Commit Graph

85 Commits

Author SHA1 Message Date
rafa-ruiz 6ee8583894 update 2026-03-31 01:40:23 -07:00
Rafael Ruiz 3e47c15966
Merge pull request #63 from BRUNIX-AI/mrh-online-dev-partial
Add BEIR analysis notebooks and evaluation pipeline for embedding models
2026-03-26 09:33:54 -07:00
izapata 4deda83a8e Add BEIR analysis notebooks and evaluation pipeline for embedding models
- Created `n00 Beir Analysis_cosqa.ipynb` for analyzing CoSQA dataset with BEIR.
- Created `n00 first Analysis.ipynb` for initial analysis using Ragas and Ollama embeddings.
- Implemented `evaluate_embeddings_pipeline.py` to evaluate embedding models across CodexGlue, CoSQA, and SciFact benchmarks.
- Added adapters for Ollama and HuggingFace embeddings to ensure compatibility with BEIR.
- Included functions to load datasets and evaluate models with detailed metrics.
2026-03-26 16:53:20 +01:00
Rafael Ruiz a55d4bbf5e
Merge pull request #62 from BRUNIX-AI/mrh-online-dev-partial
Update Embedding model PDF and enhance documentation
2026-03-26 08:36:53 -07:00
rafa-ruiz fe43cd6fa9 scripts documentation 2026-03-26 07:51:01 -07:00
izapata 76250a347b feat(docs): typo fix 2026-03-26 10:30:12 +01:00
izapata 64d487e20d chore: update changelog for version 1.6.2 and enhance README.md documentation 2026-03-26 10:25:34 +01:00
izapata e4a8e5b85d chore: update Embedding model selection PDF with new content 2026-03-26 10:19:24 +01:00
rafa-ruiz ccd9073a52 feat(dataset): add ADR-0006 and scaffold reward algorithm pipeline 2026-03-25 22:19:19 -07:00
Rafael Ruiz f9b2b014bb
Merge pull request #59 from BRUNIX-AI/mrh-online-dev-partial
Added embeddings research
2026-03-24 06:38:59 -07:00
rafa-ruiz 59c1748594 feat: editor context injection (PRD-0002) + repository governance 2026-03-20 19:43:48 -07:00
rafa-ruiz 2fbfad41df feat: editor context injection (PRD-0002) + repository governance 2026-03-20 19:25:29 -07:00
acano 14b279b8af Refactor code structure for improved readability and maintainability 2026-03-19 16:40:57 +01:00
acano 16acdfb1f3 DOCS: Add research directory description in README 2026-03-19 16:30:44 +01:00
acano b6f9b386ef Add BEIR analysis notebooks for different datasets and models
- Created `n00 Beir Analysis.ipynb` for analyzing BEIR dataset with Ollama embeddings.
- Added `n00 Beir Analysis_cosqa.ipynb` for evaluating the CosQA dataset using similar methods.
- Introduced `n00 first Analysis.ipynb` for initial analysis with Ragas embeddings and semantic similarity evaluation.
- Implemented data loading, processing, and evaluation metrics for each notebook.
- Included functionality to save results to JSON files for further analysis.
2026-03-19 16:27:25 +01:00
Rafael Ruiz 3ca8fc450c
Merge pull request #58 from BRUNIX-AI/online-fork
Online fork
2026-03-18 19:13:30 -07:00
Rafael Ruiz 52d381fa22
Merge branch 'main' into online-fork 2026-03-18 19:09:47 -07:00
rafa-ruiz fda47edae0 UPGRADE: New RAG functional 2026-03-18 18:56:01 -07:00
rafa-ruiz 1daac66f89 UPGRADE: New RAG functional 2026-03-18 18:55:48 -07:00
Rafael Ruiz dfcbf43fa2
Merge pull request #55 from BRUNIX-AI/mrh-online-dev-partial
Refactored ingestion pipeline and created AVAP synthethic dataset generation pipeline
2026-03-12 11:22:28 -07:00
acano f986c70845 fix: load environment variables and add elasticsearch_index to Settings class 2026-03-12 17:37:22 +01:00
acano 9a435120d5 Merge branch 'online' into mrh-online-dev-partial 2026-03-12 17:09:00 +01:00
acano 2493723f8b docs: correct spelling errors in changelog and update project root method name in Settings class 2026-03-12 16:09:41 +01:00
acano 4fce9c9a98 refactor: streamline Settings class by removing unused properties and simplifying path resolution 2026-03-12 15:55:05 +01:00
acano 0abbae93a4 docs: update usage instructions and improve validation error messages in generate_mbap.py 2026-03-12 13:19:10 +01:00
acano 90ba49d613 refactor: remove unused test scripts for Elasticsearch integration 2026-03-12 12:32:05 +01:00
acano 01ce959aab refactor: remove unused BNF file generator script 2026-03-12 12:31:05 +01:00
acano 3463fb05e8 docs: update README and changelog to reflect ingestion folder addition 2026-03-12 12:30:39 +01:00
acano 654ac88da7 feat: Enhance Elasticsearch ingestion with metadata export
- Added `export_documents` function to save processed documents to JSON.
