◐ Shell
reader mode source ↗
Skip to content
Merged

feat: Updating documents to highlight v2 api for Vector Similarity Se… #5000

Show file tree
Hide file tree
Changes from all commits
File filter
Conversations
Jump to
Diff view
Apply and reload
Show whitespace
Diff view
Apply and reload
212 changes: 146 additions & 66 deletions docs/reference/alpha-vector-database.md
View file Edit file Delete file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,20 +7,35 @@ Vector database allows user to store and retrieve embeddings. Feast provides gen
## Integration
Below are supported vector databases and implemented features:

| Vector Database | Retrieval | Indexing |
|-----------------|-----------|----------|
| Pgvector | [x] | [ ] |
| Elasticsearch | [x] | [x] |
| Milvus | [ ] | [ ] |
| Faiss | [ ] | [ ] |
| SQLite | [x] | [ ] |
| Qdrant | [x] | [x] |

Note: SQLite is in limited access and only working on Python 3.10. It will be updated as [sqlite_vec](https://github.com/asg017/sqlite-vec/) progresses.

## Example

See [https://github.com/feast-dev/feast-workshop/blob/rag/module_4_rag](https://github.com/feast-dev/feast-workshop/blob/rag/module_4_rag) for an example on how to use vector database.

### **Prepare offline embedding dataset**
Run the following commands to prepare the embedding dataset:
Expand All @@ -34,25 +49,23 @@ The output will be stored in `data/city_wikipedia_summaries.csv.`
Use the feature_store.yaml file to initialize the feature store. This will use the data as offline store, and Pgvector as online store.

```yaml
project: feast_demo_local
provider: local
registry:
registry_type: sql
path: postgresql://@localhost:5432/feast
online_store:
type: postgres
vector_enabled: true
vector_len: 384
host: 127.0.0.1
port: 5432
database: feast
user: ""
password: ""


offline_store:
type: file
entity_key_serialization_version: 2
```
Run the following command in terminal to apply the feature store configuration:

Expand All @@ -63,75 +76,128 @@ feast apply
Note that when you run `feast apply` you are going to apply the following Feature View that we will use for retrieval later:

```python
city_embeddings_feature_view = FeatureView(
name="city_embeddings",
entities=[item],
schema=[
Field(name="Embeddings", dtype=Array(Float32)),
],
source=source,
ttl=timedelta(hours=2),
)
```

Then run the following command in the terminal to materialize the data to the online store:

```shell
CURRENT_TIME=$(date -u +"%Y-%m-%dT%H:%M:%S")
feast materialize-incremental $CURRENT_TIME
```

### **Prepare a query embedding**
```python
from batch_score_documents import run_model, TOKENIZER, MODEL
from transformers import AutoTokenizer, AutoModel

question = "the most populous city in the U.S. state of Texas?"

tokenizer = AutoTokenizer.from_pretrained(TOKENIZER)
model = AutoModel.from_pretrained(MODEL)
query_embedding = run_model(question, tokenizer, model)
query = query_embedding.detach().cpu().numpy().tolist()[0]
```

### **Retrieve the top 5 similar documents**
First create a feature store instance, and use the `retrieve_online_documents` API to retrieve the top 5 similar documents to the specified query.

```python
from feast import FeatureStore
store = FeatureStore(repo_path=".")
features = store.retrieve_online_documents(
feature="city_embeddings:Embeddings",
query=query,
top_k=5
).to_dict()

def print_online_features(features):
for key, value in sorted(features.items()):
print(key, " : ", value)

print_online_features(features)
```

### Configuration

We offer [PGVector](https://github.com/pgvector/pgvector), [SQLite](https://github.com/asg017/sqlite-vec), [Elasticsearch](https://www.elastic.co) and [Qdrant](https://qdrant.tech/) as Online Store options for Vector Databases.

#### Installation with SQLite

If you are using `pyenv` to manage your Python versions, you can install the SQLite extension with the following command:
```bash
PYTHON_CONFIGURE_OPTS="--enable-loadable-sqlite-extensions" \
LDFLAGS="-L/opt/homebrew/opt/sqlite/lib" \
CPPFLAGS="-I/opt/homebrew/opt/sqlite/include" \
pyenv install 3.10.14
```
And you can the Feast install package via:

```bash
pip install feast[sqlite_vec]
```

#### Installation with Elasticsearch

```bash
Expand All @@ -143,3 +209,17 @@ pip install feast[elasticsearch]
```bash
pip install feast[qdrant]
```
5 changes: 3 additions & 2 deletions docs/reference/online-stores/milvus.md
View file Edit file Delete file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,7 @@ The set of functionality supported by online stores is described in detail [here
Below is a matrix indicating which functionality is supported by the Milvus online store.

| | Milvus |
| :-------------------------------------------------------- |:-------|
| write feature values to the online store | yes |
| read feature values from the online store | yes |
| update infrastructure (e.g. tables) in the online store | yes |
Expand All @@ -59,6 +59,7 @@ Below is a matrix indicating which functionality is supported by the Milvus onli
| support for deleting expired data | yes |
| collocated by feature view | no |
| collocated by feature service | no |
| collocated by entity key | yes |

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