Skip to content
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.

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

[ENH] Update documentation for generate ids changes #2775

Closed
Show file tree
Hide file tree
Changes from 1 commit
Commits
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
Next Next commit
update doc
  • Loading branch information
spikechroma authored and atroyn committed Oct 2, 2024
commit be602259ac404b23e3117a3c085215b02fc6cf5d
24 changes: 23 additions & 1 deletion docs/docs.trychroma.com/pages/getting-started.md
Original file line number Diff line number Diff line change
Expand Up @@ -143,12 +143,23 @@ const collection = await client.createCollection({

### 4. Add some text documents to the collection

Chroma will store your text and handle embedding and indexing automatically. You can also customize the embedding model.
Chroma will store your text and handle embedding and indexing automatically. You can also customize the embedding model. When you add documents, IDs are optional. If you don't provide `ids`, Chroma will automatically generate `ids` for you.

{% tabs group="code-lang" hideTabs=true %}
{% tab label="Python" %}

```python
# Add docs without IDs
result = collection.add(
documents=[
"This is a document about pineapple",
"This is a document about oranges"
]
)

ids = result["ids"]

# Add docs with IDs
collection.add(
documents=[
"This is a document about pineapple",
Expand All @@ -162,6 +173,17 @@ collection.add(
{% tab label="Javascript" %}

```js
// Add docs without Ids
result = await client.addRecords(collection, {
documents: [
"This is a document about pineapple",
"This is a document about oranges",
]
});

ids = result.ids

// Add docs with Ids
await collection.add({
documents: [
"This is a document about pineapple",
Expand Down
19 changes: 6 additions & 13 deletions docs/docs.trychroma.com/pages/guides/index.md
Original file line number Diff line number Diff line change
Expand Up @@ -112,8 +112,7 @@ async def main():
collection = await client.create_collection(name="my_collection")

await collection.add(
documents=["hello world"],
ids=["id1"]
documents=["hello world"]
)

asyncio.run(main())
Expand Down Expand Up @@ -358,26 +357,24 @@ Raw documents:
```python
collection.add(
documents=["lorem ipsum...", "doc2", "doc3", ...],
metadatas=[{"chapter": "3", "verse": "16"}, {"chapter": "3", "verse": "5"}, {"chapter": "29", "verse": "11"}, ...],
ids=["id1", "id2", "id3", ...]
metadatas=[{"chapter": "3", "verse": "16"}, {"chapter": "3", "verse": "5"}, {"chapter": "29", "verse": "11"}, ...]
)
```

{% /tab %}
{% tab label="Javascript" %}

Add data to Chroma with `.addRecords`.
Add data to Chroma with `.add`.

Raw documents:

```javascript
await collection.add({
ids: ["id1", "id2", "id3", ...],
metadatas: [{"chapter": "3", "verse": "16"}, {"chapter": "3", "verse": "5"}, {"chapter": "29", "verse": "11"}, ...],
documents: ["lorem ipsum...", "doc2", "doc3", ...],
})
// input order
// ids - required
// ids - optional
// embeddings - optional
// metadata - optional
// documents - optional
Expand All @@ -400,8 +397,7 @@ Alternatively, you can supply a list of document-associated `embeddings` directl
collection.add(
documents=["doc1", "doc2", "doc3", ...],
embeddings=[[1.1, 2.3, 3.2], [4.5, 6.9, 4.4], [1.1, 2.3, 3.2], ...],
metadatas=[{"chapter": "3", "verse": "16"}, {"chapter": "3", "verse": "5"}, {"chapter": "29", "verse": "11"}, ...],
ids=["id1", "id2", "id3", ...]
metadatas=[{"chapter": "3", "verse": "16"}, {"chapter": "3", "verse": "5"}, {"chapter": "29", "verse": "11"}, ...]
)
```

Expand All @@ -410,7 +406,6 @@ collection.add(

```javascript
await collection.add({
ids: ["id1", "id2", "id3", ...],
embeddings: [[1.1, 2.3, 3.2], [4.5, 6.9, 4.4], [1.1, 2.3, 3.2], ...],
metadatas: [{"chapter": "3", "verse": "16"}, {"chapter": "3", "verse": "5"}, {"chapter": "29", "verse": "11"}, ...],
documents: ["lorem ipsum...", "doc2", "doc3", ...],
Expand All @@ -432,8 +427,7 @@ You can also store documents elsewhere, and just supply a list of `embeddings` a
```python
collection.add(
embeddings=[[1.1, 2.3, 3.2], [4.5, 6.9, 4.4], [1.1, 2.3, 3.2], ...],
metadatas=[{"chapter": "3", "verse": "16"}, {"chapter": "3", "verse": "5"}, {"chapter": "29", "verse": "11"}, ...],
ids=["id1", "id2", "id3", ...]
metadatas=[{"chapter": "3", "verse": "16"}, {"chapter": "3", "verse": "5"}, {"chapter": "29", "verse": "11"}, ...]
)
```

Expand All @@ -442,7 +436,6 @@ collection.add(

