Add tests for RAG prompt

[andrewsykim]

No description provided.

[andrewsykim]

/gcbrun

[andrewsykim]

/gcbrun

[andrewsykim]

/gcbrun

[andrewsykim]

Passing results from CI:

2024-04-01 05:23:18,178	SUCC cli.py:60 -- ------------------------------------------
2024-04-01 05:23:18,178	SUCC cli.py:61 -- Job 'raysubmit_AQ5UwhxiVXv7fph7' succeeded
2024-04-01 05:23:18,178	SUCC cli.py:62 -- ------------------------------------------
Handling connection for 8081
Handling connection for 8081
Handling connection for 8081
Handling connection for 8081
Handling connection for 8081
Handling connection for 8081
Testing prompt: List the cast of Squid Game
Reply:  The cast of Squid Game includes:

  * Lee Jung-jae
  * Park Hae-soo
  * Wi Ha-jun
  * Oh Young-soo
  * Jung Ho-yeon
  * Heo Sung-tae
  * Kim Joo-ryoung
  * Tripathi Anupam
  * You Seong-joo
  * Lee You-mi
Testing prompt: When was Squid Game released?
Reply: 
Squid Game was released on September 17, 2021.
Testing prompt: What is the rating of Squid Game?
Reply: 
The rating of Squid Game is TV-MA.
Testing prompt: List the cast of Avatar: The Last Airbender
Reply:  The cast of Avatar: The Last Airbender includes:

1. Zach Tyler as Aang
2. Mae Whitman as Katara
3. Jack De Sena as Sokka
4. Dee Bradley Baker as Toph, Sokka, and other characters
5. Dante Basco as Bolin
6. Jessie Flower as Suki
7. Mako Iwamatsu as Sokka (Japanese dub)
Testing prompt: When was Avatar: The Last Airbender added on Netflix?
Reply: 
Avatar: The Last Airbender was added to Netflix on May 15, 2020.
Testing prompt: What is the rating of Avatar: The Last Airbender?
Reply: 
The rating of Avatar: The Last Airbender is TV-Y7.

Unfortunately the adds an extra ~10m to the e2e tests to run the ray job, but I think the coverage is worth it.

[andrewsykim]

/gcbrun