Naive RAG on streamlit using a vllm API for the generator and a text embedding inference api for the embedding model. Both are compatible with openai api and have seamless integration with langchain.
-
Notifications
You must be signed in to change notification settings - Fork 0
Naive RAG on streamlit using a vllm API for the generator and a text embedding inference api for the embedding model. Both are compatible with openai api and have seamless integration with langchain.
LLM-devops/RAG-streamlit
About
Naive RAG on streamlit using a vllm API for the generator and a text embedding inference api for the embedding model. Both are compatible with openai api and have seamless integration with langchain.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published