fix: Upgrade Hugging Face Inference API to support Inference Providers (#5454)

- Upgrade @huggingface/inference from v2.6.1 to v4.13.2
- Update ChatHuggingFace to use InferenceClient with chatCompletion API
- Update HuggingFaceInference (LLM) to use v4 HfInference with Inference Providers
- Update HuggingFaceInferenceEmbedding to use v4 HfInference
- Add endpoint handling logic to ignore custom endpoints for provider-based models
- Add improved error handling and validation for API keys
- Update UI descriptions to guide users on proper configuration

Fixes #5161

Co-authored-by: Henry <hzj94@hotmail.com>
This commit is contained in:
Siddharth Chauhan
2025-11-25 17:13:36 +05:30
committed by GitHub
parent 097404f24a
commit 0cc7b3036e
9 changed files with 192 additions and 82 deletions
@@ -241,8 +241,11 @@ class HumanInput_Agentflow implements INode {
if (isStreamable) {
const sseStreamer: IServerSideEventStreamer = options.sseStreamer as IServerSideEventStreamer
for await (const chunk of await llmNodeInstance.stream(messages)) {
sseStreamer.streamTokenEvent(chatId, chunk.content.toString())
response = response.concat(chunk)
const content = typeof chunk === 'string' ? chunk : chunk.content.toString()
sseStreamer.streamTokenEvent(chatId, content)
const messageChunk = typeof chunk === 'string' ? new AIMessageChunk(chunk) : chunk
response = response.concat(messageChunk)
}
humanInputDescription = response.content as string
} else {