FastGPT

mirror of https://github.com/labring/FastGPT.git synced 2026-05-07 01:02:55 +08:00

Files

T

Octopus c0072fabbc fix(embedding): decode base64 embedding responses before vector processing (#6807 )

* fix(embedding): decode base64 embedding responses before vector processing

When a model's extra body config includes `encoding_format: "base64"`, the
embedding API returns a base64-encoded IEEE 754 little-endian float32 array
instead of a `number[]`. The previous code passed this raw string directly
to `formatVectors`, which called `.reduce()` on it and threw:
  TypeError: a.reduce is not a function

Add `decodeEmbedding()` that detects base64 strings and decodes them to
`number[]` via `Buffer → Float32Array → Array.from()`, then use it in
`getVectorsByText` before calling `formatVectors`.

Fixes #6769

* perf: test

---------

Co-authored-by: octo-patch <octo-patch@github.com>
Co-authored-by: archer <545436317@qq.com>

2026-04-26 21:12:40 +08:00

cases

fix(embedding): decode base64 embedding responses before vector processing (#6807 )

2026-04-26 21:12:40 +08:00

datas

V4.12.4 features (#5626 )

2025-09-15 20:02:54 +08:00

integrationTest

feat: add openGauss DataVec as vector database backend (#6666 )

2026-04-13 20:41:33 +08:00

mocks

V4.14.x (#6751 )