@mastra/fastembed 1.3.4-alpha.0 → 1.3.4-alpha.2
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/README.md +4 -0
- package/dist/_types/@internal_ai-sdk-v5/dist/index.d.ts +206 -873
- package/dist/_types/@internal_ai-v6/dist/index.d.ts +851 -1176
- package/dist/fastembed.d.ts +7 -0
- package/dist/fastembed.d.ts.map +1 -1
- package/dist/index.cjs +585 -2932
- package/dist/index.cjs.map +1 -1
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +586 -2933
- package/dist/index.js.map +1 -1
- package/package.json +5 -5
package/README.md
CHANGED
|
@@ -24,6 +24,10 @@ const memory = new Memory({
|
|
|
24
24
|
});
|
|
25
25
|
```
|
|
26
26
|
|
|
27
|
+
### Input length
|
|
28
|
+
|
|
29
|
+
FastEmbed models embed at most 512 tokens per input (roughly 2,000 to 2,500 characters of English text). Longer inputs are truncated: text past the limit doesn't affect the embedding. The AI SDK v3 models return a warning when this happens. Chunk long documents to fit the window, for example with `maxSize: 1500` in `MDocument.chunk()`.
|
|
30
|
+
|
|
27
31
|
## Documentation
|
|
28
32
|
|
|
29
33
|
- [Use FastEmbed for local semantic recall](https://mastra.ai/docs/memory/semantic-recall#using-fastembed-local)
|