Refactor DocumentManager with Orama integration and new web server - #17
Merged
Conversation
…search - Removed DocumentIndex and related indexing logic. - Introduced OramaStore for managing document and chunk databases with persistence. - Updated DocumentManager methods to utilize OramaStore for adding, retrieving, and deleting documents. - Implemented migration from legacy JSON files to Orama. - Added new search capabilities across all documents using hybrid search (full-text + vector). - Updated server to include a new tool for cross-document search. - Adjusted types to accommodate Orama DB schema.
- Introduced a new web server module (`web-server.ts`) to handle REST API routes for document management, including CRUD operations and search functionalities. - Integrated the web server startup in the main server file (`server.ts`), allowing it to run alongside the main application. - Implemented file upload handling and processing capabilities. - Added endpoints for listing documents, searching within documents, and managing uploads.
- Added OramaParentDocument and ParentChunkData interfaces to define parent chunk structure. - Introduced parentsDb in OramaStore to manage parent chunks separately. - Implemented methods to add and retrieve parent chunks in OramaStore. - Updated deleteDocument to remove associated parent chunks. - Modified search results handling in server to support parent-child deduplication and provide full context.
…tting in search results
…text window navigation
…ts, retrieving web UI URL, and processing uploads
|
🎉 This PR is included in version 1.13.0 🎉 The release is available on: Your semantic-release bot 📦🚀 |
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 makes substantial improvements to the MCP Documentation Server, focusing on modernizing the architecture, improving documentation, and adding a built-in web interface. The changes replace the legacy JSON and manual indexing system with an embedded Orama vector database, introduce parent-child chunking for better search results, and streamline the environment variable configuration. The documentation (
README.md) is overhauled to reflect these updates, and new scripts and dependencies are added to support the web UI and Orama integration.Major architecture and feature upgrades:
README.md,src/document-manager.ts, [1] [2] [3]README.md, README.mdL10-R43)http://localhost:3080by default. New scripts are provided to run the UI in development or production. (README.md,package.json, [1] [2] [3]Documentation and configuration improvements:
README.md, [1] [2] [3]README.md, README.mdL56-R219)Dependency and script updates:
@orama/orama,@orama/plugin-data-persistence,express,multer, and related type packages. Removes unused dependencies (glob). (package.json, [1] [2]package.json, package.jsonL19-R22)These changes collectively modernize the server, enhance usability, and prepare the project for scalable document intelligence and search.