Skip to content

D
dify
Unverified Commit 18d38771 authored by takatost's avatar takatost Committed by GitHub
Browse files
Options

feat: optimize xinference stream (#989)

parent 53e83d86
Show whitespace changes
Inline Side-by-side
Showing with 3 additions and 3 deletions
api/core/third_party/langchain/llms/xinference_llm.py
View file @ 18d38771
...@@ -108,12 +108,12 @@ class XinferenceLLM(Xinference): ...@@ -108,12 +108,12 @@ class XinferenceLLM(Xinference):
Yields: Yields:
A string token. A string token.
""" """
if isinstance(model, RESTfulGenerateModelHandle): if isinstance(model, (RESTfulChatModelHandle, RESTfulChatglmCppChatModelHandle)):
streaming_response = model.generate( streaming_response = model.chat(
prompt=prompt, generate_config=generate_config prompt=prompt, generate_config=generate_config
) )
else: else:
streaming_response = model.chat( streaming_response = model.generate(
prompt=prompt, generate_config=generate_config prompt=prompt, generate_config=generate_config
) )
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment