vecs
vecs copied to clipboard
supabase
Postgres/pgvector Python Client
Currently vecs uses string pattern matching on the index name to determine if an index exists and supports the correct vector ops Logic is here https://github.com/supabase/vecs/blob/cc412ce43b525486e8b4e1c376f71227fc1ef5c2/src/vecs/collection.py#L623-L677 It would be preferable...
Vecs does not currently interop well with migrations. Provide a function that exports a SQL snippet that can be used to setup a migration Example ```python docs = vx.create_collection(...) docs.export_migration()...
## What kind of change does this PR introduce? Feature: add support for connecting to a user-specified database schema (instead of hard-coding `vecs`). This was accomplished by adding the `schema`...
The lack of feedback during `Collection.upsert` and `Collection.create_index` is a bad DX. It would be great to get some progress bars but I haven't been able to get them working...
It creates tables by default in 'vecs' schema. It'd be great if users had flexibility to choose another schema when creating a client.Thanks
It could be useful to optionally allow users to provide a `statement_timeout` during `create_index` as it can be difficult to interrupt once started and could potentially take a long time...
## Context Markdown is a common format for documents ingested into vector systems and has more exploitable structure than simple text. This task is to create an `vecs.adapters.base.AdapterStep` that handles...
# Feature Request: Async Client Most of what `vecs` manages involves interacting with a database over a network. Sqlalchemy and psycopg2 both support async operations but `vecs` does not. Creating...
**Describe the bug** A clear and concise description of what the bug is. **To Reproduce** I have some embedding to be upsert: ```python transcript = vx.get_or_create_collection(name="Transcript", dimension=DIMENSION) transcript.upsert(records=embeddings) transcript.create_index() ```...
# Summary [summary]: #summary This RFC proposes adding support for the latest `pgvector` features into the `vecs` Python client. These include new vector types (`halfvec`, `sparsevec`), enhanced indexing capabilities, and...
