@mastra/lance 1.2.0 → 1.2.1-alpha.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,14 @@
|
|
|
1
1
|
# @mastra/lance
|
|
2
2
|
|
|
3
|
+
## 1.2.1-alpha.0
|
|
4
|
+
|
|
5
|
+
### Patch Changes
|
|
6
|
+
|
|
7
|
+
- dependencies updates: ([#19779](https://github.com/mastra-ai/mastra/pull/19779))
|
|
8
|
+
- Updated dependency [`@lancedb/lancedb@^0.31.0` ↗︎](https://www.npmjs.com/package/@lancedb/lancedb/v/0.31.0) (from `^0.22.3`, in `dependencies`)
|
|
9
|
+
- Updated dependencies [[`723aa54`](https://github.com/mastra-ai/mastra/commit/723aa5437106bdb708ae03c0ef6b77aa11291e73), [`723aa54`](https://github.com/mastra-ai/mastra/commit/723aa5437106bdb708ae03c0ef6b77aa11291e73), [`723aa54`](https://github.com/mastra-ai/mastra/commit/723aa5437106bdb708ae03c0ef6b77aa11291e73)]:
|
|
10
|
+
- @mastra/core@1.55.0-alpha.3
|
|
11
|
+
|
|
3
12
|
## 1.2.0
|
|
4
13
|
|
|
5
14
|
### Minor Changes
|
package/dist/docs/SKILL.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# Storing embeddings in a vector database
|
|
4
4
|
|
|
5
|
-
After generating embeddings, you need to store them in a database that supports vector similarity search. Mastra provides a consistent interface for storing and querying embeddings across
|
|
5
|
+
After generating embeddings, you need to store them in a database that supports vector similarity search. Mastra provides a consistent interface for storing and querying embeddings across vector databases.
|
|
6
6
|
|
|
7
7
|
## Supported databases
|
|
8
8
|
|
|
@@ -571,7 +571,7 @@ The upsert operation:
|
|
|
571
571
|
|
|
572
572
|
Vector stores support rich metadata (any JSON-serializable fields) for filtering and organization. Since metadata is stored with no fixed schema, use consistent field naming to avoid unexpected query results.
|
|
573
573
|
|
|
574
|
-
> **Warning:** Metadata is
|
|
574
|
+
> **Warning:** Metadata is important for vector storage. Without it, you'd only have numerical embeddings with no way to return the original text or filter results. Always store at least the source text as metadata.
|
|
575
575
|
|
|
576
576
|
```ts
|
|
577
577
|
// Store embeddings with rich metadata for better organization and filtering
|
|
@@ -117,7 +117,7 @@ LanceDB storage can be configured for different deployment scenarios:
|
|
|
117
117
|
```text
|
|
118
118
|
db://host:port
|
|
119
119
|
```
|
|
120
|
-
- **S3 Storage**: Use Amazon S3 for
|
|
120
|
+
- **S3 Storage**: Use Amazon S3 for high-capacity cloud storage
|
|
121
121
|
```text
|
|
122
122
|
s3://bucket/db
|
|
123
123
|
```
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@mastra/lance",
|
|
3
|
-
"version": "1.2.0",
|
|
3
|
+
"version": "1.2.1-alpha.0",
|
|
4
4
|
"description": "Lance provider for Mastra - includes both vector and db storage capabilities",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "dist/index.js",
|
|
@@ -19,7 +19,7 @@
|
|
|
19
19
|
"./package.json": "./package.json"
|
|
20
20
|
},
|
|
21
21
|
"dependencies": {
|
|
22
|
-
"@lancedb/lancedb": "^0.
|
|
22
|
+
"@lancedb/lancedb": "^0.31.0",
|
|
23
23
|
"apache-arrow": "^18.1.0"
|
|
24
24
|
},
|
|
25
25
|
"devDependencies": {
|
|
@@ -34,7 +34,7 @@
|
|
|
34
34
|
"@internal/lint": "0.0.118",
|
|
35
35
|
"@internal/storage-test-utils": "0.0.114",
|
|
36
36
|
"@internal/types-builder": "0.0.93",
|
|
37
|
-
"@mastra/core": "^1.
|
|
37
|
+
"@mastra/core": "^1.55.0-alpha.3"
|
|
38
38
|
},
|
|
39
39
|
"peerDependencies": {
|
|
40
40
|
"@mastra/core": ">=1.0.0-0 <2.0.0-0"
|