The Gemini API doesn't explicitly document a sendMessage() function.

[albort11]

Description of the feature request:

I saw an example using sendMessage() to implement multi-turn conversation at this link: https://ai.google.dev/gemini-api/docs/text-generation?lang=python#chat, where the model apparently maintains message history internally.

However, the API reference lacks further details on this feature. I'm unable to determine how to identify different chat sessions, how to clear the context, or how to check the current context length using this method. Does anyone know where I can find more detailed usage information?

What problem are you trying to solve with this feature?

My translation application requires continuous contextual information. Having more control over sendMessage(), such as setting the length of the message history, the number of turns in a dialogue, or reading the current message history, would be extremely helpful.

Any other information you'd like to share?

No response

[gmKeshari]

Hi @albort11,

Kiran Sai explained it nicely in forum and provided the colab gist also. Please follow this forum discussion.

If you still have any doubt, please reach out.

Thanks.