Conversation
- Introduce `NodeReference` and `RefType` for representing in-document references like "see Appendix G" or "Table 5.3" - Add `ReferenceExtractor` for parsing references using regex patterns - Implement `ReferenceResolver` for batch resolution of references - Add `references` field to `TreeNode` to store extracted references - Support resolving references to target nodes in document tree - Include reference types: Section, Appendix, Table, Figure, Page, Equation, Footnote, and Listing feat(pilot): add context modes for configurable verbosity - Introduce `ContextMode` enum with Full, Summary and Minimal options - Implement dynamic context building based on selected mode - Add configuration methods for overriding mode defaults - Support configurable candidate limits, path depth, and summary inclusion per mode - Add text truncation utilities for token-efficient context
- Add reference_following.rs example demonstrating reference extraction, resolution, and following capabilities with various reference types (sections, appendices, tables, figures) - Implement ReferenceFollower with configurable depth, reference limits, and confidence thresholds for expanding search results through document cross-references - Add KeywordPilot implementation in custom_pilot.rs showing how to create custom navigation logic based on keyword matching instead of LLM dependencies - Update NodeId creation in content_aggregation.rs to initialize empty references vector for proper reference tracking - Remove environment variable support from ConfigLoader to enforce explicit configuration via TOML files only, simplifying deployment and reducing configuration complexity - Consolidate LLM configuration in vectorless.example.toml under unified [llm] section with dedicated pools for summary, retrieval, and pilot operations while removing legacy configuration sections - Add reference following configuration options to retrieval settings including max depth, reference limits, and content type preferences
…ample Remove unused NodeReference and RefType imports from reference_following.rs example file to clean up the code.
Add comprehensive research paper documenting the Vectorless framework, including abstract, introduction, background, and system architecture sections covering the learning-enhanced reasoning-based document retrieval approach with feedback-driven adaptation. --- refactor(client): update example code return types and async calls Change example code return types from vectorless::Result<()> to Result<(), Box<dyn std::error::Error>> and ensure proper async/await usage in EngineBuilder build() calls across documentation examples. --- refactor(index_context): update example code return types and async calls Standardize example code return types to Result<(), Box<dyn std::error::Error>> and ensure proper async/await syntax in index context documentation examples. --- refactor(mod): update example code return types and event imports Update documentation examples to use standard error handling with Result<(), Box<dyn std::error::Error>> and fix event module imports by removing redundant path specification. --- refactor(lib): update example code return types and async syntax Standardize main function return types in examples and ensure consistent async/await usage throughout library documentation. --- docs(llm): mark unstable examples as ignore Add ignore attribute to LLM fallback and retry example code blocks to prevent test failures on unstable examples. --- feat(metrics): export InterventionPoint in metrics module Export the InterventionPoint type in metrics hub and module to make it available for import in example code. --- refactor(retrieval): fix strategy module path in example Correct the module path import in LLM strategy example documentation from retriever::strategy to retrieval::strategy. --- refactor(util): update format utility imports in examples Fix import paths in format utility examples to use direct module imports instead of nested paths (e.g., util::truncate instead of util::format::truncate). --- refactor(util): update timing utility imports in examples Correct import path in timing utility example to use direct module import (util::Timer instead of util::timing::Timer).
- rewrite main README with comprehensive overview of Vectorless features - add dual pipeline guide explaining index and retrieval architecture - create quick start guide with installation and basic usage examples - update RFCs table with implemented parser statuses - reorganize documentation structure with clear sections - add architecture diagrams and detailed pipeline explanations - include practical examples for different document formats feat: rename JudgeStage to EvaluateStage for clarity - rename JudgeStage to EvaluateStage to better reflect functionality - update all references in orchestrator, pipeline, and stage implementations - change metric field from judge_time_ms to evaluate_time_ms - update stage names in pipeline context and execution flow - maintain preserved names like LlmJudge for specific components - update documentation and examples to use new naming convention docs(rfcs): add RFC-0003 for evaluate stage naming - document rationale for renaming JudgeStage to EvaluateStage - explain motivation behind choosing "Evaluate" over "Judge" - specify changes to file names, struct names, and references - preserve existing LlmJudge terminology where appropriate - update pipeline flow diagrams and implementation steps
- Update package version in Cargo.toml from 0.1.13 to 0.1.14
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.
No description provided.