big-ann-benchmarks
big-ann-benchmarks copied to clipboard
harsha-simhadri
Framework for evaluating ANNS algorithms on billion scale datasets.
As I understand big-ann-benchmark is used for benchmarking algorithms. Looking at [ann-benchmarks](https://github.com/erikbern/ann-benchmarks/blob/main/ann_benchmarks/algorithms/), they also have support for databases, such as postgres (pgvector) and redis. I have a few questions: 1)...
The generic function `get_dataset_fn()` implemented in the `DatasetCompetitionFormat` class in `benchmark/datasets.py` did not work properly, as it contained some code that was specific to the billion-size datasets, and caused some...
I'm trying to repro the faiss GPU baseline results with MSSPACEV dataset. I'm following the instructions using the [FAISS T3 Baseline] (https://github.com/harsha-simhadri/big-ann-benchmarks/tree/main/neurips21/track3_baseline_faiss). Built FAISS using source from the main branch....
is there a plan to upload the code which is written to created create pinecone index or zilliz index and upload embeddings and metadata? For ex: code for pys2.FilterIndexWrapper
Add --from-to option to azcopy command as downloading turing-1b dataset is failing without this option.
backfilling some missing results of the submission `sustech-whu` on the sparse track. The result for the public query set was missing. (This has no effect on any leaderboard since this...
Hi, I need to download the datasets such as "YFCC-10M + CLIP" to compare between different vector databases. Where can I find the download links?
Closes https://github.com/harsha-simhadri/big-ann-benchmarks/issues/293. * Add .vscode to .gitignore * Add support for pgvector's hnsw and generic support for Postgres indexes See below explanation, this is the meat of the PR. *...
Metadata
Owner
Metadata
Framework for evaluating ANNS algorithms on billion scale datasets.