mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-05-28 03:33:05 +08:00
733d75d6a7
### What problem does this PR solve? The Baidu (Qianfan) `Encode` method silently swallowed malformed responses. If a `data[]` item from the API was missing a field (`index`, `embedding`, or unexpected shape), the loop did `continue` instead of returning an error, leaving `nil` entries in the result slice. Callers got back partial results with no indication anything went wrong, which then crashes downstream consumers when they try to use a `nil` vector. Concrete gaps fixed: - No count-mismatch check between `data` length and input texts (only checked for empty) - No duplicate-index detection (a duplicate would silently overwrite) - No missing-index final scan - No empty-embedding rejection - No per-call context timeout - `EmbeddingConfig.Dimension` (added in #14735) was not propagated This PR replaces `map[string]interface{}` parsing with a typed `baiduEmbeddingResponse` struct, applies the standard four-layer validation (count → out-of-range → duplicate → empty → final missing-index scan), adds `context.WithTimeout(nonStreamCallTimeout)`, and forwards `embeddingConfig.Dimension` as the `dimensions` parameter (Baidu Qianfan v2 uses an OpenAI-compatible API). ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)