- Added GoldPool class to manage a top-K pool of high-reward examples.
- Implemented compute_reward function to calculate composite rewards based on execution coverage, novelty, and test quality.
- Introduced call_api_reward function for API calls in the new reward mode.
- Updated main function to support new reward mode with adjustable weights for ECS, novelty, and test quality.
- Enhanced dataset saving functionality to include reward statistics.
- Refactored existing code for improved readability and consistency.
- Updated `elasticsearch_ingestion.py` to streamline document processing and ingestion into Elasticsearch.
- Introduced `generate_mbap.py` for generating benchmark problems in AVAP language from a provided LRM.
- Created `prompts.py` to define prompts for converting Python problems to AVAP.
- Enhanced chunk processing in `chunk.py` to support markdown and AVAP documents.
- Added `OllamaEmbeddings` class in `embeddings.py` for handling embeddings with Ollama model.
- Updated dependencies in `uv.lock` to include new packages and versions.
acano
rafa-ruiz