[DERCBOT-1173] RAG Evaluation - Langfuse

[assouktim]

This pull request includes several updates and improvements to the gen-ai/orchestrator-server project, focusing on dependency updates, configuration enhancements, and documentation improvements.

Dependency Updates:

• gen-ai/orchestrator-server/src/main/python/server/pyproject.toml: Updated various dependencies to their latest versions, including uvicorn, pydantic-settings, fastapi, langchain, colorlog, boto3, and google-cloud-secret-manager.

Configuration Enhancements:

• gen-ai/orchestrator-server/src/main/python/server/src/gen_ai_orchestrator/configurations/environment/settings.py: Added a new configuration setting llm_rate_limits to enable or disable rate limiting for LLM providers.
• gen-ai/orchestrator-server/src/main/python/server/src/gen_ai_orchestrator/services/langchain/factories/llm/llm_factory.py: Implemented a new method llm_rate_limits to enable rate limiting based on the new configuration setting.

Codebase Simplification:

• gen-ai/orchestrator-server/src/main/python/server/src/gen_ai_orchestrator/services/langchain/factories/llm/azure_openai_llm_factory.py and gen-ai/orchestrator-server/src/main/python/server/src/gen_ai_orchestrator/services/langchain/factories/llm/openai_llm_factory.py: Removed unused imports and added the rate_limiter parameter to the get_language_model method. [1] [2]

Documentation Improvements:

• gen-ai/orchestrator-server/src/main/python/tock-llm-indexing-tools/README.md: Updated the documentation to reflect changes in the CSV file format and added details about new options and parameters for various scripts. [1] [2] [3] [4] [5]

Testing and Validation:

• gen-ai/orchestrator-server/src/main/python/server/tests/services/test_qa_chain.py: Updated test cases to match changes in the metadata field from url to source. [1] [2]

[Benvii]

Making this PR as draft as there is still work in progress on it.