Feature/vectors split#3
Open
scottgal wants to merge 10 commits into
Open
Conversation
…uctured logging for embedding disagreements with a learning loop for exemplar generation.
…rketing page. - Added collection auto-routing logic in `AgenticSearchService.cs` to automatically determine and use the best collection if not specified. - Implemented salient segment caching for follow-up queries in ongoing conversations to improve result relevance. - Enhanced error handling in `PostgresBm25Service.cs` by checking for valid `topK` values. - Created a new marketing page (`marketing/index.html`) to promote features and capabilities of the product.
The AI-powered response engine, deterministic resolver, and related augmented response systems have been deleted. This includes associated helper classes, embedding cache logic, and unit tests. These modules are likely deprecated or no longer needed in the runtime core services.
Introduce new marketing components to showcase product use cases, answer FAQs, and present pricing tiers. These include visually rich layouts and interactive elements to enhance user understanding and engagement.
Improved middleware logic for API authentication, including HMAC headers and alternative routing prefixes. Updated UI elements across marketing views for better responsiveness and consistency in typography, spacing, and visual hierarchy. Enhanced pricing tiers with added features, file upload size limits, and detailed overage options.
This commit introduces hosted search pages and improves widget configurability via the new `_DashboardWidgetConfig` partial. It also restructures the dashboard to include tabs for streamlined navigation and updates the key management section with hosted URL options. Enhancements support user-facing customization features such as custom CSS, logos, and domain settings.
Introduces Typesense-based search extensions, replacing Lucene for indexing and search. Adds widget and domain customization entities, middleware improvements for CORS handling, and schema migrations to support new features. Includes enhancements for query parsing and search result curation using Typesense.
Revised shadow DOM handling, added safety checks for CSS and URLs, limited in-flight requests, and improved resilience with request retries and input validations. Updated pricing plans, analytics, and test cases to align with new features.
Updated SaaS plan configurations with stress-test limits and added new features such as query retention and export options. Introduced LucidEncrypt.Core with KMS provider support and tracking for encryption migration progress. Expanded LucidRAG.App UI with document explorer, detail views, and a knowledge graph powered by D3.js.
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 significant documentation improvements and workflow automation for the LucidRAG and DoomSummarizer projects. The main changes include adding detailed design documents for background learning and vector store abstraction, updating the semantic query classifier documentation with new tuning and test details, introducing a new GitHub Actions workflow for NuGet publishing, and removing an obsolete project from the solution.
Documentation Enhancements:
Automation and Build System:
.github/workflows/publish-lucidrag-nuget.yml) to automate publishing LucidRAG Core and Postgres NuGet packages, supporting both tag-based and manual dispatch triggers.Solution Maintenance:
LucidRAGproject from the solution file (LucidRAG.sln) and cleaned up related configuration entries. [1] [2] [3]