LongProbe v0.1.2#1
Open
mohsin1218 wants to merge 8 commits into
Open
Conversation
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Key Additions & Enhancements:
🧪 Pytest Integration (@golden_check):
Introduced the @golden_check decorator for writing inline, sub-second RAG regression tests directly inside existing test suites.
Added configuration auto-discovery (longprobe.yaml) with support for session-level longprobe_adapter fixture overrides.
🔍 Retrieval Diagnostic Tool (longprobe explain):
Added a troubleshooting CLI command to analyze regressions.
Detects "interloper" chunks that pushed down expected content and runs extended searches to find exactly where missing chunks shifted in rank.
🖥️ Interactive Terminal Editor (longprobe edit):
Built a terminal-native, dual-pane Textual TUI to interactively manage golden questions.
Supports creating, deleting, and updating questions, tags, top_k, and match modes directly from the terminal (Ctrl+S, Ctrl+N, Ctrl+D).
📚 Enterprise-First Documentation:
Realigned guides to favor the production-grade HTTP Adapter as the default recommendation (supporting any API or LongTrainer backend).
Promoted Qdrant as the primary direct-database adapter example, moving ChromaDB to a local prototyping footnote.
📦 Release Packaging:
Added the [tui] optional dependency group to pyproject.toml.
Bumped package version to 0.1.2 across the entire codebase.