update for Dapr 1.16 conversation SDK Python quickstart

[filintod]

Description

Please explain the changes you've made

Issue reference

We strive to have all PRs being opened based on an issue, where the problem or feature have been discussed prior to implementation.

#1157

Checklist

Please make sure you've completed the relevant tasks for this PR, out of the following list:

• The quickstart code compiles correctly
• You've tested new builds of the quickstart if you changed quickstart code
• You've updated the quickstart's README if necessary
• If you have changed the steps for a quickstart be sure that you have updated the automated validation accordingly. All of our quickstarts have annotations that allow them to be executed automatically as code. For more information see mechanical-markdown. For user guide with examples see Examples.

[alicejgibbons]

@filintod not sure we want to put this example in quickstarts otherwise it runs as a test and we dont have an API key to use? we could talk about putting it in https://github.com/dapr/quickstarts/tree/master/tutorials ?

[filintod]

@alicejgibbons make sense, some updates are still ok and use the echo provider, I guess we can move the API-dependant parts to the tutorial. I have created a lengthier example one in python-sdk that I could bring to the tutorial instead, like a multi-turn example that is more interesting.

[alicejgibbons]

@filintod here's what i would propose:

• Move the ollama sample to a new folder here called conversation. That way it's not a part of the built-in quickstarts testing and we can keep the basic sample using echo mock llm
• Update the conversation sdk sample with the comments I've added so that it aligns with the other conversation ones weve agreed on: Updated request url to alpha2 and updated quickstart to support toolcalling #1209

[alicejgibbons]

Not opposed to adding venv details but Sam does have this qs open here: #1208

[filintod]

I'll rebase to work on top of that as it is now merged

[filintod]

there are still some contrib changes required.

[alicejgibbons]

We need to keep all the tests in, you can run make validate locally to check

[filintod]

I kept the steps further down but I'll check

[alicejgibbons]

Lets keep the tool calling sample in the same file as the basic python qs so that there is only one app to run as Constantin did here: #1209

The mechanical markdown test should test the same input/output as well:

== APP - conversation == Tool calling input sent: What is the weather like in San Francisco in celsius?
== APP - conversation == Output message: What is the weather like in San Francisco in celsius?
== APP - conversation == No tool calls in response

[filintod]

I updated this as the outputs are outdated from latest changes in contrib and expected PRs there

[alicejgibbons]

We need to set the version per quickstart and this should pull in the latest python sdk rc: v1.16.0rc1

[filintod]

sure, this is all temporary to work in my computer, we need python sdk with my changes that is not merged yet

[filintod]

@alicejgibbons I removed the openai/ollama references and I'll add to tutorials after this is done, and also the Python SDK PR is done (required for this one).