trait definitions to extend. Test by building a minimal Groq client that can be integrated.

Escrita pelo modelo de indexação a partir do texto da issue.

Avaliação

Stack de tecnologia
rust
Domínio
ai, backend
Tipo de issue
Funcionalidade
Dificuldade
4/5
Tempo estimado
3-5 dias
Status de atividade
Estagnada
Clareza
Razoavelmente clara
Facilidade para iniciantes
45/100

Receba novas issues na sua caixa de entrada

Um resumo curto de issues do GitHub para quem está começando.