Austin/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2024-11-16 19:59:50 +08:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

fix: xinference chat completion error (#952)

Browse Source
This commit is contained in:
takatost 2023-08-22 15:58:04 +08:00 committed by GitHub
parent b3c2bf125f
commit 4f3053a8cc
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
api/core/third_party/langchain/llms/xinference_llm.py vendored
View File

@ -46,7 +46,7 @@ class XinferenceLLM(Xinference):
return combined_text_output return combined_text_output
else: else:
completion = model.chat(prompt=prompt, generate_config=generate_config) completion = model.chat(prompt=prompt, generate_config=generate_config)
return completion["choices"][0]["text"] return completion["choices"][0]["message"]["content"]
elif isinstance(model, RESTfulGenerateModelHandle): elif isinstance(model, RESTfulGenerateModelHandle):
generate_config: "LlamaCppGenerateConfig" = kwargs.get("generate_config", {}) generate_config: "LlamaCppGenerateConfig" = kwargs.get("generate_config", {})
@ -82,7 +82,7 @@ class XinferenceLLM(Xinference):
completion = combined_text_output completion = combined_text_output
else: else:
completion = model.chat(prompt=prompt, generate_config=generate_config) completion = model.chat(prompt=prompt, generate_config=generate_config)
completion = completion["choices"][0]["text"] completion = completion["choices"][0]["message"]["content"]
if stop is not None: if stop is not None:
completion = enforce_stop_tokens(completion, stop) completion = enforce_stop_tokens(completion, stop)