Document Retriever vs Examples Selector

[arademaker]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

No code

Description

I am trying to use retriever in a chain to compose the final prompt with examples.

System Info

I want to implement a prompt with few examples and I am almost following the tutorial

https://python.langchain.com/docs/how_to/few_shot_examples_chat/#dynamic-few-shot-prompting

But how to replace the vectordb with a Document retriever in the chain? I am specially interested in trying the TFIDF.

So maybe the more general question is what is the difference between the

https://python.langchain.com/api_reference/core/example_selectors/langchain_core.example_selectors.base.BaseExampleSelector.html#langchain_core.example_selectors.base.BaseExampleSelector

and

https://python.langchain.com/api_reference/core/retrievers/langchain_core.retrievers.BaseRetriever.html#langchain_core.retrievers.BaseRetriever