Created Python Code to set up the entire pipeline for benchmarking faiss-index with DuckDB and PGVector #1984
Conversation
This file contains 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
adopted hnsw index and fixed incorrect sql queries
…/pyserini into performance_benchmark
Modified the benchmark files to record performance
Refactored Benchmark Scripts + Added Faiss Dense Vector Extractor
lintool
requested changes
Sep 12, 2024
collections/.gitkeep
Outdated
| @@ -1 +0,0 @@ | |||
| # This is the default directory for document collections. Placeholder so that directory is kept in git. | |||
There was a problem hiding this comment.
This file shouldn't be removed.
lintool
reviewed
Sep 12, 2024
| The entire process may take over a day to complete, depending on your hardware set up. This code will download the index, extract the embedded vectors of the index, build the table in duckdb and run the benchmark. | ||
|
|
||
| ## PGVector | ||
| PGVector is an extension of PostgreSQL, so you will need to install PostgreSQL and PGVector. Here, it is assumed that you have a PostgreSQL server running on your local machine, and you have the PGVector extension installed and enabled in PostgreSQL. Make sure you supply the correct database configuration in the `db_config.txt` file. For example: |
There was a problem hiding this comment.
Can we install Postgres using conda? e.g., https://anaconda.org/anaconda/postgresql
If so, please provide instructions?
Performance benchmark
Performance benchmark: readded content of gitkeep
filename change
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Outdated suggestions cannot be applied.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.
This PR created multiple python classes and facilities aimed at making the benchmarking process of DuckDB and PGVector on HNSW indexes easier. The faiss_index_adaptor.py is the base class for duckdb_faiss_index_adaptor and pgvector_faiss_index_adaptor. It uses the faiss_index_extractor class to download and extract a 768 dimension Faiss index, then creates a database table in DuckDB/PGVector. Currently run_benchmark.py invokes the benchmarking process, see experiment_vectordbs.md for detailed instructions.