Add Claude 3 Labrador model

What does this merge request do and why?

Relates to https://gitlab.com/gitlab-org/gitlab/-/issues/465576

gitlab-org/modelops/ai-model-validation-and-research/annoucements#23 (moved)

How to set up and validate locally

1. Ensure GCP environment variables and Anthropic API key are setup.

   1. Use an Anthropic API key with Retention On

      

2. Check out to this merge request's branch.

3. Use the following config to evaluate the new model

   {
     "beam_config": {
       "pipeline_options": {
         "runner": "DirectRunner",
         "project": "dev-ai-research-0e2f8974",
         "region": "us-central1",
         "temp_location": "gs://prompt-library/tmp/",
         "save_main_session": false
       }
     },
     "input_source": {
       "type": "bigquery",
       "path": "dev-ai-research-0e2f8974.duo_chat.sampled_code_generation_v1"
     },
     "output_sinks": [
       {
         "type": "local",
         "path": "data/output",
         "prefix": "experiment_code_generation"
       },
       {
         "type": "bigquery",
         "path": "dev-ai-research-0e2f8974.duo_chat_experiments",
         "prefix": "tle_claude_labrador_20240618"
       }
     ],
     "throttle_sec": 0.1,
     "batch_size": 10,
     "eval_setup": {
       "answering_models": [
         {
           "name": "claude-3-labrador",
           "prompt_template_config": {
             "templates": [
               {
                 "name": "claude",
                 "template_path": "data/prompts/duo_chat/answering/claude-2.txt.example"
               }
             ]
           }
         },
         {
           "name": "claude-3-sonnet",
           "prompt_template_config": {
             "templates": [
               {
                 "name": "claude",
                 "template_path": "data/prompts/duo_chat/answering/claude-2.txt.example"
               }
             ]
           }
         }
       ],
       "metrics": [
         {
           "metric": "similarity_score"
         },
         {
           "metric": "collective_llm_judge",
           "evaluating_models": [
             {
               "name": "text-bison-32k@latest",
               "prompt_template_config": {
                 "templates": [
                   {
                     "name": "claude-2-collective",
                     "template_path": "data/prompts/duo_chat/evaluating/claude-2-collective-xml.txt.example"
                   }
                 ]
               }
             }
           ]
         }
       ]
     }
   }

4. Run the follow command to kick off the pipeline.

   poetry run promptlib duo-chat eval --config-file data/config/duo_chat/eval_code_generation.json --sample-size 1 --test-run

• https://console.cloud.google.com/bigquery?ws=!1m5!1m4!4m3!1sdev-ai-research-0e2f8974!2sduo_chat_experiments!3stle_claude_labrador_20240618__collective_llm_judge
• https://console.cloud.google.com/bigquery?ws=!1m5!1m4!4m3!1sdev-ai-research-0e2f8974!2sduo_chat_experiments!3stle_claude_labrador_20240618__similarity_score

Merge request checklist

• I've ran the affected pipeline(s) to validate that nothing is broken.
• Tests added for new functionality. If not, please raise an issue to follow up.
• Documentation added/updated, if needed.