- Extended `ElasticHandshake` to include chunk metadata during ingestion.
- Updated `process_documents` to include extra metadata for each chunk.
- Modified `ingest_documents` to return Elasticsearch responses for further processing.
- Adjusted `elasticsearch_ingestion` command to accept output path for exported JSON.
2026-03-12 12:28:17 +01:00
acano f183beb088 docs: update README and changelog for PYTHONPATH variable addition 2026-03-12 10:39:30 +01:00
acano 648f0f7318 refactor: reorganize file structure and update import paths for clarity 2026-03-12 10:21:44 +01:00
acano a4478cb7ff refactor: remove unused BNF file generator script 2026-03-12 10:09:25 +01:00
acano dc7568b622 docs: enhance function docstrings for Elasticsearch ingestion and document processing 2026-03-12 09:54:24 +01:00
acano aa80f60fdc refactor: update Elasticsearch ingestion pipeline and document processing logic 2026-03-12 09:51:00 +01:00
rafa-ruiz 90857e1b0a UPDATE: Modified LRM and generate_mbap.py to ensure better samples 2026-03-11 20:09:05 -07:00
rafa-ruiz b5167b71e3 UPDATE: Sample generator now includes a new key in each item. 2026-03-11 12:22:08 -07:00
acano de21bcb5fb Refactor code structure for improved readability and maintainability 2026-03-11 17:48:54 +01:00
rafa-ruiz 35ca56118d feat: add MBPP-style dataset generator and evaluation docs 2026-03-10 13:37:19 -07:00
Rafael Ruiz a08f754e25
Merge pull request #24 from BRUNIX-AI/mrh-online-dev-partial
Implemented basic elasticsearch ingestion pipeline and built langgraph RAG agent skeleton
2026-03-05 13:10:04 -08:00
rafa-ruiz 7839793eff docs: align function syntax and cleanup docker config 2026-03-05 11:57:29 -08:00
acano a4267e1b60 feat: implement Elasticsearch ingestion pipeline and embedding factories 2026-03-05 16:26:22 +01:00
acano 8914acbb95 Add comprehensive documentation for AVAP™ language features
- Introduced sections on Persistence, Connectors, and Native ORM, detailing the avapConnector, ORM commands, and data access abstraction.
- Documented System Utilities and Transformation, covering time management, string manipulation, and security operations.
- Explained Function Architecture and Scopes, including function definition, invocation, and middleware usage.
- Provided a Master Example that integrates various sections to demonstrate practical application.
- Detailed the dynamic nature of AVAP™ as a programming language, including dynamic typing and memory management.
- Established notation conventions and lexical analysis processes for code clarity and structure.
- Outlined data types and structures available in AVAP™, emphasizing their usage in program development.
- Discussed variable management, including local and global variables, and best practices for comments.
- Explained expressions in AVAP™, including types, operators, and practical examples with lists.
2026-03-05 15:54:05 +01:00
rafa-ruiz 8379033900 Sample avap code 2026-03-04 20:21:27 -08:00
rafa-ruiz 1c9ee8d5dd docs(core): add official AVAP documentation in Markdown (iii) 2026-03-04 18:44:22 -08:00
rafa-ruiz 0113b32f8a docs(core): add official AVAP documentation in Markdown (ii) 2026-03-04 18:31:50 -08:00
rafa-ruiz 2d66266fd8 docs(core): add official AVAP documentation in Markdown 2026-03-04 18:25:15 -08:00
Rafael Ruiz 86f426ae48
Fix formatting of secret values warning in README 2026-03-03 13:35:27 -08:00
Rafael Ruiz 39a9e7eaba
Rename 'main' branch to 'online' in documentation
Updated branch naming from 'main' to 'online' in CONTRIBUTING.md.
2026-03-03 13:34:22 -08:00
rafa-ruiz aa9865f5d0 docs: add contribution standards, PR template and env vars policy 2026-03-03 13:19:42 -08:00
rafa-ruiz 5024bde8fb removed workspace 2026-02-23 22:21:04 -08:00