Skip to main content

Launch Local Visual Studio Preview (v0.2.2+)

pip install -U pgrag-eval-lite
pgrag studio

Opens the dark-mode visual diagnostic dashboard at http://127.0.0.1:8787 with pre-index table health auditing and Hybrid RRF vs. Pure Dense benchmarks.

pgRAG-Inspector (pgrag-eval-lite & Pro Visual Studio)

Local-First RAG Retrieval, Chunking & pgvector 0.8+ Diagnostic Workbench ($0.00 LLM API Cost).

👉 Download pgRAG-Inspector Pro (4-Page Visual Workbench + 1-Click SQLAlchemy 2.0 / Alembic / Pytest Exporter) or the Free Lite Bundle on Gumroad

Quickstart (CLI)

pip install pgrag-eval-lite
pgrag init-samples
pgrag check --chunks examples/sample_chunks.json --golden examples/sample_golden_qa.json --fail-under-recall5 95

What It Diagnoses Locally

  1. Pre-Index Chunk & Markdown Table Health Scanner: Deterministically flags sliced Markdown/PDF tables (BROKEN_MARKDOWN_TABLE), >80% sliding-window token overlap, and mid-sentence cutoffs before indexing.
  2. Multi-Strategy Polars/NumPy IR Sweep ($0.00 API Cost): Benchmarks Pure Dense (pgvector <=>), Pure Sparse FTS (ts_rank_cd), and Hybrid RRF across Exact SKUs/Error Codes, Financial Tables, and Semantic Paraphrases.
  3. pgRAG-Inspector Pro Visual Studio (127.0.0.1:8787): Side-by-side 3-strategy chunk diffing (Docling HybridChunker), interactive RRF rank profiler, and 1-click code generation for async SQLAlchemy 2.0, Alembic (hnsw + tsvector GIN + SET LOCAL hnsw.iterative_scan = 'relaxed_order'), and Pytest CI gates.

🔗 Get the Full Visual Workbench: https://mtalha5.gumroad.com/l/pgrag-inspector

Metadata

Release files for pgrag-eval-lite 0.2.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distribution (wheel)

Table of built distributions (wheels) for pgrag-eval-lite 0.2.2
File Interpreter ABI Platform Actions
pgrag_eval_lite-0.2.2-py3-none-any.whl Python 3 none any Details for pgrag_eval_lite-0.2.2-py3-none-any.whl

Release files / pgrag_eval_lite-0.2.2-py3-none-any.whl

Download URL pgrag_eval_lite-0.2.2-py3-none-any.whl
Size 49.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
e2b7534336ffcba525dc5c810caf2f1581ed3dcf95cda0575998b47c6b0f8125
BLAKE2b-256 checksum
How to use checksums
4b3e7d8079b084377c9278ef52d00b1330c809357592d7a14dd7c0354e3028a1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.3

Security for pgrag-eval-lite 0.2.2

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.2.2 This release

1 release file No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page