mirror of
https://github.com/supabase/supabase.git
synced 2026-10-08 19:05:06 +03:00
0aa7b4965f
Contributes to DOCS-1052 Contributes to DOCS-1057 ## I have read the [CONTRIBUTING.md](https://github.com/supabase/supabase/blob/master/CONTRIBUTING.md) file. YES ## What kind of change does this PR introduce? Resolves linting warning for "let's" and adds an exception for product name. ## Tophatting 1. Read the diff and see if changes make sense in context. 2. Run `pnpm lint:mdx`, search for "let's" and see no instances. <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Documentation** * Updated instructional copy across multiple AI, authentication, database, functions, realtime, storage, and troubleshooting guides to improve clarity and consistency. * Replaced conversational phrasing (for example, “Let’s…/Let’s see…”) with direct imperatives, tightened example lead-ins, and adjusted a few step explanations for readability. * Refreshed some tutorial text and code-sample presentation in guides (no behavioral changes). * Added/adjusted minor MDX lint guidance in a couple of documents. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Nik Richers <nrichers@gmail.com>
85 lines
2.2 KiB
Plaintext
85 lines
2.2 KiB
Plaintext
---
|
|
id: 'ai-vecs-python-client'
|
|
title: 'Python client'
|
|
subtitle: 'Manage unstructured vector stores in Postgres.'
|
|
breadcrumb: 'AI Quickstarts'
|
|
---
|
|
|
|
Supabase provides a Python client called [`vecs`](https://github.com/supabase/vecs) for managing unstructured vector stores. This client provides a set of useful tools for creating and querying collections in Postgres using the [pgvector](/docs/guides/database/extensions/pgvector) extension.
|
|
|
|
## Quick start
|
|
|
|
To see how Vecs works, use a local database. Make sure you have the Supabase CLI [installed](/docs/guides/cli#installation) on your machine.
|
|
|
|
### Initialize your project
|
|
|
|
Start a local Postgres instance in any folder using the `init` and `start` commands. Make sure you have Docker running!
|
|
|
|
```bash
|
|
# Initialize your project
|
|
supabase init
|
|
|
|
# Start Postgres
|
|
supabase start
|
|
```
|
|
|
|
### Create a collection
|
|
|
|
Inside a Python shell, run the following commands to create a new collection called "docs", with 3 dimensions.
|
|
|
|
```py
|
|
import vecs
|
|
|
|
# create vector store client
|
|
vx = vecs.create_client("postgresql://postgres:postgres@localhost:54322/postgres")
|
|
|
|
# create a collection of vectors with 3 dimensions
|
|
docs = vx.get_or_create_collection(name="docs", dimension=3)
|
|
```
|
|
|
|
### Add embeddings
|
|
|
|
Now we can insert some embeddings into our "docs" collection using the `upsert()` command:
|
|
|
|
```py
|
|
import vecs
|
|
|
|
# create vector store client
|
|
docs = vecs.get_or_create_collection(name="docs", dimension=3)
|
|
|
|
# a collection of vectors with 3 dimensions
|
|
vectors=[
|
|
("vec0", [0.1, 0.2, 0.3], {"year": 1973}),
|
|
("vec1", [0.7, 0.8, 0.9], {"year": 2012})
|
|
]
|
|
|
|
# insert our vectors
|
|
docs.upsert(vectors=vectors)
|
|
```
|
|
|
|
### Query the collection
|
|
|
|
You can now query the collection to retrieve a relevant match:
|
|
|
|
```py
|
|
import vecs
|
|
|
|
docs = vecs.get_or_create_collection(name="docs", dimension=3)
|
|
|
|
# query the collection filtering metadata for "year" = 2012
|
|
docs.query(
|
|
data=[0.4,0.5,0.6], # required
|
|
limit=1, # number of records to return
|
|
filters={"year": {"$eq": 2012}}, # metadata filters
|
|
)
|
|
```
|
|
|
|
## Deep dive
|
|
|
|
For a more in-depth guide on `vecs` collections, see [API](/docs/guides/ai/python/api).
|
|
|
|
## Resources
|
|
|
|
- Official Vecs Documentation: https://supabase.github.io/vecs/api
|
|
- Source Code: https://github.com/supabase/vecs
|