Skip to content

fix: Pgvector patch #4108

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
HaoXuAI merged 7 commits into from
Apr 17, 2024
Merged

fix: Pgvector patch #4108

Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
e274a23
update postgres online store to make it work with write and read APIs.
HaoXuAI Apr 16, 2024
6abffbf
format
HaoXuAI Apr 16, 2024
ce854d4
update doc
HaoXuAI Apr 16, 2024
1bad023
update doc
HaoXuAI Apr 16, 2024
1c62a34
minor change on return value
HaoXuAI Apr 17, 2024
d5d93e7
minor change on return value
HaoXuAI Apr 17, 2024
8bdbbdc
sync master
HaoXuAI Apr 17, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
update doc 
Signed-off-by: cmuhao <sduxuhao@gmail.com>
  • Loading branch information
@HaoXuAI
HaoXuAI committed Apr 16, 2024
commit ce854d48865f4aeb1492ede12e5eb3c16f791c71
28 changes: 28 additions & 0 deletions docs/reference/online-stores/postgres.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,8 @@ online_store:
sslkey_path: /path/to/client-key.pem
sslcert_path: /path/to/client-cert.pem
sslrootcert_path: /path/to/server-ca.pem
pgvector_enabled: false
vector_len: 512
```
{% endcode %}

Expand Down Expand Up @@ -60,3 +62,29 @@ Below is a matrix indicating which functionality is supported by the Postgres on
| collocated by entity key | no |

To compare this set of functionality against other online stores, please see the full [functionality matrix](overview.md#functionality-matrix).

## PGVector
The Postgres online store supports the use of [PGVector](https://pgvector.dev/) for storing feature values.
To enable PGVector, set `pgvector_enabled: true` in the online store configuration.
The `vector_len` parameter can be used to specify the length of the vector. The default value is 512.

Then you can use `retrieve_online_documents` to retrieve the top k closest vectors to a query vector.

{% code title="python" %}
```python
from feast import FeatureStore
from feast.infra.online_stores.postgres import retrieve_online_documents

feature_store = FeatureStore(repo_path=".")

query_vector = [0.1, 0.2, 0.3, 0.4, 0.5]
top_k = 5

feature_values = retrieve_online_documents(
feature_store=feature_store,
feature_view_name="document_fv:embedding_float",
query_vector=query_vector,
top_k=top_k,
)
```
{% endcode %}