- 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.
- Updated `read_files` function to return a list of dictionaries containing 'content' and 'title' keys.
- Added logic to handle concatenation of file contents and improved handling of file prefixes.
- Introduced `get_chunk_docs` function to chunk document contents using `SemanticChunker`.
- Added `convert_chunks_to_document` function to convert chunked content into `Document` objects.
- Integrated logging for chunking process.
- Updated dependencies in `uv.lock` to include `chonkie` and other related packages.
- Implemented `elasticsearch_ingestion` function to handle document ingestion into Elasticsearch.
- Created `build_chunks_from_folder` function to read and clean text files, generating document chunks.
- Added logging for better traceability during the ingestion process.
- Updated `uv.lock` to include `boto3` as a new dependency.
- Removed network_mode: "host" from docker-compose.yaml for better isolation.
- Updated execution counts in langgraph_agent_simple.ipynb to reflect new cell order.
- Added OLLAMA_LOCAL_URL to imports in langgraph_agent_simple.ipynb.
- Included base_url parameter for create_chat_model and create_embedding_model functions in langgraph_agent_simple.ipynb.
- Added litellm>=1.82.0 to the development dependencies in pyproject.toml.
- Updated uv.lock to include litellm and its dependencies, along with fastuuid package.
- Set execution counts to null for initial cells in langgraph_agent_simple.ipynb
- Update execution counts for subsequent cells to maintain order
- Change output stream name from stdout to stderr for error handling
- Capture and log detailed error messages for failed Langfuse client authentication
Update uv.lock to manage accelerate dependency
- Remove accelerate from main dependencies
- Add accelerate to dev dependencies with version specification
- Adjust requires-dist section to reflect changes in dependency management
- Created a new Jupyter notebook for analyzing BEIR dataset with CosQA using Ollama embeddings.
- Implemented a custom embedding class to integrate LangChain's OllamaEmbeddings with BEIR.
- Added data loading and evaluation logic for the CosQA dataset.
- Updated `uv.lock` to remove unnecessary dependencies (`mteb` and `polars`) and incremented revision number.
acano
izapata
pseco