zilliztech / zilliztech/VectorDBBench

Termial output: "access method 'HNSW' does not exist" Error

Open
#759 4 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
1.2k
Forks
438
Avg merge
1d 4h
Merged PRs (30d)
1

Description

When running the VectorDB benchmark (VectorDBBench) against PgVector on webui, the test case fails with the error:
access method "HNSW" does not exist
This occurs during the performance test for the 1M dataset with 768-dimensional vectors, specifically when the benchmark attempts to optimize (create) an HNSW index. The error results in the termination of the benchmark run.

  1. VDBB Version:1.0.20
    (.venv) [root@server VectorDBBench-1.0.20]#
  2. PostgreSQL Version
    `
    [postgres@server ~]$ psql
    psql (18.3)
    Type "help" for help.

postgres=# show server_version;
server_version

18.3
postgres=# show search_path ;
search_path

"$user", public
(1 row)
postgres=# SELECT n.nspname as schema_name, p.proname as function_name
FROM pg_proc p
JOIN pg_namespace n ON p.pronamespace = n.oid
WHERE p.proname = 'hnswhandler';
schema_name | function_name
-------------+---------------
public | hnswhandler
(1 row)

postgres=# SELECT amname FROM pg_am;
amname

heap
btree
hash
gist
gin
spgist
brin
ivfflat
hnsw
(9 rows)
`
3. Configuration information

Image

4.Terminal display details:

Image

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the VectorDBBench web UI performance test against PgVector with the 1M, 768-dimensional dataset, then trace the benchmark path that creates the HNSW index. Check why the PostgreSQL environment reports the HNSW access method as unavailable during creation; done means the benchmark completes without terminating on this error.

Written by the indexing model from the issue text.

Assessment

Tech stack
postgresql, python
Domain
databases, performance
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.