feat: retrieval benchmark suite — recall@K vs Pinecone, Weaviate, pgvector#51
Open
kaising-openclaw1 wants to merge 1 commit into
Open
feat: retrieval benchmark suite — recall@K vs Pinecone, Weaviate, pgvector#51kaising-openclaw1 wants to merge 1 commit into
kaising-openclaw1 wants to merge 1 commit into
Conversation
…pgvector) Implements the benchmark described in Issue Dipraise1#24: - Reproducible harness in scripts/bench/ - Loads BEIR datasets (NQ, HotpotQA, FiQA) via HuggingFace datasets - Benchmarks Engram, Pinecone, Weaviate, and pgvector - Reports recall@1/5/10, p50/p95/p99 latency, storage overhead - Generates markdown report for docs/benchmarks.md - Quick mode for CI (1000 docs, 50 queries) - Rich console output with progress bars Usage: python scripts/bench/run_benchmarks.py --datasets nq,hotpotqa,fiqa
|
Someone is attempting to deploy a commit to the praise's projects Team on Vercel. A member of the Team first needs to authorize it. |
4 tasks
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Implements the benchmark described in Issue #24: a reproducible harness that runs the same queries against Engram and baseline vector databases (Pinecone, Weaviate, pgvector) on public BEIR datasets.
What's included
scripts/bench/run_benchmarks.py— Main benchmark orchestratordatasetsscripts/bench/requirements-bench.txt— Isolated dependency filescripts/bench/__init__.py— Package initUsage
Architecture
Each system (EngramRunner, PineconeRunner, WeaviateRunner, PgvectorRunner) implements a common interface:
prepare(docs, embeddings)— ingest/index documentsquery(queries_emb, queries_text, top_k)— run queriesstorage_size()— report storage overheadcleanup()— tear down resourcesResults are saved as JSON and a markdown report is generated at
bench_results/benchmarks.md, ready to be copied todocs/benchmarks.md.Closes #24