Austin/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2024-11-15 19:22:36 +08:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

fix: Azure OpenAI o1 max_completion_token error (#10593)

Browse Source
This commit is contained in:
Kevin9703 2024-11-12 21:40:13 +08:00 committed by GitHub
parent 62642443ef
commit e03ec0032b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
api/core/model_runtime/model_providers/azure_openai/llm/llm.py
View File

@ -113,7 +113,7 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
try: try:
client = AzureOpenAI(**self._to_credential_kwargs(credentials)) client = AzureOpenAI(**self._to_credential_kwargs(credentials))
if model.startswith("o1"): if "o1" in model:
client.chat.completions.create( client.chat.completions.create(
messages=[{"role": "user", "content": "ping"}], messages=[{"role": "user", "content": "ping"}],
model=model, model=model,
@ -311,7 +311,7 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
prompt_messages = self._clear_illegal_prompt_messages(model, prompt_messages) prompt_messages = self._clear_illegal_prompt_messages(model, prompt_messages)
block_as_stream = False block_as_stream = False
if model.startswith("o1"): if "o1" in model:
if stream: if stream:
block_as_stream = True block_as_stream = True
stream = False stream = False
@ -404,7 +404,7 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
] ]
) )
if model.startswith("o1"): if "o1" in model:
system_message_count = len([m for m in prompt_messages if isinstance(m, SystemPromptMessage)]) system_message_count = len([m for m in prompt_messages if isinstance(m, SystemPromptMessage)])
if system_message_count > 0: if system_message_count > 0:
new_prompt_messages = [] new_prompt_messages = []
@ -653,7 +653,7 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
tokens_per_message = 4 tokens_per_message = 4
# if there's a name, the role is omitted # if there's a name, the role is omitted
tokens_per_name = -1 tokens_per_name = -1
elif model.startswith("gpt-35-turbo") or model.startswith("gpt-4") or model.startswith("o1"): elif model.startswith("gpt-35-turbo") or model.startswith("gpt-4") or "o1" in model:
tokens_per_message = 3 tokens_per_message = 3
tokens_per_name = 1 tokens_per_name = 1
else: else: