Skip to content

fix: Add vector database doc #4165

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 3 commits into from
May 11, 2024
Merged

fix: Add vector database doc #4165

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7c83a27
add vector database doc
HaoXuAI May 1, 2024
792b238
Update Doc
HaoXuAI May 2, 2024
fbc5945
update format
HaoXuAI May 6, 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
96 changes: 96 additions & 0 deletions docs/reference/alpha-vector-database.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,96 @@
# [Alpha] Vector Database
**Warning**: This is an _experimental_ feature. To our knowledge, this is stable, but there are still rough edges in the experience. Contributions are welcome!

## Overview
Vector database allows user to store and retrieve embeddings. Feast provides general APIs to store and retrieve embeddings.

## Integration
Below are supported vector databases and implemented features:

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


## 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:
```shell
python pull_states.py
python batch_score_documents.py
```
The output will be stored in `data/city_wikipedia_summaries.csv.`

### **Initialize Feast feature store and materialize the data to the online store**
Use the feature_tore.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
pgvector_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 to apply the feature store configuration:

```shell
feast apply
```

Then run the following command to materialize the data to the online store:
Copy link
Copy Markdown
Member

@franciscojavierarceo franciscojavierarceo May 1, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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


```shell
!feast materialize 2024-04-01T00:00:00 2024-04-17T00:00:00
Copy link
Copy Markdown
Member

@franciscojavierarceo franciscojavierarceo May 1, 2024 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Would suggest the below so time doesn't impact this

Suggested change
!feast materialize 2024-04-01T00:00:00 2024-04-17T00:00:00
```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)
```