Context Caching with Gemini LLM

Demonstrates how to use context caching with Gemini 1.5 Flash.
Notebook: github.com/dai...
To learn more, check out our upcoming live training to learn more about building with LLMs:
maven.com/dair...
#ai #education #tech #engineering

[@essay-writer]

Great stuff Elvis, just subscribed annually to your newsletter. :)

[@elvissaravia]

Thank you. I appreciate the support.

[@TooyAshy-100]

Thank you,,,

[@pikachupay69]

is already available in VertexAI Tool?

[@elvissaravia]

Not checked yet.

[@ammarfasih3866]

A question on this,
In the tutorial above we are using that txt file to answer our queries, it's more like grounding the results of our query to certain datastore (txt file in this case). So what is the difference in terms of functionality for using this context cached feature and grounding response on some datastore (with this txt file stored in it).
Appreciate response.

[@elvissaravia]

We don't know exactly how the cached context is used at inference but I assume it's not much different from the latter you mentioned.

[@claytoncarroll2309]

Can you please provide the code

[@elvissaravia]

Let me work on that. Check back by end of the day and I will share the link here.