Scripts to create a Dbizi dataset and evaluate an assistant

[mBerasategui-ehu]

Added 2 scripts in scripts/langsmith:
-dbizi_dataset.py (creates a dataset in LangSmith with 15 questions about dbizi)
-evaluate_assistant.py (an llm-as-a-judge evaluates a given lamb assistant with the given dataset in LangSmith)

To try them, first configure these LangSmith env variables in backend/.env:
-LANGCHAIN_TRACING_V2=true
-LANGCHAIN_API_KEY=YOUR_LANGCHAIN_API_KEY
-LANGCHAIN_PROJECT=lamb-assistants
-LANGCHAIN_ENDPOINT=https://api.smith.langchain.com

And these 2 variables in evaluate_assistant.py:
-JWT_TOKEN = "your_jwt_token_here"
-ASSISTANT_ID = 1 (this should be the id of the dbizi assistant in lamb)

Then, run the scripts:
-first, dbizi_dataset.py
-then, evaluate_assistant.py

[mBerasategui-ehu]

Fixed issues in evaluate_assistant.py and added dbizi_dataset_eus.py (same as dizi_dataset.py but in basque).

[mBerasategui-ehu]

Now these variables are loaded from lamb-kb-server-stable/backend/.env instead of having them hardcoded:
API_BASE_URL = os.getenv("API_BASE_URL")
JWT_TOKEN = os.getenv("JWT_TOKEN")
ASSISTANT_ID = int(os.getenv("ASSISTANT_ID"))
DATASET_NAME = os.getenv("DATASET_NAME")