UI port - #2
Merged
Merged
Conversation
- Added a new section in CLAUDE.md and README.md to clarify the concept of "corpus" as the primary unit for indexing and searching, replacing the previous "repo" terminology. - Updated API endpoints to reflect the new corpus-centric approach, including changes to endpoint paths and request parameters. - Enhanced the configuration management to support corpus-specific settings, ensuring backward compatibility with the existing `repo_id` field. - Improved the indexing process with better error handling and support for corpus management. - Updated the documentation to provide clear instructions for creating and indexing corpora via the API. This commit significantly improves the clarity and functionality of the API, aligning it with the new corpus-first architecture.
…base management - Updated `.env.example` and `docker-compose.yml` to support external database storage, allowing users to specify a directory for PostgreSQL and Neo4j data. - Added new environment variables for Neo4j image selection and license agreement handling. - Enhanced `tribrid_config.json` with new parameters for Neo4j database management, including shared and auto-creation options. - Improved documentation in `mkdocs` to reflect changes in configuration and provide clearer guidance on setup and usage. - Introduced a new script for enhanced documentation generation using OpenAI, streamlining the documentation process. These changes improve the flexibility and usability of the Docker setup, aligning it with the corpus-first architecture and enhancing overall user experience.
…file inclusion/exclusion - Added methods to read and normalize .gitignore patterns, allowing for nested gitignore semantics. - Enhanced the file loading process to respect gitignore rules, ensuring that ignored files and directories are not included in the results. - Introduced a new test suite to validate the behavior of FileLoader with various gitignore configurations, confirming that only the intended files are loaded. These changes significantly enhance the FileLoader's functionality, aligning it with common version control practices and improving overall usability.
DMontgomery40
added a commit
that referenced
this pull request
Feb 6, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This pull request introduces several improvements and refactors to the TriBridRAG codebase and documentation, focusing on clarifying the "corpus-first" architecture, updating API endpoints, improving Docker and environment configuration, and enhancing type generation and documentation tooling. The changes aim to make the system more modular, user-friendly, and maintainable as it evolves.
Key changes include:
Corpus-first architecture and API updates
README.md,CLAUDE.md) to clarify that TriBridRAG is "corpus-first" rather than "repo-first", explaining that a corpus can be any folder (not just a git repo), and thatrepo_idshould be treated as a corpus identifier for backward compatibility. [1] [2]/api/prefixes and corpus terminology, including new endpoints for corpus management and indexing. [1] [2]Docker and environment configuration improvements
.env.exampleto support storing Postgres and Neo4j data outside the repo by default, using a configurableTRIBRID_DB_DIRvariable for easier local development and persistence. [1] [2]Type generation and serialization
scripts/generate_types.py) to include new domain models for corpora, chunk summaries, keywords, and eval-related types, and to generate schemas in serialization mode (using aliases such ascorpus_idinstead ofrepo_id). This supports the corpus-first migration and improves API/TypeScript alignment. [1] [2] [3] [4] [5]Documentation and tooling improvements
Codebase refactoring
TriBridFusionimplementation, supporting per-corpus configuration. [1] [2]These changes collectively modernize the codebase, clarify the architecture, and lay groundwork for future features and scaling.