```javascript
await collection.add({
ids: ["id1", "id2", "id3", ...],
embeddings: [[1.1, 2.3, 3.2], [4.5, 6.9, 4.4], [1.1, 2.3, 3.2], ...],
metadatas: [{"chapter": "3", "verse": "16"}, {"chapter": "3", "verse": "5"}, {"chapter": "29", "verse": "11"}, ...],
})
Expand Down
5 changes: 1 addition & 4 deletions docs/docs.trychroma.com/pages/guides/multimodal.md
Original file line number Diff line number Diff line change
Expand Up @@ -65,7 +65,6 @@ You can add data to a multi-modal collection by specifying the data modality. Fo

```python
collection.add(
ids=['id1', 'id2', 'id3'],
images=[...] # A list of numpy arrays representing images
)
```
Expand All @@ -76,7 +75,6 @@ However, you can use Chroma in combination with data stored elsewhere, by adding

```python
collection.add(
ids=['id1', 'id2', 'id3'],
uris=[...] # A list of strings representing URIs to data
)
```
Expand All @@ -85,8 +83,7 @@ Since the embedding function is multi-modal, you can also add text to the same c

```python
collection.add(
ids=['id4', 'id5', 'id6'],
documents=["This is a document", "This is another document", "This is a third document"]
texts=["This is a document", "This is another document", "This is a third document"]
)
```

Expand Down
11 changes: 2 additions & 9 deletions docs/docs.trychroma.com/pages/reference/cheatsheet.md
Original file line number Diff line number Diff line change
Expand Up @@ -98,21 +98,17 @@ collection.count()
# add new items to a collection
# either one at a time
collection.add(
embeddings=[1.5, 2.9, 3.4],
metadatas={"uri": "img9.png", "style": "style1"},
documents="doc1000101",
ids="uri9",
)
# or many, up to 100k+!
collection.add(
embeddings=[[1.5, 2.9, 3.4], [9.8, 2.3, 2.9]],
metadatas=[{"style": "style1"}, {"style": "style2"}],
ids=["uri9", "uri10"],
metadatas=[{"style": "style1"}, {"style": "style2"}]
)
collection.add(
documents=["doc1000101", "doc288822"],
metadatas=[{"style": "style1"}, {"style": "style2"}],
ids=["uri9", "uri10"],
metadatas=[{"style": "style1"}, {"style": "style2"}]
)

# update items in a collection
Expand Down Expand Up @@ -200,21 +196,18 @@ await collection.count()
// add new items to a collection
// either one at a time
await collection.add({
ids: "id1",
embeddings: [1.5, 2.9, 3.4],
metadatas: {"source": "my_source"},
documents: "This is a document",
})
// or many, up to 100k+!
await collection.add({
ids: ["uri9", "uri10"],
embeddings: [[1.5, 2.9, 3.4], [9.8, 2.3, 2.9]],
metadatas: [{"style": "style1"}, {"style": "style2"}],
documents: ["This is a document", 'that is a document']
})
// including just documents
await collection.add({
ids: ["uri9", "uri10"],
metadatas: [{"style": "style1"}, {"style": "style2"}],
documents: ["doc1000101", "doc288822"],
})
Expand Down
6 changes: 3 additions & 3 deletions docs/docs.trychroma.com/pages/reference/js-collection.md
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ ___

### add

▸ **add**(`params`): `Promise`\<`void`\>
▸ **add**(`params`): `Promise`\<`AddResponse`\>

Add items to the collection

Expand All @@ -40,7 +40,7 @@ Add items to the collection

#### Returns

`Promise`\<`void`\>
`Promise`\<`AddResponse`\>

- The response from the API. True if successful.

Expand Down Expand Up @@ -294,7 +294,7 @@ Upsert items to the collection

| Name | Type | Description |
| :------ | :------ | :------ |
| `params` | `AddRecordsParams` | The parameters for the query. |
| `params` | `UpsertRecordsParams` | The parameters for the query. |

#### Returns

Expand Down
Loading