Commit
·
fc44b3f
1
Parent(s):
0c05b88
Update README.md
Browse files
README.md
CHANGED
|
@@ -7,4 +7,39 @@ sdk: static
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
+
## Chroma Datasets
|
| 11 |
+
|
| 12 |
+
Making it easy to load data into Chroma since 2023
|
| 13 |
+
|
| 14 |
+
```
|
| 15 |
+
pip install chroma_datasets
|
| 16 |
+
```
|
| 17 |
+
|
| 18 |
+
### Current Datasets
|
| 19 |
+
- State of the Union `from chroma_datasets import StateOfTheUnion`
|
| 20 |
+
- Paul Graham Essay `from chroma_datasets import PaulGrahamEssay`
|
| 21 |
+
- Glue `from chroma_datasets import Glue`
|
| 22 |
+
- SciPy `from chroma_datasets import SciPy`
|
| 23 |
+
|
| 24 |
+
`chroma_datasets` is generally backed by hugging face datasets, but it is not a requirement.
|
| 25 |
+
|
| 26 |
+
### How to use
|
| 27 |
+
|
| 28 |
+
The following will:
|
| 29 |
+
1. Download the 2022 State of the Union
|
| 30 |
+
2. Chunk it up for you
|
| 31 |
+
3. Embed it using Chroma's default open-source embedding function
|
| 32 |
+
4. Import it into Chroma
|
| 33 |
+
|
| 34 |
+
```python
|
| 35 |
+
import chromadb
|
| 36 |
+
from chroma_datasets import StateOfTheUnion
|
| 37 |
+
from chroma_datasets.utils import import_into_chroma
|
| 38 |
+
|
| 39 |
+
chroma_client = chromadb.Client()
|
| 40 |
+
collection = import_into_chroma(chroma_client=chroma_client, dataset=StateOfTheUnion)
|
| 41 |
+
result = collection.query(query_texts=["The United States of America"])
|
| 42 |
+
print(result)
|
| 43 |
+
```
|
| 44 |
+
|
| 45 |
+
Learn about how to create and contribute a package at [chroma-core/chroma_datasets](https://github.com/chroma-core/chroma_datasets).
|